Description:
FORM 2
The Patent Act 1970
(39 of 1970)
&
The Patent Rules, 2005

COMPLETE SPECIFICATION
(SEE SECTION 10 AND RULE 13)

TITLE OF THE INVENTION

“Artificial intelligence enabled automatic real-time transformer monitoring and control system and method thereof”

APPLICANTS:
Name : EFICAA Ensmart Solutions Private Limited

Nationality : India

Address : Fortune 9 6-3-1091, C/1, Raj Bhavan Rd, Somajiguda, Hyderabad, Telangana 500082

The following specification particularly describes and ascertains the nature of this invention and the manner in which it is to be performed:-

FIELD OF INVENTION
[0001] The present invention relates to a transformer. More particularly relates to a system and a method to monitor and control the transformer in real-time based on an Artificial Intelligence (AI) technique.
BACKGROUND OF INVENTION
[0002] In general, a distribution transformer is a costly and critical part of an equipment in an electricity distribution network. The safe and economic operation of the distribution transformer have a major impact on the development of power grid. With the continuous development of power industry, the power grid has become more complex to increase the safety, reliability, and monitoring levels of the distribution transformer. In case the distribution transformer faces any issues such as for example circuit failure and abnormal parameters (voltage flow, current flow, oil level, temperature, etc.), then it will affect normal power supply of the power grid. It requires technicians to go to on-site to check and repair the distribution transformer parts which are inefficient and facing abnormality. The entire repair process is complicated and the amount of work is large, and it cause mistakes in man-made recording and processing of data.
[0003] Similarly, whenever the distribution transformer faces any failure issues, then it causes immense inconvenience in network management and involves high expenditure on repair/replacement of the distribution transformer and any of a distribution utility takes all possible actions to reduce downtime/failure of the distribution transformers and to enlarge the distribution transformer lives at the most economical cost. To address all the issues, the proposed Transformer Management System configured to monitor the transformer's operational state and take corrective actions in real-time using an Artificial Intelligence (AI) technique.

OBJECT OF INVENTION
[0004] The principal object of the embodiments herein is to provide a system and a method to monitor and control a transformer in real-time. In the proposed method, a current state of the transformer is remotely monitored and controlled using a wireless connection based on an Artificial Intelligence (AI) technique. The proposed method reduces failure of the transformer with minimal cost and also reduces manual work by automatically rectifying anomalies of the transformer.
SUMMARY
[0005] Accordingly, the embodiments herein provide a Transformer Monitoring and Control Unit (TMCU) including an electric circuit connected to a transformer, located in a first geographic location, for providing electricity to a plurality of electricity consumers. A plurality of sensors are connected to the electric circuit to measure unique parameters of the transformer. An energy meter is connected to the plurality of sensors to measure power passing through the transformer. A display is connected to the energy meter. A microcontroller is coupled to the electric circuit, the plurality of sensors, the energy meter, and the display. The microcontroller is configured to receive the unique parameters of the transformer measured by the plurality of sensors, and create a wireless connection with a Management Control Centre (MCC) server located at a second geographic location for remote monitoring and controlling the transformer. The TMCU displays a current state of the transformer on the display for remote monitoring and controlling the transformer by the MCC server using the wireless connection, the current state indicates the unique parameters of the transformer. The current state of transformer is remotely monitored and controlled by using the wireless connection with the MCC server.
[0006] In an embodiment, the microcontroller configured to detect whether primary anomalies associated with the transformer by comparing the unique parameters of the transformer with a predefined criteria stored at the TMCU and generate control actions to rectify the primary anomalies of the transformer when the primary anomalies associated with the transformer is detected. The control actions are applied to rectify the primary anomalies of the transformer and update the current state of the transformer displayed on the display of the TMCU for remote monitoring and controlling the transformer by the MCC server using the wireless connection. The updated current state indicates the unique parameters of the transformer, the primary anomalies associated with the transformer, and the control actions applied to rectify the primary anomalies of the transformer.
[0007] In another embodiment, the current state of transformer is remotely monitored and controlled by using the wireless connection with the MCC server. The TMCU receives information about secondary anomalies of the transformer predicted by the MCC server and receives the control commands indicative of corrective actions to be performed by the TMCU from the MCC server to rectify the secondary anomalies of the transformer. The TMCU performs the corrective actions by applying the received control commands on the transformer to rectify the secondary anomalies of the transformer, and updates the current state of the transformer on the display of the TMCU for remote monitoring and controlling the transformer by the MCC server using the wireless connection. The updated current state indicates the unique parameters of the transformer, the secondary anomalies associated with the transformer, and the control commands applied to rectify the secondary anomalies of the transformer.
[0008] In another embodiment, the current state of the transformer is remotely monitored and controlled by using the wireless connection with the MCC server. The TMCU receives information about events associated with the other transformer located in the first geographic location from the MCC server located in the second geographic location and also receives the control commands indicative of events based transformer configuration to be applied by the TMCU from the MCC server based on the event associated with other transformers available in the area from the MCC server. Applying the event based transformer configuration on the transformer based on the received control commands and update the current state of the transformer displayed on the display of the TMCU for remote monitoring and controlling the transformer by the MCC server using the wireless connection. The updated current state of the transformer indicates the unique parameters of the transformer, information about the events associated with the other transformers available in the area, and the event based transformer configuration applied to the transformer associated with the TMCU.
[0009] In another embodiments, the unique parameters includes current voltage range of the transformer, current flow of the transformer, input power of the transformer, output power of the transformer, current temperature of the transformer, short circuit current deviation of the transformer, oil level of the transformer, oil temperature variation of the transformer, winding temperature variation of the transformer, surface temperature of the transformer, mechanical vibration of the transformer, magnetic field of the transformer, gases emitted by the transformer, loss of life of the transformer, number of consumers connected to the transformer, a load level of each consumer connected to the transformer, and frequency of the transformer.
[0010] In another embodiment, the plurality of sensors includes a voltage sensor configured to measure the current voltage range, the current flow, the short circuit current deviation, the current frequency, the input power, and the output power of the transformer. A temperature sensor configured to measure the current temperature, the oil temperature variation, surface temperature, and the winding temperature variation of the transformer. An oil level sensor measures the oil level of the transformer. A vibration sensor measures the mechanical vibrations of the transformer. A current sensor measures the load level of each consumer connected to the transformer, and the number of consumers connected to the transformer. A magnetic field sensor detects the magnetic field generated by the transformer. A gas sensor measures the gases emitted by the transformer. A frequency meter measures the current frequency of the transformer.
[0011] In another embodiment, the TMCU includes a coil winding that receives power supply from the transformer. A power supply unit receives the power supply from the coil winding and provides the power supply to the plurality of sensors, the energy meter, the display, and the microcontroller. A circuit breaker protects the TMCU from overload power or short circuits. A power factor unit adjusts phase relationship between the voltage and current of the TMCU. A memory stores the unique parameters and the predefined criteria of the transformer. A display displays measured unique parameters of the transformer, the primary anomalies of the transformer, the secondary anomalies of the transformer, and the predefined criteria of the transformer. A communicator is connected to the microcontroller for creating the wireless connection with the MCC server.
[0012] In another embodiment, the control actions includes increase cooling rate, reduce cooling rate, adjust tap changer, increase oil flow, decrease oil flow, activate alarms, activate automatic shutdown, adjust load sharing, adjust phase balance, adjust frequency, adjust cooling system, adjust the winding temperature, and activate dehumidifiers in the transformer.
[0013] Accordingly, the embodiments herein provide a Management Control Centre (MCC) server including a database that stores information of a plurality of transformers. A wireless unit is configured to create the wireless connection with a plurality of TMCUs. Each TMCU of the plurality of TMCUs is connected to each transformer of the plurality of transformers located in the first geographic location and the MCC server is located in the second geographic location. A MCC controller is connected to the database and the wireless unit, configured to remotely monitor the current state of the transformer displayed on the display of each TMCU of the plurality of TMCUs using the wireless connection, the current state indicates unique parameters of the plurality of transformers measured by the corresponding TMCUs and detect anomalies associated with the transformer of the plurality of transformers by applying machine learning model on the remotely monitored unique parameters of the plurality of transformers located in the first geographic location. The MCC server determines corrective actions to be performed by the TMCU of the transformer and an event based transformer configuration to be applied by the TMCU of the transformer, and sends control commands to the TMCU corresponding to the transformer using the wireless connection, the control commands indicative of the event based transformer configuration to be applied by the TMCU and the corrective actions to be performed by the TMCU of the transformer.
[0014] In another embodiment, the anomalies associated with the transformer is one of primary anomalies and secondary anomalies, the primary anomalies has higher priority over the secondary anomalies.
[0015] In another embodiment, the MCC server further comprises an Artificial Intelligence (AI) engine which is trained to detect or predict the anomalies associated with the transformer by collecting statistical data of the unique parameters from the plurality of transformers to generate a model for identifying the anomalies of the transformer, and training the model based on machine learning techniques to detect or predict the anomalies associated with the transformer.
[0016] In another embodiment, determine the anomalies associated with the transformer based on the current state of the transformer includes determining anomalies by comparing the unique parameters of the transformer with a predefined criteria stored in the database.
[0017] In another embodiment, generate the control commands indicative of the corrective actions includes analyze the anomalies associated with the transformer based on the unique parameters received from the TMCU and determine the corrective actions from the plurality of predetermined corrective actions based on the type of the anomalies, and generate the control commands indicating the corrective actions to be performed by the TMCU of the transformer for rectifying the anomalies associated with the transformer, and sending the control commands to the TMCU over the wireless connection.
[0018] In another embodiment, the MCC server further comprises the database configured to store the unique parameters of the transformer and historical unique parameters of the plurality of transformers, and generate a report based on the unique parameters of the transformer and predict the anomalies based on the historical unique parameters of the plurality of transformers.
[0019] In another embodiment, the report includes information of the unique parameters of the transformer, and the anomalies associated with the transformer, and the corrective actions are determined from the plurality of predetermined corrective actions based on the high priority anomalies and low priority anomalies associated with the transformer.
[0020] In another embodiment, the plurality of predetermined corrective actions includes adjusting the load balancing and optimizing the power distribution for the transformer, regulating the input and output power of the transformer, adjusting a cooling system of the transformer, repairing damaged components of the transformer, and rectifying potential failures in the transformer.
[0021] Accordingly, the embodiments herein provide a method for monitoring and controlling the transformer based on the TMCU. The method includes measuring unique parameters of the transformer using the TMCU. The TMCU is electrically connected to the transformer located in the first geographic location. The method includes creating the wireless connection with the MCC server located at the second geographic location for remote monitoring and controlling the transformer based on the unique parameters measured by the plurality of sensors. Further, the method includes displaying the current state of the transformer on the display for remote monitoring and controlling the transformer by the MCC server using the wireless connection, the current state indicates at least one of the unique parameters of the transformer; and monitoring and controlling the current state of the transformer using the wireless connection with the MCC server.
[0022] Accordingly, the embodiments herein provide a method for monitoring and controlling the plurality of transformers based on the MCC server. The method includes storing information of the plurality of transformers and creating the wireless connection with the plurality of TMCUs. Each TMCU of the plurality of TMCUs is connected to each transformer of the plurality of transformers located in the first geographic location and the MCC server is located in the second geographic location. The current state of each transformer of the plurality of transformers are remotely monitored and controlled based on each TMCU of the plurality of TMCUs by using the wireless connection, the current state indicates the unique parameters of the plurality of transformers measured by the corresponding TMCUs. The method also includes detecting the anomalies associated with each transformer of the plurality of transformers by applying the machine learning model on the remotely monitored unique parameters of the plurality of transformers located in the first geographic location. Further, the method includes determining the corrective actions to be performed by the TMCU of the transformer and an event based transformer configuration to be applied by the TMCU of the transformer; and sending control commands to the TMCU corresponding to the transformer using the wireless connection, the control commands indicative of the event based transformer configuration to be applied by the TMCU and the corrective actions to be performed by the TMCU of the transformer.
[0023] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
BRIEF DESCRIPTION OF FIGURES
[0024] This invention is illustrated in the accompanying drawings, throughout which like reference letters indicate corresponding parts in the various figures. The embodiments herein will be better understood from the following description with reference to the drawings, in which:
[0025] FIG. 1 is a block diagram of a Transformer Monitoring and Controlling Unit (TMCU), according to the embodiments as disclosed herein;
[0026] FIG. 2 illustrates a block diagram of a transformer management system, according to the embodiments as disclosed herein;
[0027] FIG. 3 illustrates an architecture for a Key Performance Indicator (KPI) manager in the transformer management system, according to the embodiments as disclosed herein;
[0028] FIG. 4 is a flow chart illustrating step-by-step process for automatically monitoring and controlling the transformer, according to the embodiments as disclosed herein;
[0029] FIG. 5 is a flow chart illustrating step-by-step process for automatically monitoring and controlling the transformer by the TMCU, according to the embodiments as disclosed herein;
[0030] FIG. 6 is a flow chart illustrating step-by-step process for remotely monitoring and controlling the transformer by a Management Control Centre (MCC) server, according to the embodiments are disclosed herein.
DETAILED DESCRIPTION OF INVENTION
[0031] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term “or” as used herein, refers to a non-exclusive or, unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[0032] As is traditional in the field, embodiments may be described and illustrated in terms of blocks that carry out a described function or functions. These blocks, which may be referred to herein as managers, units, modules, hardware components or the like, are physically implemented by analog and/or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits and the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, or by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the proposed method. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the proposed method.
[0033] The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the proposed method should be construed to extend to any alterations, equivalents and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.
[0034] Accordingly, the embodiments herein provide a Transformer Monitoring and Control Unit (TMCU) that includes an electric circuit connected to a transformer, located in a first geographic location for providing electricity to a plurality of electricity consumers. A plurality of sensors is connected to the electric circuit to measure unique parameters of the transformer. An energy meter is connected to the plurality of sensors to measure power passing through the transformer. A display connected to the energy meter. A microcontroller coupled to the electric circuit, the plurality of sensors, the energy meter, and the display. The microcontroller is configured to receive the unique parameters of the transformer measured by the plurality of sensors and create a wireless connection with a Management Control Centre (MCC) server located at a second geographic location for remote monitoring and controlling the transformer. The TMCU displays a current state of the transformer on the display for remote monitoring and controlling the transformer by the MCC server using the wireless connection. The current state indicates the unique parameters of the transformer. Further, the TMCU remotely monitors and controls the current state of the transformer using the wireless connection with the MCC server.
[0035] Accordingly, the embodiments herein provide the MCC server includes a database that stores information of the plurality of transformers. A wireless unit configured to create the wireless connection with the plurality of TMCUs. Each TMCU of the plurality of TMCUs is connected to the transformer of the plurality of transformers located in the first geographic location and the MCC server is located in the second geographic location. A MCC controller is connected to the database and the wireless unit. The MCC controller is configured to remotely monitor the current state of the transformer displayed on the display of each TMCU of the plurality of TMCUs by the wireless connection. The current state indicates the unique parameters of the plurality of transformers measured by the corresponding TMCUs. The MCC controller detects the anomalies associated with each transformer of the plurality of transformers by applying the machine learning model on the remotely monitored unique parameters of the plurality of transformers located in the first geographic location. The MCC server determines corrective actions to be performed by the TMCU of the transformer and an event based transformer configuration to be applied by the TMCU of the transformer, and sends control commands to the TMCU corresponding to the transformer by the wireless connection. The control commands indicative of event based transformer configuration to be applied by the TMCU and the corrective actions to be performed by the TMCU of the transformer.
[0036] Accordingly, the embodiments herein provide a method for monitoring and controlling the transformer based on the TMCU. The method includes measuring the unique parameters of the transformer using the TMCU. The TMCU is electrically connected to the transformer located in the first geographic location and creating the wireless connection with the MCC server located at the second geographic location for remote monitoring and controlling the transformer based on the unique parameters measured by the plurality of sensors. The method also includes displaying the current state of the transformer on the display for remote monitoring and controlling the transformer by the MCC server using the wireless connection. The current state indicates the unique parameters of the transformer and monitoring and controlling the current state of the transformer by using wireless connection with the MCC server.
[0037] Accordingly, the embodiments herein provide a method for monitoring and controlling the plurality of transformers based on the MCC server. The method includes storing information of the plurality of transformers and creating the wireless connection with the plurality of TMCUs. Each TMCU of the plurality of TMCUs is connected to each transformer of the plurality of transformers located in the first geographic location and the MCC server is located in the second geographic location. The current state of each transformer of the plurality of transformers is remotely monitored and controlled by using each TMCU of the plurality of TMCUs based on the wireless connection. The current state indicates the unique parameters of the plurality of transformers measured by the corresponding TMCUs. The MCC server detects the anomalies associated with the plurality of transformers by applying the machine learning model on the remotely monitored unique parameters of the plurality of transformers located in the first geographic location and determining the corrective actions to be performed by the TMCU of the transformer and the event based transformer configuration to be applied by the TMCU of the transformer. Further, the method includes sending the control commands to the TMCU corresponding to the transformer by using the wireless connection and the control commands indicative of the event based transformer configuration to be applied by the TMCU and the corrective actions to be performed by the TMCU of the transformer.
[0038] In a conventional method, rectification of the transformer is one of the very cost-effective processes in a power distribution network. Whenever the transformer fails, then the transformer needs manual power for repairing, which consumes more manpower as well as cost. To overcome this problem, another conventional method is used to detect the issue of the transformer and sends the issue notification to an operator to proceed with the further steps. It also takes manpower to rectify the transformer problems and also there is no automatic way to rectify the issues in the transformer.
[0039] Unlike the conventional methods, a transformer management system includes the TMCU to detect the unique parameters of the transformer and sends the unique parameters to the MCC server to detect and predict the anomalies associated with the transformers. Once the MCC server receives the unique parameters of the transformer, then the MCC server detects and predicts the anomalies associated with the transformer and sends the control commands to the TMCU to automatically rectify the detected and predicted anomalies associated with the transformer by using the AI technique.
[0040] Referring now to the drawings and more particularly to FIGS. 1 through 6, where similar reference characters denote corresponding features consistently throughout the figure, these are shown preferred embodiments.
[0041] FIG. 1 illustrates a block diagram of the TMCU (100a), according to the embodiments as disclosed herein.
[0042] Referring to the FIG. 1, the TMCU (100a) includes an electric circuit (102), a sensor (103a), a processor (104), an energy meter (105), a display (106), and a microcontroller (107). The electric circuit (102) includes a coil winding unit (102a), a circuit breaker (102b), and a power supply unit (102c). The electric circuit (102) is configured to receive power from a transformer (101a) by using the coil winding unit (102a). The transformer (101a) can be but not limited to a distribution transformer, a power transformer, a pole mount transformer, a pad mounted transformer, a service transformer, a phase-shifting transformers, etc. The coil winding unit (102a) is configured with a primary winding and a secondary winding, where the primary winding is used to receive electrical power and the secondary winding is used to supply power to the power supply unit (102c). The circuit breaker (102b) is used to protect the TMCU (100a) from overload power or short circuits. The power supply unit (102c) is used to receive the power supply from the coil winding unit (102a) and provide the power supply to the plurality of sensors (103a-N), the energy meter (105), the display (106), and the microcontroller (107). The circuit breaker (102b) is used to protect the TMCU (100a) from overload power or short circuits.
[0043] The electric circuit (102) of the TMCU (100a) is connected to the transformer (101a) that is located in the first geographic location providing electricity to the plurality of electricity consumers. The plurality of sensors (103a-N) are connected to the electric circuit (102) to measure the unique parameters of the transformer (101a). The energy meter (105) is connected to the plurality of sensors (103a-N) to measure power passing through the transformer (101a) based on the unique parameters which are measured by the plurality of sensors (103a-N). The display (106) is connected to the energy meter (105) and displays the measured unique parameters of the transformer (101a) based on the unique parameters received from the energy meter (105).
[0044] The microcontroller (107) of the TMCU (100a) is configured to receive the unique parameters of the transformer (101a) measured by the plurality of sensors (103a-N) and transferring the unique parameters to a MCC server (210) via wireless medium (201) which is located at the second geographic location for remote monitoring and controlling the transformer (101a).
[0045] The microcontroller (107) is implemented by processing circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like.
[0046] At least one of the plurality of modules/ components of the microcontroller (107) may be implemented through an AI model. A function associated with the AI model may be performed through memory (108) and the processor (not shown in figures). The one or a plurality of processors controls the processing of the input data in accordance with a predefined operating rule or the AI model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.
[0047] Here, being provided through learning means that, by applying a learning process to a plurality of learning data, a predefined operating rule or AI model of a desired characteristic is made. The learning may be performed in a device itself in which AI according to an embodiment is performed, and/or may be implemented through a separate server/system.
[0048] The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include, but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.
[0049] The learning process is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning processes include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.
[0050] The display (106) is configured to display the current state of the transformer (101a) for remote monitoring and controlling the transformer by the MCC server (210) using the wireless medium (201), where the current state indicates the unique parameters of the transformer (101a), and remotely monitor and control the current state of the transformer (101a) using the wireless medium (201) with the MCC server (210).
[0051] The TMCU (100a) further includes a memory (108), a communicator (109), a control unit (110), and a surge protection unit (111). The memory (108) is configured for storing the unique parameters and the predefined criteria of the transformer (101a). Also, the memory (108) is configured to store instructions to be executed by the processor (not shown in figure). The memory (108) can include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory (108) may, in some examples, be considered a non-transitory storage medium. The term “non-transitory” may indicate that the storage medium is not embodied in a carrier wave or a propagated signal. However, the term “non-transitory” should not be interpreted that the memory (108) is non-movable. In some examples, the memory (108) is configured to store larger amounts of information. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache).
[0052] The communicator (109) is connected to the microcontroller (107) for transferring the unique parameters to the MCC server (210) via the wireless medium (201). The control unit (110) includes a voltage regulator (110a), a power factor unit (110b), and a relay unit (110c). For example, if the transformer (101a) facing the overvoltage or under voltage issues, then the voltage regulator (110a) of the control unit (110) regulates the voltage of the transformer (101a) and maintains it within a specified range, to ensure the proper functioning of the transformer (101a) and prevent damage due to the overvoltage or under voltage of the transformer (101a). Also, the voltage regulator (110a) is used to regulate the voltage of the TMCU (100a). Similarly, if the transformer (101a) facing the uninterrupted power supply to the consumers, then the relay unit (110c) controls the switching of the transformer (101a) between different power sources or loads during maintenance or emergencies to ensure uninterrupted power supply to the consumers. The surge protection unit (111) is used to protect the transformer (101a) from power surges and transient voltage spikes occurring on the transformer (101a). Also, the surge protection unit (111) protects the TMCU (100a) from the power surges and the transient voltage spikes occurring on the TMCU (100a).
[0053] The control unit (110) is implemented by processing circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like.
[0054] At least one of the plurality of modules/ components of the control unit (110) may be implemented through an AI model. A function associated with the AI model may be performed through memory (108) and the processor (not shown in figures). The one or a plurality of processors controls the processing of the input data in accordance with a predefined operating rule or the AI model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.
[0055] Here, being provided through learning means that, by applying a learning process to a plurality of learning data, a predefined operating rule or AI model of a desired characteristic is made. The learning may be performed in a device itself in which AI according to an embodiment is performed, and/or may be implemented through a separate server/system.
[0056] The AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks include, but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.
[0057] The learning process is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning processes include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.
[0058] The microcontroller (107) of the TMCU (100a) is configured to detect the primary anomalies associated with the transformer (101a). The primary anomalies is detected by comparing the unique parameters of the transformer (101a) received from the plurality of sensors (103a-N) with the predefined criteria stored in the memory (108) of the TMCU (100a). The microcontroller (107) generates the control actions to rectify the primary anomalies of the transformer (101a) when the primary anomalies associated with the transformer is detected and applies the control actions to rectify the primary anomalies of the transformer (101a). Also, the microcontroller (107) updates the current state of the transformer (101a) to the MCC server (210) by using the wireless medium (201) that is established between the TMCU (100a) and the MCC server (210), where the updated current state indicates the unique parameters of the transformer (101a). Therefore, the microcontroller (107) of the TMCU (100a) have capabilities to execute the calculations to detect the primary anomalies associated with the transformer (101a) and rectify the primary anomalies locally.
[0059] The TMCU (100a) is configured to remotely monitor and control the current state of the transformer (101a) by using the wireless medium (201) with the MCC server (210). The MCC server (210) receives the information of the secondary anomalies associated with the transformer (101a) and the MCC server (210) sends the control commands to the TMCU (100a), where the control commands indicates the corrective actions to be performed by the TMCU (100a). Once the TMCU (100a) receives the control commands from the MCC server (210), then the secondary anomalies associated with the transformer is rectified by the TMCU (100a) based on performing corrective actions by applying the received control commands on the transformer (101a). Also, the TMCU (100a) updates the current state of the transformer on the display (106) of the TMCU (100a) and sends the updated current state of the transformer (101a) to the MCC server (210) via the wireless medium (201) once the corrective actions are applied by the TMCU (100a).
[0060] The primary anomalies associated with the transformer (101a) is rectified by applying the control actions to the transformer (101a). The primary anomalies associated with the transformer (101a) include but not limited to abnormal cooling rate, abnormal voltage, abnormal oil flow, facing overload issue, abnormal phase, abnormal frequency, abnormal oil level, abnormal oil quality, abnormal temperature, abnormal winding temperature, abnormal oil pressure, abnormal current, high humidity, abnormal gas levels, etc.
[0061] Once the primary anomalies associated with the transformer (101a) is detected, then the microcontroller (107) sends the command to the control unit (110) to take the necessary control actions to rectify the primary anomalies associated with the transformer (101a), where the control actions include but not limited to increase cooling rate, reduce cooling rate, adjust tap changer, increase oil flow, decrease oil flow, activate alarms, activate automatic shutdown, adjust load sharing, adjust phase balance, adjust frequency, adjust cooling system, adjust the winding temperature, activate dehumidifiers, etc.
[0062] In an embodiment, if the temperature within the transformer (101a) is too high, then the TMCU (100a) can increase the cooling rate to bring it down to a safe level. This can be done by increasing the flow of coolant or adjusting fans (not shown in figures). The nominal temperature range for a transformer (101a) is typically between 60-90°C, and the TMCU (100a) may trigger the control actions if the temperature exceeds the upper limit of this range.
[0063] In another embodiment, if the temperature within the transformer (101a) is too low, then the TMCU (100a) can reduce the cooling rate to prevent damage to the transformer (101a). This can be done by decreasing the flow of coolant or adjusting the fans. The nominal temperature range for the transformer is typically between 60-90°C, and the TMCU (100a) may trigger the control actions if the temperature falls below the lower limit of this range.
[0064] In another embodiment, basically, a tap changer is responsible for regulating the voltage levels of the transformer (101a). If the voltage is outside the desired range, then the TMCU (100a) can trigger the tap changer to adjust the transformer's voltage to its nominal level. The parameters ranges for the tap changer adjustment can vary depending on the transformer's rating and design, but typically the acceptable voltage range is between 95% and 105% of the nominal voltage rating.
[0065] In another embodiment, basically, the oil of the transformer (101a) helps to lubricate the components and cool the transformer (101a). If the oil flow is too low, it can cause damage to the transformer (101a). The TMCU (100a) can trigger an increase in oil flow by opening valves or pumps to ensure the transformer (101a) is properly lubricated. The nominal range for oil flow can also vary depending on the transformer's rating and design, but it typically ranges between 0.05% and 0.2% of the transformer's total volume.
[0066] In another embodiment, if the oil flow is too high, it can cause issues such as foaming and overpressure within the transformer (101a). At that time, the TMCU (100a) can trigger decrease in oil flow by closing valves or reducing the speed of pumps. The acceptable range for oil flow is usually between 0.05% and 0.2% of the transformer's total volume.
[0067] In another embodiment, the TMCU (100a) can trigger alarms to alert operators when a primary anomalies is detected. The parameters that trigger the alarms can vary depending on the type of anomalies being detected, but they typically include high temperatures, low oil levels, and abnormal gas concentrations.
[0068] In another embodiment, if the primary anomalies is detected, then the TMCU (100a) can initiate an automatic shutdown of the transformer (101a) to prevent further damage. The parameters that trigger the automatic shutdown can also vary depending on the type of anomalies being detected, but they typically include severe overloads, high temperatures, and low oil levels.
[0069] In another embodiment, the transformer (101a) is part of the plurality of transformers (101a-N), the TMCU (100a) can adjust the load sharing to ensure that the transformers (101a-N) are operating within their safe limits. The parameters that trigger load sharing adjustments can include transformer ratings, load demand, and ambient temperatures.
[0070] In another embodiment, the TMCU (100a) can adjust the phase balance to ensure that the transformer (101a) is operating within its safe limits. The acceptable range for phase balance is typically between 1% and 3% of the nominal voltage.
[0071] In another embodiment, if the frequency of the transformer (101a) is outside the desired range, then the TMCU (100a) can adjust it to bring it back into the acceptable range. The acceptable frequency range varies depending on the transformer's design and location, but it is typically between 48 and 52 Hz.
[0072] In another embodiment, the TMCU (100a) can adjust the cooling system (not shown in figures) to ensure that the transformer (101a) is operating within its safe temperature range. The acceptable temperature range can vary depending on the transformer's rating and design, but it is typically between 50°C and 90°C.
[0073] In another embodiment, if the humidity of the transformer (101a) is too high, then the TMCU (100a) can activate dehumidifiers to prevent damage to the transformer (101a). The nominal range for humidity is typically 30% to 60%, but may vary depending on the specific application and environmental conditions.
[0074] In another embodiment, the control actions includes alert the operator if the oil level is too low. The acceptable oil level range can vary depending on the transformer’s rating and design, but it is typically between 25% and 75% of the total oil volume.
[0075] In another embodiment, the control actions includes indicating the quality of the oil within the transformer (101a) and alert the operator if oil needs to be changed. The acceptable range for oil quality can vary depending on the transformer's design and oil type, but it typically includes factors such as acidity, water content, and dissolved gas concentrations.
[0076] In another embodiment, the control actions include adjusting the cooling system to ensure that the transformer (101a) is operating within its safe temperature range. The safe temperature range can vary depending on the transformer's rating and design, but it is typically between 50°C and 90°C.
[0077] In another embodiment, the control actions include alerting the operator if the temperature of the transformer (101a) is too hot. The nominal range for winding temperature depends on the type of transformer (101a) and the application. For example, the winding temperature of the distribution transformer is typically maintained between 65-85°C. If the temperature goes beyond the nominal range, then the TMCU (100a) can trigger the control actions to adjust the cooling system, increase the oil flow, or activate an alarm.
[0078] In another embodiment, the control actions includes alert the operator if the oil pressure of the transformer (101a) is too low. The nominal range for the oil pressure also depends on the type of transformer (101a) and the application. For example, the oil pressure of the power transformer is typically maintained between 35-45 psi. If the pressure goes below the nominal range, then the TMCU (100a) trigger the control actions to adjust the oil flow, adjust the cooling system, or activate the alarm.
[0079] In another embodiment, the control actions includes alerting the operator if the voltage is outside of the desired range. The nominal range for voltage may vary depending on the specific transformer and its application, but typical ranges are 110 kV to 500 kV for high voltage power transformers and 10 kV to 35 kV for distribution transformers.
[0080] In another embodiment, the control actions includes alert the operator if the current is outside of the desired range. The nominal range for current may also vary depending on the specific transformer and its application, but typical ranges are several hundred amps to several thousand amps for power transformers and up to few hundred amps for distribution transformers.
[0081] In one or more embodiments, the control actions include alerting the operator if the gas level is outside of the desired range, indicating a possible fault. The gas levels can include hydrogen, carbon monoxide, and moisture, which are byproducts of transformer operation. The nominal ranges for these gases may vary depending on the specific transformer and its application, but typical ranges are less than 1000 ppm for hydrogen, less than 50 ppm for carbon monoxide, and less than 500 ppm for moisture. Elevated gas levels can indicate a developing fault within the transformer (101a), and prompt action may be necessary to prevent further damage. TMCU (100a) will execute the control actions locally to isolate the transformer (101a) from the grid (not shown in figure) and inform the MCC server (210) accordingly.
[0082] Similarly, the secondary anomalies associated with the transformer (101a) is rectified by applying the control commands received from the MCC server (210), where the secondary anomalies associated with the transformer (101a) include but not limited to abnormal load balancing, abnormal input and output power abnormal cooling system, components damage, potential failures, etc.
[0083] Once the secondary anomalies is detected by the TMCU (100a), then the microcontroller (107) triggers the communicator (109) to send the command to the MCC server (210), where the MCC server (210) identifies the corrective actions with respect to the secondary anomalies and generates the control commands based on the corrective actions. The control commands transmitting to the TMCU (100a) to apply the corrective actions to rectify the anomalies associated with the transformer (101a), where the corrective actions such as adjusting the load balancing and optimizing the power distribution, regulating the input and output power, adjusting the cooling system, repairing damaged components, and rectifying potential failures, etc.
[0084] The MCC server (210) is configured to monitor and control the current state of the transformer (101a) by using the wireless medium (102) with the TMCU (100a). The MCC server (210) receives the information about the event associated with the another transformers (101b-N) which is available in same area of the first geographic location, where the TMCU (100a) of the transformer (101a) receives the control commands with respect to the event which is associated with the another transformers (101b-N) available in the same area of the first geographic location. The TMCU (100a) applies the event based transformer configuration on the transformer (101a) based on the received control commands from the MCC server (210). Also, the TMCU (100a) updates the current state of the transformer (101a) to the MCC server (210) via the wireless medium (201), where the updated current state of the transformer (101a) indicates the unique parameters of the transformer (101a) and the information about the event associated with the another transformers (101b-N) available in the same area of the first location.
[0085] For example, considering a scenario, where the plurality of transformers (101a-N) are located in the same area of the first geographical location which transmits the unique parameters to the common centralized MCC server (210) via the wireless medium (201) by using the TMCUs (100a-N) associated with the each of the plurality of transformers (101a-N). If the specific transformer (101a) of the plurality of transformers (101a-N) facing any events, then the event information of the specific transformer (101a) is sent to the MCC server (210) by using the TMCUs (100a) which is connected with the specific transformer (101a). The MCC server (210) sends the control commands to the another transformers of the plurality of transformers (101b-N) by receiving the event information associated with the specific transformer (101a) which is located in the same area of the first geographical location, where the event associated with the specific transformer (101a) such as abnormal voltage, facing overload issue, abnormal phase, abnormal frequency, abnormal current, etc. Whenever the event occurring in the particular transformer of the plurality of transformer (101a-N), then the MCC server (210) sends the control commands to the all other transformers of the plurality of transformers (101a-N) which are located in the same area of the first geographical location.
[0086] The plurality of sensors (103a-N) of the TMCU (100a) are configured to detect the unique parameters of the transformer (101a), where the unique parameters include but not limited to a current voltage range of the transformer , a current flow of the transformer, an input power of the transformer, an output power of the transformer, a current temperature of the transformer, a short circuit current deviation of the transformer, an oil level of the transformer, an oil temperature variation of the transformer, a winding temperature variation of the transformer, a surface temperature of the transformer, a mechanical vibration of the transformer, a magnetic field of the transformer, a gases emitted by the transformer, a loss of life of the transformer, a number of consumers connected to the transformer, a load level of each consumer connected to the transformer, and a frequency of the transformer.
[0087] The TMCU (100a) includes the plurality of sensors (103a-N), where the plurality of sensors (103a-N) include but not limited to a voltage sensor, a temperature sensor, an oil level sensor, a vibration sensor, a current sensor, a magnetic field sensor, and a gas sensor, where the voltage sensor is configured to measure the current voltage range, the current flow, the short circuit current deviation, the current frequency, the input power, and the output power of the transformer (101a). The temperature sensor is configured to measure the current temperature, the oil temperature variation, surface temperature, and the winding temperature variation of the transformer (101a). The oil level sensor is configured to measure the oil level of the transformer (101a). The vibration sensor measures the mechanical vibrations of the transformer (101a). The current sensor measures the load level of each consumer connected to the transformer (101a), and the number of consumers connected to the transformer (101a). The magnetic field sensor detects the magnetic field generated by the transformer (101a). The gas sensor measures the gases emitted by the transformer (101a). The TMCU (100a) further includes a frequency meter (not shown in figures) that measures the current frequency of the transformer (101a).
[0088] In an embodiment, referring to the FIG. 1, the TMCU (100a) is connected with a backup power supply (112) that provides emergency power to the TMCU (100a) in case of a power outage, to ensure the continuous operation of the TMCU (100a) and prevent data loss or system failure.
[0089] Although the FIG. 1 illustrates the hardware elements of the TMCU (100a) but it is to be understood that other embodiments are not limited thereon. In other embodiments, the TMCU (100a) may include less or more number of elements. Further, the labels or names of the elements are used only for illustrative purpose and does not limit the scope of the invention. One or more components can be combined together to perform same or substantially similar function.
[0090] FIG. 2 illustrates a block diagram of the transformer management system (200), according to the embodiments as disclosed herein.
[0091] Referring to the FIG. 2, the transformer management system (200) includes the plurality of TMCUs (100a-N) connected to the transformers (101a-N), the MCC server (210), and a Utility Management System (212).
[0092] The plurality of TMCUs (100a-N) are configured to monitor and control the respective transformer of the plurality of transformers (101a-N), where the plurality of TMCUs (100a-N) are configured to send the unique parameters associated with the respective transformers (101a-N) via the wireless medium (201) to the MCC server (210) which is located in the second geographical location. The MCC server (210) includes a transceiver (202), a database (203), and a MCC controller (211).
[0093] The database (203) stores information of the plurality of transformers (101a-N), where the information of the transformer include but not limited to serial number of the transformer, exact location of the transformer, predefined criteria with respect to the each of the transformer (101a), the unique parameters of the transformer (101a), historical unique parameters of the plurality of transformers (101a-N), predetermined corrective actions and so on. The database (203) further configured to store the updated current state of the transformer (101a) based on the primary anomalies and the secondary anomalies rectified by the TMCU (100a) connected to the transformer (101a), where the updated current state indicates the unique parameters of the transformers (101a-N) after the rectification of the primary anomalies and the secondary anomalies.
[0094] The wireless unit (202) of the MCC server (210) is configured to receive the real-time unique parameters and updated unique parameters of the plurality of transformers (101a-N) from the TMCUs (100a-N) associated with the each of the transformer of the plurality of transformers (101a-N).
[0095] The MCC controller (211) includes the AI engine (204), an optimization engine (205), a Key performance Indicator (KPI) rules engine (206), an authorization engine (207), a crew control manager (208), and a real time analytics monitor (209).
[0096] The MCC controller (211) is connected to the database (203) and the wireless unit (202), where the MCC controller (211) is configured to monitor the current state of the transformer (101a) by receiving the unique parameters of the transformer (101a) from the TMCU (100a), where the current state indicates the unique parameters of the plurality of transformers (101a-N) measured by the corresponding TMCUs (100a-N).
[0097] The plurality of TMCUs (100a-N) of the plurality of transformers (101a-N) detects the unique parameters of the plurality of transformers (101a-N) and sends the information of the unique parameters to the MCC server (210). Once the MCC server (210) receives the information of the unique parameters, then the MCC controller (211) determines and predicts either the secondary anomalies and/or any event by comparing the unique parameters with the predefined criteria which is stored in the database (203). If the secondary anomalies and/or any event is detected among the plurality of transformers (101a-N), then the database (203) stores either the secondary anomalies and/or any event corresponding to the unique parameters which is detected in the respective transformer of the plurality of transformers (101a-N). The secondary anomalies and/or any event of the plurality of transformers (101a-N) is determined by the AI engine (204) of the MCC controller (211).
[0098] Once the AI Engine (204) determines either the secondary anomalies and/or any event associated with the plurality of transformers (101a-N) and applies the machine learning model on the unique parameters of the plurality of transformers (101a-N) located in the first geographical location. The AI Engine (204) is connected to the KPI rules engine (206) to detect and predict either the type of secondary anomalies and/or type of event associated with the plurality of transformers (101a-N) by getting the estimation of the KPI values from the KPI rules engine (206). The KPI values include but not limited to prediction of failure probability of the plurality of transformers (101a-N) and operational state of the plurality of transformers (101a-N). The operational state includes but not limited to transformer's age, usage patterns, and environmental conditions with respect to the location of the transformer (101a). Based on the KPI values, the AI engine (204) is configured to detect and predict either the type of secondary anomalies and/or the type of event associated with the plurality of transformers (101a-N).
[0099] The AI engine (204) is interconnected to the optimization engine (205) and the KPI rules engine (206), and configured to detect and predict either the type of secondary anomalies and/or the type of event associated with the plurality of transformers (101a-N) by using the KPI rules engine (206). Once the type of secondary anomalies and/or type of event is detected, then the AI engine (204) is configured to determine the corrective actions corresponding to the secondary anomalies and/or the type of event associated with the plurality of transformers (101a-N) and send the control commands to the each TMCU of the plurality of TMCUs (100a-N) for applying the control commands to the each transformer of the plurality of transformers (101a-N). The control commands are generated based on the determination of corrective actions with respect to the type of anomalies and/or the type of event associated with the each transformer of the plurality of transformers (101a-N) and transmitting the control commands to each TMCU of the plurality of TMCUs (100a-N) through the authorization engine (207), where the authorization engine (207) connected to the crew control manager (208) and the wireless unit (202).
[00100] If one or more secondary anomalies or event is detected with respect to one of the abnormal load balancing, abnormal input and output power, abnormal cooling system, potential failures, abnormal voltage, facing overload issue, abnormal phase, abnormal frequency or abnormal current, then the AI engine (203) triggers the authorization engine (202) to send the control commands to the each TMCU of the plurality of TMCUs (100a-N) for controlling the each transformer of the plurality of transformers (101a-N) via the wireless medium (201) by establishing the communication between each TMCU of the plurality of TMCUs (100a-N) and the wireless unit (202).
[00101] In an embodiment, if one or more secondary anomalies is detected with respect to the abnormal cooling rate or abnormal oil flow or abnormal oil level or abnormal oil quality or abnormal oil pressure or abnormal gas levels or abnormal temperature or abnormal voltage or current range, then the AI engine (203) triggers the authorization engine (202) to send the alert to the crew control manager (208). The crew control manager (208) sends the notification to the operator to take the necessary actions to rectify the secondary anomalies.
[00102] In another embodiment, the MCC server (210) controls each transformer of the plurality of transformers (101a-N) based on the determined corrective actions, where the corrective actions are determined based on both the secondary anomalies and the event associated with each transformer of the plurality of transformers (101a-N) which are available in the same area of the first geographical location. The MCC server (210) sends the control commands indicative of corrective actions to the each TMCU of the plurality of TMCUs (100a-N) for controlling each transformer of the plurality of transformers (101a-N) with respect to the secondary anomalies and the event associated with the each transformer of the plurality of transformers (101a-N).
[00103] In another embodiment, the anomalies associated with the plurality of transformers (101a-N) is one of the primary anomalies and the secondary anomalies. The primary anomalies has higher priority over the secondary anomalies, so that the primary anomalies are rectified by each TMCU of the plurality of TMCUs (100a-N) itself and similarly, the secondary anomalies are rectified by each TMCU of the plurality of TMCUs (100a-N) by receiving the control commands from the MCC server (210) via the wireless medium (201).
[00104] The real time analytics monitor (209) of the MCC server (210) is used to display the unique parameters, the primary anomalies, the secondary anomalies, and the events of each transformer of the plurality of transformers (101a-N) which are received from the database (203).
[00105] In an embodiment, the AI engine (204) of the MCC server (210) is trained to detect and predict the anomalies associated with each transformer of the plurality of transformers (101a-N). The AI engine (204) is trained based on collecting the statistical data of the unique parameters from the plurality of transformers (101a-N) to generate a model for identifying the anomalies of the plurality of transformers (101a-N), where the model is trained based on the machine learning techniques to detect or predict the anomalies associated with each transformer of the plurality of transformers (101a-N). The AI engine (204) is trained using the machine learning approach. To train the AI engine (204), historical data from the plurality of transformers (101a-N) is collected and used to develop the model that can identify patterns and anomalies in the data. The model is then trained using various machine learning algorithms and techniques, such as regression, classification, or clustering, depending on the type of data being analyzed and the problem being addressed. The dataset includes information on various unique parameters of transformers, such as voltage, current, temperature, and vibration, as well as information on the operational state of the transformers, such as maintenance history and failure rates.
[00106] In an embodiment, the AI engine (204) is trained using supervised learning, where the model is given a set of labeled examples and is trained to learn the relationship between the input (transformer parameters) and the output (operational state or anomalies prediction). The labeled examples are created by human experts who manually inspect the transformers and record their status or anomalies. During the training process, the model is fed with a labeled dataset, where each data point is associated with a specific label or outcome, such as a failure, anomalies, or operational state. The method tries to find the best fit function that can map the input features to the corresponding labels. The training process involves adjusting the parameters of the model iteratively until the predicted outcomes match the labeled data as closely as possible.
[00107] In another embodiment, the MCC server (210) is configured to generate the report based on the unique parameters of each transformer of the plurality of transformers (101a-N) and predicting the anomalies based on the historical unique parameters of the plurality of transformers (101a-N), where the report includes the information of plurality of transformers (101a-N) such as serial number, location of transformers, unique parameters, historical unique parameters, primary anomalies, secondary anomalies, control actions taken for primary anomalies, corrective actions taken for secondary anomalies, etc. The report can be a JPEG or PDF or XLSX or CSV or XPS or .DOC or CSV or XML, files.
[00108] The Utility Management System (UMS) (213) controls the MCC server (210) from the power grid operations point of view through the use of an Enterprise Service Bus (ESB) (212). The ESB (212) enables communication between different applications in a distributed computing environment. In this case, the ESB (212) acts as a middleware layer that connects the UMS (213) to the MCC server (210). The UMS (213) can send instructions to the MCC server (210) through the ESB (212), which can then be executed by the MCC server (210) to control the transformers (101a-N).
[00109] The MCC server (210) is a critical component of the UMS (213), which plays a vital role in monitoring and controlling the transformers (101a-N) in real-time. The MCC server (210) is equipped with various AI-enabled components, as described, to enable real-time monitoring and control of transformers. Through the enterprise service bus, the MCC server (210) is connected to the UMS (213). This connection allows the UMS (213) to control the MCC server (210), which in turn enables the UMS (213) to control the transformers (101a-N). The AI-enabled components and other units in the MCC server (210) allow for real-time monitoring of the transformers (101a-N) and its performance, which can be used to make adjustments to the transformer's operations as needed.
[00110] With the ability to receive and analyze the data from the transformers (101a-N), the MCC server (210) can predict potential issues and take proactive measures to prevent the transformer failures. This can greatly improve the reliability of the power distribution system and reduce downtime due to the transformer failures.
[00111] The communication between the MCC server (210) and the UMS (213) is facilitated by the ESB (212), which acts as a middleware. The ESB (212) provides a platform for the communication and integration of various applications, allowing the MCC server (210) and the UMS (213) to interact seamlessly. The ESB (212) allows the MCC server (210) to receive instructions and configurations from the UMS (213), and also enables the MCC server (210) to send real-time data and alerts the UMS (213) as necessary for the power grid operations at a higher level. The real-time data includes transformer real-time status and the unique parameters that are constantly monitored by the AI-enabled system in the MCC server (210).
[00112] In an embodiment, the MCC server (210) can also communicate with the UMS (213) via the wireless medium, providing additional flexibility and redundancy to the communication system. The ESB (212) also provides methods for secure communication between the MCC server (210) and the UMS (213), ensuring that all data transmissions are encrypted and protected. Thereby, ensuring the critical information is not intercepted or compromised by unauthorized parties.
[00113] The use of the ESB (212) in the transformer monitoring and control system provides a reliable and efficient way for the MCC server (210) and the UMS (213) to communicate and collaborate, allowing for real-time monitoring and control of transformers in the power distribution network.
[00114] Although the FIG. 2 illustrates the hardware elements of the transformer management system (200) but it is to be understood that other embodiments are not limited thereon. In other embodiments, the transformer management system (200) may include less or more number of elements. Further, the labels or names of the elements are used only for illustrative purpose and does not limit the scope of the invention. One or more components can be combined together to perform same or substantially similar function.
[00115] FIG. 3 illustrates an architecture for the KPI manager (300) in transformer management system (200), according to the embodiments as disclosed herein.
[00116] Referring to the FIG. 3, the architecture for an AI integrated KPI manager (300) is designed to monitor the KPI status of the plurality of transformers (101a-N) in real-time. The system consists of several layers that work together to provide comprehensive analysis and insights into the condition of transformers (101a-N).
[00117] The first layer of the KPI manager (300) is an online monitoring based layer (301) in the architecture of the KPI manager (300). This online monitoring based layer (301) includes an online monitoring system, reporting system, alarms, and key performance indicator (KPI) monitoring (314). The online monitoring system measures various parameters such as voltage, current, temperature, and other critical parameters to identify any abnormalities in the transformer's functioning. The reporting system generates reports on the current condition of the transformer, and the alarms notify the operators of any potential issues. KPI monitoring tracks the transformer's performance against specific key performance indicators and generates alerts when the transformer's performance deviates from the expected parameters. During the online monitoring, the estimation of unique parameters are pushed to monitoring system (309) through software agent interactions (308).
[00118] The second layer of KPI manager (300) is the KPI Index (303) layer, where the KPI index (303) layer provides an overall KPI estimation from different monitoring techniques (310) and includes failure probability prediction methods. The KPI index (303) layer is responsible for analyzing data from the online monitoring system and deriving an overall KPI estimation based on hybrid (315) of the transformer's operational state. This estimation is based on various factors such as the transformer's age, usage patterns, and the environmental conditions it operates in. The KPI index (303) provides the measurement of the transformer's overall condition through software agent interactions (308).
[00119] The third layer of the KPI manager (300) is a hybrid AI layer (304), where the hybrid AI layer (304) involves hybrid AI modeling, training testing, and optimization processing (311) with the help of the optimization engine (205). The hybrid AI layer (304) includes diagnostic and classification methods and models, real-time and offline inspections correlations, and adjustments (317). The offline inspections are managed through the authorization engine (207) and the crew control manager (208). The hybrid AI models are trained on the historical data collected from the transformers (101a-N) and generate insights into the current state of the transformer's KPIs. The models can identify any anomalies, classify them, and recommend the best course of action to prevent any potential failure. The system also incorporates a real-time inspection feature, which provides feedback on the transformer's condition based on data collected in real-time through software agent interactions (308).
[00120] The fourth layer of KPI manager (300) is a data management layer (305). The data management layer (305) involves using hybrid communication protocols recoding data in the same database (203) based on wirelessly transfer data to the MCC server (210) through software agent interactions (308). The layer is responsible for data cleaning, processing, splitting, labeling, and AI markers (expert comments) (318). The data management layer stores the data in a database (203), which can be used to train the AI models and generate insights into the transformer's KPIs.
[00121] The fifth layer of KPI manager (300) is a data acquisition layer (306), where the data acquisition layer (306) includes the TMCU which includes smart power meter, and multi-sensor components that use hybrid monitoring techniques (313). The TMCU continuously monitors the transformer's condition in hybrid techniques, and collects data by the sensors camera (320) that is then used for analysis through software agent interactions (308). The multi-sensor components measure various parameters such as temperature, oil levels, and vibrations and provide insights into the transformer's overall condition.
[00122] The fifth layer of the KPI manager (300) is a field layer (307), where the field layer (307) provides access to the distribution transformer components, such as its windings, oil immersed (322), etc., for crew inspection and management. The field layer inputs are passed to the MCC server (210) and recorded in the server services and connected database. The data collected from the field inspections can be used to train the AI models and refine the overall KPI estimation.
[00123] The offline monitoring based layer (329) of the KPI manager (300) include a prognostic layer (330), and an expert analysis layer (331). If the offline monitoring based layer (329) predicts the failure of the transformers (101a-N), then pushing failures probabilities occurrence to monitoring system (324) though human agent interactions (323).
[00124] The prognostic layer (330) of the offline monitoring based layer of the KPI manager (300) is responsible for predicting the future condition of the transformers (101a-N) based on historical data analysis. It uses advanced AI methods to analyze the transformer’s data collected over time to estimate the remaining useful life of the transformer (101a). The prognostic layer (330) provides insights into the transformer's potential failure modes, which helps in planning maintenance and repair schedules. In addition to predicting the transformer's remaining useful life, the prognostic layer (330) can also estimate the likelihood of occurrence of the transformer failure. It can provide alerts and recommendations for maintenance and repair actions that should be taken to prevent potential transformer failures. These recommendations are based on the historical data of similar transformers that have failed in the past, and the current state of the transformer's condition. The prognostic layer (330) is a critical component of the KPI manager (300) as it helps to prevent unplanned outages, reduce maintenance costs, and improve the reliability of the transformers (101a-N).
[00125] The integrating expert comments and labels in the developed models (326) will enhance the accuracy and effectiveness of the AI models used in the KPI manager (300). The expert comments and labels provide additional insights and context that can be incorporated into the AI models during training and testing. This can improve the system's ability to accurately predict the transformer's KPIs and detect any anomalies or potential failures. Additionally, the expert comments and labels can help to refine the overall KPI estimation and provide more specific recommendations for maintenance and repairs.
[00126] The layer for expert analysis (331) will involve experts commenting and labeling the current state (327) of transformers (101a-N) based on their observations and analysis. This information will be recorded and stored in the system's database (203) and used to train the AI models in the hybrid AI layer (304). The expert’s comments and labels can help refine the KPI estimation and improve the accuracy of the system's predictions. Additionally, this information can be used by operators to make informed decisions about the maintenance and repair of transformers based on their current condition.
[00127] The expert analysis layer (331) in the offline monitoring layer (329) of the KPI manager (300) will involve analysis by experts who will review the data collected from the transformer and provide their analysis and recommendations. These experts will use their domain knowledge and experience to identify any potential issues with the transformer and recommend the best course of action to prevent any failures. The expert analysis will complement the AI models and provide a human element to the analysis, helping to ensure that all possible issues are identified and addressed.
[00128] Dissolved Gas Analysis (DGA) history (321) is a diagnostic test performed on the transformers (101a-N) to monitor their condition. The DGA history (321) refers to the historical data collected from previous DGA tests performed on the transformer (101a). This data is analyzed and used by the AI models in the hybrid AI layer (304) to provide insights into the transformer's current condition and predict potential failures. By analyzing the levels of gases dissolved in the transformer oil, DGA can detect the presence of faults and identify their severity, making it an essential tool in transformer condition monitoring.
[00129] FIG. 4 is a flow chart (400) illustrating step-by-step process for automatically monitoring and controlling the transformer (101a), according to the embodiments as disclosed herein.
[00130] Referring to the FIG. 4, at step 402, the method includes the transformer management system (200) which continuously monitor and measure the voltage, current, power factor, oil temperature, frequency, load ratios, and power quality of electricity supplied to a distribution transformer.
[00131] At step 404, the method includes the transformer management system (200) which provide alarms for overcurrent, undervoltage, undercurrent and power quality problems and also guide for the real-time control actions.
[00132] At step 406, the method includes the transformer management system (200) which provides trend data for voltage, transformer temperature, and current parameters.
[00133] At step 408, the method includes the transformer management system (200) which monitors the temperature of the transformer at different adaptive levels.
[00134] At step 410, the method includes the transformer management system (200) which produces an event log with all alarms and events detected by the unit.
[00135] At step 412, the method includes the transformer management system (200) which provides an interface for remote monitoring of any alarms or events detected by the unit on computer network or via the wireless medium (201) connection and receive the control actions in real time.
[00136] At step 414, the method includes the transformer management system (200) which produces the report in various formats on demand from remote sites, such as PDFs or CSV or XML files.
[00137] At step 414, the method includes the transformer management system (200) capability to seamlessly interact with the MCC server (210), and the other UMS (213) in an interoperable manner.
[00138] The various actions, acts, blocks, steps, or the like in the method may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the proposed method.
[00139] FIG. 5 is a flow chart (500) illustrating step-by-step process for automatically monitoring and controlling the transformer (101a) by the TMCU (100a), according to the embodiments as disclosed herein;
[00140] Referring to the FIG. 5, at step 502, the method includes the TMCU (100a) measuring unique parameters of a transformer (101a) using the TMCU (100a) that is electrically connected to the transformer (101a) located in the first geographic location.
[00141] At step 504, the method includes the TMCU (100a) creating the wireless connection with the MCC server (210) located at the second geographic location for remote monitoring and controlling the transformer (101a) based on unique parameters measured by the plurality of sensors (103a-N).
[00142] At step 506, the method includes the TMCU (100a) displaying the current state of the transformer on the display (106) for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, and the current state indicates the unique parameters of the transformer (101a).
[00143] At step 508, the method includes the TMCU (100a) monitoring and controlling the current state of the transformer (101a) by using the wireless connection with the MCC server (210).
[00144] The various actions, acts, blocks, steps, or the like in the method may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the proposed method.
[00145] FIG. 6 is a flow chart illustrating step-by-step process for remotely monitoring and controlling the transformer by the MCC server (210), according to the embodiments are disclosed herein.
[00146] Referring to the FIG. 6, at step 602, the method includes the MCC server (210) storing information of the plurality of transformers (101a-N).
[00147] At step 604, the method includes the MCC server (210) creating the wireless connection with the plurality of TMCUs (100a-N), and each TMCU of the plurality of TMCUs (100a-N) is connected to the plurality of transformers (101a-N) located in the first geographic location and the MCC server (210) is located in the second geographic location.
[00148] At step 606, the method includes the MCC server (210) remotely monitoring and controlling the current state of the transformer (101a) displayed on the display (106) of the plurality of TMCUs (100a-N) using the wireless connection, and the current state indicates the unique parameters of the plurality of transformers measured by the corresponding TMCU.
[00149] At step 608, the method includes the MCC server (210) detecting anomalies associated with the plurality of transformers (101a-N) by applying machine learning model on the remotely monitored unique parameters of the plurality of transformers (101a-N) located in the first geographic location.
[00150] At step 610, the method includes the MCC server (210) determining the corrective actions to be performed by the TMCU (100a) of the transformer (101a) and the event based transformer configuration to be applied by the TMCU (100a) of the transformer (101a).
[00151] At step 612, the method includes the MCC server (210) sending the control commands to the TMCU (100a) corresponding to the transformer (101a) using the wireless connection, and the control commands indicative of the event based transformer configuration to be applied by the TMCU (100a) and the corrective actions to be performed by the TMCU (100a) of the transformer (101a).
[00152] The various actions, acts, blocks, steps, or the like in the method may be performed in the order presented, in a different order or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the proposed method.
[00153] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the embodiments as described herein.
, Claims:CLAIMS
We claim:
1. A Transformer Monitoring and Control Unit (TMCU) (100a) comprises:
an electric circuit (102) connected to a transformer (101a), located in a first geographic location, providing electricity to a plurality of electricity consumers;
a plurality of sensors (103a-N), connected to the electric circuit (102), to measure unique parameters of the transformer (101a);
an energy meter (105), connected to the plurality of sensors (103a-N), to measure power passing through the transformer (101a);
a display (106) connected to the energy meter (105);
a microcontroller (107), coupled to the electric circuit (102), the plurality of sensors (103a-N), the energy meter (105), and the display (106), wherein the microcontroller (107) is configured to:
receive the unique parameters of the transformer (101a) measured by the plurality of sensors (103a-N);
create a wireless connection with a Management Control Centre (MCC) (210) server located at a second geographic location for remote monitoring and controlling the transformer (101a);
display a current state of the transformer (101a) on the display (106) of the TMCU (100a) for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the current state indicates at least one of the unique parameter of the transformer (101a); and
remotely monitor and control the current state of the transformer (101a) using the wireless connection with the MCC server (210).
2. The TMCU (100a) as claimed in claim 1, wherein the microcontroller (107) configured to:
detect whether at least one primary anomaly associated with the transformer (101a) by comparing the unique parameters of the transformer (101a) with a predefined criteria stored at the TMCU (100a);
generate at least one control action to rectify at least one primary anomaly of the transformer (101a) when the at least one primary anomaly associated with the transformer (101a) is detected;
applying the at least one control action to rectify the at least one primary anomaly of the transformer (101a);
updating the current state of the transformer (101a) displayed on the display (106) of the TMCU (100a) for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the updated current state indicates the unique parameters of the transformer (101a), the at least one primary anomaly associated with the transformer (101a), and the at least one control action applied to rectify the at least one primary anomaly of the transformer (101a).
3. The TMCU (100a) as claimed in claim 1, wherein remotely monitor and control the current state of the transformer (101a) using the wireless connection with the MCC server (210) comprises:
receive information about at least one secondary anomaly of the transformer (101a) predicted by the MCC server (210);
receive at least one control command indicative of at least one corrective action to be performed by the TMCU (100a) from the MCC server (210) to rectify the at least one secondary anomaly of the transformer (101a);
perform the at least one corrective action by applying the received at least one control command on the transformer (101a) to rectify the at least one secondary anomaly of the transformer (101a); and
update the current state of the transformer (101a) on the display (106) of the TMCU (100a) for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the updated current state indicates the unique parameters of the transformer (101a), the at least one secondary anomaly associated with the transformer (101a), the at least one control command applied to rectify the at least one secondary anomaly of the transformer (101a).
4. The TMCU (100a) as claimed in claim 1, wherein remotely monitor and control the current state of the transformer (101a) using the wireless connection with the MCC server (210) comprises:
receive information about at least one event associated with at least one other transformer (101b) located in the first geographic location from the MCC server (210) located in the second geographic location;
receive the at least one control command indicative of an event based transformer (101a) configuration to be applied by the TMCU (100a) from the MCC server (210) based on the at least one event associated with at least one other transformer (101b) available in the area from the MCC server (210);
apply the event based transformer (101a) configuration on the transformer (101a) based on the received at least one control command; and
update the current state of the transformer (101a) displayed on the display of the TMCU (100a) for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the updated current state of the transformer (101a) indicates the unique parameters of the transformer (101a), information about the at least one event associated with at least one other transformer (101b) available in the area, the event based transformer configuration applied to the transformer (101a) associated with the TMCU (100a).
5. The TMCU (100a) as claimed in claim 1, wherein the unique parameters comprises a current voltage range of the transformer, a current flow of the transformer, an input power of the transformer, an output power of the transformer, a current temperature of the transformer, a short circuit current deviation of the transformer, an oil level of the transformer, an oil temperature variation of the transformer, a winding temperature variation of the transformer, a surface temperature of the transformer, a mechanical vibration of the transformer, a magnetic field of the transformer, a gases emitted by the transformer, a loss of life of the transformer, a number of consumers connected to the transformer, a load level of each consumer connected to the transformer, and a frequency of the transformer.
6. The TMCU (100a) as claimed in claim 5, wherein the plurality of sensors (103a-N) comprises:
a voltage sensor configured to measure the current voltage range, the current flow, the short circuit current deviation, the current frequency, the input power, and the output power of the transformer (101a),
a temperature sensor configured to measure the current temperature, the oil temperature variation, surface temperature, and the winding temperature variation of the transformer (101a),
an oil level sensor that measures the oil level of the transformer,
a vibration sensor that measures the mechanical vibrations of the transformer (101a),
a current sensor that measures the load level of each consumer connected to the transformer, and the number of consumers connected to the transformer (101a),
a magnetic field sensor that detects the magnetic field generated by the transformer (101a),
a gas sensor that measures the gases emitted by the transformer (101a), and
a frequency meter that measures the current frequency of the transformer (101a).
7. The TMCU (100a) as claimed in claim 1, wherein the TMCU (100a) comprises:
a coil winding (102a) that receives power supply from the transformer (101a);
a power supply unit (102c) that receives the power supply from the coil winding (102a) and provides the power supply to the plurality of sensors (103a), the energy meter (105), the display (106), and the microcontroller (107);
a circuit breaker (102b) that protects the TMCU (100a) from overload power or short circuits;
a power factor unit (110b) that adjusts phase relationship between the voltage and current of the TMCU (100a);
a memory (108) that stores the unique parameters and the predefined criteria of the transformer (101a);
a display (106) that displays at least one of the measured unique parameter of the transformer (101a), the at least one primary anomaly of the transformer (101a), at least one secondary anomaly of the transformer (101a), and the predefined criteria of the transformer (101a); and
a communicator (109), connected to the microcontroller (107), to create the wireless connection with the MCC server (210).
8. The TMCU (100a) as claimed in claim 1, wherein the at least one control action comprises increase cooling rate, reduce cooling rate, adjust tap changer, increase oil flow, decrease oil flow, activate alarms, activate automatic shutdown, adjust load sharing, adjust phase balance, adjust frequency, adjust cooling system, adjust the winding temperature, activate dehumidifiers in the transformer.
9. A Management Control Centre (MCC) server (210) comprises:
a database (203) that stores information of a plurality of transformers (101a-N);
a wireless unit (202) configured to create a wireless connection with a plurality of TMCUs (100a-N), wherein each TMCU of the plurality of TMCUs (100a-N) is connected to a transformer (101a) of the plurality of transformers (101a-N) located in a first geographic location and the MCC server (210) is located in a second geographic location;
a MCC controller (211), connected to the database (203) and the wireless unit (202), configured to:
remotely monitor current state of the transformer (101a) displayed on display (106) of each TMCU of the plurality of TMCUs (100a-N) using the wireless connection, wherein the current state indicates unique parameters of the plurality of transformers (101a-N) measured by the corresponding TMCUs (101a-N);
detect at least one of an anomaly associated with at least one transformer (101a) of the plurality of transformers (101a-N) by applying machine learning model on the remotely monitored unique parameters of the plurality of transformers (101a-N) located in the first geographic location;
determine at least one of a corrective action to be performed by the TMCU (100a) of the at least one transformer (101a) and an event based transformer configuration to be applied by the TMCU (100a) of the at least one transformer (101a); and
send the at least one control command to the TMCU (100a) corresponding to the at least one transformer (101a) using the wireless connection, wherein the at least one control command indicative of at least one of the event based transformer (101a) configuration to be applied by the TMCU (100a) and the at least one corrective action to be performed by the TMCU (100a) of the at least one transformer (101a).
10. The MCC server (210) as claimed in claim 9, wherein the anomaly associated with at least one transformer (101a) is one of a primary anomaly and a secondary anomaly, wherein the primary anomaly has higher priority over the secondary anomaly.
11. The MCC server (210) as claimed in claim 9, wherein MCC server (210) further comprises Artificial intelligence engine (204) which is trained to detect or predict the at least one anomaly associated with the at least transformer (101a) by:
collect statistical data of the unique parameters from the plurality of transformers (101a-N) to generate a model for identifying the at least one anomaly of the at least one transformer (101a), and
train the model based on machine learning techniques to detect or predict the at least one anomaly associated with the at least one transformer (101a).
12. The MCC server (210) as claimed in claim 9, wherein determine the at least one anomaly associated with the at least one transformer (101a) based on the current state of the at least one transformer (101a) comprises:
at least one anomaly is determined by comparing the unique parameters of the at least one transformer (101a) with a predefined criteria stored in the database (203).
13. The MCC server (210) as claimed in claim 9, wherein generate the at least one control command indicative of the at least one corrective action comprises:
analyze the at least one anomaly associated with the at least one transformer (101a) based on unique parameters received from the at least one TMCU (100a) and determine the at least one corrective action from the plurality of predetermined corrective actions based on the type of the at least one anomaly; and
generate the at least one control command indicating the at least one corrective action to be performed by the at least one TMCU (100a) of the at least one transformer (101a) for rectifying the at least one anomaly associated with the at least one transformer (101a); and sending the at least one control command to the at least one TMCU (100a) over the wireless connection.
14. The MCC server (210) as claimed in claim 9, wherein the MCC server (210) further comprises a database (203) configured to store the unique parameters of the at least one transformer (101a) and historical unique parameters of the plurality of transformers (101a-N); and
generate the report based on the unique parameters of the at least one transformer (101a) and predicting the at least one anomaly based on the historical unique parameters of the plurality of transformers (101a-N).
15. The MCC server (210) as claimed in claim 14, wherein the report includes information of the unique parameters of the at least one transformer (101a), anomaly associated with the at least one transformer (101a), and the at least one corrective action is determined from the plurality of predetermined corrective actions based on the at least one high priority anomaly and at least one low priority anomaly associated with the at least one transformer (101a).
16. The MCC server (210) as claimed in claim 9, wherein the plurality of predetermined corrective actions comprises adjusting the load balancing and optimizing the power distribution for the at least one transformer (101a), regulating the input and output power of the at least one transformer (101a), adjusting the cooling system of the at least one transformer(101a), repairing damaged components of the at least one transformer (101a), and rectifying potential failures in the at least one transformer (101a).
17. The MCC server as claimed in claim 9, wherein the unique parameters comprises a current voltage range of the at least one transformer (101a), a current flow of the at least one transformer (101a), an input power of the at least one transformer (101a), an output power of the at least one transformer (101a), a current temperature of the at least one transformer (101a), a short circuit current deviation of the at least one transformer (101a), an oil level of the at least one transformer (101a), an oil temperature variation of the at least one transformer (101a), a winding temperature variation of the at least one transformer (101a), a surface temperature of the at least one transformer (101a), a mechanical vibration of the at least one transformer (101a), a magnetic field of the at least one transformer (101a), a gases emitted by the at least one transformer (101a), a loss of life of the at least one transformer (101a), a number of consumers connected to the at least one transformer (101a), a load level of each consumer connected to the at least one transformer (101a), and a current frequency of the at least one transformer (101a).
18. A method for monitoring and controlling a transformer (101a) based on Transformer Monitoring and Control Unit (TMCU) (100a), wherein the method comprises;
measuring unique parameters of a transformer (101a) using the TMCU (100a), wherein the TMCU (100a) is electrically connected to the transformer (101a) located in a first geographic location;
creating, by the TMCU (100a), a wireless connection with a Management Control Centre (MCC) server (210) located at a second geographic location for remote monitoring and controlling the transformer (101a) based on unique parameters measured by the plurality of sensors (103a-N);
displaying, by the TMCU (100a), a current state of the transformer (101a) on a display for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the current state indicates at least one of the unique parameter of the transformer (101a); and
monitoring and controlling, by the TMCU (100a), the current state of the transformer (101a) using wireless connection with the MCC server (210).
19. The method as claimed in claim 18, wherein detecting, by the TMCU (100a), whether at least one primary anomaly associated with the transformer (101a) by comparing the unique parameters of the transformer (101a) with a predefined criteria stored at the TMCU;
generating, by the TMCU (100a), at least one control action to rectify at least one primary anomaly of the transformer (101a) when the at least one primary anomaly associated with the transformer (101a) is detected;
applying, by the TMCU (100a), the current state of the transformer (101a) displayed on the display for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the updated current state indicates the unique parameters of the transformer (101a), the at least one primary anomaly associated with the transformer (101a), and the at least one control action applied to rectify the at least one primary anomaly of the transformer (101a).
20. The method as claimed in claim 18, wherein remotely monitoring and controlling, by the TMCU (100a), the current state of the transformer (101a) using the wireless connection with the MCC server (210) comprises:
receiving, by the TMCU (100a), information about at least one secondary anomaly of the transformer (101a) predicted by the MCC server (210);
receiving, by the TMCU (100a), at least one control command indicative of a corrective action to be performed by the TMCU (100a) from the MCC server (210) to rectify the at least one secondary anomaly of the transformer;
performing, by the TMCU (100a), the at least one corrective action by applying the received at least one control command on the transformer (101a) to rectify the at least one secondary anomaly of the transformer (101a); and
updating, by the TMCU (100a), the current state of the transformer (101a) on the display for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the updated current status indicates the unique parameters of the transformer (101a), the at least one secondary anomaly associated with the transformer (101a), the at least one control command applied to rectify the at least one secondary anomaly of the transformer (101a).
21. The method as claimed in claim 18, wherein remotely monitoring and controlling, by the TMCU (100a), the current state of the transformer (101a) using the wireless connection with the MCC server (210) comprises:
receiving, by the TMCU (100a), information about at least one event associated with at least one other transformer (101b) located in the first geographic location from the MCC server (210) located in the second geographic location;
receiving, by the TMCU (100a), at least one control command indicative of an event based transformer (101a) configuration to be applied by the TMCU (100a) from the MCC server (210) based on the at least one event associated with at least one other transformer (101b) available in the area from the MCC server (210);
applying, by the TMCU (100a), the event based transformer (101a) configuration on the transformer (101a) based on the received at least one control command; and
updating, by the TMCU (100a), the current state of the transformer (101a) displayed on the display (106) for remote monitoring and controlling the transformer (101a) by the MCC server (210) using the wireless connection, wherein the updated current status of the transformer (101a) indicates the unique parameters of the transformer (101a), information about the at least one event associated with at least one other transformer (101b) available in the area, the event based transformer (101a) configuration applied to the transformer (101a) associated with the TMCU (100a).
22. The method as claimed in claim 18, wherein determining, by the TMCU (100a), the unique parameters of the transformer (101a), wherein the unique parameters comprises a current voltage range of the transformer (101a), a current flow of the transformer (101a), an input power of the transformer (101a), an output power of the transformer (101a), a current temperature of the transformer (101a), a short circuit current deviation of the transformer (101a), an oil level of the transformer (101a), an oil temperature variation of the transformer (101a), a winding temperature variation of the transformer (101a), a surface temperature of the transformer (101a), a mechanical vibration of the transformer (101a), a magnetic field of the transformer (101a), a gases emitted by the transformer (101a), a loss of life of the transformer (101a), a number of consumers connected to the transformer (101a), a load level of each consumer connected to the transformer (101a), and a frequency of the transformer (101a).
23. The method as claimed in claim 18, wherein the method comprises:
receiving, by an coil winding (102a), electrical power from the transformer (101a) and transfer to power supply unit (102c);
providing, by the power supply unit (102c), power to the plurality of sensors (103a-N);
protecting, by a circuit breaker (102b), the TMCU (100a) from overload power or short circuits;
adjusting, by a power factor unit (110b), phase relationship between the voltage and current of the TMCU (100a);
storing, by a memory (108), the unique parameters and the predefined criteria of the transformer (101a);
displaying, by a display (106), the at least one unique parameters of the transformer (101a), the at least one primary anomaly of the transformer (101a), at least one secondary anomaly of the transformer (101a), and the predefined criteria of the transformer (101a); and
creating, by a communicator (109), the wireless connection with the MCC server (210).
24. A method for monitoring and controlling a plurality of transformers (101a-N) based on Management Control Centre (MCC) server (210), wherein the method comprises:
storing, by the MCC server (210), information of the plurality of transformers (101a-N);
creating, by the MCC server (210), a wireless connection with a plurality of TMCUs (100a-N), wherein each TMCU of the plurality of TMCUs (100a-N) is connected to each transformer of the plurality of transformers (101a-N) located in a first geographic location and the MCC server (210) is located in a second geographic location;
remotely monitoring and controlling, by the MCC server, current state of the transformer (101a) displayed on display (106) of each TMCU of the plurality of TMCUs (100a-N) using the wireless connection, wherein the current state indicates unique parameters of the plurality of transformers (101a-N) measured by the corresponding TMCUs (100a-N);
detecting, by the MCC server (210), at least one of an anomaly associated with at least one transformer (101a) of the plurality of transformers (101a-N) by applying machine learning model on the remotely monitored unique parameters of the plurality of transformers (101a-N) located in the first geographic location;
determining, by the MCC server (210), at least one of a corrective action to be performed by the TMCU (100a) of the at least one transformer (101a) and an event based transformer configuration to be applied by the TMCU (100a) of the at least one transformer (101a); and
sending, by the MCC server (210), at least one control command to the TMCU (100a) corresponding to the at least one transformer (101a) using the wireless connection, wherein the at least one control command indicative of at least one of the event based transformer (101a) configuration to be applied by the TMCU (100a) and the at least one corrective action to be performed by the TMCU (100a) of the at least one transformer (101a).
25. The method as claimed in claim 24, wherein the method further includes training the Artificial intelligence engine (204) for detecting or predicting the at least one anomaly associated with the transformer (101a) by:
collecting statistical data of the unique parameters from a plurality of transformers (101a-N) to generate a model for identifying the at least one anomaly of the at least one transformer (101a), and
training the model based on machine learning techniques for detecting or predicting the at least one anomaly associated with the at least one transformer (101a).
26. The method as claimed in claim 24, wherein determining, by the MCC server (210), the at least one anomaly associated with the at least one transformer (101a) based on the current state of the at least one transformer (101a) comprises:
determining, by the MCC server (210), the at least one anomaly by comparing the unique parameters of the at least one transformer (101a) with a predefined criteria stored at the MCC server (210).
27. The method as claimed in claim 24, wherein generate, by the MCC server (210), the at least one control command indicative of the at least one corrective action comprises:
analyzing, by the MCC server (210), the at least one anomaly associated with the at least one transformer (101a) based on unique parameters received from the at least one TMCU (100a) and determine the at least one corrective action from the plurality of predetermined corrective actions based on the type of the at least one anomaly; and
generating, by the MCC server (210), the at least one control command indicating the at least one corrective action to be performed by the at least one TMCU (100a) of the at least one transformer (101a) for rectifying the at least one anomaly associated with the at least one transformer (101a); and sending the at least one control command to the at least one TMCU (100a) over the wireless connection.
28. The method as claimed in claim 24, wherein storing, by the MCC server (210), the unique parameters of the at least one transformer (101a) and historical unique parameters of the plurality of transformers (101a-N); and
generating, by the MCC server (210), the report based on the unique parameters of the at least one transformer (101a) and predicting the at least one anomaly based on the historical unique parameters of the plurality of transformers (101a-N).
29. The method as claimed in claim 24, wherein determining, by the MCC server (210), the unique parameters of the transformer (101a), wherein the unique parameters comprises a current voltage range of the transformer (101a), a current flow of the transformer (101a), an input power of the transformer (101a), an output power of the transformer (101a), a current temperature of the transformer (101a), a short circuit current deviation of the transformer (101a), an oil level of the transformer (101a), an oil temperature variation of the transformer (101a), a winding temperature variation of the transformer (101a), a surface temperature of the transformer (101a), a mechanical vibration of the transformer (101a), a magnetic field of the transformer (101a), a gases emitted by the transformer (101a), a loss of life of the transformer (101a), a number of consumers connected to the transformer (101a), a load level of each consumer connected to the transformer (101a), and a frequency of the transformer (101a).