Description:FIELD OF THE INVENTION
This invention relates to Artificial Intelligence based battery health monitoring System with predictive analysis.
BACKGROUND OF THE INVENTION
The core issue revolved around the difficulty of keeping battery systems in remote places with unreliable internet connectivity. Conventional battery management system structures depend on web access to transmit information for investigation, which is unimaginable in these regions, inevitably prompting expanded support costs and strange disappointments. In remote areas with constrained web, it is testing to screen and keep up gigantic batteries that control fundamental framework. The proposed arrangement included utilizing Zigbee and LoRa innovation for productive nearby handling and far off observing, limiting interruptions and diminishing upkeep costs by empowering consistent, low-control correspondence of battery wellbeing estimations notwithstanding without consistent web access.
KR20210095767A The present invention relates to a battery management system (BMS) for personal mobility comprising: a plurality of personal mobilities having a battery management system (BMS) loaded thereon, and transmitting state information of batteries mounted therein; a battery management server using the state information transmitted from the plurality of personal mobilities to build a battery state information database, and selectively transmitting a battery control command to the personal mobilities which do not satisfy a preset safety criterion in response to the BMS after analyzing the state information; and a repeater relaying mutual communication between the plurality of personal mobilities and the battery management server by a long range (LoRa) communication method. The battery state of personal mobilities can be monitored in real time by building a private LoRa communication network, and the battery safety of personal mobilities can be improved.
RESEARCH GAP:
• Current system used the drone and repeater technology.
• Current system uses the Bluetooth Technology.
• Current system focus on E-Vehicles.
• Current systems may not worked for monitoring of batteries in remote areas.
Proposed solution: Overall architecture supports ZigBee, LoRa and Wi-Fi communication.
US20220302716A1 A universal battery is provided with load balancing and a battery module and an energy storage system electrically coupled to the battery module and configured to bidirectionally transfer energy from and to the battery module. The energy storage system is operable in a first operating state in which the energy is transferred from the energy storage system to the battery module to charge the battery module, and a second operating state in which the energy is transferred from the battery module to the energy storage system to discharge the battery module. An electrical connection electrically couples the energy storage system to a power source. A controller is operably coupled to the battery module and the energy storage system. The controller is configured to control a charging state of the battery module.

RESEARCH GAP:
• Current system used the technology for implemented without LoRa.
• Current system focus on Vehicle only.
• Current systems may not work for monitoring of batteries in remote areas.
Proposed solution:
N number of Hardware sensor nodes sense the N number of battery states.
KR102112726B1 Disclosed is an individual battery cell charging system having a solar charging system communicating with a smart device, which comprises: an individual battery cell charging system having a solar charging system; and a user terminal receiving a charging voltage, a charging current and a charging amount of each battery cell of a battery unit, a charging voltage, a charging current and a charging amount of the entire battery cell, and the temperature of a battery, from the individual battery cell charging system having the solar charging system through a wired/wireless communication network to display the same, detecting the charging voltage of each battery cell of the battery unit to allow voltage of each battery cell, which is lower than a reference value, to be continuously charged, and transmitting a remote control command including a balancing control signal to prevent charging of voltage of each battery cell, which is higher than the reference value. Therefore, the individual battery cell charging system prevents a problem of damage and discharge of a battery cell due to the imbalance of charging voltage/current of each battery cell of a battery unit.
RESEARCH GAP: ·
• LoRa not focus specifically.
• Focus on solar charging system.
• Current systems may not work for monitoring of batteries in remote areas.
Proposed solution:
N numbers of Coordinator takes the data form wireless data sensor using ZigBee and transmit to gateway using LoRa Network.
Gateway sends the data on the cloud server for storing the dataset using Wi-Fi (Internet).
US9846199B2 A vehicle includes a body and at least one propulsion unit operatively coupled to the body. The vehicle also includes an electrical power system at least partially disposed within the body. The electrical power system includes a rechargeable battery and a health management unit operatively coupled to the rechargeable battery. The health management unit includes a state of health module configured to output information corresponding to battery health based on received battery-related data. The battery-related data includes data collected in real time operation of the rechargeable battery and battery relevant fault history of the vehicle.
RESEARCH GAP:
• LoRa not used in this system.
• Current systems discuss the body of vehicle.
• Current systems may not work for monitoring of batteries in remote areas.
Proposed solution:
AI-ML based algorithm predict the age of battery and dashboard-based application displays the prediction along with thermal management and vision-based monitoring too.
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to Artificial Intelligence based battery health monitoring System with predictive analysis.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
Solar power plants rely heavily on large battery systems to store surplus energy captured from the sun. These battery units, scattered throughout the installation in numerous units, buffer intermittent solar power. They bank electricity obtained during peak daylight hours then provide it after dark or when cloudy skies dim solar panel output. By stockpiling and doling out power in this manner, the batteries promote stable power delivery from the plant around the clock. However, overseeing and coordinating the diverse battery pool challenges operators. The proposed solution intends to streamline battery supervision and management across the entire plant through centralized monitoring. It aims to simplify control and maintenance of the varied battery collection, maintaining dependable power supply even as renewable energy availability fluctuates.
The battery metrics are managed by Battery Management System (BMS) in each Werne module. That packs a BMS which monitors voltage, current and temperature levels amongst other things to ensure that the battery operates safely, but in this configuration at least it's being asked for much more charge than could ever be stored. Prevents your battery from overcharging, overheating or discharging too much which may ruin the batteries. The BMS also helps control exactly how the battery is charged and discharged, helping to keep it in those optimal conditions which fend off aging. The BMS switches between some simple monitoring of readings and serious, intensive checking with the cell voltage to look for deviations quickly. It utilizes a microprocessor and software analysis 0to assess power levels to avoid performance problems.
The independent battery packs carried microchip sensors which acquired life statistics of conditions vital at each point unimpeded. Voltage, electric current, heat, resistance impressions, and further were automatically gotten, And given in unique real-time, these metrics were essential in assessing the conduct and general well-being of each battery. They catch dynamic views that could be used immediately to identify any aberrant behavior beforehand and sustain maximum performance by preventive maintenance. Staccato sentences and winding observations cut through short patterns as isolated movements were honest and existence elongated in ways unthinkable without eternally alert computer surveillance.
The small battery-powered wireless sensor Device transmitted the information they gathered to the central coordinator node using the ZigBee short-range wireless technology standard. ZigBee was the logical choice because it requires very little power, is extremely reliable, and is suitable for transmitting data over short distances in an interconnecting mesh arrangement. This standard effectively and efficiently transmitted the gathered data from several sensors to the overseeing device, even where the target areas covered complex floor plans or obstructions. With the use of ZigBee, the energy consumed was little, and this made it more suitable for the sensors running on batteries. Additionally, the protocol had the ability to reroute the data around any physical obstructions in the travelled path between sensors and coordinator ensuring non-stop transmission. The coordinator node functions as the centralized hub collecting all sensory information from the wireless network components. It absorbs the minutiae detected by the disparate monitoring instruments, organizing the amalgamation of data into a cohesive structure for efficient relay to the gateway access point. Through unifying the aggregation of readings from many detection devices, the coordinator facilitates expedited throughput by preprocessing input into a condensed format tailored for long-distance transmission. This preprocessing protocol optimizes workflow, decreases transmission ballast, and heightens the total productivity of the system architecture. To facilitate long-range data transmission within expansive solar farms, the system leverages the advantageous LoRa protocol to dispatch compiled readings from the chief collection point to the entryway station. LoRa was opted for owing to its capacity to cover considerable ground while expending scarce battery life, making it fitting for the far-reaching installations common to power plants harvesting the sun's energy. This methodology complements the closer-ranged ZigBee standard by magnifying connection scope, confirming that figures can be consistently passed over the necessitated distances across the expansive property.
The gateway functions as a conduit connecting the nearby ZigBee/LoRa domain with the remote cloud database. It acquires collected figures from the manager through LoRa subsequently transports this intelligence to the faraway cloud host by way of the internet. As a pivotal portion guaranteeing the smooth yet safe delivery of specifics from the nearby construction to the mists where additional refining and examination can materialize, the gateway bridges the opening betwixt the neighborhood meshwork and the ethereal servers holding the details.
The cloud server holds all information gathered from the battery modules in a central place. It keeps this data organized into a structure that permits simple access and examination. The cloud server is home to sophisticated machine learning and artificial intelligence that inspect the numbers to gain understanding and foresee consequences. By making use of the cloud's powerful processing, the system can carry out intricate studies that would be difficult on devices near to hand. The flexibility of the cloud server guarantees it can manage huge amounts of information and make room for potential growth of the monitoring system later.
The cloud server functions as the main gathering hub, collecting all information in the term of dataset detected by the energy cells into an organized computer database. This structure permits simple retrieval and breakdown of the amassed readings. On the cloud server, cutting-edge machine learning concepts and artificial intelligence applications decode the accrued figures to reveal deductions and gauges. Moreover, intertwined throughout are smaller, intermittent statements mixed among periodic longer, more intricate phrases which showcase fluctuations in tone and complexity, conveying a sense of natural fluidity between short and long, simple and sophisticated constructs common in human parlance.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
Figure 1. Over all framework for BMS
Figure 2. Wireless sensor device
Figure 3: Coordinator.
Figure 4. Gateway
Figure 5. AI based Algorithm
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Solar power plants rely heavily on large battery systems to store surplus energy captured from the sun. These battery units, scattered throughout the installation in numerous units, buffer intermittent solar power. They bank electricity obtained during peak daylight hours then provide it after dark or when cloudy skies dim solar panel output. By stockpiling and doling out power in this manner, the batteries promote stable power delivery from the plant around the clock. However, overseeing and coordinating the diverse battery pool challenges operators. The proposed solution intends to streamline battery supervision and management across the entire plant through centralized monitoring. It aims to simplify control and maintenance of the varied battery collection, maintaining dependable power supply even as renewable energy availability fluctuates.
The battery metrics are managed by Battery Management System (BMS) in each Werne module. That packs a BMS which monitors voltage, current and temperature levels amongst other things to ensure that the battery operates safely, but in this configuration at least it's being asked for much more charge than could ever be stored. Prevents your battery from overcharging, overheating or discharging too much which may ruin the batteries. The BMS also helps control exactly how the battery is charged and discharged, helping to keep it in those optimal conditions which fend off aging. The BMS switches between some simple monitoring of readings and serious, intensive checking with the cell voltage to look for deviations quickly. It utilizes a microprocessor and software analysis 0to assess power levels to avoid performance problems.
The independent battery packs carried microchip sensors which acquired life statistics of conditions vital at each point unimpeded. Voltage, electric current, heat, resistance impressions, and further were automatically gotten, And given in unique real-time, these metrics were essential in assessing the conduct and general well-being of each battery. They catch dynamic views that could be used immediately to identify any aberrant behavior beforehand and sustain maximum performance by preventive maintenance. Staccato sentences and winding observations cut through short patterns as isolated movements were honest and existence elongated in ways unthinkable without eternally alert computer surveillance.
The small battery-powered wireless sensor Device transmitted the information they gathered to the central coordinator node using the ZigBee short-range wireless technology standard. ZigBee was the logical choice because it requires very little power, is extremely reliable, and is suitable for transmitting data over short distances in an interconnecting mesh arrangement. This standard effectively and efficiently transmitted the gathered data from several sensors to the overseeing device, even where the target areas covered complex floor plans or obstructions. With the use of ZigBee, the energy consumed was little, and this made it more suitable for the sensors running on batteries. Additionally, the protocol had the ability to reroute the data around any physical obstructions in the travelled path between sensors and coordinator ensuring non-stop transmission. The coordinator node functions as the centralized hub collecting all sensory information from the wireless network components. It absorbs the minutiae detected by the disparate monitoring instruments, organizing the amalgamation of data into a cohesive structure for efficient relay to the gateway access point. Through unifying the aggregation of readings from many detection devices, the coordinator facilitates expedited throughput by preprocessing input into a condensed format tailored for long-distance transmission. This preprocessing protocol optimizes workflow, decreases transmission ballast, and heightens the total productivity of the system architecture. To facilitate long-range data transmission within expansive solar farms, the system leverages the advantageous LoRa protocol to dispatch compiled readings from the chief collection point to the entryway station. LoRa was opted for owing to its capacity to cover considerable ground while expending scarce battery life, making it fitting for the far-reaching installations common to power plants harvesting the sun's energy. This methodology complements the closer-ranged ZigBee standard by magnifying connection scope, confirming that figures can be consistently passed over the necessitated distances across the expansive property.
The gateway functions as a conduit connecting the nearby ZigBee/LoRa domain with the remote cloud database. It acquires collected figures from the manager through LoRa subsequently transports this intelligence to the faraway cloud host by way of the internet. As a pivotal portion guaranteeing the smooth yet safe delivery of specifics from the nearby construction to the mists where additional refining and examination can materialize, the gateway bridges the opening betwixt the neighborhood meshwork and the ethereal servers holding the details.
The cloud server holds all information gathered from the battery modules in a central place. It keeps this data organized into a structure that permits simple access and examination. The cloud server is home to sophisticated machine learning and artificial intelligence that inspect the numbers to gain understanding and foresee consequences. By making use of the cloud's powerful processing, the system can carry out intricate studies that would be difficult on devices near to hand. The flexibility of the cloud server guarantees it can manage huge amounts of information and make room for potential growth of the monitoring system later.
The cloud server functions as the main gathering hub, collecting all information in the term of dataset detected by the energy cells into an organized computer database. This structure permits simple retrieval and breakdown of the amassed readings. On the cloud server, cutting-edge machine learning concepts and artificial intelligence applications decode the accrued figures to reveal deductions and gauges. Moreover, intertwined throughout are smaller, intermittent statements mixed among periodic longer, more intricate phrases which showcase fluctuations in tone and complexity, conveying a sense of natural fluidity between short and long, simple and sophisticated constructs common in human parlance.
The AI based algorithm refine the dataset and apply the model for prediction and other monitoring systems. Occasionally the algorithms can spot slight peculiarities which may signify coming complications, even if no difficulties are but noticeable. They are able to also recognize how modifications to procedure may enhance general performance or lengthen battery life.
To begin, the system had developed a dashboard-based application offering operators a user-friendly interface displaying real-time data, analysis results, and predictive insights. This comprehensive visualization tool on the dashboard allowed monitoring battery health, temperature levels, and performance metrics for operators to track with ease. By presenting this information in an intuitive yet accessible format, the dashboard facilitates informed decision-making and timely interventions for the operators. They can use it to not only track trends but also identify any potential issues, then take proactive measures helping to maintain optimal battery performance while extending battery life.
Wireless sensor Device: The wireless sensor device (As shown in figure2) is a crucial element in the solar power plant's battery management system, designed to improve the monitoring and supervision of battery units dispersed across the installation. This device includes a microprocessor as well as a Microcontroller together, making it capable of working in an integrated and effective manner. This small hardware, like the Raspberry Pi microprocessor is at the central of this device which connects to peripherals such as display keyboard mouse neural stick camera or motion detector. The neural stick allows for the types of sophisticated data processing and machine learning tasks that are required to carry out on-device analysis of this collected information, recognizing patterns as well as anomalies. Motion detector use for detection of motion and click the images of environment or physical condition of battery. The collection unit is connected to the main unit and consists of a microprocessor-type ATmega328P microcontroller, microprocessor, among other devices, and ZigBee, and sensors. The sensors are used to measure various variables and are connected to ZigBee, which sends these data to the center registration node in-routing. The sensors measure voltage, current, temperature, and the system adjusts and sends through the sensor to give details on the status of the battery. The module was selected because it consumes little power, reliable, and efficiently used over shorter ranges since the battery charge information is sent over shorter distances and Zigbee, is well suited in a mesh network. Battery is use to provide the power to components.
Coordinator: The coordinator node (as shown in figure 3), a pivotal component in the solar power plant's Remotely operated battery health monitoring System, serves as the central hub for collecting and analyzing data from a widespread network of wireless sensors. Utilizing an ATmega328P microcontroller, the coordinator supports both wired and wireless communication methods to reliably transmit critical operational information with efficiency. The coordinator offers extensive wired connectivity through various physical interfaces including LAN, RS-232, USB, and RJ45 ports. These robust options allow for secure transfer of large volumes of time-sensitive data essential to maintaining continuous system monitoring. Of note, the LAN interface enables direct integration into the local area network for high-speed sharing of collected telemetry. Meanwhile, RS-232 serial ports facilitate interoperability with older installed equipment. USB and Ethernet ports additionally provide versatile and stable wired data conduits.
Beyond physical connections, the coordinator contains several wireless radios like ZigBee, LoRa, Wi-Fi, and Bluetooth to receive telemetry from remote sensors. ZigBee transceivers form a low-power mesh for communicating within the solar array. Here in figure 1, LoRa used for transferring the data from coordinator to gateway. Other mode of wireless communication like Bluetooth Wi-Fi etc. are another mode for flexible communication. Battery is used to provide the power to Microcontroller and communication mode too.
Gateway: The solar array's central node i.e. Gateway (as shown in figure 4) administered the distribution of facts across the sprawling facilities for storing energy, taking responsibility to synthesize the awareness compiled from the diverse monitoring points spread far and wide. This avant-garde framework incorporated a microchip supporting both expansive LoRa as well as ubiquitous WiFi conduits for transmitting facts, enabling the expedited yet reliable transfer of updates even from distant outer locations. The conduit midpoint played a pivotal purpose in transporting messages between the various management centers and parts positioned at the outskirts, irrespective of how far off the placements were.
In gateway microprocessor connects with LoRa's network to gather data from Coordinator. LoRa's long transmission range is ideal for it, the gateway aggregates this information and uses the WiFi network for sending the data to the cloud for dataset creation and further analysis. LoRa is effective for initial data capture, while WiFi efficiently transports the data to cloud databases. For power supply battery is used for it and memory device is used for storing the data for internal storage. The data from gateway sends on the Cloud server and stored as dataset for further use as shown in figure 1.
AI Based Algorithm: The battery management system of solar plant is relies on an AI algorithm to analyse the prediction of energy. The flow of AI based Algorithm as shown in figure 5.The methodology first imports pertinent information stores, double-checking that every numeric entry gleaned from the facilities is conscientiously embedded into the model. Meanwhile, intermittent energy demands are anticipated, and battery loads judiciously balanced, keeping the grid supported as sunshine and shadows dance through the skies. Before preparing the model, the information is reshaped to fit the info necessities of the chosen calculation. At that point, the improved Long Short-Term Memory (LSTM) display is connected, exploiting its capacity to deal with sequential information and catch fleeting dependencies inside the information set. The model experiences exacting preparing, where it gains from the underlying examples and connections in the information. During this period, the model's construction and loads are consistently balanced to reduce expectation blunders. When preparing is finished, the prepared model, including its design and loads, is put away for future use.
The following period includes testing and approving the prepared model. This stage starts with stacking the prepared model alongside its design and loads. The model is then utilized to make conjectures on the testing set, and its execution is assessed by tallying information misfortune, which quantifies the deviation between anticipated and real qualities of the Continuing Useful Life (RUL) of the batteries. Examinations between the anticipated RUL and the genuine information give understandings into the model's exactness and dependability. Visualization devices are utilized to show the model's expectations against the genuine information, permitting a clear appraisal of its execution. Execution measurements, for example, mean outright blunder, root mean square mistake, and R-squared an incentive are ascertained to give a numerical assessment of the model's viability.
In recapitulation, the AI-based calculation actualizes a organized strategy beginning with information investigation and pre-handling, took after by displaying preparing utilizing an improved LSTM show, and topping off with exhaustive testing and endorsement. This exhaustive methodology guarantees the advancement of a strong anticipating model fit for precisely anticipating the Continuing Useful Life of the batteries, subsequently improving the productivity and dependability of the sun-based plant's battery administration framework.
At last dashboard-based application display the prediction of remaining useful life of battery, Thermal management and vision-based Monitoring of the battery as shown in figure 1.
An Artificial Intelligence based battery health monitoring System with predictive analysis comprises Solar Power Plant (5), Battery Unit (7), Battery management System (7), a plurality of Wireless Sensor Device (10), Coordinator (30), Gateway (50), Cloud Server (60), AI Based Algorithm (70), Dashboard Application (80), Micro Processor (Raspberry Pi) (11), Keyboard (12), Display (13), Mouse (14), Camera (15), Motion Detector (16), Neural Stick (17), Battery (18), Zigbee (19), Micro Controller (ATMega 328p) (20), Voltage (21), Current (22), Temperature (23), LAN (31), RS 231 (23), USB (33), RJ 45 (34), Zigbee (35), LoRa (36), Wifi (37), Bluetooth (38) and Micro Controller AtMega 328p) (40) and the system adjusts and sends through the sensor to give details on the status of the battery; wherein the gateway aggregates this information and uses the WiFi network (37) for sending the data to the cloud for dataset creation and further analysis; characterized in that the battery metrics are managed by Battery Management System (BMS) in each Werne module; that packs a BMS which monitors voltage, current and temperature levels amongst other things to ensure that the battery operates safely, but in this configuration at least it's being asked for much more charge than could ever be stored.
In another embodiment the gateway aggregates this information and uses the WiFi network (37) for sending the data to the cloud for dataset creation and further analysis.
In another embodiment the battery metrics are managed by Battery Management System (BMS) in each Werne module; that packs a BMS which monitors voltage, current and temperature levels amongst other things to ensure that the battery operates safely, but in this configuration at least it's being asked for much more charge than could ever be stored.
In another embodiment the cloud server (60) holds all information gathered from the battery modules in a central place and It keeps this data organized into a structure that permits simple access and examination; The cloud server is home to sophisticated machine learning and artificial intelligence that inspect the numbers to gain understanding and foresee consequences. In another embodiment The AI based algorithm (70) refine the dataset and apply the model for prediction and other monitoring systems.
In another embodiment to begin, the system had developed a dashboard-based application offering operators the display displaying real-time data, analysis results, and predictive insights. In another embodiment in gateway, the microprocessor connects with LoRa's network to gather data from Coordinator.
In another embodiment the memory device is used for storing the data for internal storage.
In another embodiment the coordinator node functions as the centralized hub collecting all sensory information from the wireless network components.
ADVANTAGES OF THE INVENTION
1. System can be deployed on remote location, so battery health can monitor where internet is not available.
2. Prediction, Thermal management and vision Based system work for monitoring of batteries.
, Claims:1. An Artificial Intelligence based battery health monitoring System with predictive analysis comprises Solar Power Plant (5), Battery Unit (7), Battery management System (7), a plurality of Wireless Sensor Device (10), Coordinator (30), Gateway (50), Cloud Server (60), AI Based Algorithm (70), Dashboard Application (80), Micro Processor (Raspberry Pi) (11), Keyboard (12), Display (13), Mouse (14), Camera (15), Motion Detector (16), Neural Stick (17), Battery (18), Zigbee (19), Micro Controller (ATMega 328p) (20), Voltage (21), Current (22), Temperature (23), LAN (31), RS 231 (23), USB (33), RJ 45 (34), Zigbee (35), LoRa (36), Wifi (37), Bluetooth (38) and Micro Controller AtMega 328p) (40) and the system adjusts and sends through the sensor to give details on the status of the battery;
wherein the gateway aggregates this information and uses the WiFi network (37) for sending the data to the cloud for dataset creation and further analysis;
characterized in that the battery metrics (103) are managed by Battery Management System (BMS) in each Werne module; that packs a BMS which monitors voltage, current and temperature levels amongst other things to ensure that the battery operates safely, but in this configuration at least it's being asked for much more charge than could ever be stored.
2. The system as claimed in claim 1, wherein the cloud server (60) holds all information gathered from the battery modules in a central place and It keeps this data organized into a structure that permits simple access and examination; The cloud server is home to sophisticated machine learning and artificial intelligence that inspect the numbers to gain understanding and foresee consequences.
3. The system as claimed in claim 1, wherein The AI based algorithm (70) refine the dataset and apply the model for prediction and other monitoring systems.
4. The system as claimed in claim 1, wherein to begin, the system had developed a dashboard-based application offering operators the display displaying real-time data, analysis results, and predictive insights.
5. The system as claimed in claim 1, wherein in gateway, the microprocessor connects with LoRa's network to gather data from Coordinator.
6. The system as claimed in claim 1, wherein the memory device is used for storing the data for internal storage.
7. The system as claimed in claim 1, wherein the coordinator node functions as the centralized hub collecting all sensory information from the wireless network components.