Claims:

1. A processor implemented method (700) for optimization of industrial processes in a plant using artificial intelligence (AI), the method comprising:

receiving, via one or more hardware processors, a plurality of data related to the industrial processes from a plurality of data sources (702);
preprocessing, via the one or more hardware processors, the received plurality of data to extract distinct steady state data (704);
generating, via the one or more hardware processors, a plurality of models using the distinct steady state data, wherein the plurality of models represents a plurality of performance indicators in the industrial processes (706);
providing, via the one or more hardware processors, a plurality of manipulated variables (MVs) and a plurality of disturbance variables (DVs) corresponding to the industrial processes to an input multiplexer, wherein the input multiplexer is configured to select a set of MVs from amongst the plurality of MVs, and a set of DVs from amongst of the plurality of DVs corresponding to each model of the plurality of models (708);
sorting, via the one or more hardware processors, the plurality of models in a topological order (710);
generating, via the one or more hardware processors, a set of output process variables using each model of the plurality of models in the sorted topological order, wherein the set of output process variables are generated using the selected set of MVs, the selected set of DVs and a set of input process variables (PVs), wherein the set of output process variables are further configured to be used as the set of input PVs to one or more models amongst the plurality of models (712);
identifying in real-time, via the one or more hardware processors, a set of objectives for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of objectives is represented as a multiple cost function (714);
identifying in real-time, via the one or more hardware processors, a set of constraints for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of constraints is represented as a multiple equality function and a multiple inequality function (716);
solving, via the one or more hardware processors, a generic nonlinear optimization problem to give an optimal set of manipulated variables (MVs) as output, using the multiple cost function, the multiple equality function and the multiple inequality function as inputs (718); and
providing the optimal set of manipulated variables to the plant for optimization of industrial processes in the plant (720).

2. The method of claim 1, wherein the generic nonlinear optimization problem comprises identifying minimum of the multiple cost function such that the multiple inequality function is more than or equal to zero and the multiple equality function is equal to zero.

3. The method of claim 1, wherein the preprocessing comprises:
splitting the plurality of data received from the industrial processes into a plurality of continuous time-series portions;
smoothening the split plurality of data to remove spikes or noises;
performing a dimensionality reduction technique on the smoothened data to transform into a low dimensional space;
extracting lower dimension data from the low dimension space obtained from the dimensionality reduction technique, wherein a window of time-series data is considered for steady state detection, where the probability of each point in the window whether it is steady state, is calculated based on a corresponding deviation;
ranking each of the steady state points present in steady state data based on a distance between steady state points using a ranking algorithm; and
selecting unique steady state points out of the ranked steady state points, if the respective distance is more than a predefined threshold.

4. The method of claim 1 further comprising storing the optimal set of MVs in a data repository.

5. The method of claim 1, wherein the plurality of models is physics-based models or data-based models.

6. The method of claim 1, wherein the plurality of data sources comprises of distributed control system (DCS), historian, laboratory information management system (LIMS), a plurality of external sources, manual input and a plurality of digital systems used in the industrial processes.

7. A system (100) for optimization of industrial processes using artificial intelligence (AI), the system comprising:

an input/output interface (106) for receiving a plurality of data related to the industrial processes from a plurality of data sources;
one or more hardware processors (110);
a memory (112) in communication with the one or more hardware processors, wherein the one or more first hardware processors are configured to execute programmed instructions stored in the one or more first memories, to:
receive a plurality of data related to the industrial processes from a plurality of data sources;
preprocess the received plurality of data to extract distinct steady state data;
generate a plurality of models using the distinct steady state data, wherein the plurality of models represents a plurality of performance indicators in the industrial processes;
provide a plurality of manipulated variables (MVs) and a plurality of disturbance variables (DVs) corresponding to the industrial processes to an input multiplexer, wherein the input multiplexer is configured to select a set of MVs from amongst the plurality of MVs, and a set of DVs from amongst of the plurality of DVs corresponding to each model of the plurality of models;
sort the plurality of models in a topological order;
generate a set of output process variables using each model of the plurality of models in the sorted topological order, wherein the set of output process variables are generated using the selected set of MVs, the selected set of DVs and a set of input process variables (PVs), wherein the set of output process variables are further configured to be used as the set of input PVs to one or more models amongst the plurality of models;
identify in real-time, a set of objectives for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of objectives is represented as a multiple cost function;
identify in real-time, a set of constraints for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of constraints is represented as a multiple equality function and a multiple inequality function;
solve a generic nonlinear optimization problem to give an optimal set of manipulated variables (MVs) as output, using the multiple cost function, the multiple equality function and the multiple inequality function as inputs; and
provide the optimal set of manipulated variables to the plant for optimization of industrial processes in the plant.

8. The system of claim 7, wherein the preprocessing comprises:
splitting the plurality of data received from the industrial processes into a plurality of continuous time-series portions;
smoothening the split plurality of data to remove spikes or noises;
performing a dimensionality reduction technique on the smoothened data to transform into a low dimensional space;
extracting lower dimension data from the low dimension space obtained from the dimensionality reduction technique, wherein a window of time-series data is considered for steady state detection, where the probability of each point in the window whether it is steady state, is calculated based on a corresponding deviation;
ranking each of the steady state points present in steady state data based on a distance between steady state points using a ranking algorithm; and
selecting unique steady state points out of the ranked steady state points, if the respective distance is more than a predefined threshold.

9. The system of claim 7 further configured to store the optimal set of MVs in a data repository.

10. The system of claim 7, wherein the plurality of data sources comprises of distributed control system (DCS), historian, laboratory information management system (LIMS), a plurality of external sources, manual input and a plurality of digital systems used in the industrial processes.
, Description:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:
METHOD AND SYSTEM FOR OPTIMIZATION OF INDUSTRIAL PROCESSES USING ARTIFICIAL INTELLIGENCE

Applicant:
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th Floor,
Nariman Point, Mumbai 400021,
Maharashtra, India

The following specification particularly describes the invention and the manner in which it is to be performed.
TECHNICAL FIELD
The disclosure herein generally relates to the field of industrial data analysis, and, more particularly, to a method and system for optimization of industrial processes in a plant using artificial intelligence (AI).

BACKGROUND

Industries today (e.g., chemical & petro-chemical, oil & gas, pharmaceutical, minerals, utilities, etc.) are facing increasing pressure to reduce their operational cost and energy consumption and increase productivity and efficiency while meeting safety, reliability, and emission standards, due to increasing concerns of natural resource exhaust as well as the environment issues. With a complex operation of many devices integrated in the system, large-scale real time optimization of their operation is a promising solution for solving these above problems.
Conventional approaches usually focus on individual or several devices with a low dimensional system while industrial process is a complex and high dimensional system with many integrated devices. Especially, operation of a large-scale system requires flexibility with many regimes. That shows difficulties for conventional approaches in adapting with this flexibility. Therefore, it would require an automatic design of large-scale optimization framework for this complex system.

SUMMARY
Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a system for optimization of industrial processes using artificial intelligence (AI) is provided. The system comprises an input/output interface, one or more hardware processors, and a memory. The input/output interface receives a plurality of data related to the industrial processes from a plurality of data sources. The memory is in communication with the one or more hardware processors, wherein the one or more first hardware processors are configured to execute programmed instructions stored in the one or more first memories, to: receive a plurality of data related to the industrial processes from a plurality of data sources; preprocess the received plurality of data to extract distinct steady state data; generate a plurality of models using the distinct steady state data, wherein the plurality of models represents a plurality of performance indicators in the industrial processes; provide a plurality of manipulated variables (MVs) and a plurality of disturbance variables (DVs) corresponding to the industrial processes to an input multiplexer, wherein the input multiplexer is configured to select a set of MVs from amongst the plurality of MVs, and a set of DVs from amongst of the plurality of DVs corresponding to each model of the plurality of models; sort the plurality of models in a topological order; generate a set of output process variables using each model of the plurality of models in the sorted topological order, wherein the set of output process variables are generated using the selected set of MVs, the selected set of DVs and a set of input process variables (PVs), wherein the set of output process variables are further configured to be used as the set of input PVs to one or more models amongst the plurality of models; identify in real-time, a set of objectives for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of objectives is represented as a multiple cost function; identify in real-time, a set of constraints for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of constraints is represented as a multiple equality function and a multiple inequality function; solve a generic nonlinear optimization problem to give an optimal set of manipulated variables (MVs) as output, using the multiple cost function, the multiple equality function and the multiple inequality function as inputs; and provide the optimal set of manipulated variables to the plant for optimization of industrial processes in the plant.
In another aspect, a method for optimization of industrial processes in a plant using artificial intelligence (AI) is provided. Initially, a plurality of data related to the industrial processes is received from a plurality of data sources. The received plurality of data is then preprocessed to extract distinct steady state data. In the next step, a plurality of models is generated using the distinct steady state data, wherein the plurality of models represents a plurality of performance indicators in the industrial processes. Further, a plurality of manipulated variables (MVs) and a plurality of disturbance variables (DVs) corresponding to the industrial processes is provided to an input multiplexer, wherein the input multiplexer is configured to select a set of MVs from amongst the plurality of MVs, and a set of DVs from amongst of the plurality of DVs corresponding to each model of the plurality of models. In the next step, the plurality of models is sorted in a topological order. In the next step, a set of output process variables is generated using each model of the plurality of models in the sorted topological order, wherein the set of output process variables are generated using the selected set of MVs, the selected set of DVs and a set of input process variables (PVs), wherein the set of output process variables are further configured to be used as the set of input PVs to one or more models amongst the plurality of models. Further, a set of objectives is identified in real time for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of objectives is represented as a multiple cost function. In the next step, a set of constraints are identified in real time for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs, wherein the set of constraints is represented as a multiple equality function and a multiple inequality function. Further, a generic nonlinear optimization problem is solved to give an optimal set of manipulated variables (MVs) as output, using the multiple cost function, the multiple equality function and the multiple inequality function as inputs. And finally, the optimal set of manipulated variables is provided to the plant for optimization of industrial processes in the plant.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
FIG. 1 is a network diagram of a system for optimization of industrial processes in a plant using artificial intelligence (AI) according to some embodiments of the present disclosure.
FIG. 2 is a functional block diagram of the system for optimization of industrial processes in the plant using artificial intelligence (AI) according to some embodiments of the present disclosure.
FIG. 3 is flowchart showing steps involved in the preprocessing of data used in the system of FIG. 1 according to some embodiments of the present disclosure.
FIG. 4 shows a block diagram of a modelling unit of the system of FIG. 1 according to some embodiments of the present disclosure.
FIG. 5 shows a block diagram of an interface controller according to some embodiments of the present disclosure.
FIG. 6 shows a block diagram of an optimization unit of the system of FIG. 1 according to some embodiments of the present disclosure.
FIG. 7 is a flowchart showing a method for optimization of industrial processes in a plant using artificial intelligence (AI) in accordance with some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS

Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments.
Industries today are facing increasing pressure to reduce their operational cost and energy consumption and increase productivity and efficiency while meeting safety, reliability, and emission standards. With a complex operation of many devices integrated in the system, large-scale optimization of their operation is a promising solution for solving these above problems.
There are few methods existing in the prior art which talks about the optimization of industrial processes. These methods lack an appropriate procedure for extracting distinct steady state data from multivariate time-series data. The conventional approaches require significant domain knowledge to mimic plant behavior using phenomenological or first principle models. Further, the existing methods lack a standard for building models and aggregating multiple models that are used in large-scale optimization of the complex system. Moreover, a standard of large-scale optimization framework that can automatically aggregate multiple models with a flexible selection of their input/output interface, which is required when optimization runs at different modes is also not known in the art.
The disclosure provides a system and a method for optimization of industrial processes in a plant using artificial intelligence (AI). The operational optimization is performed for a large-scale system in industrial processes. The disclosure provides an end-to-end framework for data preprocessing, data modelling and large-scale optimization. The system is configured to extract distinct steady state data for predictive modelling. A standard has been set for building models and aggregating models in optimization. A standard has also been set for large-scale optimization framework for automatically aggregating multiple models with a flexible selection of their input/output interface.
Referring now to the drawings, and more particularly to FIG. 1 through FIG. 7, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
According to an embodiment of the disclosure, a system 100 for optimization of industrial processes in a plant using artificial intelligence (AI) is shown in a network diagram of FIG. 1 and a block diagram of FIG. 2. As shown in FIG. 2 the system 100 is in communication with a plant 102 such as an industrial plant. The example of industrial plant may include, but not limited to chemical industry, oil & gas refinery, pharmaceutical industry, minerals industry, power plants etc. The system 100 work in an offline mode and in an online mode.
It may be understood that the system 100 may comprises one or more computing devices 104, such as a laptop computer, a desktop computer, a notebook, a workstation, a cloud-based computing environment and the like. It will be understood that the system 100 may be accessed through one or more input/output interfaces 106-1, 106-2... 106-N, collectively referred to as I/O interface 106. Examples of the I/O interface 106 may include, but are not limited to, a user interface, a portable computer, a personal digital assistant, a handheld device, a smartphone, a tablet computer, a workstation and the like. The I/O interface 106 are communicatively coupled to the system 100 through a network 108.
In an embodiment, the network 108 may be a wireless or a wired network, or a combination thereof. In an example, the network 108 can be implemented as a computer network, as one of the different types of networks, such as virtual private network (VPN), intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network 108 may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), and Wireless Application Protocol (WAP), to communicate with each other. Further, the network 108 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices. The network devices within the network 108 may interact with the system 100 through communication links.
In an embodiment, the computing device 104 further comprises one or more hardware processors 110, hereinafter referred as a processor 110, one or more memory 112, hereinafter referred as a memory 112 and a data repository 114 or a database 114, for example, a repository 114. The memory 112 is in communication with the one or more hardware processors 110, wherein the one or more hardware processors 110 are configured to execute programmed instructions stored in the memory 112, to perform various functions as explained in the later part of the disclosure. The repository 114 may store data processed, received, and generated by the system 100.
The system 110 supports various connectivity options such as BLUETOOTH®, USB, ZigBee and other cellular services. The network environment enables connection of various components of the system 110 using any communication link including Internet, WAN, MAN, and so on. In an exemplary embodiment, the system 100 is implemented to operate as a stand-alone device. In another embodiment, the system 100 may be implemented to work as a loosely coupled device to a smart computing environment. The components and functionalities of the system 110 are described further in detail.
According to an embodiment of the disclosure, the system 100 for optimization of industrial processes in the plant 102 using artificial intelligence (AI) is shown in the block diagram of FIG. 2. The system 100 comprises of a processing unit 116, a modelling unit 118 and an optimization unit 120. The processing unit 116 and the modelling unit 118 work in the offline mode. The optimization unit 120 works in the online mode and remains in communication with the plant 102. A plurality of data related to the industrial processes is received from a plurality of data sources. The plurality of data sources comprises of distributed control system (DCS), historian, laboratory information management system (LIMS), a plurality of external sources, manual input and a plurality of digital systems used in the industrial processes.
According to an embodiment of the disclosure, the processing unit 116 is configured to preprocess the plurality of data received from the data repository 114. A flowchart 300 illustrates the steps involved in the preprocessing of the plurality of data is shown in FIG. 3. Initially, at step 302, the plurality of data received from the industrial processes is split into a plurality of continuous time-series portions. The continuous time-series portions refer to uninterrupted data at a predefined frequency. At step 304, the split plurality of data is smoothened to remove spikes or noises present in the data. The use any known technique for smoothening is well within the scope of this disclosure. At step 306, a dimensionality reduction technique is performed on the smoothened data to transform into a low dimensional space. At step 308, a lower dimension data is extracted from the low dimension space obtained from the dimensionality reduction technique. A window of time-series data is considered for steady state detection, where a probability of each point in the window whether it is steady state, is calculated based on its deviation. At step 310, each of the steady state points present in the steady state data are ranked based on a distance between steady state points using a ranking algorithm. The ranking algorithm initially identifies the distinct and distant points. Further subsequent points ranked such a way that the new point is as unique and away from previously identified points. And finally, at step 312, unique steady state points are extracted out of the ranked steady state points if the respective distance is more than a predefined threshold. An example of the ranking algorithm is shown below:
Ranking Algorithm
1: procedure RANKING
Input: O:={o1, o1, …. on,} – input set in index order
? – vector of weights.
Output: S – ranked set in distance order
2: S: = { oi, i = random (1,n)}}
3: O: = O \ S
4: repeat
5: o* : = argmax {P2S_Distance(o, S, ?)}
o?O
6: S: = S Union {o*}
7: O: = O \ {o*}
8: until O = ø

According to an embodiment of the disclosure, the system 100 comprises the modelling unit 118 as shown in the block diagram of FIG. 4. The modelling unit 118 is configured to generate a plurality of models. The plurality of models uses the distinct steady state data, wherein the plurality of models represents a plurality of performance indicators present in the industrial processes of the plant 102.
The modelling unit 118 further comprises an input multiplexor 122, an output multiplexor 124, an interface controller 126 and a plurality of models generated within. The plurality of models is physics-based models or data-based models. The input multiplexor 122 is configured to receive a data for plurality of manipulated variables (MVs) and a plurality of disturbance variables (DVs) corresponding to the industrial processes as input. The input multiplexer 122 is configured to select a set of MVs from amongst the plurality of MVs, and a set of DVs from amongst of the plurality of DVs corresponding to each model of the plurality of models. The output multiplexor 124 is configured to sort the plurality of models in a topological order. The topological ordering of the plurality of models is needed for proper functioning. Most of the plurality of models generally receives the output of other models as input. Therefore, the plurality of models needs to be sorted in such a way that, the model which is not taking output of any other model as input need to be first in the sorting order. For example, the first model is the model which is not taking input as output of any other model. The second model is chosen in the topological order such a way that output of the first model is one of the inputs of the second model. Similarly, the third model is chosen such a way that the output of one or more of the first and the second model is one or more inputs of the third model and so on.
The selected set of MVs, the selected set of DVs and a set of input process variables (PVs) are provided to each model of the plurality of models. Each model is configured to generate a set of output process variables (PVs), and the set of output process variables are further configured to be used as the set of input PVs to one or more models based on the sorted plurality of models.
The interface controller 126 acts as an interface between the input multiplexor 122 and the output multiplexor 124 as shown in the block diagram of FIG. 5. The interface controller 126 is configured to control data of the plurality of DVs, the plurality of MVs, and the set of PVs for the input multiplexor 122 and the output multiplexor 124. FIG. 5 also shows an example of how the output multiplexor 124 is used to sort the plurality of models. The output multiplexor 124 comprises m number of models present in an unsorted acyclic graph. The output multiplexor 124 is configured to sort the order in topological ordering which decides which model should be built used first and followed by other models. In the shown example, model 5 and model m-1 is not taking input from the output of any other model, so these two models will be first and second in the order while sorting. Model m is taking input only from model m-1, so it comes next in the order. Similarly, followed by model 4, model 2, model 3 and model 1.
According to an embodiment of the disclosure, the system 100 comprises the optimization unit 120 as shown in the block diagram of FIG. 6. The optimization unit 120 is configured to give an optimal set of manipulated variables (MVs) as output. The optimal set of manipulated variables are then provided to the plant 102 for optimization of industrial processes in the plant 102. The optimization unit 120 is also configured to identify in real-time a set of objectives for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs. The set of objectives is represented as a multiple cost function. The formulas for calculation the cost functions are provided by the user. The optimization unit 120 is further configured to identify in real-time a set of constraints for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs. The set of constraints is represented as a multiple equality function and a multiple inequality function.
According to an embodiment of the disclosure, the optimization unit 120 is also configured to solve a generic nonlinear optimization problem to give an optimal set of manipulated variables (MVs) as output, using the multiple cost function, the multiple equality function and the multiple inequality function as inputs. The optimization unit 120 can be explained with the help of following formulas:

multiple cost function = f (x, d, y)
multiple inequality function = g (x, d, y)
multiple equality function = h(x, d, y)
where,
x = a plurality of manipulated variables
d = a plurality of distributed variables
y = a plurality of process variables
optimization equation is:
min{f(x)} s.t.g(x)=0 and h(x)=0

FIG. 7 illustrates an example flow chart of a method 700 for optimization of industrial processes in a plant using artificial intelligence (AI), in accordance with an example embodiment of the present disclosure. The method 700 depicted in the flow chart may be executed by a system, for example, the system 100 of FIG. 1. In an example embodiment, the system 100 may be embodied in the computing device.
Operations of the flowchart, and combinations of operations in the flowchart, may be implemented by various means, such as hardware, firmware, processor, circuitry and/or other device associated with execution of software including one or more computer program instructions. For example, one or more of the procedures described in various embodiments may be embodied by computer program instructions. In an example embodiment, the computer program instructions, which embody the procedures, described in various embodiments may be stored by at least one memory device of a system and executed by at least one processor in the system. Any such computer program instructions may be loaded onto a computer or other programmable system (for example, hardware) to produce a machine, such that the resulting computer or other programmable system embody means for implementing the operations specified in the flowchart. It will be noted herein that the operations of the method 700 are described with help of system 100. However, the operations of the method 700 can be described and/or practiced by using any other system.
Initially at step 702 of the method 700, a plurality of data is received related to the industrial processes from a plurality of data sources. The plurality of data sources comprises of distributed control system (DCS), historian, laboratory information management system (LIMS), a plurality of external sources, manual input and a plurality of digital systems used in the industrial processes
At step 704 of the method 700, the received plurality of data is preprocessed to extract distinct steady state data. Further at step 706, a plurality of models is generated using the distinct steady state data, wherein the plurality of models represents a plurality of performance indicators in the industrial processes present in the plant 102.
At step 708 of the method 700, the plurality of manipulated variables (MVs) and the plurality of disturbance variables (DVs) corresponding to the industrial processes are then provided to the input multiplexer 122. The input multiplexer 122 is configured to select the set of MVs from amongst the plurality of MVs, and the set of DVs from amongst of the plurality of DVs corresponding to each model of the plurality of models. At step 710, the plurality of models is then sorted in a topological order. The sorting is performed by the output multiplexor 124 as explained in the earlier part of the disclosure.
At step 712 of the method 700, a set of output process variables (PVs) is generated using each model of the plurality of models in the sorted topological order, wherein the set of output process variables are generated using the selected set of MVs, the selected set of DVs and a set of input process variables (PVs). The set of output process variables are further configured to be used as the set of input PVs to one or more models amongst the plurality of models. Further at step 714, the set of objectives are identified for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs. The set of objectives is represented as a multiple cost function. The multiple cost function is function of the plurality of distributed variables, the plurality of manipulated variables and the plurality of process variables.
Further at step 716 of the method 700, the set of constraints is identified in the real-time for the industrial processes using the plurality of MVs, the plurality of DVs and the plurality of output PVs. The set of constraints is represented as the multiple equality function and the multiple inequality function. Both the multiple equality function and the multiple inequality function are a function of the plurality of distributed variables, the plurality of manipulated variables and the plurality of process variables
At step 718 of the method 700, a generic nonlinear optimization problem is solved to give an optimal set of manipulated variables (MVs) as output, using the multiple cost function, the multiple equality function, and the multiple inequality function as inputs. The generic nonlinear optimization problem comprises identifying minimum of the multiple cost function such that the multiple inequality function is more than or equal to zero and the multiple equality function is equal to zero. And finally, at step 720, the optimal set of manipulated variables is provided to the plant 102 for optimization of industrial processes in the plant 102. The optimal set of MVs is stored in the data repository 114.
The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
The embodiments of present disclosure herein address unresolved problem of the presence of a user with significant domain knowledge, lack a standard for building models and aggregating multiple models that are used in large-scale optimization of the complex system. The embodiment thus provides the method and system for optimization of industrial processes in a plant using artificial intelligence (AI).
The embodiments of present disclosure check for the anomalous behavior of the system and define the root cause of the identified anomaly. Process optimization module get triggered only in the absence of any anomaly of the system. Furthermore, the embodiments of present disclosure identify the operational state of the CCGT plant 102 namely steady and unsteady states.
It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software processing components located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various components described herein may be implemented in other components or combinations of other components. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims.