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 DETERMINING OPTIMUM CONFIGURATIONS IN INDUSTRIAL SYSTEMS

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

Preamble to the description:
The following specification particularly describes the invention and the manner in which it is to be performed.
TECHNICAL FIELD
[001] The disclosure herein generally relates to industrial method systems, and, more particularly, to a method and system for determining optimum configurations in industrial systems.

BACKGROUND
[002] In manufacturing, healthcare and insurance a very common problem is that the system configuration of a product or the criterion changes frequently. However even under such changing environments that entails changing constraints corporations would like to optimize the quality of their product. A batch that produces optimum quality of product is commonly known as a Golden Batch. It is a huge challenge to consistently produce golden batches specially under dynamically changing environment.
[003] State of the art approaches for finding optimum configurations resulting in golden batches require experiments to be performed. In these approaches, quality of optimum configurations identified has a dependency on expertise of a domain expert who conducts the experiments to define process parameters. These approaches further have dependency on various visualization techniques that are used to manually identify drift from original plan.

SUMMARY
[004] 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 processor implemented method is provided. The method includes generating, via one or more hardware processors, a reference trajectory for an industrial process. The step of generating the reference trajectory includes the following steps. Initially, one or more estimators are trained using historical data pertaining to a past performance of an industrial manufacturing process, wherein by training the one or more estimators, a trained model is generated. Further, an acquisition function is generated using the trained model and values of a plurality of dynamic constraints obtained at runtime, after verifying that the one or more estimators have been fully trained, wherein an exploration space considered for generating the acquisition function is cut and shrunk based on one or more dynamic constraints. Further, coordinates of the exploration space, corresponding to maxima of the acquisition function as recommendation, are returned, wherein the acquisition function is created with a high value on exploitation. Further, a feedback is obtained for the recommendation and the obtained feedback is then stored for a pre-defined time period. Further, the one or more estimators are retrained based on one or more of the feedback obtained during a predefined time period, to obtain retrained estimators. Further, the reference trajectory is generated using one or more parameters that maximize the acquisition function, generated from the retrained estimators, based on a new exploration space created from the dynamic constraints obtained in a plurality of subsequent iterations.
[005] In another aspect, the method includes generating a real-time trajectory based on values of a plurality of parameters obtained for a plurality of real-time inputs, using a trained estimator from among the one or more estimators; comparing the real-time trajectory with the reference trajectory to identify any drift; and dynamically recommending values of a plurality of parameters obtained for the plurality of real-time inputs, to match a corresponding real-time trajectory with the reference trajectory, if an identified drift is exceeding a threshold of drift.
[006] In yet another aspect, a system is provided. The system includes one or more hardware processors, a communication interface, and a memory storing a plurality of instructions. The plurality of instructions cause the one or more hardware processors to generate a reference trajectory, by initially training one or more estimators using historical data pertaining to a past performance of an industrial manufacturing process, wherein by training the one or more estimators, a trained model is generated. Further, an acquisition function is generated using the trained model and values of a plurality of dynamic constraints obtained at runtime, after verifying that the one or more estimators have been fully trained, wherein an exploration space considered for generating the acquisition function is cut and shrunk based on one or more dynamic constraints. Further, coordinates of the exploration space, corresponding to maxima of the acquisition function as recommendation, are returned, wherein the acquisition function is created with a high value on exploitation. Further, a feedback is obtained for the recommendation and the obtained feedback is then stored for a pre-defined time period. Further, the one or more estimators are retrained based on one or more of the feedback obtained during a predefined time period, to obtain retrained estimators. Further, the reference trajectory is generated using one or more parameters that maximize the acquisition function, generated from the retrained estimators, based on a new exploration space created from the dynamic constraints obtained in a plurality of subsequent iterations.
[007] In yet another aspect, the system generates a real-time trajectory based on values of a plurality of parameters obtained for a plurality of real-time inputs, using a trained estimator from among the one or more estimators; compares the real-time trajectory with the reference trajectory to identify any drift; and dynamically recommends values of a plurality of parameters obtained for the plurality of real-time inputs, to match a corresponding real-time trajectory with the reference trajectory, if an identified drift is exceeding a threshold of drift.
[008] In yet another aspect, a non-transitory computer readable medium is provided. The non-transitory computer readable medium includes a plurality of instructions, which when executed, cause the one or more hardware processors to initially train one or more estimators using historical data pertaining to a past performance of an industrial manufacturing process, wherein by training the one or more estimators, a trained model is generated. Further, an acquisition function is generated using the trained model and values of a plurality of dynamic constraints obtained at runtime, after verifying that the one or more estimators have been fully trained, wherein an exploration space considered for generating the acquisition function is cut and shrunk based on one or more dynamic constraints. Further, coordinates of the exploration space, corresponding to maxima of the acquisition function as recommendation, are returned, wherein the acquisition function is created with a high value on exploitation. Further, a feedback is obtained for the recommendation and the obtained feedback is then stored for a pre-defined time period. Further, the one or more estimators are retrained based on one or more of the feedback obtained during a predefined time period, to obtain retrained estimators. Further, the reference trajectory is generated using one or more parameters that maximize the acquisition function, generated from the retrained estimators, based on a new exploration space created from the dynamic constraints obtained in a plurality of subsequent iterations.
[009] In yet another aspect, the non-transitory computer readable medium generates a real-time trajectory based on values of a plurality of parameters obtained for a plurality of real-time inputs, using a trained estimator from among the one or more estimators; compares the real-time trajectory with the reference trajectory to identify any drift; and dynamically recommends values of a plurality of parameters obtained for the plurality of real-time inputs, to match a corresponding real-time trajectory with the reference trajectory, if an identified drift is exceeding a threshold of drift.
[010] 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
[011] 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:
[012] FIG. 1 illustrates an exemplary system for recommending optimum configuration according to some embodiments of the present disclosure.
[013] FIG. 2 is a flow diagram illustrating steps involved in the process of generating a reference trajectory for recommending optimum configuration, by the system of FIG. 1, according to some embodiments of the present disclosure.
[014] FIG. 3 is a flow diagram depicting steps involved in the process of recommending the optimum configuration, using the reference trajectory, by the system of FIG. 1, in accordance with some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[015] 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.
[016] State of the art approaches for finding optimum configurations resulting in golden batches require experiments to be performed. In these approaches, quality of optimum configurations identified has a dependency on expertise of a domain expert who conducts the experiments to define process parameters. These approaches further have dependency on various visualization techniques that are used to manually identify drift from original plan.
[017] System and method disclosed in the embodiments herein facilitate determining optimum configurations for producing golden batches in industrial systems. The system generates a reference trajectory for an industrial manufacturing process, which acts as a baseline of performance. Further, a real-time trajectory is generated based on values of a plurality of parameters, obtained for a plurality of real-time inputs. If a measured drift is exceeding a threshold of drift, then values of one or more of a plurality of parameters obtained for a plurality of real-time inputs, are varied dynamically to match a corresponding real-time trajectory with the reference trajectory.
[018] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3, 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.
[019] FIG. 1 illustrates an exemplary system for recommending optimum configuration according to some embodiments of the present disclosure. The system 100 includes or is otherwise in communication with hardware processors 102, at least one memory such as a memory 104, an I/O interface 112. The hardware processors 102, memory 104, and the Input /Output (I/O) interface 112 may be coupled by a system bus such as a system bus 108 or a similar mechanism. In an embodiment, the hardware processors 102 can be one or more hardware processors.
[020] The I/O interface 112 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface 112 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a printer and the like. Further, the I/O interface 112 may enable the system 100 to communicate with other devices, such as web servers, and external databases.
[021] The I/O interface 112 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite. For the purpose, the I/O interface 112 may include one or more ports for connecting several computing systems with one another or to another server computer. The I/O interface 112 may include one or more ports for connecting several devices to one another or to another server.
[022] The one or more hardware processors 102 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, node machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more hardware processors 102 is configured to fetch and execute computer-readable instructions stored in the memory 104.
[023] The memory 104 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. In an embodiment, the memory 104 includes a plurality of modules 106.
[024] The plurality of modules 106 include programs or coded instructions that supplement applications or functions performed by the system 100 for executing different steps involved in the process of generating the reference trajectory, and for recommending optimum configuration using the reference trajectory, being performed by the system 100. The plurality of modules 106, amongst other things, can include routines, programs, objects, components, and data structures, which performs particular tasks or implement particular abstract data types. The plurality of modules 106 may also be used as, signal processor(s), node machine(s), logic circuitries, and/or any other device or component that manipulates signals based on operational instructions. Further, the plurality of modules 106 can be used by hardware, by computer-readable instructions executed by the one or more hardware processors 102, or by a combination thereof. The plurality of modules 106 can include various sub-modules (not shown). The plurality of modules 106 may include computer-readable instructions that supplement applications or functions performed by the system 100 for generating the reference trajectory, and for recommending optimum configuration using the reference trajectory.
[025] The data repository (or repository) 110 may include a plurality of abstracted piece of code for refinement and data that is processed, received, or generated as a result of the execution of the plurality of modules in the module(s) 106.
[026] Although the data repository 110 is shown internal to the system 100, it will be noted that, in alternate embodiments, the data repository 110 can also be implemented external to the system 100, where the data repository 110 may be stored within a database (repository 110) communicatively coupled to the system 100. The data contained within such external database may be periodically updated. For example, new data may be added into the database (not shown in FIG. 1) and/or existing data may be modified and/or non-useful data may be deleted from the database. In one example, the data may be stored in an external system, such as a Lightweight Directory Access Protocol (LDAP) directory and a Relational Database Management System (RDBMS). Functions of the components of the system 100 are now explained with reference to the steps in flow diagrams in FIG. 2 and FIG. 3.
[027] FIG. 2 is a flow diagram illustrating steps involved in the process of generating a reference trajectory for recommending optimum configuration, by the system of FIG. 1, according to some embodiments of the present disclosure.
[028] Steps in the method 200 are explained with reference to the components of the system 100. In an embodiment, the system 100 comprises one or more data storage devices or the memory 104 operatively coupled to the processor(s) 102 and is configured to store instructions for execution of steps of method 200 in FIG. 2 by the processor(s) or one or more hardware processors 102. The steps of the method 200 of the present disclosure will now be explained with reference to the components or blocks of the system 100 as depicted in FIG. 1 and the steps of flow diagram as depicted in FIG. 2. Although process steps, method steps, techniques or the like may be described in a sequential order, such processes, methods, and techniques may be configured to work in alternate orders. In other words, any sequence or order of steps that may be described does not necessarily indicate a requirement that the steps to be performed in that order. The steps of processes described herein may be performed in any order practical. Further, some steps may be performed simultaneously.
[029] Result of any industrial process depends on values of various parameters, which may be parameters such as but not limited to temperature, humidity, and pressure. For example, in a typical realization inputs could be temperature range 0 to 200-degree c, humidity 10% to 30% and constraints pH = 5. Determining the optimum configuration in the context of the embodiments disclosed herein refers to determining optimum values of the parameters which provides an intended result. To determine the optimum configuration, the system 100 generates via method 200 in FIG. 2, via the one or more hardware processors 102, a reference trajectory for an industrial process. Steps of the method 200 are further elaborated below.
[030] At step 202 of the method 200, the system 100 trains one or more estimators using historical data pertaining to a past performance of an industrial manufacturing process, wherein by training the one or more estimators, a trained model is generated. In an embodiment, the system 100 may use any suitable machine learning approach to train the estimators and generate the trained model. The historical data pertaining to the past performance of the industrial manufacturing process, which is used for training the estimators, may include information on a set of parameters, i.e. values of each of the parameters, for different operating conditions of the industrial manufacturing process. The different operating conditions maybe defined in terms of percentage of result obtained and/or a state of the industrial manufacturing process i.e. failure, success, partially completed and so on.
[031] Further, at step 204 of the method 200, the system 100 generates an acquisition function using the trained model and values of a plurality of dynamic constraints obtained at runtime. The acquisition function is a function that can be evaluated at a given point that is commensurate with how desirable evaluating f at x is expected to be for the minimization problem. In an embodiment, the system 100 performs the step of generating the acquisition function after verifying that the one or more estimators have been fully trained. Percentage of completion of the training of the one or more estimators maybe collected as in input by the system 100, or may be automatically determined by monitoring the training of the estimators. The system 100 generates the acquisition function such that an exploration space considered for generating the acquisition function is cut and shrunk based on one or more dynamic constraints. In an embodiment, the acquisition function is created with a high value on exploitation. The term ‘exploitation’ refers to reuse of decisions that have worked well in the past, whereas 'exploration’ refers to step of generating new decisions. Exploitation and exploration maybe performed as per known approaches, when required.
[032] In an embodiment, the system 100 accommodates the dynamic constraints by means of the following process.
• Step 1:- Receive upper bound and lower bound for all variables. At this step, the upper bound and the lower bound maybe received as input from a user.
• Step 2:- Receive information as to which are constraints and which are variable parameters, from the user or from an associated automated system. Also receive value of the constraint.
• Step 3:- Create a first random variable (RV1) which has a probability distribution within the received upper bound and the lower bound.
• Step 4:- Create a second random variable (RV2) which has a conditional probability distribution that is conditioned on the probability distribution associated with RV1. The Condition mentioned here is the scaled version of the constraint value received at step 2.
• Step 5:- Sampling n points (where, n = 10000 (approximately) in typical realizations) from the conditioned probability distribution created at step4.
• Step 6:- Pass the n points into the acquisition function.
[033] Further, at step 206 of the method 200, the system 100 returns coordinates of the exploration space, corresponding to a maxima of the acquisition function, as a recommendation. The coordinates indicate values of the recommendation which have high probability of optimizing a product/process quality being monitored, based on the reference trajectory. In addition, the recommendation also includes indices of sensors which sense/monitor/measure the parameters that are to be optimized. The system 100 may use any suitable optimization approach, for example a Bayesian optimization process, to generate the recommendation. The Bayesian optimization process, when used, optimizes a given set of parameters subjected to a predefined objective value. Further, at step 208 of the method 200, the system 100 obtains a feedback for the recommendation and storing the obtained feedback for a pre-defined time period. After collecting the feedback for the pre-defined time period, at step 210 of the method 200, the system 100 retrains the one or more estimators based on one or more of the feedback, to obtain retrained estimators. In an embodiment, the system 100 retrains the one or more estimators even if the one or more feedback indicates that the recommendations are satisfactory or good, so that confidence with which the one or more estimators generate the recommendations increases. In another embodiment, the system 100 may use incremental data or complete data to retrain the one or more estimators. Further, at step 212 of the method 200, the system 100 generates the reference trajectory using one or more parameters that maximize the acquisition function, generated from the retrained estimators, based on a new exploration space created from the dynamic constraints obtained in a plurality of subsequent iterations.
[034] The generated reference trajectory may then act as a baseline of performance i.e. representing a minimum performance level that is to be obtained in any practical scenario, and is further used for determining the optimum configuration. Steps involved in the process of determining the optimum configuration using the generated reference trajectory are depicted in method 300 in FIG. 3, and are explained hereafter. At step 302 of the method 300, the system 100 generates a real-time trajectory based on values of a plurality of parameters obtained for a plurality of real-time inputs, using a trained estimator from among the one or more estimators. Further, at step 304 of the method 300, the system 100 compares the real-time trajectory with the reference trajectory to identify any drift. In another embodiment, the system 100 may compare the real-time trajectory with the reference trajectory after reaching each of a plurality of pre-defined milestones. The pre-defined milestones may be in terms of percentage of completion of an ongoing process (for example, 25% completion, 40% completion and so on) and/or any other similar parameter(s) associated with the industrial process.
[035] In the context of the embodiments disclosed herein, the term ‘drift’ indicates a deviation of the real-time trajectory from the reference trajectory, which causes a dip in result in comparison with the baseline of performance. At this stage, as the system 100 identifies that the current values of one or more of the parameters has caused the dip in result, in order to improve the result to at least match the baseline of performance, at step 306 of the method 300, the system 100 dynamically recommends values of a plurality of parameters obtained for the plurality of real-time inputs, such that the corresponding real-time trajectory (i.e. generated based on the recommended values of the plurality of parameters) at least matches the reference trajectory. For example, in a typical realization under consideration, say after nth milestone, the desirable pH value should be 10 and instead the system 100 identifies that a pH value of 8 was obtained, which results into the deviation from the reference trajectory. So the system optimizes one or more other controllable parameters, for example, temperature, so that the difference of the reference trajectory and the real-time trajectory is below a pre-defined threshold. In an embodiment, the system 100 iteratively performs the steps 302 through 306, after recommending values of the plurality of parameters, till the real-time trajectory at least matches the reference trajectory. At this step, the system 100 determines the parameters (controllable parameters) to be optimized, based on the coordinates recommended at step 206 of the method 200, i.e. sensors at the recommended coordinates are identified, and corresponding parameters (i.e. the parameters being sensed by the sensors at the recommended parameters) are optimized. Further, optimization may involve increasing or decreasing values of the parameters. The values for optimization of the parameters are obtained as the recommendation at step 206 of the method 200, and accordingly the values of each of the parameters are increased or decreased, at once or in iterations, as maybe configured.
[036] 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.
[037] The embodiments of present disclosure herein address unresolved problem of determining optimum configurations in industrial systems. The embodiment, thus provides a mechanism of generating a reference trajectory for an industrial process. Moreover, the embodiments herein further provide a mechanism of determining the optimum configuration such that a real-time trajectory matches the reference trajectory.
[038] 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.
[039] 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.
[040] 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.
[041] 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.
[042] 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.
, Claims:We Claim:

1. A processor implemented method, comprising:
generating, via one or more hardware processors, a reference trajectory for an industrial process, comprising:
training (202) one or more estimators using historical data pertaining to a past performance of an industrial manufacturing process, wherein by training the one or more estimators, a training data is generated;
generating (204) an acquisition function using the training data, after verifying that the one or more estimators have been fully trained, wherein an exploration space considered for generating the acquisition function is cut and shrunk based on one or more dynamic constraints;
returning (206) parameters corresponding to maxima of the acquisition function as recommendation, wherein the acquisition function is created with a high value on exploitation;
obtaining (208) a feedback for the recommendation, at a pre-defined time interval;
optimizing (210) the recommendation based on the feedback obtained at the pre-defined time interval; and
generating (212) the reference trajectory using one or more of the optimized recommendations.

2. The method as claimed in claim 1, further comprising:
generating (302) a real-time trajectory based on values of a plurality of parameters obtained for a plurality of real-time inputs;
comparing (304) the real-time trajectory with the reference trajectory to identify any drift; and
dynamically (306) varying values of one or more of a plurality of parameters obtained for the plurality of real-time inputs, to match a corresponding real-time trajectory with the reference trajectory, if an identified drift is exceeding a threshold of drift.

3. The method as claimed in claim 1, wherein the one or more estimators are trained by using information on a set of parameters depicting different operating conditions of the industrial manufacturing process as input.

4. The method as claimed in claim 1, wherein the real-time trajectory is compared with the reference trajectory after reaching each of a plurality of pre-defined milestones.

5. A system (100), comprising:
one or more hardware processors (102);
a communication interface (112); and
a memory (104) storing a plurality of instructions, wherein the plurality of instructions cause the one or more hardware processors to:
generate a reference trajectory, by:
train one or more estimators using historical data pertaining to a past performance of an industrial manufacturing process, wherein by training the one or more estimators, a training data is generated;
generate an acquisition function using the training data, after verifying that the one or more estimators have been fully trained, wherein an exploration space considered for generating the acquisition function is cut and shrunk based on one or more dynamic constraints;
return parameters corresponding to maxima of the acquisition function as recommendation, wherein the acquisition function is created with a high value on exploitation;
obtain a feedback for the recommendation, at a pre-defined time interval;
optimize the recommendation based on the feedback obtained at the pre-defined time interval; and
generate the reference trajectory using one or more of the optimized recommendations.

6. The system as claimed in claim 5, wherein the one or more hardware processors are further configured by the plurality of instructions to:
generate a real-time trajectory based on values of a plurality of parameters obtained for a plurality of real-time inputs;
compare the real-time trajectory with the reference trajectory to identify any drift; and
dynamically vary values of one or more of a plurality of parameters obtained for the plurality of real-time inputs, to match a corresponding real-time trajectory with the reference trajectory, if an identified drift is exceeding a threshold of drift.

7. The system as claimed in claim 5, wherein the one or more hardware processors are configured to train the one or more estimators by using information on a set of parameters depicting different operating conditions of the industrial manufacturing process as input.

8. The system as claimed in claim 5, wherein the one or more hardware processors are configured to compare the real-time trajectory with the reference trajectory after reaching each of a plurality of pre-defined milestones.

Dated this 10th Day of October 2022

Tata Consultancy Services Limited
By their Agent & Attorney

(Adheesh Nargolkar)
of Khaitan & Co
Reg No IN-PA-1086