WO2021210019A1

WO2021210019A1 - Method and system for material balance and data reconciliation in a plant

Info

Publication number: WO2021210019A1
Application number: PCT/IN2021/050373
Authority: WO
Inventors: Vishnu Swaroopji Masampally; Aditya Pareek; Nagaravi Kumar Varma Nadimpalli; Venkataramana Runkana
Original assignee: Tata Consultancy Services Limited
Priority date: 2020-04-14
Filing date: 2021-04-14
Publication date: 2021-10-21

Abstract

Material balancing is one of the important feature of the manufacturing plant. The existing methods for material balancing have limited applicability as they require lot of manual intervention by experienced plant engineers. A system and a method for achieving automated material balancing or mass balancing and data reconciliation in a manufacturing or a process plant to solve the technical problems of the prior art. The system is configured to automatically identify operating process flow circuit in real-time for data reconciliation and material balancing in the manufacturing plant. The automated preprocessing identifies and flags whether the material is balanced at each nodes present in the plant and also identifies the flow rates based on their values. These flags help in identifying the nodes and tags or material flow rates and further give importance to those nodes and tags for which mass is not balanced during the mass balance and reconciliation activity.

Description

METHOD AND SYSTEM FOR MATERIAL BALANCE AND DATA RECONCILIATION IN A PLANT

CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY

[001] The present application claims priority from Indian provisional patent application no. 202021016143, filed on April 14, 2020. The entire contents of the aforementioned application are incorporated herein by reference.

TECHNICAL FIELD

[002] The disclosure herein generally relates to the field of material balancing, and, more particularly, to a method and system for material balance and data reconciliation in a manufacturing plant or in a process industry.

BACKGROUND

[003] Manufacturing or production of chemicals or materials involves a complex network of flow of materials between various equipment in a manufacturing or a process plant. Raw materials are transformed into products and by-products through a complex process flow circuit. This circuit, in general, is dynamic and may change every day, or every shift depending on raw material availability, product demand, or unplanned breakdown of equipment. The process flow circuit mainly consists of nodes that could be processing equipment, pipes, storage tanks and auxiliary equipment such as pumps and blowers through which materials flow. All the materials that flow through the manufacturing or the process plant needs to be accounted for. The process of accounting for the material at each node individually, as well as reconciling it across the whole circuit is called mass balance or material balance. In simple terms, material or mass balance is essentially the law of conservation of mass across the system under consideration using the flow rates of streams of materials that flow between nodes measured using flow measurement instruments or sensors such as orifice meter, venturi meter or mass flow meter.

[004] One of the key challenges in process industries is to perform material balance across the plant. Plant-wide material balance is performed to account for financial accounting and to evaluate the plant performance in a given period of time. This evaluation includes detecting leaks, losses and degradation of key performance indicators in the plant. Further, while the measurements may be precise at the input and output nodes of the process flow circuit as mandated by regulation as well as financial accounting requirements, the measurements within the plant may be uncertain at some locations due to malfunctioning or infrequent calibration of sensors or instruments used for the measurement of flow rates of streams of chemicals or materials. Material balancing has to be carried out for the total or overall flow of materials as well as for flow of individual chemical or material species present.

[005] Current practice in large process industries is to perform material balance on a daily basis as it requires considerable amount of effort by a team of plant engineers for analyzing the sensor and production data. Since the sensor data is not accurate for all the sensors, the material balance for some nodes or a sub-system in the plant or the whole plant does not match.

SUMMARY

[006] 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 online material balance and data reconciliation in a plant is provided. The system includes an input/output interface, one or more hardware processors and a memory. The input/output interface configured to: collect data from a plurality of data sources as an input data, wherein the input data is representative of information at a plurality of nodes present in the manufacturing plant, and receive sensor data from the plurality of data sources present in the manufacturing plant. The memory 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: extract flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes using the collected input data from the manufacturing plant; extract stock levels of the plurality of materials maintained at each of the plurality of nodes using the collected input data; create a process flow circuit using the extracted flow rates and the stock levels at each of the plurality of nodes using a graph algorithm; preprocess the sensor data received from the plurality of data sources; estimate initial guess values of the flow rates of the plurality of materials using one or more of: the preprocessed sensor data over a period of time, a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and a set of data-based models created using historical data and material balance data, if the sensor data and the set of physics-based models are not available; estimate confidence interval values of the estimated initial guess value of the flow rates; generate a plurality of equations for material balancing based on a type of material balancing in the manufacturing plant; estimate a degree of freedom (DoF) at each of the plurality of nodes in the manufacturing plant; solve a set of equations out of the plurality of equations at each of the plurality of nodes where the DoF is zero; provide the estimated initial guess values of the flow rates of the plurality of materials which is not available to make the DoF zero at the nodes where degree of freedom is not zero; calculate a material balance error at each of the plurality of nodes using initial guess values across the process flow circuit; and estimate accurate values of the flow rates of the plurality of materials within their estimated confidence interval values by minimizing the calculated material balance error at each node using an optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes.

[007] In another aspect, a method for online material balancing and data reconciliation of a plurality of materials in a manufacturing plant is provided. Initially, data from a plurality of data sources as is collected an input data, wherein the input data is representative of information at a plurality of nodes present in the manufacturing plant. Further, flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes are extracted using the collected input data from the manufacturing plant. Similarly, stock levels of the plurality of materials maintained at each of the plurality of nodes are also extracted using the collected input data. In the next step, a process flow circuit is created using the extracted flow rates and the stock levels at each of the plurality of nodes using a graph algorithm. Further, sensor data is received from the plurality of data sources present in the manufacturing plant. The sensor data received from the plurality of data sources is then preprocessed. Further, initial guess values of the flow rates of the plurality of materials are estimated using one or more of: the preprocessed sensor data over a period of time, a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and a set of data- based models created using historical data and material balance data, if the sensor data and the set of physics-based models are not available. Further, confidence interval values of the estimated initial guess value of the flow rates are estimated. In the next step, a plurality of equations is generated for material balancing based on a type of material balancing in the manufacturing plant. In the next step, a degree of freedom (DoF) is estimated at each of the plurality of nodes in the manufacturing plant. Further, a set of equations out of the plurality of equations is solved at each of the plurality of nodes where the DoF is zero. The estimated initial guess values of the flow rates of the plurality of materials which is not available to make the DoF zero is provided at the nodes where degree of freedom is not zero. Further, a material balance error is calculated at each of the plurality of nodes using initial guess values across the process flow circuit. And finally, accurate values of the flow rates of the plurality of materials are estimated within their estimated confidence interval values by minimizing the calculated material balance error at each node using an optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes.

[008] In yet another aspect, one or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause online material balancing and data reconciliation of a plurality of materials in a manufacturing plant. Initially, data from a plurality of data sources as is collected an input data, wherein the input data is representative of information at a plurality of nodes present in the manufacturing plant. Further, flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes are extracted using the collected input data from the manufacturing plant. Similarly, stock levels of the plurality of materials maintained at each of the plurality of nodes are also extracted using the collected input data. In the next step, a process flow circuit is created using the extracted flow rates and the stock levels at each of the plurality of nodes using a graph algorithm. Further, sensor data is received from the plurality of data sources present in the manufacturing plant. The sensor data received from the plurality of data sources is then preprocessed. Further, initial guess values of the flow rates of the plurality of materials are estimated using one or more of: the preprocessed sensor data over a period of time, a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and a set of data-based models created using historical data and material balance data, if the sensor data and the set of physics-based models are not available. Further, confidence interval values of the estimated initial guess value of the flow rates are estimated. In the next step, a plurality of equations is generated for material balancing based on a type of material balancing in the manufacturing plant. In the next step, a degree of freedom (DoF) is estimated at each of the plurality of nodes in the manufacturing plant. Further, a set of equations out of the plurality of equations is solved at each of the plurality of nodes where the DoF is zero. The estimated initial guess values of the flow rates of the plurality of materials which is not available to make the DoF zero is provided at the nodes where degree of freedom is not zero. Further, a material balance error is calculated at each of the plurality of nodes using initial guess values across the process flow circuit. And finally, accurate values of the flow rates of the plurality of materials are estimated within their estimated confidence interval values by minimizing the calculated material balance error at each node using an optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes. [009] 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

[010] 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:

[Oil] FIG. 1 illustrates a network diagram of a system for material balance and data reconciliation in a manufacturing plant according to some embodiments of the present disclosure.

[012] FIG. 2 shows a schematic block diagram of a system for material balance and data reconciliation in the manufacturing plant according to an embodiment of the present disclosure.

[013] FIG. 3 is a flow diagram illustrating the function of a process flow circuit identification module of the system of FIG. 1 according to some embodiments of the present disclosure.

[014] FIG. 4 is a flow diagram illustrating the function of a preprocessing module of the system of FIG. 1 in accordance with some embodiments of the present disclosure.

[015] FIG. 5 is a flow diagram illustrating the function of a knowledge extraction module of the system of FIG. 1 according to some embodiments of the present disclosure.

[016] FIG. 6 is a flow diagram illustrating the function of a material balancing module of the system of FIG. 1 in accordance with some embodiments of the present disclosure.

[017] FIG. 7 is a flow diagram illustrating the function of a recommendation module of the system of FIG. 1 in accordance with some embodiments of the present disclosure.

[018] FIGS. 8A-8B is a flow diagram illustrating a method for material balance and data reconciliation in the manufacturing plant the in accordance with some embodiments of the present disclosure.

DETAIFED DESCRIPTION OF EMBODIMENTS [019] 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. [020] One of the methods for overcoming the problem stated above is to ensure material balance across the system under consideration, using software packages available. However, these packages themselves have limitations and they require experienced plant engineers to examine the output or results of data reconciliation packages, and make appropriate corrections in flow rates of some process streams based on their past knowledge and experience. Currently, material balance and data reconciliation activity using sensor and production data, for a day’s production at a large chemical or mineral processing plant may take an entire day of effort to perform necessary post-processing by a team of qualified and experienced plant engineers.

[021] Some other methods are available in the prior art for material balancing based on simulation of the operation of the plant. But they have a limited applicability as they require a lot of manual intervention by experienced plant engineers. These methods work only when all the data from various units of the manufacturing plant is available. Moreover, majority of the methods do not take data based models into account and utilize only physics-based models for simulations. Another important limitation of the existing methods and data reconciliation methods is that one cannot determine or conclude with guarantee whether a measurement error is a random error or a gross error.

[022] The present disclosure herein provides a system and a method for achieving automated material balancing or mass balancing and data reconciliation in a manufacturing or a process plant to solve the technical problems of the prior art. The system can be configured to automatically identify the operating process flow circuit in real-time for data reconciliation and material balancing in the manufacturing plant. The automated preprocessing identifies and flags whether the material is balanced at each of a plurality of nodes present in the plant and also identifies the flow rates based on their values. These flags help in identifying the nodes and tags or material flow rates and further give importance to those nodes and tags for which mass is not balanced during the mass balance and reconciliation activity. The system is configured to reduce the human effort and to increase the frequency at which material balance can be reported that helps in better decision making.

[023] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 8B, 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.

[024] Normally, the processing or manufacturing plant or any process industry can be represented in terms of a plurality of nodes and a plurality of material or process streams that are either inputs or outputs of each node. The plurality of nodes are various equipment or various points within the plant which has some importance in relation to the operation of the plant. Additionally, materials flow or move across the plurality of nodes through inlet and outlet pipes or ducts. The materials or process streams may be single -phase materials like liquid or gas or solid, or multi-phase materials like vapor-liquid, gas-liquid, gas-solid, gas-liquid-solid, etc. Similarly, the materials or process streams may be pure chemical or materials species (for example, water, alcohol, hematite, alumina, etc.) or a mixture of chemical or material species (for example, mixture of water, alcohol and benzene, mixture of materials like iron ore, coal and limestone, or a mixture of mineral species like hematite and magnetite, etc.). The nodes may be unit operations such as mixing tanks, storage tanks, heat exchangers, boilers, distillation columns, gas absorption columns, liquid-liquid extraction columns, single or multi-phase reactors, furnaces, converters, etc., with applications in chemical process industries, refineries, drugs and pharmaceuticals, power plants, steel plants, pulp and paper mills, cement plans, mineral processing plants, etc. In an example, the flow rates of materials can also be represented by “TAGS”. The flow rate could be in terms of mass flow, molar flow or volumetric flow. For example in a chemical or materials processing plant, the materials can be raw materials such as ore, petroleum crude or wood pulp, utilities like water or steam, or the final products like steel or mineral concentrate or cement or an intermediate product and the mass flow of these raw materials or products is referred to as TAGS, while the plurality of nodes may be flocculation tank, mixing tank, stirred tank reactor, distillation column, heat exchanger, boiler, blending unit, surge tank, etc. The TAGS constitute total or species-wise mass flow or volumetric flow rate of materials from one node to another.

[025] According to an embodiment of the disclosure, a system 100 for automated material balancing or mass balancing and data reconciliation in a manufacturing plant 102 or a process plant 102 is shown in FIG 2. Although the present disclosure is explained considering that the system 100 is implemented on a server, it may also be present elsewhere such as a local machine. It may be understood that the system 100 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 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. [026] 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.

[027] The system 100 may be implemented in a workstation, a mainframe computer, a server, and a network server. In an embodiment, the computing device 104 further comprises one or more hardware processors 110, one or more memory 112, hereinafter referred as a memory 112 and a data repository 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.

[028] The system 100 supports various connectivity options such as BLUETOOTH®, USB, ZigBee and other cellular services. The network environment enables connection of various components of the system 100 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 100 are described further in detail.

[029] According to an embodiment of the disclosure, the memory 112 comprises a plurality of modules. The plurality of modules are set of instructions and configured to perform a plurality of functions. The plurality of modules comprises a process flow circuit identification module 116, a preprocessing module 118, a knowledge extraction module 120, a material balance equation module 122, a material balancing module 124 and a recommendation module 126.

[030] According to an embodiment of the disclosure, an input data is collected from a plurality of data sources 128. The plurality of data sources 128 comprises one or more of Supervisory Control and Data Acquisition (SCADA) System, Distributed Control System (DCS), Enterprise Resource Planning (ERP) system, Laboratory Information and Management System (LIMS), Manufacturing Execution System (MES), Manufacturing Operations Management System (MOM), Historian that contains archival data, etc. The data can also be entered manually by the user/operator using the I/O interface 104.

[031] According to an embodiment of the disclosure, the process flow circuit identification module 116 is configured to extract flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes using the collected input data from the manufacturing plant as shown in the flowchart 300 of FIG. 3. The process flow circuit identification module 116 also configured to extract stock levels of the plurality of materials maintained at each of the plurality of nodes using the collected input data.

[032] Further the process flow circuit identification module 116 is configured to create a process flow circuit or a network map based on the available flows between the nodes using a graph algorithm. The process flow circuit consists of nodes, TAGS connecting these nodes, information of nodes and TAGS like flow rates, stock levels, calculated mass balance error, etc. The process flow circuit is also used for visualization of the process flow circuit that is currently operating at that instance of time based on the information received from a plurality of sensors 128.

[033] According to an embodiment of the disclosure, the plurality of data sources is also configured to provide sensor data corresponding to a plurality of sensors present in the manufacturing plant. The preprocessing module 118 is configured to preprocess the plurality of data and the created process flow circuit, as shown in flowchart 400 of FIG. 4. The plurality of nodes and the flow rates of materials or process streams are provided as inputs to the preprocessing module 118. The preprocessing module 118 is configured to handle data received from the plurality of sensors 128. The preprocessing module 118 is configured to identify the sensors corresponding to the plurality of the flow rates of materials or process streams that are passed as an input to the module. The preprocessing module 118 is further configured to remove random error in the identified sensor data from the plurality of sensors, remove anomalies in the sensor data from the plurality of sensors and impute the missing data in the sensor data from the plurality of sensors. Thus, the output of the preprocessing module 118 is the information about the plurality of nodes with corresponding flags, errors and flow rates of materials and the preprocessed sensor data.

[034] According to an embodiment of the disclosure, the knowledge extraction module 120 is configured to estimate an initial guess value of the flow rates of the plurality of materials as shown in the flowchart 500 of FIG. 5. The initial guess values of the flow rates of the plurality of materials is estimated using one or more of:

• The preprocessed sensor data over a period of time. The plurality of sensors provides the flow rates of materials over a period of time. Further, the amount of material passing through the unit can be determined by calculating the area under the curve for the period of time under consideration for all the sensors that are tagged to the flowrate of material of interest and taking the summation of all these areas.

• a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and

• a set of data-based models created using historical data and material balance data, if the sensor data and the set of physics-based models are not available. The data-based model uses machine learning or deep learning techniques for estimating the flow rate of total mass and flow of each component or chemical species in total mass with corresponding confidence intervals for all tags for which sensor data is not available in the historical data [035] The knowledge extraction module 120 is also configured to estimate confidence interval values of the estimated initial guess values of the flow rates. The confidence interval value is calculated using a plurality of statistical methods based on the historical data and the set of accuracies of physics-based models and data-based models. Thus, the output of the knowledge extraction module 120 is the extracted knowledge that can provide initial guess values based on current and historical sensor and production data along with their confidence intervals.

[036] According to an embodiment of the disclosure, the material balance equations module 122 is configured to automatically generate a plurality of equations for material balancing based on a type of material balancing in the manufacturing plant. The type of material balance includes one of the plurality of material balance and data reconciliation for total flow rates or for combined total and component or chemical or material species flow rates. The material balance equations 122 module is further configured to provide the equations for material balance based on the subset of process flow circuit chosen from the entire plant circuit or for the entire plant circuit.

[037] According to an embodiment of the disclosure, the material balancing module 124 is configured to estimate a degrees of freedom (DoF) at each of the plurality of nodes for solving one or more of material balance equations at each of the plurality of nodes as shown in flow chart 600 of FIG. 6. The material balancing module 124 solves the mass balance equation or set of mass balance equations wherever the DoF is zero to find the unknown values of the flow rates of materials or process streams at a certain node. This reduces the DoF of neighboring nodes of the node where DoF is zero. The material balancing module 124 performs this steps till there are no further nodes with zero DoF. At the nodes where degree of freedom is not zero, the material balancing module 124 identifies the node with lowest DoF and utilizes the information received from the knowledge extractor module 120 to provide guess values of the flow rates of materials to make the DoF zero. The flow of materials for which the guess value is utilized is flagged as ‘Guessed’. The material balancing module 124 further solves material balance (MB) at these nodes and flag the corresponding estimated flowrate of materials as “Estimated”. This reduces the DoF of the neighboring node and the above process is continued iteratively till the values at raw material (feed) and product tanks are estimated where ground truth or accurate measurement data is already available. A material balance error (MBE) between the ground truth and the estimated flow rates of materials at the raw material and product tanks is the calculated. Thus, the output of the material balancing module 124 is the information about the plurality of nodes and flow rates of materials data with corresponding flags, values and the calculated material balance error at the raw material and product nodes.

[038] According to an embodiment of the disclosure, the recommendation module 126 is configured to solve an optimization problem to minimize the error at the raw material and product nodes calculated by the material balancing module 124 as shown in the flowchart 700 of FIG. 7. The recommendation module 124 estimates accurate values of the ‘Guessed’ flow rates of the plurality of materials within their estimated confidence interval values by minimizing the calculated material balance error at each node and error at raw material and product nodes using the optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes. The recommendation module 126 estimates accurate values of the ’Guessed’ flow rates of materials for which the knowledge extractor module 120 was only able to guess the values. Thus the final output of the system 100 is balanced material data and reconciled data for all the materials or process streams and the individual chemical or materials species in the plant at each of the plurality of nodes.

[039] The system 100 is configured to perform automated estimation of the total and individual chemical or material species flow rates even if the sensor data is not available in the historical data. The key challenge in this activity is the dynamic nature of the process flow circuit and its effect in building data-based models as features used in building these models may or may not be active in the given period of time. The knowledge extraction module 120 extracts a set of features that can be calculated in presence or absence of each sensor that are active nodes in the given period of time. These features are used to create the models for estimating the flow rates of materials from one node to another. Therefore, estimation of flow rates of materials from one node to another using historical data is independent of the process flow circuit structure as the features used for estimating the flow rates of materials are independent of the structure.

[040] In operation, referring to FIG. 8A-8B, flow diagram of a method 800 for online material balancing and data reconciliation of a plurality of materials in a manufacturing plant is described in accordance with an example embodiment. The method 800 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 as explained above.

[041] Operations of the flowchart, and combinations of operation 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 800 are described with help of system 100. However, the operations of the method 800 can be described and/or practiced by using any other system.

[042] Initially at step 802, data is collected from the plurality of data sources as an input data, wherein the input data is representative of information at the plurality of nodes present in the manufacturing plant 102.

[043] Further at step 804, flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes is extracted using the collected input data from the manufacturing plant 102. Similarly, at step 806, stock levels of the plurality of materials maintained is also extracted at each of the plurality of nodes using the collected input data.

[044] Further at step 808, the process flow circuit or the network diagram is created using the extracted flow rates and the stock levels at each of the plurality of nodes using a graph algorithm. [045] In the next step 810, sensor data is received from the plurality of data sources 128 present in the manufacturing plant 102. At step 812, the sensor data received from the plurality of data sources is preprocessed.

[046] Further at step 814, the initial guess values of the flow rates of the plurality of materials is estimated using one or more of: the preprocessed sensor data over a period of time, a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and a set of data-based models created using historical data and material balance data, if the sensor data and the set of physics-based models are not available. At step 816, the confidence interval values are also calculated of the estimated initial guess value of the flow rates.

[047] Further at step 818, a plurality of equations is generated for material balancing based on a type of material balancing in the manufacturing plant 102. At step 820, a degrees of freedom (DoF) is estimated at each of the plurality of nodes in the manufacturing plant 102.

[048] At step 822, a set of equations is solved out of the plurality of equations at each of the plurality of nodes where the DoF is zero. At step 824, the estimated initial guess values of the flow rates of the plurality of materials is provided which is not available to make the DoF zero at the nodes where degree of freedom is not zero.

[049] Further at step 826, the material balance error is calculated at each of the plurality of nodes and material balance error at raw material and product nodes using initial guess values across the process flow circuit. And finally at step 828, the accurate values of the flow rates of the plurality of materials is estimated within their estimated confidence interval values by minimizing the calculated material balance error at each node using an optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes.

[050] 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.

[051] The embodiments of present disclosure herein addresses unresolved problem of inaccurate material balancing and mass balancing. The embodiment, thus provides a method and system for online material balancing and data reconciliation of a plurality of materials in a manufacturing plant [052] 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.

[053] 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.

[054] 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.

[055] 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.

[056] 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

CLAIMS:

1. A method (800) for online material balancing and data reconciliation of a plurality of materials in a manufacturing plant, the method comprising: collecting data from a plurality of data sources as an input data, wherein the input data is representative of information at a plurality of nodes present in the manufacturing plant (802); extracting, via one or more hardware processors, flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes using the collected input data from the manufacturing plant (804); extracting, via the one or more hardware processors, stock levels of the plurality of materials maintained at each of the plurality of nodes using the collected input data (806); creating, via the one or more hardware processors, a process flow circuit using the extracted flow rates and the stock levels at each of the plurality of nodes using a graph algorithm (808); receiving sensor data from the plurality of data sources present in the manufacturing plant (810); preprocessing, via one or more hardware processors, the sensor data received from the plurality of data sources (812); estimating, via the one or more hardware processors, initial guess values of the flow rates of the plurality of materials using one or more of: the preprocessed sensor data over a period of time, a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and a set of data-based models created using historical data and the input data, if the sensor data and the set of physics-based models are not available (814); estimating, via the one or more hardware processors, confidence interval values of the estimated initial guess value of the flow rates (816); generating, via the one or more hardware processors, a plurality of equations for material balancing based on a type of material balancing in the manufacturing plant (818); estimating, via the one or more hardware processors, a degree of freedom (DoF) at each of the plurality of nodes in the manufacturing plant (820); solving, via the one or more hardware processors, a set of equations out of the plurality of equations at each of the plurality of nodes where the DoF is zero (822); providing, via the one or more hardware processors, the estimated initial guess values of the flow rates of the plurality of materials which is not available to make the DoF zero at the nodes where degree of freedom is not zero (824); calculating, via the one or more hardware processors, a material balance error at each of the plurality of nodes using initial guess values across the process flow circuit (826); and estimating, via the one or more hardware processors, accurate values of the flow rates of the plurality of materials within their estimated confidence interval values by minimizing the calculated material balance error at each node using an optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes (828).

2. The method of claim 1, wherein the plurality of nodes comprises a plurality of equipment and a group of equipment within the manufacturing plant.

3. The method of claim 1, wherein the flow rate is measured in terms of one or more of a mass flow, a molar flow and a volumetric flow using a plurality of flow meters.

4. The method of claim 1, wherein the process flow circuit comprises one or more of the plurality of nodes, flow rate between the nodes, information of the plurality of nodes, stock levels, and calculated mass balance error.

5. The method of claim 1, wherein the preprocessing is configured to: remove random error in the sensor data from the plurality of sensors, remove anomalies in the sensor data from the plurality of sensors; and impute the missing data in the sensor data from the plurality of sensors.

6. The method of claim 1, wherein the knowledge extraction is configured to provide the initial guess values using physics-based models tuned with data from plurality of data sources and data-based models built using historical sensor and material balance data.

7. The method of claim 1, wherein the confidence interval value is calculated using a plurality of statistical methods based on the historical data and the set of physics-based model accuracies.

8. The method of claim 1, wherein the plurality of data sources comprises one or more of Supervisory Control and Data Acquisition (SCAD A) System, Distributed Control System (DCS), Enterprise Resource Planning (ERP) system, Laboratory Information and Management System (LIMS), Manufacturing Execution System (MES), Manufacturing Operations Management System (MOM), or Historian containing archival data.

9. A system for online material balance and data reconciliation in a plant, the system comprises: an input/output interface (104) configured to: collect data from a plurality of data sources as an input data, wherein the input data is representative of information at a plurality of nodes present in the manufacturing plant, and receive sensor data from the plurality of data sources present in the manufacturing plant; one or more hardware processors (108); a memory (110) 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: extract flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes using the collected input data from the manufacturing plant; extract stock levels of the plurality of materials maintained at each of the plurality of nodes using the collected input data; create a process flow circuit using the extracted flow rates and the stock levels at each of the plurality of nodes using a graph algorithm; preprocess the sensor data received from the plurality of data sources; estimate initial guess values of the flow rates of the plurality of materials using one or more of: the preprocessed sensor data over a period of time, a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and a set of data-based models created using historical data and the input data, if the sensor data and the set of physics-based models are not available; estimate confidence interval values of the estimated initial guess value of the flow rates; generate a plurality of equations for material balancing based on a type of material balancing in the manufacturing plant; estimate a degree of freedom (DoF) at each of the plurality of nodes in the manufacturing plant; solve a set of equations out of the plurality of equations at each of the plurality of nodes where the DoF is zero; provide the estimated initial guess values of the flow rates of the plurality of materials which is not available to make the DoF zero at the nodes where degree of freedom is not zero; calculate a material balance error at each of the plurality of nodes using initial guess values across the process flow circuit; and estimate accurate values of the flow rates of the plurality of materials within their estimated confidence interval values by minimizing the calculated material balance error at each node using an optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes.

10. The system of claim 9, wherein the plurality of nodes comprises a plurality of equipment and a plurality of points within the manufacturing plant.

11. The system of claim 9, wherein the flow rate is measured in terms of one or more of a mass flow, a molar flow and a volumetric flow using a plurality of flow meters.

12. The system of claim 9, wherein the process flow circuit comprises one or more of the plurality of nodes, flow rate between the nodes, information of the plurality of nodes, stock levels, and calculated mass balance error.

13. The system of claim 9, wherein the step of preprocessing is configured to: remove random errors in the sensor data from the plurality of sensors, remove anomalies in the sensor data from the plurality of sensors; and impute the missing data in the sensor data from the plurality of sensors.

14. The system of claim 9, wherein the knowledge extraction is configured to provide the initial guess values using physics-based models tuned with data from plurality of data sources and data-based models built using historical sensor and material balance data.

15. The system of claim 9, wherein the confidence interval value is calculated using a plurality of statistical methods based on the historical data and the set of physics-based model accuracies.

16. The system of claim 9, wherein the plurality of data sources comprises one or more of Supervisory Control and Data Acquisition (SCAD A) System, Distributed Control System (DCS), Enterprise Resource Planning (ERP) system, Laboratory Information and Management System (LIMS), Manufacturing Execution System (MES), Manufacturing Operations Management System (MOM), or Historian containing archival data.

17. A computer program product comprising a non-transitory computer readable medium having a computer readable program embodied therein, wherein the computer readable program, when executed on a computing device, causes the computing device to: collect data from a plurality of data sources as an input data, wherein the input data is representative of information at a plurality of nodes present in the manufacturing plant; extract flow rates of the plurality of materials flowing from one node of the plurality of nodes to another node of the plurality of nodes using the collected input data from the manufacturing plant; extract stock levels of the plurality of materials maintained at each of the plurality of nodes using the collected input data; create a process flow circuit using the extracted flow rates and the stock levels at each of the plurality of nodes using a graph algorithm; receive sensor data from the plurality of data sources present in the manufacturing plant; preprocess the sensor data received from the plurality of data sources; estimate initial guess values of the flow rates of the plurality of materials using one or more of: the preprocessed sensor data over a period of time, a set of physics-based models tuned with historical data obtained from the plurality of data sources, if the sensor data is not available, and a set of data-based models created using historical data and the input data, if the sensor data and the set of physics-based models are not available; estimate confidence interval values of the estimated initial guess value of the flow rates; generate a plurality of equations for material balancing based on a type of material balancing in the manufacturing plant; estimate a degree of freedom (DoF) at each of the plurality of nodes in the manufacturing plant; solve a set of equations out of the plurality of equations at each of the plurality of nodes where the DoF is zero; provide the estimated initial guess values of the flow rates of the plurality of materials which is not available to make the DoF zero at the nodes where degree of freedom is not zero; calculate a material balance error at each of the plurality of nodes using initial guess values across the process flow circuit; and estimate accurate values of the flow rates of the plurality of materials within their estimated confidence interval values by minimizing the calculated material balance error at each node using an optimization algorithm, wherein the accurate values indicate material balancing and data reconciliation for the plurality of materials in the manufacturing plant at each of the plurality of nodes.