Process optimization simulation device and method

Abstract

One embodiment of the present invention can provide a process optimization simulation device and method in which process data is used to drive a neural network-based optimization engine, thereby performing process optimization so that process yield or efficiency can be increased and operation conditions for reducing discharged pollutants can be derived.

Description

Process optimization simulation device and method

[0001] These embodiments relate to a process optimization simulation device and method for optimizing operating conditions and equipment conditions of an operating process.

[0002] Data-driven process optimization, which measures processes with sensors and performs optimization based on sensor data, is recognized for its importance in that it can automate process optimization.

[0003] Process monitoring, process anomaly detection, process optimization, and control are fields that are being studied together, and since the release of the Tennessee Eastman Process Simulation Dataset in 1993, research on real-time monitoring and optimization based on time series data has been actively conducted.

[0004] However, if an abnormality occurs in the equipment of each production line, it is not easy to check and respond in real time because the chemical process itself is complex.

[0005] In particular, process monitoring, process abnormality detection, process optimization, and control are difficult to perform even for skilled workers on site because it is difficult to know which process elements are related to which result values.

[0006] These embodiments aim to perform process optimization by driving a neural network-based optimization engine using process data.

[0007] In one aspect, the present embodiments may provide a process optimization simulation device including a process management server that is connected to one or more automated production facilities via wired or wireless communication, receives process data of the automated production facilities, and stores the process data in a database for each automated production facility; a user terminal that receives the stored process data from the process management server and outputs process status including the operating status and working status according to the type of the automated production facility in real time; and a central controller that performs process optimization by driving a neural network-based optimization engine using the process data of the process management server, displays a change in an objective function value that needs to be improved in the process on the user terminal according to a change in each process value, and controls the automated production facility with the process optimization result value.

[0008] In another aspect, the present embodiments may provide a process optimization simulation method including a process data storage step in which a process management server connected to one or more automated production facilities via wired or wireless communication receives process data of the automated production facilities and stores it in a database for each automated production facility; a process status monitoring step in which a user terminal receives the stored process data from the process management server and outputs process status including the operating status and working status according to the type of the automated production facility in real time; and a production facility control step in which a central controller performs process optimization by driving a neural network-based optimization engine using the process data of the process management server, displays a change in an objective function value that needs to be improved in the process on the user terminal according to a change in each process value, and controls the automated production facility with the process optimization result value.

[0009] According to these embodiments, process optimization can be provided by driving a neural network-based optimization engine using process data.

[0010] FIG. 1 is a schematic diagram illustrating a process optimization simulation device according to one embodiment.

[0011] Figure 2 is a block diagram illustrating a user terminal of a process optimization simulation device according to an embodiment.

[0012] Figures 3 to 5 are drawings showing example screens of a user terminal according to one embodiment.

[0013] Figure 6 is a flowchart illustrating a process optimization simulation method according to one embodiment.

[0014] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to exemplary drawings. When adding reference numerals to components in each drawing, identical components may have the same numerals as much as possible even if they are shown in different drawings. In addition, when describing the present embodiments, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the technical idea of ​​the present invention, the detailed description may be omitted. When "includes," "has," "consists of," etc. are used in this specification, other parts may be added unless "only" is used. When a component is expressed in the singular, it may include a case in which the plural is included unless specifically stated otherwise.

[0015] Additionally, terms such as first, second, A, B, (a), (b), etc. may be used to describe components of the present disclosure. These terms are only intended to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by the terms.

[0016] In a description of the positional relationship of components, when it is described that two or more components are "connected," "combined," or "connected," it should be understood that the two or more components may be directly "connected," "combined," or "connected," but that the two or more components may also be further "interposed" with another component to be "connected," "combined," or "connected." Here, the other component may be included in one or more of the two or more components that are "connected," "combined," or "connected" to each other.

[0017] In the description of the temporal flow relationship related to components, operation methods, or manufacturing methods, for example, when the temporal or flow relationship is described as “after”, “following”, “next to”, “before”, etc., it may also include cases where it is not continuous, unless “immediately” or “directly” is used.

[0018] Meanwhile, when numerical values ​​or corresponding information (e.g., levels, etc.) for components are mentioned, even without separate explicit description, the numerical values ​​or corresponding information may be interpreted as including an error range that may occur due to various factors (e.g., process factors, internal or external impact, noise, etc.).

[0019] FIG. 1 is a schematic diagram illustrating a process optimization simulation device according to one embodiment, FIG. 2 is a block diagram illustrating a user terminal of a process optimization simulation device according to one embodiment, and FIGS. 3 to 5 are diagrams illustrating example screens of a user terminal according to one embodiment.

[0020] In one aspect, the present embodiment can provide a process optimization simulation device including a process management server (200) that is connected to one or more automated production facilities (100) via wired or wireless communication, receives process data of the automated production facilities (100), and stores the received process data in a database for each automated production facility (100); a user terminal (500) that receives the stored process data from the process management server (200) and outputs process status including the operating status and working status according to the type of automated production facility (100) in real time; and a central controller (300) that performs process optimization by driving a neural network-based optimization engine using the process data of the process management server (200), displays a change in an objective function value that needs to be improved in the process according to a change in each process value on the user terminal (500), and controls the automated production facility (100) with the process optimization result value.

[0021] The process optimization simulation device is described in detail with reference to the drawings below.

[0022] The process management server (200) is connected to one or more automated production facilities (100) via wired or wireless communication, and can receive process data from the automated production facilities (100) and store it in a database for each automated production facility (100).

[0023] Such a process management server (200) can be implemented as a standard server or as a group of such standard servers.

[0024] Here, the process management server (200) may include one or more other computing devices or may be configured to communicate with one or more other computing devices.

[0025] The user terminal (500) can receive stored process data from the process management server (200) and visually output information such as the process status on the screen so that the user can monitor the process status, including the operating status and work status according to the type of automated production equipment (100) in real time.

[0026] Here, the user terminal (500) can be divided into an administrator terminal and a worker terminal depending on the user, and the user terminal (500) can be a desktop, laptop, tablet PC, smartphone, etc., and is not limited to a specific form.

[0027] The central controller (300) performs process optimization by driving a neural network-based optimization engine using process data of the process management server (200), and can display changes in objective function values ​​that need to be improved in the process on the user terminal (500) according to changes in each process value.

[0028] In addition, the central controller (300) is connected to one or more automated production facilities (100) via wired or wireless communication to control the automated production facilities (100) using process optimization results.

[0029] Here, a neural network is an engineering information processing network that mimics the human neural circuit, and can be a neural network that estimates output results for arbitrary inputs by self-learning the relationship between input data and output data that is already known.

[0030] Continuing, the user terminal (500) may include a 3D viewer module (510), a 2D viewer module (520), an analysis module (530), a measurement module (540), a setting module (550), an input module (560), and an output module (570).

[0031] At this time, each module of the user terminal (500) can output the transmitted data signal on the screen in a form that can be recognized by the operator.

[0032] The 3D viewer module (510) can output the process status including the operating status and work status according to each type of automated production equipment (100) through 3D shape visualization using information from the process management server (200).

[0033] When one of the automated production facilities (100) is selected on a 3D drawing, the 3D viewer module (510) can output the type, OP value, SP value, temperature, and pressure of the selected automated production facility (100).

[0034] The 2D viewer module (520) can output the connection relationship between automated production facilities (100) through 2D shape visualization using information from the process management server (200).

[0035] The 2D viewer module (520) can output equipment connected to the selected automated production equipment (100) when one of the automated production equipment (100) is selected on the 2D drawing.

[0036] At this time, the 3D viewer module (510) and the 2D viewer module (520) are configured to operate in conjunction with each other, so that when one of the automated production facilities (100) is selected on the 3D drawing or the 2D drawing, the type, OP value, SP value, temperature, and pressure of the selected automated production facility (100) are output through the 3D viewer module (510), and the facility connected to the selected automated production facility (100) can be output through the 2D viewer module (520).

[0037] The analysis module (530) can output an objective function value for a selected type of automated production equipment (100).

[0038] The analysis module (530) can receive and output the current objective function value for the type of automated production equipment (100) selected on a 3D drawing or 2D drawing from the process management server (200).

[0039] Here, the objective function value can output information on process yield including H2 production and energy consumption and information on pollutant emissions including COx emissions and NOx emissions by using information from the process management server (200) based on sensor data.

[0040] Additionally, the analysis module (530) may output an indication of which indicators require improvement based on current information.

[0041] When the measurement module (540) selects the optimization mode, it can output the current status variable value of the automated production facility (100) using information from the process management server (200) based on sensor data.

[0042] The current state variable values ​​include manipulable variable values, measured variable values, and equipment variable values, and each variable value can be output according to the type of automated production equipment (100).

[0043] When the optimization mode is selected, the setting mode outputs the objective function value for the selected type of automated production equipment (100) and allows selection and setting of constraints for the objective function value.

[0044] When the optimization mode is selected, the input module (560) outputs an input window for receiving hyper parameter values ​​and can transmit the input hyper parameter values ​​to the central controller (300).

[0045] At this time, the input module (560) outputs input windows for model learning rate, model max epochs, model tolerance, ext learning rate, ext max epochs, ext tolerance, and ext maximization for receiving hyperparameter values, and can transmit the input values ​​to the central controller (300).

[0046] Continuing, when the central controller (300) selects to execute optimization, it receives the hyperparameter values ​​of the input module (560) and drives a neural network-based optimization engine to perform process optimization, and can display the change in the objective function value that needs to be improved in the process on the user terminal (500) according to the change in each process value.

[0047] At this time, when the output module (570) selects to execute optimization, it can display the change in the objective function value that needs to be improved in the process as a graph according to the change in each process value, and output the optimization result value.

[0048] That is, when the output module (570) selects to execute optimization, it can display the change in the objective function value that needs to be improved in the process as a graph according to the change in each process value, and output the optimization result value including the current value and the recommended value.

[0049] In addition, the output module (570) can output information about the process in which the optimization engine performs process optimization in real time.

[0050] Figure 6 is a flowchart illustrating a process optimization simulation method according to one embodiment.

[0051] In another aspect, the present embodiments can provide a process optimization simulation method including a process data storage step in which a process management server (200) connected to one or more automated production facilities (100) via wired or wireless communication receives process data of the automated production facilities (100) and stores the received process data in a database for each automated production facility (100); a process status monitoring step in which a user terminal (500) receives the stored process data from the process management server (200) and outputs the process status including the operating status and working status according to the type of the automated production facility (100) in real time; and a production facility control step in which a central controller (300) uses the process data of the process management server (200) to drive a neural network-based optimization engine to perform process optimization, displays a change in an objective function value that needs to be improved in the process on the user terminal (500) according to a change in each process value, and controls the automated production facility (100) with the process optimization result value.

[0052] The process optimization simulation method is described in detail with reference to the drawings below.

[0053] The process data storage step is such that a process management server (200) connected to one or more automated production facilities (100) via wired or wireless communication can receive process data from the automated production facilities (100) and store it in a database for each automated production facility (100).

[0054] And, in the process status monitoring step, the user terminal (500) can receive the stored process data from the process management server (200) and output the process status including the operating status and work status according to the type of automated production equipment (100) in real time.

[0055] More specifically, in the process status monitoring step, the 3D viewer module (510) can output the process status including the operating status and work status according to each type of automated production equipment (100) through 3D shape visualization using information from the process management server (200).

[0056] In addition, in the process status monitoring stage, the 2D viewer module (520) can output the connection relationship between automated production facilities (100) through 2D shape visualization using information from the process management server (200).

[0057] At this time, the 3D viewer module (510) and the 2D viewer module (520) are configured to operate in conjunction with each other, so that when one of the automated production facilities (100) is selected on the 3D drawing or the 2D drawing, the type, OP value, SP value, temperature, and pressure of the selected automated production facility (100) are output through the 3D viewer module (510), and the facility connected to the selected automated production facility (100) can be output through the 2D viewer module (520).

[0058] In addition, in the process status monitoring step, the analysis module (530) can output an objective function value for a selected type of automated production equipment (100).

[0059] Here, when the optimization mode is selected, the connection relationship between the process status of the 3D viewer module (510) and the automated production equipment (100) of the 2D viewer module (520) is output, and at the same time, an input window for inputting the current state variable value of the measurement module (540), the objective function value of the setting module (550), and the hyperparameter value of the input module (560) can be output.

[0060] In other words, in the process status monitoring step, when the optimization mode is selected, the measurement module (540) can output the current status variable value of the automated production facility (100) using information from the process management server (200) based on sensor data.

[0061] In addition, in the process status monitoring step, when the optimization mode is selected, the setting module (550) can output the objective function value for the selected type of automated production equipment (100) and output an input window so that restriction conditions can be selected and set.

[0062] And, in the process status monitoring step, when the optimization mode is selected, the input module (560) outputs an input window for receiving hyperparameter values ​​and transmits the input hyperparameter values ​​to the central controller (300).

[0063] Here, if optimization execution is selected, the central controller (300) performs process optimization, the output module (570) outputs the optimization result value, and the central controller (300) can control the automated production facility (100) with the process optimization result value.

[0064] In more detail, the production facility control step is performed by a central controller (300) using process data of a process management server (200) to drive a neural network-based optimization engine to perform process optimization, displaying changes in objective function values ​​that need to be improved in the process on a user terminal (500) according to changes in each process value, and controlling the automated production facility (100) with the process optimization result value.

[0065] That is, in the production facility control stage, when optimization execution is selected, the central controller (300) receives the hyperparameter values ​​of the input module (560) and drives a neural network-based optimization engine to perform process optimization, and can display the change in the objective function value that needs to be improved in the process on the user terminal (500) according to the change in each process value.

[0066] Accordingly, in the process status monitoring step, when optimization execution is selected, the output module (570) can display the change in the objective function value that needs to be improved in the process as a graph according to the change in each process value, and output the optimization result value.

[0067] According to the examples thus presented, by driving a neural network-based optimization engine using process data to perform process optimization, operating conditions for increasing the yield or efficiency of the process and reducing the amount of pollutants emitted can be derived.

[0068] The above description is merely an illustrative example of the technical idea of ​​the present disclosure, and those skilled in the art to which the present disclosure pertains will appreciate that various modifications and variations can be made without departing from the essential characteristics of the technical idea of ​​the present disclosure. In addition, the present embodiments are not intended to limit the technical idea of ​​the present disclosure but rather to explain it, and therefore the scope of the technical idea of ​​the present disclosure is not limited by these embodiments. The scope of protection of the present disclosure should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included within the scope of the rights of the present disclosure.

[0069]

[0070] CROSS-REFERENCE TO RELATED APPLICATION

[0071] This patent application claims priority under 35 USC § 119(a) to Korean Patent Application No. 10-2023-0180914, filed December 13, 2023, the entire contents of which are incorporated herein by reference. Furthermore, this patent application claims priority in countries other than the United States for the same reasons, the entire contents of which are incorporated herein by reference.

Claims

1. A process management server connected to one or more automated production facilities via wired or wireless communication, receives process data from said automated production facilities, and stores the data in a database for each automated production facility; A user terminal that receives the stored process data from the above process management server and outputs the process status including the operating status and work status according to the type of the automated production facility in real time; and A central controller that performs process optimization by operating a neural network-based optimization engine using the process data of the above process management server, displays changes in the objective function value that must be improved in the process on the user terminal according to changes in each process value, and controls the automated production facility with the process optimization result value; A process optimization simulation device including:

2. In paragraph 1, The above user terminal, A 3D viewer module that outputs process status including the operating status and work status for each type of automated production equipment through 3D shape visualization using information from the above process management server; A process optimization simulation device including:

3. In paragraph 2, The above user terminal, A 2D viewer module that outputs the connection relationship between the automated production facilities through 2D shape visualization using information from the above process management server; A process optimization simulation device including:

4. In paragraph 3, The above user terminal, An analysis module that outputs an objective function value for a selected type of the above automated production facility; A process optimization simulation device including:

5. In paragraph 4, The above user terminal, When the optimization mode is selected, a measurement module that outputs the current status variable value of the automated production facility using information from the process management server based on sensor data; A process optimization simulation device including:

6. In paragraph 5, The above user terminal, When the optimization mode is selected, a setting module is provided that outputs the objective function value for the selected type of automated production equipment and allows selection and setting of constraints; A process optimization simulation device including:

7. In paragraph 6, The above user terminal, When the optimization mode is selected, an input module that outputs an input window for entering hyper parameter values ​​and transmits the entered hyper parameter values ​​to the central controller; A process optimization simulation device including:

8. In paragraph 7, The above central controller, A process optimization simulation device that, when optimization execution is selected, receives the hyperparameter values ​​of the input module, operates a neural network-based optimization engine to perform process optimization, and displays changes in the objective function values ​​that need to be improved in the process on the user terminal according to changes in each process value.

9. In paragraph 8, The above user terminal, When optimization execution is selected, an output module displays the change in the objective function value that needs to be improved in the process as a graph according to the change in each process value, and outputs the optimization result value; A process optimization simulation device including:

10. A process data storage step in which a process management server connected to one or more automated production facilities via wired or wireless communication receives process data from the automated production facilities and stores the data in a database for each automated production facility; A process status monitoring step in which the user terminal receives the stored process data from the process management server and outputs the process status including the operating status and working status according to the type of the automated production facility in real time; and A production facility control step in which a central controller performs process optimization by driving a neural network-based optimization engine using the process data of the process management server, displays changes in the objective function value that need to be improved in the process according to changes in each process value on the user terminal, and controls the automated production facility with the process optimization result value; A process optimization simulation method including:

11. In Article 10, In the above process status monitoring step, A process optimization simulation method in which a 3D viewer module uses information from the above process management server to visualize 3D shapes and output the process status including the operating status and work status for each type of the above automated production equipment.

12. In paragraph 11, In the above process status monitoring step, A process optimization simulation method in which a 2D viewer module outputs the connection relationship between the automated production facilities through 2D shape visualization using information from the above process management server.

13. In paragraph 12, In the above process status monitoring step, A process optimization simulation method in which an analysis module outputs an objective function value for a selected type of the above-mentioned automated production facility.

14. In paragraph 13, In the above process status monitoring step, A process optimization simulation method in which, when the optimization mode is selected, the measurement module outputs the current status variable values ​​of the automated production equipment using information from the process management server based on sensor data.

15. In paragraph 14, In the above process status monitoring step, A process optimization simulation method in which, when the optimization mode is selected, the setting module outputs an objective function value for the selected type of automated production equipment and allows selection and setting of constraints.

16. In paragraph 15, In the above process status monitoring step, A process optimization simulation method in which, when the optimization mode is selected, the input module outputs an input window for entering hyperparameter values ​​and transmits the entered hyperparameter values ​​to the central controller.

17. In paragraph 16, In the above production facility control stage, A process optimization simulation method in which, when optimization execution is selected, the central controller receives the hyperparameter values ​​of the input module, operates a neural network-based optimization engine to perform process optimization, and displays changes in the objective function values ​​that need to be improved in the process on the user terminal according to changes in each process value.

18. In paragraph 17, In the above process status monitoring step, A process optimization simulation method that displays the change in the objective function value that must be improved in the process as a graph according to the change in each process value when optimization execution is selected, and outputs the optimization result value.

Images