Management systems, management methods, and management programs

Abstract

To provide a management system, a management method, and a management program for making a substrate processing device autonomous.SOLUTION: A management system for managing a substrate manufacturing process includes: agent units configured to monitor a state of a substrate processing device that performs the substrate manufacturing process and detect a predetermined event; and transmission paths configured to, when a predetermined event is detected in any one of the agent units, transmit and receive information between the agent units based on the detected event. Therein the one agent unit derives an instruction to the substrate processing device on the basis of the information transmitted and received via the transmission paths so that an index value of the substrate manufacturing process is optimized.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a management system, a management method, and a management program.

Background Art

[0002] In recent years, in the field of substrate manufacturing processes, various efforts have been made towards realizing a smart factory. Specifically, a management system collects various types of data measured in the substrate manufacturing process (data in the physical space), and the development of digital twin technology for reproducing the physical space in the cyber space has been advanced.

[0003] On the other hand, towards realizing a smart factory, further, a mechanism for appropriately dealing with various events occurring in the physical space is constructed, and each substrate processing apparatus that executes the substrate manufacturing process is required to be automated.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present disclosure provides a management system, a management method, and a management program for automating a substrate processing apparatus.

Means for Solving the Problems

[0006] The management system according to one aspect of the present disclosure has, for example, the following configuration. That is, A management system for managing the substrate manufacturing process, In a substrate processing apparatus that performs the aforementioned substrate manufacturing process Therefore, the target value needs to be changed. phenomenon The occurrence of An agent that detects and A model storage unit stores a state estimation model that estimates the state of the substrate processing apparatus based on information obtained from the substrate manufacturing process, The system includes an acquisition unit that acquires the state of the substrate processing apparatus, which is estimated by inputting information obtained from the substrate manufacturing process into the state estimation model, Based on the state of the substrate processing apparatus obtained above, The aforementioned phenomenon The fact that it happened detection In that case, the agent will To optimize the overall indicator values ​​of the aforementioned substrate manufacturing process Calculate the target value, The substrate processing apparatus operates based on control values ​​derived from the calculated target values. . [Effects of the Invention]

[0007] According to this disclosure, a management system, a management method, and a management program for making a substrate processing device autonomous can be provided. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of a system configuration of a cyber-physical system that includes multiple substrate processing devices for executing a substrate manufacturing process. [Figure 2] Figure 2 shows an example of the hardware configuration of the management device. [Figure 3] Figure 3 is a first diagram showing an example of the functional configuration of a cyber-physical system according to the first embodiment. [Figure 4] Figure 4 is a second diagram showing an example of the functional configuration of the cyber-physical system according to the first embodiment. [Figure 5] Figure 5 is a third diagram showing an example of the functional configuration of the cyber-physical system according to the first embodiment. [Figure 6]FIG. 6 is a diagram showing an example of various processes executed in the cyber-physical system according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing an overview of the functional configuration of the gas-related digital twin. [Figure 8] FIG. 8 is a diagram showing the details of the functional configuration of the gas-related digital twin. [Figure 9A] FIG. 9A is a flowchart showing the flow of the gas flow control process. [Figure 9B] FIG. 9B is a flowchart showing the flow of the adjustment process. [Figure 10] FIG. 10 is a diagram showing an example of the functional configuration of the cyber-physical system according to the second embodiment. [Figure 11] FIG. 11 is a diagram showing an example of various processes executed in the cyber-physical system according to the second embodiment. [Figure 12] FIG. 12 is a diagram showing an example of the functional configuration of the cyber-physical system according to the third embodiment. [Figure 13] FIG. 13 is a diagram showing an example of various processes executed in the cyber-physical system according to the third embodiment. [Figure 14] FIG. 14 is a diagram showing an example of the functional configuration of the Fab layer digital twin. [Figure 15] FIG. 15 is a diagram showing the details of the functional configuration of the Fab layer digital twin. [Figure 16] FIG. 16 is a diagram showing an example of the conversation content transmitted and received between layers during the production management process.​​​​​​​​​​​

[0010] [First Embodiment] <System Configuration of Cyber-Physical Systems> First, we will describe the system configuration of a cyber-physical system equipped with multiple substrate processing devices that perform the substrate manufacturing process. Figure 1 is a diagram showing an example of the system configuration of a cyber-physical system equipped with multiple substrate processing devices that perform the substrate manufacturing process.

[0011] As shown in Figure 1, the cyber-physical system 100 includes server devices 110_1 to 110_3, management devices 120_1 to 120_n, substrate processing devices 130_1 to 130_n, and an administrator terminal 140.

[0012] In the cyber-physical system 100, server devices 110_1 to 110_3, management devices 120_1 to 120_n, and administrator terminal 140 are connected to each other via a network 150 so that they can communicate with each other.

[0013] Server devices 110_1 to 110_3 are devices that manage the entire cyber-physical system 100. Server devices 110_1 to 110_3 perform tasks such as manufacturing management, data management, and equipment management for the substrate manufacturing process executed by each substrate processing device 130_1 to 130_n, as well as managing the models used in cyberspace by each management device 120_1 to 120_n.

[0014] The control devices 120_1 to 120_n are each connected to the substrate processing devices 130_1 to 130_n, and together they constitute a management system.

[0015] Furthermore, the management devices 120_1 to 120_n have various models that reproduce the functions of the corresponding substrate processing devices 130_1 to 130_n, forming a cyberspace. The management devices 120_1 to 120_n collect data in the physical space acquired by the substrate processing devices 130_1 to 130_n, • Understanding the status of substrate processing devices 130_1 to 130_n. Detection of events occurring in substrate processing devices 130_1 to 130_n. • Coordination with other management devices to address detected events. Instructions to the substrate processing devices 130_1 to 130_n to address the detected event. These measures are taken to appropriately address various phenomena that occur in the physical space.

[0016] In this way, the management devices 120_1 to 120_n appropriately deal with various events occurring in the substrate processing devices 130_1 to 130_n in cyberspace and derive instructions for the substrate processing devices 130_1 to 130_n. As a result, the management devices 120_1 to 120_n can automate the substrate processing devices.

[0017] The substrate processing devices 130_1 to 130_n are devices that execute the substrate manufacturing process and constitute the physical space. The substrate processing devices 130_1 to 130_n include, for example, devices that perform film deposition, devices that perform lithography, devices that perform etching, and devices that perform cleaning. The substrate processing devices 130_1 to 130_n transmit data from the physical space acquired during the execution of the substrate manufacturing process to the management devices 120_1 to 120_n.

[0018] The administrator terminal 140 is a terminal operated by an administrator who manages the cyber-physical system 100. The administrator terminal 140 is used, for example, when generating various models possessed by management devices 120_1 to 120_n.

[0019] In Figure 1, the cyber-physical system 100 is shown as a case where the management devices 120_1 to 120_n and the substrate processing devices 130_1 to 130_n are configured as separate units. However, the management devices 120_1 to 120_n and the substrate processing devices 130_1 to 130_n may be configured as a single unit.

[0020] <Hardware configuration of the management device> Next, we will describe the hardware configuration of the management devices 120_1 to 120_n. Since the management devices 120_1 to 120_n all have the same hardware configuration, we will describe them together using Figure 2. Figure 2 is a diagram showing an example of the hardware configuration of a management device.

[0021] As shown in Figure 2, the management devices 120_1 to 120_n each include a processor 201, memory 202, auxiliary storage device 203, I / F (Interface) device 204, communication device 205, and drive device 206. The hardware components of the management devices 120_1 to 120_n are interconnected via a bus 207.

[0022] The processor 201 has various computing devices such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processor 201 reads various programs (for example, management programs described later) into memory 202 and executes them.

[0023] Memory 202 has main memory devices such as ROM (Read Only Memory) and RAM (Random Access Memory). The processor 201 and memory 202 form a so-called computer, and the computer realizes various functions by having the processor 201 execute various programs read from memory 202.

[0024] The auxiliary storage device 203 stores various programs and various data used when those programs are executed by the processor 201.

[0025] The I / F device 204 is a connection device that connects the substrate processing devices 130_1 to 130_n, which are examples of external devices, to the management devices 120_1 to 120_n.

[0026] The communication device 205 is a communication device for communicating with other devices (in this embodiment, server devices 110_1 to 110_3, other management devices, administrator terminal 140, etc.) via the network 150.

[0027] The drive device 206 is a device for setting the recording medium 210. The recording medium 210 here includes media that record information optically, electrically, or magnetically, such as CD-ROMs, flexible disks, and magneto-optical disks. The recording medium 210 may also include semiconductor memory that records information electrically, such as ROMs and flash memory.

[0028] The various programs to be installed on the auxiliary storage device 203 are installed, for example, when the distributed recording medium 210 is set in the drive device 206 and the various programs recorded on the recording medium 210 are read by the drive device 206. Alternatively, the various programs to be installed on the auxiliary storage device 203 may be installed by downloading them from the network via the communication device 205.

[0029] <Functional Configuration of Cyber-Physical Systems (1)> Next, the functional configuration of the cyber-physical system 100 will be described. Figure 3 is a first diagram showing an example of the functional configuration of the cyber-physical system according to the first embodiment.

[0030] As shown in Figure 3, the cyberspace 310 formed by the management devices 120_1 to 120_n includes multiple digital twins, including various models that reproduce the functions of the substrate processing devices 130_1 to 130_n.

[0031] The example in Figure 3 shows that multiple digital twins include a process-wide digital twin 311, an APC / AEC-related digital twin 312, a process recipe-related digital twin 313, and a maintenance-related digital twin 314. The example in Figure 3 also shows that multiple digital twins include a transport-related digital twin 315, a gas-related digital twin 316, a temperature-related digital twin 317, a particle-related digital twin 318, and an operation-related digital twin 319.

[0032] Furthermore, as shown in Figure 3, each digital twin included in cyberspace 310 is connected to some other digital twins via transmission paths (see dotted lines in cyberspace 310) and transmits and receives information with these other digital twins. For example, the process-wide digital twin 311 is connected to the APC / AEC-related digital twin 312, the maintenance-related digital twin 314, and the transport-related digital twin 315 via transmission paths, and transmits and receives information with each of them.

[0033] Furthermore, it is assumed that the direction of information transmission and reception between the connected digital twin and the connected digital twin is predetermined for the source digital twin connected via the transmission path.

[0034] Furthermore, as shown in Figure 3, data from the physical space 330 is input to a specific digital twin contained in cyberspace 310. This allows the specific digital twin contained in cyberspace 310 to perform tasks such as understanding the state, detecting events, coordinating with other digital twins, and issuing instructions to the substrate processing device (hereinafter referred to as "digital twin processing").

[0035] The example in Figure 3 shows that when gas flow rate information, temperature information, pressure information, etc. 321 are input to the gas-related digital twin 316 as data in the physical space, the gas-related digital twin 316 performs digital twin processing. In the example in Figure 3, when the gas-related digital twin 316 cooperates with other digital twins, it sends and receives information with the process recipe-related digital twin 313 and the temperature-related digital twin 317.

[0036] Furthermore, the example in Figure 3 shows that when data such as gas flow rate information, temperature information, and pressure information 321 are input to the temperature-related digital twin 317 as data in the physical space, the temperature-related digital twin 317 performs digital twin processing. In the example in Figure 3, when the temperature-related digital twin 317 cooperates with other digital twins, it sends and receives information with the process recipe-related digital twin 313 and the gas-related digital twin 316.

[0037] Furthermore, the example in Figure 3 shows that when particle information 323 is input to the particle-related digital twin 318 as data in physical space, the particle-related digital twin 318 performs digital twin processing. In the example in Figure 3, when the particle-related digital twin 318 cooperates with other digital twins, it sends and receives information with the maintenance-related digital twin 314.

[0038] Furthermore, the example in Figure 3 shows that when maintenance information 324 and equipment configuration information 325 are input to the process recipe-related digital twin 313 as data in the physical space, the process recipe-related digital twin 313 performs digital twin processing. In the example in Figure 3, when the process recipe-related digital twin 313 cooperates with other digital twins, it sends and receives information with the gas-related digital twin 316, the temperature-related digital twin 317, and the APC / AEC-related digital twin 312.

[0039] Furthermore, the example in Figure 3 shows that when maintenance information 324 is input to the maintenance-related digital twin 314 as data in the physical space, the maintenance-related digital twin 314 performs digital twin processing. In the example in Figure 3, when the maintenance-related digital twin 314 cooperates with other digital twins, it sends and receives information with the particle-related digital twin 318 and the operation-related digital twin 319. In addition, when the maintenance-related digital twin 314 cooperates with other digital twins, it sends and receives information with the APC / AEC-related digital twin 312 and the overall process-related digital twin 311.

[0040] Furthermore, the example in Figure 3 shows that when operation information is input to the operation-related digital twin 319 as data in the physical space, the operation-related digital twin 319 performs digital twin processing. In the example in Figure 3, when the operation-related digital twin 319 cooperates with other digital twins, it sends and receives information with the maintenance-related digital twin 314 and the transport-related digital twin 315.

[0041] Furthermore, the example in Figure 3 shows that when the transport-related digital twin 315 receives the equipment configuration information 325 as data in the physical space, the transport-related digital twin 315 performs digital twin processing. In the example in Figure 3, when the transport-related digital twin 315 cooperates with other digital twins, it sends and receives information with the overall process-related digital twin 311 and the operation-related digital twin 319.

[0042] Furthermore, the example in Figure 3 shows that when the APC / AEC-related digital twin 312 receives the equipment configuration information 325 as data in the physical space, the APC / AEC-related digital twin 312 performs digital twin processing. In the example in Figure 3, when the APC / AEC-related digital twin 312 cooperates with other digital twins, it sends and receives information with the overall process-related digital twin 311, the process recipe-related digital twin 313, and the maintenance-related digital twin 314.

[0043] On the other hand, the physical space 330, composed of the substrate processing devices 130_1 to 130_n, includes elements for providing data to be input to the cyber space 310, or elements to which instructions are transmitted from the cyber space 310.

[0044] The example in Figure 3 shows that the elements for providing data input into cyberspace 310 include a sensor 331, an external measuring instrument 333, a maintenance information storage unit 334, a device configuration information storage unit 335, and an operation information storage unit 336. The example in Figure 3 also shows that the elements to which instructions are transmitted from cyberspace 310 include an actuator 332.

[0045] Sensor 331 measures gas flow rate information, temperature information, pressure information, etc. 321. The gas flow rate information, temperature information, pressure information, etc. 321 measured by sensor 331 are input into cyberspace 310 as data in physical space.

[0046] The external measuring device 333 measures particle information 323. The particle information 323 measured by the external measuring device 333 is input into cyberspace 310 as data in physical space. The device for measuring particle information 323 is not limited to an external measuring device, but may also be an internal measuring device installed within the substrate processing devices 130_1 to 130_n. For example, it may be a device that measures the internal state of the substrate processing devices 130_1 to 130_n through a window provided in the wall of the substrate processing devices 130_1 to 130_n. Furthermore, the device for measuring particle information 323 may be a device that observes the state on the substrate to be processed, or a device that acquires the state of the processing space in which the substrate to be processed is processed.

[0047] The maintenance information storage unit 334 stores maintenance information 324 related to the maintenance (repair, replacement) of the main components of the circuit board processing device performed in physical space 330. The maintenance information 324 stored in the maintenance information storage unit 334 is input into cyber space 310 as data in physical space.

[0048] The device configuration information storage unit 335 stores device configuration information 325 indicating the device configuration of each substrate processing device 130_1 to 130_n in the physical space 330. The device configuration information 325 stored in the device configuration information storage unit 335 is input into the cyber space 310 as data in the physical space.

[0049] The operation information storage unit 336 stores operation information 326 indicating various operations performed on the substrate processing device in physical space 330. The operation information 326 stored in the operation information storage unit 336 is input into cyber space 310 as data in physical space.

[0050] The actuator 332 operates based on instructions from cyberspace 310. The example in Figure 3 shows that the actuator 332 operates based on control information 322 (an example of a control value) calculated by the gas-related digital twin 316 and the temperature-related digital twin 317.

[0051] <Functional Configuration of Cyber-Physical Systems (2)> Next, we will describe another functional configuration of the cyber-physical system 100, specifically one in which the transmission path connection configuration differs from that shown in Figure 3. Figure 4 is a second diagram showing an example of the functional configuration of the cyber-physical system according to the first embodiment.

[0052] The difference from Figure 3 is that in Figure 4, among the multiple digital twins, the digital twins other than the process-wide digital twin 311 are each connected to the process-wide digital twin 311 via a transmission path.

[0053] For example, the APC / AEC-related digital twin 312 is connected to the overall process-related digital twin 311 via a transmission path, and transmits and receives information between them. Similarly, the process recipe-related digital twin 313 is connected to the overall process-related digital twin 311 via a transmission path, and transmits and receives information between them. The same applies to the maintenance-related digital twins 314 to the operation-related digital twins 319.

[0054] <Functional Configuration of Cyber-Physical Systems (3)> Next, we will describe another functional configuration of the cyber-physical system 100, specifically one in which the transmission path connection configuration differs from that shown in Figures 3 and 4. Figure 5 is a third diagram showing an example of the functional configuration of the cyber-physical system according to the first embodiment.

[0055] The difference between Figure 5 and Figures 3 and 4 is that, in Figure 5, all of the multiple digital twins are interconnected via a transmission path.

[0056] For example, the gas-related digital twin 316 is connected via transmission paths to the overall process-related digital twin 311 to the transport-related digital twin 315, and to the temperature-related digital twin 317 to the operation-related digital twin 319. In other words, the gas-related digital twin 316 sends and receives information with digital twins other than the gas-related digital twin 316.

[0057] Furthermore, the process recipe-related digital twin 313 is connected via a transmission path to the overall process-related digital twins 311 to 312 and the APC / AEC-related digital twins 314 to 319, as well as the maintenance-related digital twins 314 to 319. In other words, the process recipe-related digital twin 313 sends and receives information with other digital twins. The same applies to the other digital twins.

[0058] <Various processes performed in cyber-physical systems> Next, various processes performed in the cyber-physical system 100 will be described. Figure 6 is a diagram showing an example of various processes performed in the cyber-physical system according to the first embodiment. In Figure 6, an example of various processes performed when the connection configuration of the transmission path is the same as the connection configuration shown in Figure 3 is shown.

[0059] In Figure 6, the processes indicated by the thick black border represent an example of a process primarily executed by the corresponding digital twin. As shown in Figure 6, for example, the process-wide related digital twin 311 executes the index value management process.

[0060] The indicator value management process is a process that manages indicator values ​​for the entire substrate manufacturing process. These indicator values ​​include sub-indicators such as the overall yield of the substrate manufacturing process, the processing volume per unit time for the entire substrate manufacturing process, and the energy consumption of the entire substrate manufacturing process.

[0061] In the process-wide digital twin 311, for example, information is sent and received with other digital twins via a transmission path to acquire their respective sub-indicator values, and the overall index value of the substrate manufacturing process is calculated based on the acquired sub-indicator values. Furthermore, the process-wide digital twin 311 sends various instructions to other digital twins to optimize the calculated index value.

[0062] Furthermore, the index value management process performed by the process-wide digital twin 311 is related to various processes primarily performed by other digital twins. In other words, the various processes primarily performed by other digital twins are executed in such a way that the index values ​​for the entire substrate manufacturing process are optimized.

[0063] Recipe optimization is the process of optimizing the process recipe. Recipe optimization includes optimizing the substrate processing quality under predetermined equipment conditions (such as component wear status and deposit status on the chamber wall), as well as optimizing the substrate processing time or substrate processing volume.

[0064] In the process recipe-related digital twin 313, for example, the current state of the equipment is grasped by sending and receiving information with other digital twins via a transmission path, and the optimal process recipe for the grasped state is derived from learning results based on past data.

[0065] Maintenance optimization processing is a process that optimizes the key components of a circuit board processing apparatus that should be replaced or repaired, as well as the timing of such replacement or repair.

[0066] The maintenance-related digital twin 314, for example, transmits and receives information with other digital twins via a transmission path to understand the wear status of key components and predict the lifespan of key components based on future equipment operating conditions. Furthermore, the maintenance-related digital twin 314 derives the optimal timing for replacement or repair of each key component based on the predicted lifespan.

[0067] Transport optimization processing is a process that optimizes the transport of substrates. Transport optimization processing includes maximizing the processing amount per unit time by the substrate processing equipment.

[0068] In the transport-related digital twin 315, for example, information is sent and received with other digital twins via a transmission path to determine the amount of processing that the substrate processing device should handle, and the optimal transport method for processing that amount is derived from learning results based on past data.

[0069] Gas flow rate control processing is a process that derives control information so that the flow rate of the gas used in processing the substrate reaches a predetermined target value.

[0070] In the gas-related digital twin 316, for example, if an event occurs in the substrate processing device, information is sent and received with other digital twins via the transmission path to calculate a target value that can be processed, and control information to realize the calculated target value is derived.

[0071] The various processes shown in Figure 6 are just examples of processes executed in the cyber-physical system 100, and each of the digital twins described above may execute processes other than those described above. Furthermore, the main digital twin is not limited to those shown in Figure 6; other digital twins whose processes are not illustrated in Figure 6 may take the lead and execute any process.

[0072] Below, we will explain in detail the gas flow rate control process performed by the gas-related digital twin 316, among the various processes shown in Figure 6.

[0073] <Overview of the Functional Configuration of Gas-Related Digital Twins> First, we will describe the overview of the functional configuration of the gas-related digital twin that performs gas flow rate control processing. Figure 7 is a diagram showing the overview of the functional configuration of the gas-related digital twin. In Figure 7, the cyberspace 310 and physical space 330 are shown as extracted digital twins and elements related to the gas-related digital twin 316 from the cyberspace 310 and physical space 330 shown in Figure 3. In addition, Figure 7 shows extracted data and instructions related to the gas-related digital twin 316 from the data input to the cyberspace 310 and instructions to the substrate processing device in the physical space 330.

[0074] The gas-related digital twin 316 includes an agent unit 710, a state estimation unit 720, and a model prediction control unit 730 as functional blocks for executing gas flow rate control processing. The models of each unit are stored in a model storage unit 740 and are read from the model storage unit 740 when gas flow rate control processing is executed.

[0075] The agent unit 710 manages the state estimation unit 720 and the model prediction control unit 730. Specifically, the agent unit 710 grasps the state of the substrate processing apparatus estimated by the state estimation unit 720 in real time and monitors whether any events have occurred that require a change in the target value in the gas flow rate control process.

[0076] Furthermore, the agent unit 710 changes the target value when it determines that an event has occurred that necessitates a change in the target value in the gas flow rate control process. At this time, the agent unit 710 determines whether or not it is necessary to send and receive information with the agent units of other digital twins (i.e., between agents), and if it determines that it is necessary, it sends and receives information with the other digital twins and then changes the target value. In addition, the agent unit 710 notifies the model prediction control unit 730 of the changed target value.

[0077] The state estimation unit 720 acquires gas flow rate information, temperature information, pressure information, etc. 321 measured by the sensor 331 and estimates the state of the gas flow rate control system, which is the control target of the gas flow rate control process of the substrate processing apparatus. The state estimation unit 720 also notifies the agent unit 710 of the estimated state of the gas flow rate control system.

[0078] The model prediction control unit 730 is an example of a control unit and derives control information 322 that realizes the modified target value notified by the agent unit 710. The model prediction control unit 730 also transmits the derived control information 322 as an instruction to the substrate processing device (specifically, the actuator 332 in physical space 330).

[0079] <Details of the functional configuration of gas-related digital twins> Next, we will describe the details of the functional configuration of the gas-related digital twin 316 that performs gas flow rate control processing. Figure 8 is a diagram showing the details of the functional configuration of the gas-related digital twin.

[0080] As shown in Figure 8, the state estimation unit 720 is an example of an acquisition unit and has a state estimation model 821. The state estimation model 821 takes gas flow rate information, temperature information, pressure information, etc. 321 as input and estimates state information indicating the state of, for example, the gas flow rate control system of the substrate processing apparatus 130_1.

[0081] The agent unit 710 includes an event detection model 811, a decision unit 812, a transmission / reception unit 813, and an analysis model 814.

[0082] The event detection model 811 is an example of a detection unit, and takes the state information estimated by the state estimation model 821 as input to estimate whether an event has occurred that requires a change in the target value in the gas flow rate control process, and the type of event.

[0083] The decision unit 812 obtains the type of event from the event detection model 811 when it estimates that an event requiring a change in the target value has occurred in the event detection model 811. The decision unit 812 also calculates the target value according to the obtained type of event, notifies the model prediction control unit 730, and determines whether control is possible, thereby determining whether it is necessary to send and receive information with other digital twins.

[0084] If the determination unit 812 determines that control is possible, it determines that sending and receiving information with other digital twins is unnecessary. On the other hand, if the determination unit 812 determines that control is not possible, it determines that sending and receiving information with other digital twins is necessary.

[0085] If the decision unit 812 determines that it is necessary to send or receive information with another digital twin, it notifies the transmission / reception unit 813 of the conversation content, including the target value calculated according to the type of event.

[0086] The transmitting / receiving unit 813 transmits and receives conversation content between the gas-related digital twin 316 and other digital twins (in the case of Figure 7, the process recipe-related digital twin 313 and the temperature-related digital twin 317).

[0087] For example, the transmitting / receiving unit 813 transmits the conversation content notified by the decision unit 812 to another digital twin. The transmitting / receiving unit 813 also receives the conversation content (response) transmitted from the other digital twin and inputs it into the analysis model 814. The transmitting / receiving unit 813 also retransmits the conversation content output from the analysis model 814 to the other digital twin. The conversation content transmitted and received between the transmitting / receiving unit 813 and the other digital twin is stored in the information storage unit 815.

[0088] The analysis model 814 takes the conversation content (response) notified from the transmitting / receiving unit 813 as input and outputs the conversation content to be sent to the other digital twin. In the case of gas flow rate control processing, the other digital twin sends acceptable target values ​​or constraints in response to the target value sent to the other digital twin. Therefore, the analysis model 814 takes the acceptable target values ​​or constraints sent from the other digital twin as input and calculates a new target value.

[0089] The analysis model 814 calculates appropriate target values ​​by repeatedly sending and receiving conversation content with other digital twins and notifies the model prediction control unit 730 of them.

[0090] Furthermore, the conversation content (response) transmitted by the transmitter / receiver 813 from other digital twins is assumed to reflect various instructions sent by the process-wide related digital twin 311 to optimize the indicator values ​​for the entire substrate manufacturing process. In other words, the analysis model 814 calculates target values ​​to optimize the indicator values ​​for the entire substrate manufacturing process.

[0091] The model prediction control unit 730 includes a prediction model 831, an objective function unit 832, an optimization unit 833, and a verification unit 834.

[0092] The prediction model 831 models the behavior of the gas flow control system in physical space 330 (behavior of sensor 331, actuator 332, and controller (not shown)), and predicts the gas flow rate using control information as input.

[0093] The objective function unit 832 calculates the error between the gas flow rate predicted by the prediction model 831 and the target value, and notifies the optimization unit 833 of this error.

[0094] The optimization unit 833 searches for control information that will reduce the error notified by the objective function unit 832. The optimization unit 833 also inputs the searched control information into the prediction model 831 and obtains the error between the gas flow rate predicted by the prediction model 831 and the target value. The optimization unit 833 repeats these processes to minimize the error and derive the optimal control information 322.

[0095] Furthermore, the optimization unit 833 transmits the optimal control information 322 as an instruction to the substrate processing device (specifically, the actuator 332 in the physical space 330).

[0096] The verification unit 834 obtains optimal control information 322 from the optimization unit 833. In addition, the verification unit 834 obtains gas flow rate information provided from the physical space 330 in response to the optimal control information 322 being transmitted as an instruction to the substrate processing device (specifically, the actuator 332 in the physical space 330).

[0097] Furthermore, the verification unit 834 determines the appropriateness of the control information 322 based on the optimal control information 322 and the acquired gas flow rate information, verifies the prediction accuracy of the prediction model 831, and adjusts the model parameters of the prediction model 831 as necessary. In this way, the verification unit 834 can make the prediction model 831 match the behavior of the gas flow rate control system in the physical space 330.

[0098] <Flowchart of gas flow control process> Next, we will explain the flow of gas flow control processing using the gas-related digital twin 316. Figure 9A is a flowchart showing the flow of gas flow control processing.

[0099] In step S901, the model prediction control unit 730 acquires a target value and derives control information according to the acquired target value. The model prediction control unit 730 also transmits the derived control information as an instruction to the substrate processing device in physical space 330.

[0100] In step S902, the state estimation unit 720 acquires data such as gas flow rate information, temperature information, and pressure information 321 from the physical space 330 as data in the physical space.

[0101] In step S903, the state estimation unit 720 estimates state information indicating the state of the gas flow control system of the substrate processing apparatus based on the acquired data in physical space.

[0102] In step S904, the agent unit 710 monitors whether an event has occurred that requires a change in the target value, based on the state information estimated by the state estimation unit 720.

[0103] In step S905, the agent unit 710 determines whether an event has occurred that requires a change in the target value in the gas flow rate control process, and what type of event it is. If it is determined in step S905 that no event has occurred (i.e., the answer is NO in step S905), the process proceeds to step S912.

[0104] On the other hand, if it is determined in step S905 that an event has occurred (if the answer in step S905 is YES), the process proceeds to step S906.

[0105] In step S906, the agent unit 710 calculates a target value corresponding to the type of event that occurred.

[0106] In step S907, the model prediction control unit 730 performs an optimization process to derive control information that minimizes the error with the calculated target value.

[0107] In step S908, the agent unit 710 determines whether control is possible based on the error with the target value when the optimization process was performed by the model prediction control unit 730 in step S907.

[0108] Specifically, if the error between the output of the prediction model 831 and the target value when the control information is derived in step S907 is greater than or equal to a threshold, and it is not possible to derive control information that minimizes the error, the agent unit 710 determines that control is not possible. In other words, if the target value cannot be approached even after performing the optimization process, the agent unit 710 determines that control is not possible. On the other hand, if the error between the output of the prediction model 831 and the target value when the control information is derived in step S907 is less than a threshold, and it is possible to derive control information that minimizes the error, the agent unit 710 determines that control is possible. In other words, if the target value can be approached by performing the optimization process, the agent unit 710 determines that control is possible.

[0109] In step S909, the agent unit 710 determines whether it is necessary to send and receive information with other digital twins based on the result of the control feasibility determination.

[0110] Specifically, if it is determined in step S908 that control is possible, the agent unit 710 determines that it can approach the target value on its own. Therefore, in step S909, the agent unit 710 determines that it is not necessary to send or receive information with other digital twins (determining NO in step S909), and proceeds to step S910.

[0111] In step S910, the model prediction control unit 730 transmits the derived new control information as an instruction to the substrate processing device in physical space 330.

[0112] On the other hand, if it is determined in step S908 that control is impossible, the agent unit 710 determines that it cannot approach the target value on its own. Therefore, in step S909, the agent unit 710 determines that it is necessary to send and receive information with other digital twins (determining YES in step S909), and proceeds to step S911.

[0113] In step S911, the agent unit 710 performs adjustment processing, sends and receives information with other digital twins, and then derives new control information. The details of the adjustment processing are shown in Figure 9B. Figure 9B is a flowchart showing the flow of the adjustment processing.

[0114] In step S921, the agent unit 710 transmits the conversation content, including the target value calculated in step S906 of Figure 9A, to the other digital twin, and receives the conversation content (response) transmitted from the other digital twin.

[0115] In step S922, the agent unit 710 calculates a new target value for the gas flow rate control process by sending and receiving conversation content with other digital twins.

[0116] In step S923, the model prediction control unit 730 performs an optimization process to derive control information that minimizes the error with the newly calculated target value.

[0117] In step S924, the model prediction control unit 730 transmits the derived new control information as an instruction to the substrate processing device in physical space 330. Then, the process returns to step S912 in Figure 9A.

[0118] In step S912, the model prediction control unit 730 acquires data from the physical space 330 necessary for verifying the prediction model.

[0119] In step S913, the model prediction control unit 730 verifies the prediction accuracy of the prediction model 831 based on the control information transmitted to the physical space 330 and the data acquired from the physical space 330.

[0120] In step S914, the model prediction control unit 730 adjusts the model parameters of the prediction model 831 based on the prediction accuracy of the verified prediction model 831.

[0121] In step S915, the agent unit 710 determines whether or not to terminate the gas flow rate control process. If it determines to continue the gas flow rate control process (i.e., the answer in step S915 is NO), it returns to step S902.

[0122] On the other hand, if it is determined in step S915 to terminate the gas flow rate control process (i.e., if the answer in step S918 is YES), the gas flow rate control process is terminated.

[0123] <Summary> As is clear from the above explanation, in the cyber-physical system 100, the management system that forms cyberspace and manages the substrate manufacturing process in physical space is It has multiple digital twins. Each of the multiple digital twins also has multiple agent units that monitor the status of each substrate processing device and detect when a predetermined event occurs. A transmission path connecting multiple digital twins, which, when a predetermined event is detected in the agent unit of any of the digital twins, transmits and receives information between the agent units of other digital twins based on the detected event. When a predetermined event is detected, the agent unit derives instructions for the substrate processing device based on the information transmitted and received via the transmission path, so that the indicator values ​​of the substrate manufacturing process are optimized.

[0124] Thus, in the management system according to the first embodiment, an agent unit and a transmission path are placed in cyberspace, and multiple digital twins are linked to appropriately deal with events occurring in physical space and derive instructions for the substrate processing device. As a result, according to the management system according to the first embodiment, each substrate processing device can be made autonomous.

[0125] In other words, according to the first embodiment, a management system that enables the automation of a substrate processing device can be provided.

[0126] [Second Embodiment] In the first embodiment described above, a case was described in which one cyberspace 310 is formed in the cyber-physical system. However, the number of cyberspaces formed in the cyber-physical system is not limited to one, and multiple cyberspaces may be formed. Furthermore, the digital twins (specifically agents) contained in each of the multiple cyberspaces that have been formed may be connected via a transmission path, and information may be sent and received between the digital twins in different cyberspaces. The second embodiment will now be described, focusing on the differences from the first embodiment.

[0127] <Functional Configuration of Cyber-Physical Systems> First, the functional configuration of the cyber-physical system according to the second embodiment will be described. Figure 10 is a diagram showing an example of the functional configuration of the cyber-physical system according to the second embodiment.

[0128] As shown in Figure 10, the cyber-physical system 1000 has multiple cyberspaces (cyberspace 310 and cyberspace 1010). Note that, for space limitations, Figure 10 omits the physical spaces corresponding to each of the multiple cyberspaces. For example, cyberspace 310 is assumed to be the cyberspace corresponding to physical space 330 in Figure 3. Furthermore, cyberspace 1010 is assumed to be the cyberspace corresponding to a physical space with a similar configuration to physical space 330 in Figure 3, located in a different factory (Fab: Fabrication) than physical space 330 in Figure 3.

[0129] Therefore, the cyberspace 1010 shown in Figure 10 includes a digital twin similar to that of cyberspace 310 (see process-related digital twins 1011 to operation-related digital twins 1019).

[0130] Furthermore, the transmission paths connecting each digital twin in cyberspace 1010, as shown in Figure 10, are assumed to have the same connection configuration as the transmission paths connecting each digital twin in cyberspace 310.

[0131] However, in the case of Figure 10, the process-related digital twin 311 in cyberspace 310 and the process-related digital twin 1011 in cyberspace 1010 are connected via a transmission path (see bold dotted line). Also, in the case of Figure 10, the gas-related digital twin 316 in cyberspace 310 and the gas-related digital twin 1016 in cyberspace 1010 are connected via a transmission path (see bold dotted line).

[0132] In this way, by connecting digital twins located in different cyberspaces via transmission paths and configuring the system to send and receive information with digital twins in other cyberspaces, it becomes possible to optimize multiple physical spaces as a whole.

[0133] <Various processes performed in cyber-physical systems> Next, various processes performed in the cyber-physical system 1000 according to the second embodiment will be described. Figure 11 is a diagram showing an example of various processes performed in the cyber-physical system according to the second embodiment. Note that in the example in Figure 11, only processes performed in digital twins (process-wide digital twin, gas-related digital twin) connected via a transmission path in different cyberspaces are shown.

[0134] As shown in Figure 11, in cyberspace 310, the process-wide digital twin 311 performs indicator value management processing. Similarly, in cyberspace 1010, the process-wide digital twin 1011 performs indicator value management processing.

[0135] The index value management processes performed in the process-wide related digital twins 311 and 1011, respectively, have already been described in the first embodiment described above, and therefore will not be described here.

[0136] However, the process-wide digital twin 311 sends various instructions to other digital twins in cyberspace 310 in order to optimize the indicator values ​​of the entire substrate manufacturing process, while sending and receiving information with the process-wide digital twin 1011.

[0137] Similarly, the process-wide digital twin 1011 sends various instructions to other digital twins in cyberspace 1010 to optimize the indicator values ​​of the entire substrate manufacturing process, while sending and receiving information with the process-wide digital twin 311.

[0138] As shown in Figure 11, the process-wide digital twin 311 and the process-wide digital twin 1011 may be connected to the Fab-wide digital twin 1101, which oversees them, via a transmission path.

[0139] The Fab-wide digital twin 1101 oversees the process-wide digital twins contained within each of the multiple cyberspaces. Specifically, the Fab-wide digital twin 1101 sends and receives information with the process-wide digital twins 311 and 1011, and sends various instructions to each digital twin to optimize the metrics of the entire Fab (i.e., the entire multiple physical spaces).

[0140] The digital twin 1101 related to the entire Fab may be contained in either cyberspace 310 or 1010, or it may be contained in cyberspace formed by other devices (e.g., server devices 110_1 to 110_3).

[0141] Similarly, as shown in Figure 11, in cyberspace 310, the gas-related digital twin 316 performs gas flow rate control processing. Similarly, in cyberspace 1010, the gas-related digital twin 1016 performs gas flow rate control processing.

[0142] The gas flow rate control processes performed in the gas-related digital twins 316 and 1016, respectively, have already been described in the first embodiment described above, and therefore will not be described here.

[0143] However, the gas-related digital twin 316 calculates processable target values ​​while sending and receiving information with the gas-related digital twin 1016, in addition to the process recipe-related digital twin 313 and the temperature-related digital twin 317.

[0144] Similarly, the gas-related digital twin 1016 calculates processable target values ​​while sending and receiving information with the gas-related digital twin 316, in addition to the process recipe-related digital twin 1013 and the temperature-related digital twin 1017.

[0145] As shown in Figure 11, the gas-related digital twin 316 and the gas-related digital twin 1016 may be connected to the overall gas-related digital twin 1102, which oversees them, via a transmission path.

[0146] The overall gas-related digital twin 1102 oversees the gas-related digital twins contained in each of the multiple cyberspaces. Specifically, the overall gas-related digital twin 1102 sends and receives information with the gas-related digital twins 316 and 1016, and sends various instructions to each gas-related digital twin to optimize the target values ​​for the entire Fab (i.e., the entire multiple physical space).

[0147] The overall gas-related digital twin 1102 may be contained in either cyberspace 310 or 1010, or it may be contained in cyberspace formed by other devices (e.g., server devices 110_1 to 110_3).

[0148] <Summary> As is clear from the above explanation, in the cyber-physical system 1000, the management system that forms multiple cyberspaces and manages the substrate manufacturing processes of multiple physical spaces is Each cyberspace has multiple digital twins. Furthermore, each of these digital twins has multiple agent units that monitor the status of each substrate processing device and detect when a predetermined event occurs. • It has a transmission path that connects digital twins located in different cyberspaces. Specifically, when a predetermined event is detected in the agent unit of a digital twin located in one cyberspace, it has a transmission path that sends and receives information between the agent unit of the digital twin located in the other cyberspace based on the detected event. When a predetermined event is detected, the agent unit derives instructions for the substrate processing device based on the information transmitted and received via the transmission path, so that the indicator values ​​of the substrate manufacturing process are optimized. In this case, a digital twin that oversees the digital twins contained in each of the multiple cyberspaces may be further deployed, and instructions may be derived to optimize the entire set of multiple physical spaces.

[0149] Thus, the management system according to the second embodiment has a configuration that links digital twins in different cyberspaces, in addition to the configuration of the management system according to the first embodiment. As a result, according to the management system according to the second embodiment, each substrate processing device can be made autonomous so that the entire set of physical spaces is optimized.

[0150] [Third Embodiment] In the first and second embodiments described above, a digital twin corresponding to each function of the substrate processing device was formed in cyberspace. In other words, the case in which a digital twin is formed in cyberspace on a functional basis was described.

[0151] In contrast, in the third embodiment, a digital twin is formed using the operating units of the hardware that realize the function in the substrate processing apparatus. The third embodiment will now be described, focusing on the differences from the first and second embodiments described above.

[0152] <Functional Configuration of Cyber-Physical Systems> First, the functional configuration of the cyber-physical system according to the third embodiment will be described. Figure 12 is a diagram showing an example of the functional configuration of the cyber-physical system according to the third embodiment.

[0153] As shown in Figure 12, in the cyber-physical system 1200, the cyberspace 1210 formed by the management devices 120_1 to 120_n includes multiple digital twins that are associated with the operating units of hardware that realize the functions of the substrate processing device.

[0154] The example in Figure 12 shows that it includes a Fab layer digital twin 1211 formed at the Fab unit level, and equipment layer digital twins 1212_1 and 1212_2 formed at the equipment unit level of the substrate processing device.

[0155] Furthermore, the example in Figure 12 shows that it includes an MC layer digital twin 1213_1 formed on an MC unit, an EC layer digital twin 1213_2 formed on an EC unit, and an external measuring instrument layer digital twin 1213_3 formed on an external measuring instrument unit.

[0156] Furthermore, the example in Figure 12 shows that it includes sensor layer digital twins 1214_1 and 1214_4 corresponding to the sensor unit. In addition, the example in Figure 12 shows that it includes transport selection layer digital twin 1214_2 formed for the transport selection unit and CJ / PJ management layer digital twin 1214_3 formed for the CJ / PJ management unit.

[0157] Furthermore, as shown in Figure 12, each digital twin included in cyberspace 1210 has a hierarchical structure corresponding to the hierarchical relationship of each operating unit. For example, in Figure 12, in cyberspace 1210, the Fab layer digital twin 1211 corresponding to the Fab is placed at the highest level of the hierarchy.

[0158] Furthermore, corresponding to the substrate processing devices 130_1 and 130_2 located within the Fab, • Device Layer Digital Twin 1212_1, • Device Layer Digital Twin 1212_2, These are each placed in the second layer in cyberspace 1210.

[0159] Furthermore, corresponding to the MC layer 1240, EC layer 1250, and external measuring instrument layer 1260 located within the substrate processing apparatus 130_1, MC Layer Digital Twin 1213_1, EC Layer Digital Twin 1213_2, • External measuring instrument Layer Digital Twin 1213_3, These are each placed in the third layer in cyberspace 1210.

[0160] Furthermore, the sensor layer digital twin 1214_1, which corresponds to the sensor layer 1241 located within the MC layer 1240, is positioned at the fourth level in cyberspace 1210. Similarly, the transport selection layer digital twins 1214_2 and 1214_3, which correspond to the transport selection layer 1251 and CJ / PJ management layer 1252 located within the EC layer 1250, are each positioned at the fourth level in cyberspace 1210. Finally, the sensor layer digital twin 1214_4, which corresponds to the sensor layer 1261 located within the external measuring instrument layer 1260, is positioned at the fourth level in cyberspace 1210.

[0161] Furthermore, as shown in Figure 12, the lowest level in cyberspace 1210 (the fourth level in the example in Figure 12) receives information about the operating units located at the lowest level in physical space.

[0162] Specifically, sensor layer information 1221 is input to the sensor layer digital twin 1214_1 as information about the sensor layer 1241 located within the MC layer 1240 of the substrate processing device 130_1.

[0163] Furthermore, transport selection layer information 1222 is input to the transport selection layer digital twin 1214_2 as information regarding the transport selection layer 1251 located within the EC layer 1250 of the substrate processing device 130_1. Also, CJ / PJ management layer information 1223 is input to the CJ / PJ management layer digital twin 1214_3 as information regarding the CJ / PJ management layer 1252 located within the EC layer 1250 of the substrate processing device 130_1.

[0164] Furthermore, sensor layer information 1224 is input to the sensor layer digital twin 1214_4 as information regarding the sensor layer 1261 located within the external measuring instrument layer 1260 of the substrate processing device 130_1.

[0165] Furthermore, as shown in Figure 12, the digital twins located in all layers of cyberspace 1210 except the lowest layer (in the example in Figure 12, the highest layer, the second layer, and the third layer) are each inputted with operational information for their corresponding operational units.

[0166] For example, Fab operation information 1231 is input to the Fab layer digital twin 1211, equipment operation information 1232 to the equipment layer digital twin 1212_1, and equipment operation information 1233 to the equipment layer digital twin 1212_2. Additionally, MC operation information 1234 is input to the MC layer digital twin 1213_1, EC operation information 1235 to the EC layer digital twin 1213_2, and measuring instrument operation information 1236 to the external measuring instrument layer digital twin 1213_3.

[0167] Furthermore, as shown in Figure 12, in cyberspace 1210, digital twins located at each layer are connected to digital twins located at the layer above and digital twins located at the layer below via transmission paths.

[0168] For example, the device layer digital twin 1212_1, located at the second tier, is connected via a transmission path to the Fab layer digital twin 1211, which is located at the tier above. Similarly, the device layer digital twin 1212_1 is connected via a transmission path to the MC layer digital twin 1213_1 and the external measuring instrument layer digital twin 1213_3, which are located at the tier below. Further connections are similar and will not be explained here.

[0169] <Various processes performed in cyber-physical systems> Next, we will describe the various processes performed in the cyber-physical system 1200. Figure 13 is a diagram showing an example of the various processes performed in the cyber-physical system according to the third embodiment.

[0170] Similar to the embodiments described above, in Figure 13, the processes indicated by the thick black border represent an example of a process primarily executed by the corresponding digital twin. As shown in Figure 13, for example, the Fab layer digital twin 1211 executes production management processing.

[0171] Production management processing involves managing the total processing volume that the entire Fab should handle, as well as the processing volume allocated to each substrate processing device.

[0172] In the Fab Layer Digital Twin 1211, for example, it calculates the processing load that the entire Fab should next process based on the current operational information (Fab operation information 1231) of the corresponding operating unit (the entire Fab), and determines the processing load to be allocated to each substrate processing device 130_1 and 130_2. The Fab Layer Digital Twin 1211 also transmits the conversation content, including the determined processing load, to the device Layer Digital Twins 1212_1 and 1212_2, located one layer lower, via the transmission path.

[0173] In addition, in response to sending a conversation containing the determined processing volume, a conversation (response) indicating that the determined processing volume cannot be processed may be sent from the device layer digital twin 1212_1 or 1212_2 located one level lower.

[0174] In this case, the Fab layer digital twin 1211 changes the processing load assigned to each substrate processing device 130_1 and 130_2. The Fab layer digital twin 1211 also sends the conversation content, including the changed processing load, to the device layer digital twins 1212_1 and 1212_2, which are located one level lower.

[0175] In this way, the Fab Layer Digital Twin 1211 calculates the processing load that the entire Fab should next handle based on the current operational information of the entire Fab, and determines the processing load to be allocated to each substrate processing device. Furthermore, the Fab Layer Digital Twin 1211 changes the allocated processing load by sending and receiving information with the device layer digital twin.

[0176] Note that the production management process shown in FIG. 13 is an example of a process executed in the cyber-physical system 1200, and the Fab layer digital twin 1211 may execute processes other than the production management process. Also, the main digital twin is not limited to the Fab layer digital twin 1211, and other digital twins not illustrated in FIG. 13 as examples of processes may be the main digital twin and execute any process.

[0177] However, hereinafter, the details of the production management process executed by the Fab layer digital twin 1211 will be described.

[0178] <Overview of the Functional Configuration of the Fab Layer Digital Twin> First, an overview of the functional configuration of the Fab layer digital twin that executes the production management process will be described. FIG. 14 is a diagram showing an overview of the functional configuration of the Fab layer digital twin.

[0179] As shown in FIG. 14, the Fab layer digital twin 1211 has an agent unit 1410 and a state estimation unit 1420 as functional blocks for executing the production management process. Note that the models possessed by each unit are stored in the model storage unit 1430 and are read from the model storage unit 1430 when the production management process is executed.

[0180] The agent unit 1410 manages the state estimation unit 1420. Specifically, the agent unit 1410 grasps in real time the state information indicating the state of the corresponding operation unit (the entire Fab) estimated by the state estimation unit 1420, and calculates the processing amount that the entire Fab should process next. Also, the agent unit 1410 determines the processing amount to be assigned to each substrate processing apparatus.

[0181] In addition, the agent unit 1410 transmits the conversation content including the determined processing volume to the device layer digital twins 1212_1 and 1212_2 located one level below. Furthermore, the agent unit 1410 repeats the transmission and reception of the conversation content with the device layer digital twins 1212_1 and 1212_2 located one level below to derive an optimal allocation of the processing volume and transmits it to the device layer digital twins 1212_1 and 1212_2.

[0182] The state estimation unit 1420 acquires the current operation information (Fab operation information 1231) of the corresponding operation unit (the entire Fab), and uses the acquired Fab operation information 1231 as an input to estimate the state information indicating the state of the corresponding operation unit (the entire Fab). In addition, the state estimation unit 1420 transmits the estimated state information to the agent unit 1410.

[0183] Although FIG. 14 shows the functional configuration of the Fab layer digital twin, when the production management process is executed, it is assumed that other digital twins also execute the same process under the same functional configuration.

[0184] <Details of the functional configuration of the Fab layer digital twin 1211> Next, the details of the functional configuration of the Fab layer digital twin 1211 that executes the production management process will be described. FIG. 15 is a diagram showing the details of the functional configuration of the Fab layer digital twin.

[0185] As shown in FIG. 15, the state estimation unit 1420 has a state estimation model 1521. The state estimation model 1521 uses the Fab operation information 1231 as an input to estimate the state information indicating the state of the entire Fab. The state information estimated by the state estimation model 1521 includes any information related to the state of the entire Fab.

[0186] The agent unit 1410 has an event detection model 1511, a determination unit 1512, a transmission / reception unit 1513, and an analysis model 1514.

[0187] The event detection model 1511 takes the state information estimated by the state estimation model 1521 as input and estimates whether or not an event requiring change has occurred and what type of event it is, in order to determine the processing volume that the entire Fab should process next.

[0188] If the event detection model 1511 determines that no event has occurred, the decision unit 1512 calculates the amount of processing that the entire Fab should next process based on the current operational information, and also calculates the amount of processing to be allocated to each substrate processing device. The decision unit 1512 also notifies the transmission / reception unit 1513 of the conversation content, including the amount of processing to be allocated to each substrate processing device.

[0189] At this time, the determination unit 1512 calculates the processing volume that the entire Fab should process next and the processing volume to be allocated to each substrate processing device, in order to optimize the indicator values ​​for the entire substrate manufacturing process (in this case, the entire Fab). The indicator values ​​referred to here are the same as in the first embodiment described above, and include sub-indicator values ​​such as the yield of the entire substrate manufacturing process, the processing volume per unit time of the entire substrate manufacturing process, and the energy consumption of the entire substrate manufacturing process.

[0190] Furthermore, if the event detection model 1511 estimates that an event has occurred, the decision unit 1512 obtains the type of event from the event detection model 1511. Based on the obtained type of event, the decision unit 1512 changes the processing load that the entire Fab should process next, and also changes the processing load to be allocated to each substrate processing device. The decision unit 1512 also notifies the transmission / reception unit 1513 of the conversation content, including the processing load to be allocated to each substrate processing device.

[0191] The transmitting / receiving unit 1513 transmits the conversation content notified by the decision unit 1512 to the device layer digital twin located one level lower. The transmitting / receiving unit 1513 also receives the conversation content (response) transmitted from the device layer digital twin located one level lower and inputs it to the analysis model 1514. The transmitting / receiving unit 1513 also transmits the conversation content output from the analysis model 1514 to the device layer digital twin located one level lower.

[0192] Furthermore, when the transmitting / receiving unit 1513 transmits and receives conversation content with a device layer digital twin located one layer lower, the transmission and reception are performed in accordance with the inter-layer rules stored in the inter-layer rule storage unit 1515.

[0193] Furthermore, the conversation content transmitted and received between the transmitting / receiving unit 1513 and the device layer digital twin located one level lower is stored in the information storage unit 1516.

[0194] The analysis model 1514 takes the conversation content (response) notified from the transmitting / receiving unit 1513 as input and outputs the conversation content to be sent to the equipment layer digital twin located one level lower. In the case of production management processing, information regarding whether the processing volume allocation sent to the equipment layer digital twin located one level lower is executed is sent from one of the equipment layer digital twins located one level lower. Therefore, the analysis model 1514 takes the information regarding whether the processing volume can be executed, sent from the equipment layer digital twin located one level lower as input and calculates a new processing volume allocation.

[0195] In the analysis model 1514, the optimal allocation of processing power is derived by repeatedly sending and receiving conversation content with the device layer digital twin located one level below, and this information is then transmitted to the device layer digital twin located one level below.

[0196] In the example shown in Figure 15, the Fab layer digital twin 1211 located at the highest level was described, and therefore the transmitter / receiver 1513 transmitted the conversation content only to the digital twin located one level lower. However, in the case of digital twins located at other levels, the conversation content will be transmitted to both the digital twin located one level lower and the digital twin located one level higher. However, the decision of which conversation content is transmitted to which digital twin located at which level will be based on the inter-level rules stored in the inter-level rule storage unit 1515.

[0197] <Specific examples of conversation content exchanged between hierarchical levels in production management processes> Next, we will explain a specific example of the conversation content transmitted and received between layers in the production management process using the Fab Layer Digital Twin 1211. Figure 16 shows an example of the conversation content transmitted and received between layers during the production management process.

[0198] In step S1601, the Fab layer digital twin 1211 determines the presence or absence of an event based on the status information estimated from the Fab operation information 1231, and then calculates the processing amount that the entire Fab should process next. The Fab layer digital twin 1211 also calculates the processing amount to be allocated to the substrate processing devices 130_1 and 130_2. Of these, the Fab layer digital twin 1211 sends the message "By XX / YY, device 1 should process α units of A" to the device layer digital twin 1212_1, which includes the processing amount allocated to the substrate processing device 130_1.

[0199] In step S1602, the Fab layer digital twin 1211 receives the message "Completed" as a conversation response from the device layer digital twin 1212_1 in response to having transmitted the conversation content.

[0200] Next, in step S1611, the Fab layer digital twin 1211 sends the following message to the device layer digital twin 1212_2, which includes the processing amount assigned to the substrate processing device 130_2: "By XX / YY, device 2 should process β units of B."

[0201] In step S1612, the device layer digital twin 1212_2 outputs conversation content to be sent to the MC layer digital twin 1213_1 based on the conversation content sent from the Fab layer digital twin 1211. Specifically, it outputs "Process with condition b" as conversation content and sends it to the MC layer digital twin 1213_1. At this time, it is assumed that a problem (an event requiring a change in the processing amount that the substrate processing device 130_2 should process next) has occurred within the MC layer 1240.

[0202] In step S1613, the MC layer digital twin 1213_1 detects that an event has occurred that requires a change in the amount of processing to be done next, and sends the message "A problem has occurred" to the device layer digital twin 1212_2.

[0203] In step S1614, the device layer digital twin 1212_2 derives the processing amount that the substrate processing device 130_2 can perform based on the conversation content (response) transmitted from the MC layer digital twin 1213_1. As a result, the device layer digital twin 1212_2 transmits to the Fab layer digital twin 1211 the conversation content, which includes the derived processing amount, "Device 2 can only process (β-n) units of B."

[0204] In step S1615, the device layer digital twin 1212_2 derives the optimal solution to the problem based on the conversation content (response) transmitted from the MC layer digital twin 1213_1. The device layer digital twin 1212_2 also transmits to the MC layer digital twin 1213_1 the conversation content, which includes the derived solution, "Please restore using stock part Z."

[0205] Meanwhile, in step S1616, the Fab layer digital twin 1211 changes the processing load to be allocated to the substrate processing devices 130_1 and 130_2 based on the conversation content (response) transmitted from the device layer digital twin 1212_2. Of these, the Fab layer digital twin 1211 transmits to the device layer digital twin 1212_2 the conversation content, which includes the processing load of the substrate processing device 130_2 after the allocation has been changed, "By XX / YY, device 2 should process (β-n) units of B."

[0206] In step S1617, the device layer digital twin 1212_2 outputs conversation content to be sent to the MC layer digital twin 1213_1 based on the conversation content sent from the Fab layer digital twin 1211. Specifically, it outputs "Process with condition b'" as conversation content and sends it to the MC layer digital twin 1213_1.

[0207] In step S1618, the Fab layer digital twin 1211 receives the message "Completed" as a conversation message (response) from the device layer digital twin 1212_2, in response to having sent the conversation message including the processing amount after the assignment change.

[0208] In step S1621, the Fab layer digital twin 1211 sends the following message to the device layer digital twin 1212_1, which includes the amount of processing after the assignment has been changed: "Device 1, process an additional γ units of A."

[0209] In step S1622, the Fab layer digital twin 1211 receives the message "Completed" as a conversation message (response) from the device layer digital twin 1212_1, in response to having sent the conversation message including the processing amount after the assignment change.

[0210] <Production Management Process Flow> Next, we will explain the flow of the production management process. Figure 17 is a flowchart of the production management process. In addition, Figure 17 explains the operation of the digital twin located at a predetermined level other than the top level during the production management process.

[0211] In step S1701, a digital twin located at a predetermined level receives conversation content, including the allocated processing amount, from a digital twin located at the level above it.

[0212] In step S1702, the digital twin located at a predetermined hierarchical level acquires the current operational information of the corresponding operating unit.

[0213] In step S1703, the digital twin located at a predetermined hierarchical level estimates state information indicating the state of the corresponding operating unit based on the acquired operational information.

[0214] In step S1704, the digital twin located at a predetermined hierarchical level monitors, based on the estimated state information, whether or not an event has occurred that requires a change in the amount of processing that the corresponding operating unit should next process.

[0215] In step S1705, the digital twin located at a predetermined level determines whether an event requiring a change in processing volume has occurred, and what type of event it is. If it is determined in step S1705 that no event has occurred (i.e., the answer is NO in step S1705), the process proceeds to step S1708.

[0216] On the other hand, if it is determined in step S1705 that an event has occurred (if the answer in step S1705 is YES), the process proceeds to step S1706.

[0217] In step S1706, the digital twin located at a predetermined level transmits the conversation content, including the event that occurred and the amount of processing that can be performed, to the digital twin located at the level one level higher.

[0218] In step S1707, the digital twin located at a predetermined hierarchical level receives the processing volume after the allocation has been changed from the digital twin located at the hierarchical level one level higher.

[0219] In step S1708, the digital twin located at a predetermined hierarchical level derives the amount of processing to be allocated to the digital twin located at the next lower hierarchical level, based on the amount of processing received.

[0220] In step S1709, the digital twin located at a predetermined level transmits the conversation content, including the allocated processing volume, to the digital twin located at the level below it.

[0221] In step S1710, the digital twin located at a predetermined level determines whether or not it has received conversation content (response) containing an event from the digital twin located at the level below it. If it is determined in step S1710 that it has received conversation content (response) containing an event (if the answer in step S1710 is YES), the process returns to step S1706.

[0222] On the other hand, if it is determined in step S1710 that no conversation content (response) including the event has been received (if the answer in step S1710 is NO, proceed to step S1711).

[0223] In step S1711, the digital twin located at a predetermined level determines whether or not to terminate the production management process. If it is determined in step S1711 that the production management process should not be terminated (i.e., the answer in step S1711 is NO), the process returns to step S1702.

[0224] On the other hand, if it is determined in step S1711 to terminate the production management process (i.e., if the answer in step S1711 is YES), the production management process is terminated.

[0225] <Summary> As is clear from the above explanation, in the cyber-physical system 1200, the management system that forms cyberspace and manages the substrate manufacturing process in physical space is • It has multiple digital twins. Furthermore, the multiple digital twins correspond to the hardware operating units that realize the functions of each board processing unit, and have a hierarchical structure corresponding to the hierarchical relationship of the operating units. The system has a transmission path connecting multiple digital twins so that information based on events detected in any of the digital twins (e.g., the allocation of changed processing volume) is sent and received between digital twins located at different hierarchical levels.

[0226] In this way, by forming a digital twin corresponding to the operating unit and sending and receiving information via a transmission path according to the hierarchical structure, the management system according to the third embodiment can enjoy the same effects as the first and second embodiments described above. In addition, the management system according to the third embodiment makes it possible to efficiently execute specific processes such as production management processes.

[0227] [Other embodiments] In the first to fourth embodiments described above, the management devices 120_1 to 120_n were configured as separate management devices, but the management devices 120_1 to 120_n may be configured as a single device. In this case, the n management devices may be configured to operate virtually (i.e., as virtual machines) on the single device.

[0228] Furthermore, in the first to fourth embodiments described above, the management devices 120_1 to 120_n corresponding to the substrate processing devices 130_1 to 130_n were described as each executing a management program independently. However, a management device (e.g., management device 120_1) corresponding to a single substrate processing device (e.g., substrate processing device 130_1) may be composed of, for example, multiple computers. Then, by installing the management program on each of the multiple computers, the management program may be executed in a distributed computing manner.

[0229] Furthermore, in the first to fourth embodiments described above, as an example of a method for installing the management program to the auxiliary storage device 203 of the management devices 120_1 to 120_n, a method of downloading and installing via a network was mentioned. In this case, the download source was not specifically mentioned, but when installing by this method, the download source may be, for example, a server device that stores the management program in an accessible manner. Alternatively, the server device may be a cloud-based device that accepts access from each of the management devices 120_1 to 120_n via the network and downloads the management program on the condition of payment. In other words, the server device may be a cloud-based device that provides a management program service.

[0230] Furthermore, in the first to fourth embodiments described above, cyberspace was described as being formed in a management system including a plurality of management devices 120_1 to 120_n, but cyberspace may be formed in a location other than the management system. For example, cyberspace may be formed in server devices 110_1 to 110_3.

[0231] Furthermore, although the details of the models were not mentioned in the first to fourth embodiments described above, the models used in the first to fourth embodiments may be, for example, machine learning models including deep learning, for example, ·RNN (Recurrent Neural Network), ·LSTM(Long Short-Term Memory), ·CNN(Convolutional Neural Network), ·R-CNN(Region based Convolutional Neural Network), YOLO (You Only Look Once) ·SSD (Single Shot MultiBox Detector), ·GAN (Generative Adversarial Network), ·SVM(Support Vector Machine), Decision tree, Random Forest You may use any of the following:

[0232] Alternatively, models using genetic algorithms such as GA (Genetic Algorism) or GP (Genetic Programming), or models trained through reinforcement learning, may also be used.

[0233] Alternatively, the models used in the first to fourth embodiments described above may be models obtained by general statistical analysis other than deep learning, such as PCR (Principal Component Regression), PLS (Partial Least Square), LASSO, ridge regression, linear polynomial, autoregressive models, moving average models, autoregressive moving average models, and ARX models. Alternatively, the above models may be used in combination.

[0234] Furthermore, when training a machine learning model, for example, the data used as "input" and the data to be "estimated" in the explanation of Figure 8 may be acquired in advance, and training data consisting of these data as "input data" and "ground truth data" may be used.

[0235] Furthermore, although three connection configurations were shown in the first embodiment described above, the connection configurations for digital twins are not limited to these. The connection configuration may also be changed depending on the processing performed primarily by each digital twin.

[0236] It should be noted that the present invention is not limited to the configurations shown in the above embodiments, including combinations with other elements. These aspects can be modified without departing from the spirit of the present invention and can be appropriately determined according to their application.

[0237] This application claims priority based on Japanese Patent Application No. 2020-217779, filed on 25 December 2020, which is incorporated herein by reference to the entire contents of the said Japanese Patent Application. [Explanation of Symbols]

[0238] 100: Cyber-physical systems 120_1~120_n: Management device 130_1~130_n: Substrate processing equipment 310: Cyberspace 330: Physical space 710: Agent Department 720: State Estimation Unit 730: Model prediction control unit 811: Event detection model 812: Judgment Department 813: Transmitter / Receiver 814: Analysis Model 821: State Estimation Model 831: Predictive Model 832: Objective function section 833: Optimization Department 834: Verification Department 1000: Cyber-physical systems 1010: Cyberspace 1200: Cyber-physical systems 1210: Cyberspace 1410: Agent Department 1420: State Estimation Unit 1511: Event detection model 1512:Judgment Department 1513: Transmitter / Receiver 1514: Analytical Model 1521: State Estimation Model

Claims

1. A management system for managing the substrate manufacturing process, In a substrate processing apparatus that performs the aforementioned substrate manufacturing process, an agent is provided to detect when an event occurs that necessitates a change in the target value, A model storage unit stores a state estimation model that estimates the state of the substrate processing apparatus based on information obtained from the substrate manufacturing process, The system includes an acquisition unit that acquires the state of the substrate processing apparatus, which is estimated by inputting information obtained from the substrate manufacturing process into the state estimation model, Based on the acquired state of the substrate processing apparatus, if the agent detects that the event has occurred, it calculates a target value for optimizing the indicator values ​​of the entire substrate manufacturing process. The substrate processing apparatus operates based on a control value derived from the calculated target value. Management system.

2. When the event is detected by any of the agents, there is a transmission path for sending and receiving information with other agents based on the detected event. The agent calculates a target value for optimizing the indicator value of the substrate manufacturing process based on information transmitted and received between it and other agents via the transmission path. The management system according to claim 1.

3. The model storage unit further stores a predictive model that reproduces the control system of the substrate processing apparatus. The aforementioned management system further, A determination unit that determines whether or not it is necessary to send and receive information with other agents based on the type of event detected, If it is determined that it is necessary to send and receive information with other agents, the transmitting unit transmits information based on the detected event to other agents connected via the transmission path. A receiving unit that receives a response from the other agent to the transmission of information based on the detected event, An information storage unit that stores information transmitted and received with the aforementioned other agent, An optimization unit optimizes the control value so that the prediction model outputs a target value calculated based on the response from the other agent, A control unit that operates the substrate processing apparatus by controlling the control system using the optimized control values, The management system according to claim 2, having the following features.

4. The unit that makes the determination said, The management system according to claim 3, which determines whether or not it is necessary to send and receive information with other agents by determining whether or not control is possible based on the error between the output of the prediction model and the target value corresponding to the type of event detected, when the optimization unit optimizes the control value so that the prediction model outputs a target value corresponding to the type of event detected, and the type of event detected.

5. The acquisition unit is, The management system according to claim 3, wherein the state of the substrate processing apparatus is newly acquired by inputting information newly acquired from the substrate manufacturing process into the state estimation model in accordance with the control performed using the optimized control value, thereby acquiring the state of the substrate processing apparatus.

6. The agent further, The system further includes a verification unit that verifies the prediction accuracy of the prediction model based on the newly acquired information. The verification unit, The management system according to claim 5, which adjusts the model parameters of the prediction model based on the prediction accuracy.

7. The management system according to claim 2, wherein each of the multiple agents is connected to all other agents or to some of the other agents via the transmission path.

8. The management system according to claim 2, wherein the transmission and reception direction for each of the multiple agents when sending and receiving information with other agents connected by the transmission path is predetermined for each connection destination.

9. Multiple agents are arranged in a hierarchical structure based on the operating units of the substrate manufacturing process, corresponding to each level. The management system according to claim 3, wherein the transmission path connects a plurality of agents so that information based on the detected event is transmitted and received between agents associated with different layers.

10. The management system according to claim 9, wherein the plurality of agents further have a rule storage unit that stores rules between the layers for sending and receiving information based on the detected event between agents associated with different layers, for each associated layer.

11. The aforementioned transmitting unit The management system according to claim 10, which transmits information calculated based on information received from an agent associated with another hierarchical level to an agent associated with another hierarchical level in accordance with the rules between the hierarchical levels.

12. The management system according to claim 3, wherein the transmission path connects agents located in different cyberspaces so that information is sent and received between corresponding agents among a plurality of agents located in different cyberspaces.

13. A management method for managing the substrate manufacturing process, A detection step in which an agent detects that an event has occurred in a substrate processing apparatus that performs the substrate manufacturing process that requires a change in the target value, The model storage unit includes a storage step of storing a state estimation model that estimates the state of the substrate processing apparatus based on information obtained from the substrate manufacturing process, The acquisition unit includes an acquisition step of acquiring the state of the substrate processing apparatus, which is estimated by inputting the information acquired from the substrate manufacturing process into the state estimation model, Based on the acquired state of the substrate processing apparatus, if the agent detects that the event has occurred, it calculates a target value for optimizing the indicator values ​​of the entire substrate manufacturing process. The substrate processing apparatus operates based on a control value derived from the calculated target value. Management method.

14. The computer for the management system that controls the circuit board manufacturing process, In a substrate processing apparatus that performs the aforementioned substrate manufacturing process, an agent is provided to detect when an event occurs that necessitates a change in the target value, A model storage unit stores a state estimation model that estimates the state of the substrate processing apparatus based on information obtained from the substrate manufacturing process, The information obtained from the substrate manufacturing process is input into the state estimation model to function as an acquisition unit that acquires the estimated state of the substrate processing apparatus. Based on the acquired state of the substrate processing apparatus, if the agent detects that the event has occurred, it calculates a target value for optimizing the indicator values ​​of the entire substrate manufacturing process. The substrate processing apparatus operates based on a control value derived from the calculated target value. Management program.

Images