Information processing apparatus, detection method, substrate processing system, and method of manufacturing an article

Abstract

The present invention relates to an information processing apparatus, a detection method, a substrate processing system, and a method for manufacturing an article. An information processing apparatus detects an abnormality in a control system including a plurality of sensors and a plurality of control units. The information processing apparatus includes: a calculation unit that uses a model representing a relationship between output values of two sensors among the plurality of sensors, a relationship between control data of two control units among the plurality of control units, or a relationship between an output value of one sensor among the plurality of sensors and control data of one control unit among the plurality of control units, and calculates an abnormality degree for each of at least two groups into which the plurality of sensors or the plurality of control units are divided, the abnormality degree indicating the degree of abnormality of the output value of the sensor or the control data of the control unit; and a determination unit that determines an abnormality of the plurality of sensors or the plurality of control units for each group based on the abnormality degree calculated by the calculation unit.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, a detection method, a non-transitory computer-readable storage medium, a substrate processing system, and a method for manufacturing an article. Background Art

[0002] Regarding a substrate processing apparatus that processes a substrate in order to manufacture an article such as a semiconductor device, MEMS, or a flat panel display, the demand for improving productivity is constantly increasing. Therefore, it is necessary to suppress a situation where production is interrupted due to a sudden abnormality of the substrate processing apparatus. Therefore, it is required to detect an abnormality of the substrate processing apparatus in advance and eliminate the cause of the abnormality.

[0003] In Patent Document 1, a failure omen monitoring method is disclosed, which monitors the failure omens of a plurality of devices arranged in a factory. In Patent Document 1, in order to monitor the failure omens of a plurality of devices, a model representing the relationship of the output values of respective sensors is constructed based on the output values of sensors that measure the behavior of each device. Then, based on the difference between the output value of the sensor and the prediction data calculated using the model, a change in the invariant (invariant relationship) between the output values of the respective sensors is detected, and the failure omens of the respective devices are detected.

[0004] When detecting an abnormality of a control system including a plurality of sensors and a plurality of control units, it is possible to detect an abnormality in the output value of a sensor and the control data of a control unit related to a control unit in which no abnormality has occurred. For example, in the case of a temperature control system in which a refrigerant circulates in a pipe to adjust the temperature, there are a plurality of control units that control a plurality of temperature control units and a plurality of sensors that measure the temperature of the refrigerant, etc., and among them, the plurality of temperature control units adjust the temperature of the refrigerant such as a cooler, a heater, a heat exchanger, etc. In such a temperature control system, there is a possibility that even if an abnormality occurs in a part of the temperature control units, due to the temperature change of the refrigerant circulating in the pipe, an abnormality is detected in the output value of a sensor and the control data of a control unit related to a control unit in which no abnormality has occurred.

[0005] Prior Art Documents

[0006] Patent Documents

[0007] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2017-21702 Summary of the Invention

[0008] An object of the present invention is to provide a technique advantageous for detecting an abnormality of a control system including a plurality of sensors and a plurality of control units.

[0009] One aspect of the present invention is an information processing apparatus that detects anomalies in a control system including a plurality of sensors and a plurality of control units. In the information processing apparatus, there are: a calculation unit that uses a model representing the relationship between the output values of two sensors among the plurality of sensors, the relationship between the control data of two control units among the plurality of control units, or the relationship between the output value of one sensor among the plurality of sensors and the control data of one control unit among the plurality of control units, and calculates, for at least two groups into which the plurality of sensors or the plurality of control units are divided, an anomaly degree for each group, the anomaly degree indicating the degree of anomaly of the output value of the sensor or the control data of the control unit; and a determination unit that determines, based on the anomaly degree calculated by the calculation unit, the anomaly of the plurality of sensors or the plurality of control units for each group.

[0010] Other features of the present invention will become clearer from the description of the exemplary embodiments with reference to the accompanying drawings. [BRIEF DESCRIPTION OF THE DRAWINGS]

[0011] Figure 1 FIG. is a diagram showing the structure of a substrate processing system.

[0012] Figure 2 FIG. is a diagram showing the structure of a management apparatus.

[0013] Figure 3 FIG. is a diagram showing the structure of an exposure apparatus and a host computer.

[0014] Figure 4 FIG. is a diagram showing the structure of a temperature control system incorporated into an exposure apparatus.

[0015] Figure 5 FIG. is a flowchart showing a method for detecting anomalies in the temperature control system of the first embodiment.

[0016] Figure 6 FIG. is a diagram showing an example of grouping in Embodiment 1.

[0017] Figure 7 FIG. is a diagram showing an example of grouping in Embodiment 2.

[0018] Figure 8 FIG. is a diagram showing an example of grouping in Embodiment 3.

[0019] Figure 9 FIG. is a diagram showing an example of grouping in Embodiment 4.

[0020] Figure 10 FIG. is a flowchart showing a method for detecting anomalies in the temperature control system of the second embodiment. [DETAILED DESCRIPTION OF THE INVENTION]

[0021] Hereinafter, with reference to the accompanying drawings, preferred embodiments of the present invention will be described in detail. In each figure, the same reference numerals are given to the same components, and redundant descriptions are omitted.

[0022] <First Embodiment>

[0023] Figure 1 is a diagram showing the structure of a substrate processing system. The substrate processing system 1 (article manufacturing system) may include: a plurality of substrate processing apparatuses 10 that respectively process substrates; and a host computer 11 that controls the operations of the plurality of substrate processing apparatuses 10. The plurality of substrate processing apparatuses 10 may include, for example, a lithography apparatus (exposure apparatus, imprint apparatus, charged particle beam drawing apparatus, etc.). In addition, the plurality of substrate processing apparatuses 10 may include any of a coating apparatus, a developing apparatus, a film forming apparatus (CVD apparatus, etc.), a processing apparatus (laser processing apparatus, etc.), and an inspection apparatus (overlay inspection apparatus, etc.). Here, the exposure apparatus exposes the photoresist supplied onto the substrate by means of a reticle (master, mask), thereby forming a latent image corresponding to the pattern of the reticle in the photoresist. In addition, the imprint apparatus cures the imprint material while bringing a mold (reticle) into contact with the imprint material supplied onto the substrate, thereby forming a pattern on the substrate. In addition, the charged particle beam drawing apparatus draws a pattern in the photoresist supplied onto the substrate using a charged particle beam, thereby forming a latent image in the photoresist. In addition, as a pretreatment for the lithography process, the coating apparatus performs a coating process of a resist material (adhesive material) on the substrate. In addition, as a post-treatment for the lithography process, the developing apparatus performs a developing process. In addition, the film forming apparatus is an apparatus for forming a film such as an insulating film on the substrate. In addition, the processing apparatus performs processing of the pattern formed on the substrate, cutting of the substrate, opening of holes, etc. In addition, the inspection apparatus performs inspection of the positional accuracy, line width, etc. of the pattern formed on the substrate.

[0024] Figure 2 is a diagram showing the structure of the management apparatus 12. The management apparatus 12 can be implemented by a computer (information processing apparatus) communicably connected to each of the substrate processing apparatuses 10. In Figure 2In (a) thereof, the CPU 201 (processing unit) is a central processing unit (CPU) that executes an OS (Operating System) and various application programs. In addition, the CPU 201 is not limited to a central processing unit (CPU), and may also be a processor or circuit such as a microprocessing unit (MPU), a graphics processing unit (GPU), or an application specific integrated circuit (ASIC). In addition, the CPU 201 may also be any combination of these processors or circuits. The ROM 202 is a memory that stores fixed data among the programs executed by the CPU 201 and the parameters for arithmetic operations. The RAM 203 is a memory that provides a working area for the CPU 201 and a temporary storage area for data. The ROM 202 and the RAM 203 are connected to the CPU 201 via a bus 208. 205 is an input device (input unit) including a mouse, a keyboard, etc., and 206 is a display device (display unit) such as a CRT or a liquid crystal display. In addition, the input device 205 and the display device 206 may also be an integrated device such as a touch screen. In addition, the input device 205 and the display device 206 may also be configured as devices separate from the computer. 204 is a storage device such as a hard disk device, a CD, a DVD, or a memory card, and stores various programs, various data, etc. The input device 205, the display device 206, and the storage device 204 are respectively connected to the bus 208 via an interface (not shown). In addition, a communication device 207 for connecting to a network and performing communication is also connected to the bus 208. The communication device 207 is used, for example, for connecting to a LAN and performing data communication based on a communication protocol such as TCP / IP and communicating with other communication devices. The communication device 207 functions as a data transmitting unit and a receiving unit. For example, it receives data such as operation information from a transmitting unit (not shown) in the substrate processing device 10 and stores it in the storage device 204. In addition, Figure 2 (b) thereof is a diagram showing the structure of the CPU 201. The CPU 201 includes an acquisition unit 211, a generation unit 212, a calculation unit 213, and a determination unit 214.

[0025] As described above, with reference to Figure 2 the schematic structure of the management device 12 has been described, but the host computer 11 and the substrate processing device 10 may also include a computer similar thereto.

[0026] In the substrate processing system 1, the plurality of substrate processing devices 10 are each connected to a management device 12 for management and maintenance. In addition, as Figure 1As shown, the article manufacturing system may include a plurality of substrate processing systems 1. Therefore, the management device 12 is capable of managing each substrate processing device 10 in the plurality of substrate processing systems 1. The management device 12 is capable of functioning as a maintenance determination device that collects and analyzes the operation information of each of the plurality of substrate processing devices 10, detects anomalies or signs thereof for each substrate processing device 10, and determines whether maintenance processing (maintenance processing) is required. Figure 1 In the embodiment, the connection between the plurality of substrate processing apparatuses 10 and the host computer 11 and the connection between the plurality of substrate processing apparatuses 10 and the management apparatus 12 may be either a wired connection or a wireless connection.

[0027] Hereinafter, in order to provide a specific example, an example in which the substrate processing apparatus 10 is configured by the exposure apparatus 10 will be described. Figure 3 FIG. 2 is a diagram showing the structure of an exposure device and a host computer. Figure 3 As shown, the exposure device 10 may include a light source unit 101 , an illumination system 102 , a mask stage 104 , a projection optical system 105 , a wafer stage 106 , a wafer chuck 107 , a pre-alignment unit 109 , and a control unit 111 .

[0028] The light emitted from the light source unit 101 illuminates the mask 103 held by the mask stage 104 via the illumination system 102. The light source of the light source unit 101 may be, for example, a high pressure mercury lamp, an excimer laser, or the like. In addition, when the light source is an excimer laser, the light source unit 101 is not limited to being inside the cavity of the exposure device 10, but may also be externally arranged. A pattern to be transferred is depicted on the mask 103. The light illuminating the mask 103 reaches the wafer 108 via the projection optical system 105. The wafer 108 is, for example, a silicon wafer, a glass plate, a film substrate, or the like.

[0029] The pattern on the mask 103 is transferred to the photosensitive medium (e.g., resist) coated on the wafer 108 via the projection optical system 105. The wafer 108 is held on the wafer chuck 107 in a state corrected to be flat by vacuum adsorption or the like. In addition, the wafer chuck 107 is held on the wafer stage 106. The wafer stage 106 is constructed to be movable. And, while the wafer stage 106 is moved in two dimensions along a plane perpendicular to the optical axis of the projection optical system 105, a plurality of irradiation areas are repeatedly exposed to the wafer 108. This is an exposure method called the step-and-repeat method. In addition, there is also an exposure method called the step-and-scan method, in which the mask stage 104 and the wafer stage 106 are synchronized while scanning and exposure is performed, and this embodiment can also be applied to an exposure device using the step-and-scan method.

[0030] In the exposure apparatus 10, the wafer 108 before the exposure process is set in the exposure apparatus in a state of being placed in the cassette 110. The cassette 110 stores at least one wafer 108, and generally stores a plurality of wafers 108. Then, one wafer 108 is taken out from the cassette 110 by a robot (not shown) and placed on the pre-aligner unit 109. After the orientation and alignment of the wafer 108 are performed by the pre-aligner unit 109, the wafer 108 is set on the wafer chuck 107 by the robot and subjected to the exposure process. The wafer 108 that has completed the exposure process is taken off the wafer chuck 107 by the robot and recovered into the cassette 110, and the next wafer 108 waiting in the pre-aligner unit 109 is set on the wafer chuck 107. In this way, the wafers 108 are successively subjected to the exposure process. In addition, a structure in which the exposure apparatus 10 is connected in series with other apparatuses such as a coating apparatus (not shown) and a developing apparatus (not shown), and the wafer 108 before the exposure process is carried in from other apparatuses and the wafer 108 after the exposure process is carried out to other apparatuses may also be adopted.

[0031] The control unit 111 is an information processing apparatus such as a computer, and controls various units and devices of the exposure apparatus 10 and performs various operations. In addition, in Figure 3 the example, it is configured to have only one control unit 111, but the control unit 111 is not limited to one, and a structure in which each unit and device of the exposure apparatus 10 has a plurality of control units 111 may also be adopted.

[0032] The host computer 11 is an information processing apparatus connected to the exposure apparatus 10 via a network or the like, and is used to monitor and control the exposure apparatus 10. In addition, the host computer 11 is also connected to apparatuses other than the exposure apparatus 10 and is similarly used to monitor and control other manufacturing apparatuses and the like. For example, the host computer 11 executes a work task for instructing the operation of the exposure apparatus 10.

[0033] Figure 4 FIG. is a diagram showing the structure of the temperature control system assembled into the exposure apparatus 10. In Figure 4 it, the thick arrow 42 shows the direction of the refrigerant circulation, and the thin arrow 43 shows the direction of the information transfer related to the control. The temperature control system (control system) 301 may include, for example, a first block 40 and a second block 41. The first block 40 and the second block 41 may be, for example, chambers in the exposure apparatus 10. In addition, the number of blocks is not limited to two, and may be divided into blocks for each one or each plurality of units. In this case, in a case where it is difficult to provide a chamber for each one or each plurality of units, a container storing one or more units may also be used.

[0034] In the first block 40, the refrigerant can be temperature-controlled, and the temperature-controlled refrigerant can be supplied to the second block 41. In addition, a plurality of target units 416 to 419 can be arranged in the second block 41. The plurality of target units 416 to 419 can include, for example, a light source unit 101, an illumination system 102, a mask stage 104, a projection optical system 105, and a wafer stage 106. The refrigerant temperature-controlled in the first block 40 absorbs heat from one or more target units while temperature-controlling the one or more target units in the second block 41, and then can return to the first block 40.

[0035] The first block 40 can include, for example, a temperature control unit (controlled object unit) 401, a temperature control unit 402, sensors 401T, 402T, a control unit 401C, and a control unit 402C. The temperature control unit 401 can lower the temperature of the refrigerant to a target temperature and supply it to the temperature control unit 402. The control unit 401C determines a command value in such a manner that the temperature of the refrigerant coincides with the target temperature based on the temperature measured by the sensor 401T, and inputs the command value to the temperature control unit 401 to perform control. Then, the temperature control unit 401 operates with an operation amount corresponding to the command value.

[0036] In addition, the temperature control unit 402 can adjust the temperature of the refrigerant within a temperature range allowable for the second block 41 and supply the refrigerant to the second block 41. The control unit 402C determines a command value in such a manner that the temperature of the refrigerant converges within the temperature range allowable for the second block 41 based on the temperature measured by the sensor 402T, and causes the temperature control unit 402 to operate with an operation amount corresponding to the command value.

[0037] In the second block 41, the temperature of the refrigerant can be adjusted by the temperature control units 412 to 415 so that each of the target units 416 to 419 converges within a target temperature range. The control unit 412C can determine a command value in such a manner that the target unit 416 converges within the target temperature range based on the temperatures measured by the sensors 412T1 and 412T2, and causes the temperature control unit 412 to operate with an operation amount corresponding to the command value. The control unit 413C can determine a command value in such a manner that the target unit 417 converges within the target temperature range based on the temperatures measured by the sensors 413T1 and 413T2, and causes the temperature control unit 413 to operate with an operation amount corresponding to the command value.

[0038] The control unit 411C can determine a command value in such a way that the temperature of the refrigerant converges within a target temperature range based on the temperature measured by the sensor 411T and the information from the control units 414C and 415C, and cause the temperature control unit 411 to operate with an operation amount corresponding to the command value. That is, the control unit 414C can determine a command value in such a way that the target unit 418 converges within a target temperature range based on the temperatures measured by the sensors 414T1 and 414T2, and cause the temperature control unit 414 to operate according to the command value. The control unit 415C can determine a command value in such a way that the target unit 419 converges within a target temperature range based on the temperatures measured by the sensors 415T1 and 415T2, and cause the temperature control unit 415 to operate with an operation amount corresponding to the command value.

[0039] The temperature control units 401, 402, 412 to 415 may be heating units or cooling units based on heat exchange. In addition, for example, the temperature control unit 401 may be a cooling unit, and the temperature control units 402, 412 to 415 may be heating units. In addition, the temperature control units 401, 402, 412 to 415 may not only heat and cool the refrigerant, but also adjust the temperature of the refrigerant by controlling the flow rate and pressure of the refrigerant circulating in the pipe.

[0040] In addition, the refrigerant circulating in the pipe may be either a liquid or a gas.

[0041] In Figure 4 In the temperature control system 301 shown, the temperature of the target unit is controlled, and sensors 401T, 402T, 411T to 415T2 are provided as sensors. However, the temperature control system 301 may also include sensors that measure information other than temperature (such as a refrigerant flow rate sensor, a pressure sensor, etc.). In addition, the temperature control system 301 may include a control unit that controls the controlled object in relation to parameters other than temperature (such as the flow rate and pressure of the refrigerant).

[0042] Here, a model representing the relationship between the output values of the respective sensors will be described. Here, for simplicity, in Figure 4 In the temperature control system 301 shown, the output values of two sensors (for example, sensors 401T and 402T) at time t are set as a t , b t . The relationship between the output values a t , b t can be defined by a model (function) given by Equation (1).

[0043] b t = f(a t )... (1)

[0044] The model f may be, for example, based on the output values ​​a output by the two sensors. t 、b t The time series data is used to determine the regression equation by the least square method or the like. In addition, the model f may also be a learning model generated by machine learning, for example. For example, the model f may be a model including a neural network. A neural network refers to a model having a multi-layer network structure such as an input layer, an intermediate layer, and an output layer. Based on the output values ​​a output by the two sensors t 、b t time series data, obtain a shown as input data t and b as teaching data t The obtained learning data is used to optimize the connection weight factors and the like inside the neural network according to an algorithm such as the back propagation method, thereby obtaining a learning model. The back propagation method is a method of adjusting the connection weight factors (Japanese: 合合重み付け科數) and the like between the nodes of each neural network in such a way as to reduce the difference between the output data and the teaching data. In addition, the model f may not be a model including a neural network, but may be a learning model including, for example, an SVM (support vector machine).

[0045] For a given sensor S i The output value (hereinafter referred to as the predicted output value) x ij Model f ij (x j ), as sensor S j The output value (hereinafter referred to as the measured output value) x j The function of can be given by equation (2). Here, i is an integer from 1 to N, N is the number of sensors, and j is an integer other than i from 1 to N.

[0046] x ij =f ij (x j )……(2)

[0047] Here, the formula (2) may mean the following mathematical formula group.

[0048] x 12 =f 12 (x2)

[0049] x 13 =f 13 (x3)

[0050] x 14 =f 14 (x4)

[0051] ·

[0052] ·

[0053] ·

[0054] x 1N = f 1N (x N )

[0055] x 21 = f 21 (x1)

[0056] x 23 = f 23 (x3)

[0057] x 24 = f 24 (x4)

[0058] ·

[0059] ·

[0060] ·

[0061] And, based on the predicted output value x of the sensor S i and the measured output value x of the sensor S ij to calculate an evaluation value, and detect an abnormality related to the sensor S based on the evaluation value. The evaluation value can be, for example, a value obtained by processing the difference between each of a plurality of predicted output values x i and the corresponding measured output value x i , such as a total value obtained by summing up the differences and normalizing the total value by the number of a plurality of models. In addition, the evaluation value can be, for example, a value calculated based on the difference or ratio between statistical values such as the average value and the median of a plurality of predicted output values x i and the measured output value x ij . And, when the evaluation value is not within a predetermined allowable range, it is detected that an abnormality has occurred in the output value of the sensor S i . ij i i

[0062] Here, an example of using a model representing the relationship of the output values of each sensor has been described, but a model representing the relationship of the command values in each control unit can also be used. For example, in the temperature control system 301 shown in Figure 4 , a model representing the relationship between the command value of the control unit 401C at time t and the command value of the control unit 402C can also be used. That is, regarding the model g i that gives the command value (hereinafter referred to as the predicted command value) y ij of the control unit C ij (y j ), as the command value (hereinafter referred to as the measured command value) y j of the control unit C j ​​​The function can be given by Equation (3).

[0063] y ij = g ij (y j )……(3)

[0064] Moreover, based on the predicted command value y of the control unit C i and the measured command value y of the control unit C ij a evaluation value is calculated, and an abnormality related to the control unit C i is detected based on the evaluation value. In addition, instead of the command value in the control unit, the action amount in the temperature control unit controlled by the control unit (hereinafter, the command value or the action amount is referred to as control data) can be used. j i

[0065] In addition, a model representing the relationship between the output value of each sensor and the command value in each control unit can be used. For example, in Figure 4 the temperature control system 301 shown, a model representing the relationship between the output value of the sensor 401T at time t and the command value of the control unit 401C can also be used. That is, regarding the model h i that gives the command value (hereinafter referred to as the predicted command value) y ij of the control unit C ij (x j ), as a function of the output value (hereinafter referred to as the measured output value) x j of the sensor S j it can be given by Equation (4).

[0066] y ij = h ij (x j )……(4)

[0067] Moreover, based on the predicted command value y of the control unit C i and the measured output value x of the sensor S ij a evaluation value is calculated, and an abnormality related to the control unit C j is detected based on the evaluation value. In addition, it can also be that a model h is generated in such a way that an evaluation value is calculated based on the predicted output value x j of the sensor S i and the measured command value y i of the control unit C ij and an abnormality related to the sensor S i is detected based on the evaluation value. j i

[0068] ​​​​In addition, a model represented by at least one of Formula (2), Formula (3), and Formula (4) can be used. That is, models representing the relationships between the output values of the respective sensors, models representing the relationships between the command values of the respective control units, and models representing the relationships between the output values of the respective sensors and the command values of the control units can be arbitrarily combined and used. In addition, instead of the command value in the control unit, the amount of action in the temperature control unit controlled by the control unit can be used.

[0069] In this way, the management device 12 can acquire information related to the output values of the sensors and the control data of the control unit in the temperature control system 301, and generate a model based on the acquired information related to the output values and the control data. In addition, the management device 12 can cause the storage device 204 to store information related to the generated model.

[0070] Here, the problems in the case of detecting an abnormality in the temperature control system 301 will be described. For example, when an abnormality occurs in the temperature control unit 402, the abnormality is detected based on the evaluation value calculated according to the model related to the output value of the sensor 402T. In addition, in the refrigerant circulation piping, the temperature control units 411, 412, and 413 are located downstream of the temperature control unit 402. And due to the temperature change of the refrigerant caused by the abnormality of the temperature control unit 402, the abnormality will also be detected based on the evaluation value calculated according to the models related to the output values of the sensors 411T, 412T1, and 413T1. In addition, similarly, due to the temperature change of the refrigerant caused by the abnormality of the temperature control unit 402, the abnormality will also be detected based on the evaluation value calculated according to the models related to the control data of the control units 411C, 412C, and 413C. That is, due to the abnormality of the temperature control unit 402, abnormalities will also be detected from the sensors and control units related to the temperature control units 411, 412, and 413, and it may be difficult to determine the temperature control unit in which the abnormality has occurred.

[0071] In addition, for example, when the target unit 417 includes the projection optical system 105, the temperature of the target unit 417 rises due to the heat of the exposure light irradiated during the exposure process in the exposure device 10. In addition, for example, when the target unit 419 includes the substrate stage 6, the temperature of the target unit 419 rises due to the heat generated by the drive of the substrate stage 6 during the exposure process in the exposure device 10. In addition, when the exposure process in the exposure device 10 is completed, the exposure light is no longer irradiated, and the drive unit of the target unit 419 stops, so the temperature of the target units 417 and 419 drops. In this way, even if the target unit is controlled by a different temperature control unit, the output values ​​of each sensor are correlated (Japanese: 相関関系) due to the linkage of the operation of the target unit during the exposure process of the exposure device 10. And, for example, when an abnormality occurs in the temperature control unit 413 related to the target unit 417, the abnormality is detected based on the evaluation value calculated based on the model related to the sensors 413T1, 413T2 and the control unit 413C. Furthermore, since the temperatures of the target units 417 and 419 are correlated, an abnormality is also detected based on the evaluation value calculated based on the model related to the sensors 415T1, 415T2 and the control unit 415C. That is, although the temperature control unit in which the abnormality occurs is the temperature control unit 413, the abnormality is also detected from the sensors and control units related to the temperature control unit 415.

[0072] In this way, since an abnormality is detected based on the evaluation values ​​calculated based on the models corresponding to the plurality of temperature control units, it may be difficult to identify the temperature control unit in which the abnormality has occurred.

[0073] Therefore, the management device 12 of this embodiment groups the evaluation values ​​calculated based on the model related to the sensor and the control unit, acquires the abnormality degree for each group based on the evaluation value belonging to each group, and detects abnormality of the temperature control system 301 based on the acquired abnormality degree.

[0074] Figure 5 2 is a flowchart showing a method for detecting an abnormality of the temperature control system of the present embodiment. In S501, the acquisition unit 211 acquires information related to the output value of the sensor in the temperature control system 301 and the control data of the control unit, and the calculation unit 213 generates a model representing the relationship between the output value of the sensor and the like based on the acquired information related to the output value and the control data. Here, the generated model can be set to a model generated using the output value of the sensor in the temperature control system 301 and the control data of the control unit. In addition, the acquired model can be set to at least one of a model representing the relationship between the output values ​​of the sensors, a model representing the relationship between the control data of the control unit, and a model representing the relationship between the output value of the sensor and the control data of the control unit.

[0075] In S502, the acquisition unit 211 acquires information related to the output value of the sensor and the control data of the control unit in the temperature control system 301. Further, the calculation unit 213 calculates an evaluation value related to the output value of the sensor and the control data of each control unit, using the information related to the output value and the control data and the calculated model.

[0076] In S503, the calculation unit 213 calculates the abnormality degree of each group based on the information of the group related to the sensor and the control unit. The abnormality degree of each group is a value indicating the degree of abnormality of the output value of the sensor or the control data of the control unit belonging to the group. Further, the abnormality degree of each group may be a value obtained by statistically processing, such as a value obtained by classifying the evaluation value obtained according to the generated model into each group and summing up the evaluation values belonging to each group, or a value obtained by averaging.

[0077] Here, the information of the group is stored in the storage device 204 in advance, and the management device 12 can acquire the information of the group from the storage device 204. Further, the management device 12 may also acquire the information of the group from an external information processing device via the communication device 207. Further, a method of grouping related to the sensor and the control unit will be described later.

[0078] In S504, the determination unit 214 performs an abnormality determination for each group based on the acquired abnormality degree of each group. That is, when the abnormality degree of the group is not within a predetermined allowable range, the management device 12 determines that an abnormality has occurred in the sensor and the control unit belonging to the group.

[0079] Next, the information of the group acquired by the management device 12 in S503 will be described in detail by each embodiment.

[0080] (Embodiment 1)

[0081] In Embodiment 1, an example of grouping for each block where the sensor and the control unit are present is shown. Figure 6 FIG. is an example showing the grouping of the present embodiment. In Figure 6 (a), Figure 4 the sensors 401T, 402T, the control units 401C, and 402C included in the first block 40 in Figure 4 belong to Group 1-1. Further,

[0082] the sensors 411T, 412T1 to 415T1, 412T2 to 415T2, and the control units 411C to 415C included in the second block 41 in Figure 6 belong to Group 1-2. Figure 6 In (b),Figure 4 The sensors 401T and 402T included in the first block 40 in Figure 4 belong to groups 1-3. In addition,

[0083] In addition, it is also possible to group only the control units as in Figure 6 (c). In Figure 6 (c), Figure 4 the control units 401C and 402C included in the first block 40 in Figure 4 belong to groups 1-5. In addition,

[0084] In addition, it is also possible to arbitrarily combine the groupings in Figure 6 (a) to (c). For example, it is also possible to combine group 1-1 in Figure 6 (a) with group 1-4 in Figure 6 (b).

[0085] Through such grouping, the management device 12 can determine which of the temperature control units located in the first block 40 and the temperature control units located in the second block 41 has an abnormality.

[0086] (Embodiment 2)

[0087] In Embodiment 2, it is an example of grouping the sensors and control units for each temperature control unit. Figure 7 It is a diagram showing an example of the grouping in this embodiment. For example, Figure 4 the sensor 401T and the control unit 401C of the temperature control unit 401 in

[0088] belong to group 2-1. In addition, for example, the sensor 412T1 and the control unit 412C of the temperature control unit 412 belong to group 2-4. In addition, the sensor 412T2 of the target unit 416 may also belong to group 2-4. Similarly, the sensors 413T2 to 415T2 of each of the target units 417 to 419 may also belong to groups 2-5 to 2-7.

[0089] Through such grouping, the management device 12 can determine which of the multiple temperature control units has an abnormality.

[0090] (Embodiment 3)

[0091] In Embodiment 3, an example of grouping is given for each group (hereinafter referred to as a control group) representing the range of information transfer related to control. Figure 8 This is an example showing the grouping in this embodiment. For example, Figure 4 the sensor 401T and the control unit 401C of the temperature control unit 401 in belong to Group 3-1. That is, the information of the output value of the sensor 401T is transmitted to the control unit 401C and determines the control data, so the sensor 401T and the control unit 401C belong to the same control group. In addition, for example, the sensors 411T, 414T1, 414T2, and the control units 411C and 414C belong to Group 3-5. That is, the information of the output values of the sensors 414T1 and 414T2 is transmitted to the control unit 414C and determines the control data. In addition, the information of the output value of the sensor 411T and the information of the control data of the control unit 414C are transmitted to the control unit 411C and determine the control data. In addition, in Figure 8 Groups 3-5 and 3-6 are set as different control groups, but the information of the control data of the control units 414C and 415C is transmitted to the control unit 411C, so Groups 3-5 and 3-6 can also be set as the same control group.

[0092] In addition, similar to Embodiment 1, grouping can be performed for any one of the three combinations: only combinations of sensors, only combinations of control units, and combinations of sensors and control units.

[0093] Through such grouping, the management device 12 can determine which temperature control unit belonging to a control group has an abnormality.

[0094] (Embodiment 4)

[0095] In Embodiment 4, an example of grouping is given for each pipe of the refrigerant cycle. Figure 9 This is a diagram showing an example of the grouping in this embodiment. In Figure 9 in the example of (a), the sensors and control units of the temperature control units arranged in the pipes branched downstream of the temperature control unit 402 in the direction of the refrigerant cycle belong to Groups 4-1 and 4-2. In addition, the sensors and control units of the temperature control units arranged in the pipes branched downstream of the temperature control unit 411 in the direction of the refrigerant cycle belong to Groups 4-3 and 4-4. In Figure 4 the sensors and control units of the pipes in which the temperature control units 402, 412, and the target unit 416 are arranged belong to Group 4-1. Specifically, the sensors 402T, 412T1, 412T2, and the control units 402C and 412C belong to Group 4-1. In addition, in Figure 4The sensors and control units in the pipes where the temperature control units 411, 414 and the object unit 418 are arranged belong to Group 4-3. Specifically, the sensors 411T, 414T1, 414T2, and the control units 411C and 414C belong to Group 4-3. In addition, in Figure 4 The sensors and control units in the pipes where the temperature control units 411, 415 and the object unit 419 are arranged belong to Group 4-4. Specifically, the sensors 411T, 415T1, 415T2, and the control units 411C and 415C belong to Group 4-4.

[0096] In addition, in Figure 9 In the example of (b), the sensor 402T and the control unit 402C of the temperature control unit 402 belong to Group 4-5. Also, the sensors and control units of the temperature control unit at the position on the pipe arranged downstream in the refrigerant circulation direction with respect to the temperature control unit 402 belong to Group 4-5. In addition, the sensor 411T and the control unit 411C of the temperature control unit 411 belong to Group 4-6. Also, the sensors and control units of the temperature control unit arranged downstream in the pipe through which the refrigerant flows with respect to the temperature control unit 411 belong to Group 4-6.

[0097] In addition, in the present embodiment, the sensors and control units of the temperature control unit at the position on the pipe arranged downstream in the refrigerant circulation direction are grouped so that they all belong to a group, but only a part of the sensors and control units can be targeted. For example, since the sensors 412T1 and 412T2 are adjacent on the same pipe, either the sensor 412T1 or the sensor 412T2 can be deleted.

[0098] In addition, similar to Embodiment 1, grouping can be performed for any one of the three combinations: only the combination of sensors, only the combination of control units, and the combination of sensors and control units.

[0099] Through such grouping, the management device 12 can determine which temperature control unit arranged in the branched pipe in the pipe through which the refrigerant flows has an abnormality.

[0100] Based on the above, in the management device according to the present embodiment, the abnormality degree of each group can be calculated, and the sensor or control unit of the group where an abnormality has occurred can be determined, so it is advantageous for detecting an abnormality in the temperature control system.

[0101] <Second Embodiment>

[0102] Next, the management device 12 according to the second embodiment will be described. In addition, for matters not mentioned here, reference can be made to the first embodiment.

[0103] In the management device 12 in this embodiment, a model is generated for each group based on the output values of the grouped sensors and the control data of the control unit, and the abnormality degree of each group is calculated based on the evaluation value calculated using the models belonging to each group.

[0104] Figure 10 FIG. is a flowchart showing a method for detecting an abnormality in the temperature control system in this embodiment. In S1001, the acquisition unit 211 acquires information related to the output values of the sensors and the control data of the control unit for each group, and the generation unit 212 generates a model representing the relationship of the output values of the sensors, etc. for each group based on the acquired information related to the output values and the control data. Here, the acquired model can be set as a model generated using the output values of the sensors grouped for the sensors and the control unit in the temperature control system 301 and the control data. In addition, regarding examples of grouping, it can be the same as in Examples 1-4 in the first embodiment. In addition, the grouping information can be stored in the storage device 204 in advance, and the acquisition unit 211 can acquire the grouping information from the storage device 204. In addition, the acquisition unit 211 can also acquire the grouping information from an external information processing device via the communication device 207.

[0105] In S1002, the acquisition unit 211 acquires information related to the output values of the sensors and the control data of the control unit in the temperature control system 301. Then, the calculation unit 213 calculates an evaluation value related to the output values of the sensors and the control data of each group using the information related to the output values and the control data and the calculated models of each group.

[0106] In S1003, the calculation unit 213 calculates the abnormality degree of each group based on the evaluation value calculated using the model of each group. The abnormality degree of each group can be set as a value obtained by performing statistical processing such as summing or averaging the evaluation values obtained from the models belonging to the group.

[0107] In S1004, the determination unit 214 performs an abnormality determination for each group based on the acquired abnormality degree of each group. That is, when the abnormality degree of the group is not within a predetermined allowable range, the management device 12 determines that an abnormality has occurred in the sensors and the control unit belonging to the group.

[0108] Through the above, in the management device according to this embodiment, the abnormality degree of each group can be calculated, and the sensors or control units of the group in which an abnormality has occurred can be determined, which is advantageous for detecting an abnormality in the temperature control system.

[0109] (Method for manufacturing an article)

[0110] A manufacturing method for an article such as a device (semiconductor device, magnetic storage medium, liquid crystal display element, etc.), a color filter, or a hard disk, etc. is described. Such a manufacturing method includes a step of forming a pattern on a substrate (wafer, glass plate, film-like substrate, etc.) using a lithography apparatus (e.g., exposure apparatus, imprint apparatus, drawing apparatus, etc.). Such a manufacturing method further includes a step of processing the substrate on which the pattern is formed. The processing step may include a step of removing the residual film of the pattern. In addition, it may also include other known steps such as a step of etching the substrate using the pattern as a mask. The manufacturing method of the article in the present embodiment is advantageous in at least one aspect among the performance, quality, productivity, and production cost of the article compared with the conventional technology.

[0111] As described above, the preferred embodiments of the present invention have been described. However, it goes without saying that the present invention is not limited to these embodiments, but can be variously modified and changed within the scope of its gist.

[0112] In addition, Examples 1-4 can be implemented not only individually but also by any combination of Examples 1-4.

[0113] According to the present invention, a technique advantageous for detecting an abnormality in a control system including a plurality of sensors and a plurality of control units is provided.

[0114] Other embodiments

[0115] Embodiments of the present invention can also be implemented by a computer of a system or device that reads and executes computer-executable instructions (e.g., one or more programs) recorded on a storage medium (also fully referred to as "non-transitory computer-readable storage medium") to perform one or more functions in the above embodiments, and / or by a computer of a system or device including one or more circuits (e.g., application-specific integrated circuit (ASIC)) for performing one or more functions in the above embodiments, and a method executed by the computer of the system or device by, for example, reading and executing computer-executable instructions from the storage medium to perform one or more functions in the above embodiments, and / or by controlling one or more circuits to perform one or more functions in the above embodiments. The computer may include one or more processors (e.g., central processing unit (CPU), microprocessing unit (MPU)), and may include computer-executable instructions read and executed by a network of individual computers or individual processors. The computer-executable instructions may be provided to the computer from, for example, a network or a storage medium. The storage medium may include, for example, one or more of a hard disk, random access memory (RAM), read-only memory (ROM), memory of a distributed computing system, optical disk (e.g., compact disc (CD), digital versatile disc (DVD) or Blu-ray Disc (BD)TM), flash device, memory card, etc.

[0116] Although the present invention has been described with reference to exemplary embodiments, it should be understood that the present invention is not limited to the disclosed exemplary embodiments. The appended claims should be given the broadest interpretation to cover all such modifications as well as equivalent structures and functions.

[0117] This application claims priority to a Japanese patent application filed on April 13, 2020, with an application number of "2020-071692", which is incorporated herein by reference in its entirety.

Claims

1. An information processing device detects an abnormality in a control system having a plurality of sensors and a plurality of control units. The control system is a temperature control system that adjusts the temperature of an object unit. In the information processing device, there is: a calculation unit that uses a model representing the relationship between the output values of two sensors among the plurality of sensors, the relationship between the control data of two control units among the plurality of control units, or the relationship between the output value of one sensor among the plurality of sensors and the control data of one control unit among the plurality of control units, and calculates an abnormality degree for at least two groups into which the plurality of sensors or the plurality of control units are divided. The abnormality degree represents the degree of abnormality of the output value of the sensor or the control data of the control unit; and a determination unit that determines the abnormality of the plurality of sensors or the plurality of control units for each of the groups based on the abnormality degree calculated by the calculation unit.

2. The information processing device according to claim 1, characterized in that it has a generation unit that generates the model based on the output values of the plurality of sensors or the control data of the plurality of control units.

3. The information processing device according to claim 1, characterized in that based on the chamber of the substrate processing device having the control system, the plurality of sensors or the plurality of control units are divided into the groups.

4. The information processing device according to claim 1, characterized in that based on the range of information transfer related to the output value of the sensor or the control data of the control unit, the plurality of sensors or the plurality of control units are divided into the groups.

5. The information processing device according to claim 1, characterized in that based on the temperature control unit or the object unit controlled by the control unit, the plurality of sensors or the plurality of control units are divided into the groups.

6. The information processing device according to claim 1, characterized in that the control system is a temperature control system that circulates a refrigerant in a pipe to adjust the temperature of an object unit, and based on information related to the branch of the pipe in which the refrigerant circulates in the temperature control system, the plurality of sensors or the plurality of control units are divided into the groups.

7. The information processing device according to claim 1, characterized in that the calculation unit groups a plurality of evaluation values calculated using the model based on the information of the group, and calculates the abnormality degree for each of the groups.

8. The information processing device according to claim 1, characterized in that the calculation unit calculates the abnormality degree for each of the groups based on a plurality of evaluation values calculated using the model grouped based on the information of the group.

9. The information processing device according to claim 1, characterized in that the sensor includes a sensor for measuring temperature, flow rate, or pressure.

10. The information processing device according to claim 1, characterized in that the control data includes a command value input to a control object unit controlled by the control unit, or an operation amount by which the control object unit operates according to the command value.

11. A detection method for detecting an abnormality in a control system having a plurality of sensors and a plurality of control units, the control system being a temperature control system for adjusting the temperature of an object unit. In the detection method, it includes: A calculation step of using a model representing the relationship between the output values of two sensors among the plurality of sensors, the relationship between the control data of two control units among the plurality of control units, or the relationship between the output value of one sensor among the plurality of sensors and the control data of one control unit among the plurality of control units, and calculating an abnormality degree for each of at least two groups into which the plurality of sensors or the plurality of control units are divided. The abnormality degree represents the degree of abnormality of the output value of the sensor or the control data of the control unit; And A determination step of determining the abnormality of the plurality of sensors or the plurality of control units for each of the groups based on the abnormality degree calculated in the calculation step.

12. A non-transitory computer-readable storage medium stores a program that causes a computer to execute a detection method for detecting an abnormality in a control system including a plurality of sensors and a plurality of control units, the control system being a temperature control system that adjusts the temperature of a target unit to be adjusted, wherein, The detection method includes: A calculation step of using a model representing the relationship between the output values of two sensors among the plurality of sensors, the relationship between the control data of two control units among the plurality of control units, or the relationship between the output value of one sensor among the plurality of sensors and the control data of one control unit among the plurality of control units, and calculating an abnormality degree for each of at least two groups into which the plurality of sensors or the plurality of control units are divided. The abnormality degree represents the degree of abnormality of the output value of the sensor or the control data of the control unit; and A determination step of determining the abnormality of the plurality of sensors or the plurality of control units for each of the groups based on the abnormality degree calculated in the calculation step.

13. A substrate processing system having: A substrate processing apparatus having a control system with a plurality of sensors and a plurality of control units for processing a substrate; and A management apparatus for detecting an abnormality in the control system, The control system being a temperature control system for adjusting the temperature of an object unit, Among them, The management apparatus has: A calculation unit that uses a model representing the relationship between the output values of two sensors among the plurality of sensors, the relationship between the control data of two control units among the plurality of control units, or the relationship between the output value of one sensor among the plurality of sensors and the control data of one control unit among the plurality of control units, and calculates an abnormality degree for each of at least two groups into which the plurality of sensors or the plurality of control units are divided. The abnormality degree represents the degree of abnormality of the output value of the sensor or the control data of the control unit; And A determination unit that determines the abnormality of the plurality of sensors or the plurality of control units for each of the groups based on the abnormality degree calculated by the calculation unit.

14. A method for manufacturing an article, including: A step of processing a substrate using a substrate processing system; And A step of manufacturing an article using the substrate processed in the above step, Wherein, the substrate processing system has: A substrate processing apparatus having a control system with a plurality of sensors and a plurality of control units for processing a substrate; and A management apparatus for detecting an abnormality in the control system, The control system is a temperature control system for adjusting the temperature of the object unit. Among them, the management device has: a calculation unit that uses a model representing the relationship between the output values of two sensors among the plurality of sensors, the relationship between the control data of two control units among the plurality of control units, or the relationship between the output value of one sensor among the plurality of sensors and the control data of one control unit among the plurality of control units, and calculates an abnormality degree for at least two groups into which the plurality of sensors or the plurality of control units are divided. The abnormality degree represents the abnormality degree of the output value of the sensor or the control data of the control unit; and a determination unit that determines the abnormality of the plurality of sensors or the plurality of control units for each of the groups based on the abnormality degree calculated by the calculation unit.

Images