Substrate processing apparatus management system, auxiliary apparatus, substrate processing apparatus, inter-chamber performance comparison method, and inter-chamber performance comparison program

Abstract

A substrate processing apparatus management system according to the present invention comprises: an information analysis apparatus having a model generation unit that generates a representative model indicating a correlation relationship between a plurality of pieces of processing information indicating an operation or a state associated with processing of a substrate in a representative chamber among a plurality of chambers; and an assistance device that acquires a plurality of pieces of processing information for each of the plurality of chambers, and generates assistance information pertaining to the maintenance work of the other chambers on the basis of comparison information in which the correlation between the plurality of pieces of processing information for the other chambers is compared with the representative model.

Description

Technical Field

[0001] The present invention relates to a substrate processing device management system, an auxiliary device, a substrate processing device, a chamber performance comparison method and a chamber performance comparison program, and in particular to a substrate processing device management system having an auxiliary device and an information analysis device for assisting maintenance operations of a substrate processing device having multiple chambers for processing substrates, the auxiliary device, a substrate processing device having the auxiliary device, a chamber performance comparison method executed by the auxiliary device, and a chamber performance comparison program that enables a computer to execute the chamber performance comparison method. Background Art

[0002] The substrate processing apparatus has a plurality of chambers divided into spaces for processing substrates such as semiconductor substrates (semiconductor wafers). The plurality of chambers are composed of the same type of components to perform the same type of processing on the substrates. The plurality of chambers are adjusted so that the same performance is exerted in the plurality of chambers.

[0003] For example, Japanese Patent Publication No. 2019-140196 discloses a technique for evaluating a unit process by comparing time series data obtained from the unit process with predetermined reference data. According to the technique described in Japanese Patent Publication No. 2019-140196, adjustments can be made in each of a plurality of chambers so that the actions of a plurality of constituent elements are consistent with the reference.

[0004] Patent Document 1: Japanese Patent Application Publication No. 2019-140196 Summary of the invention

[0005] Problem that the invention aims to solve

[0006] Although multiple chambers can be made to have the same performance, there are cases where the processing results are different even if the same processing is performed on the substrate due to the location of the chamber in the substrate processing apparatus, slight differences in construction, individual differences in the multiple components constituting the chamber, etc. However, since the differences in the actions and states of processing the substrate between the multiple chambers are slight, there are cases where they cannot be detected even if the time series data is compared with the reference data.

[0007] The object of the present invention is to provide a substrate processing device management system, an auxiliary device, a substrate processing device, a chamber performance comparison method and a chamber performance comparison program that can provide information related to the performance difference between multiple chambers of the substrate processing device.

[0008] Technical means of solving problems

[0009] According to one embodiment of the present invention, a substrate processing device management system has an auxiliary device and an information analysis device, wherein the auxiliary device assists in the maintenance operation of the substrate processing device, and the substrate processing device has a plurality of chambers for processing substrates, wherein the information analysis device has a model generation unit that generates a representative model, the representative model represents the correlation between a plurality of processing information, and the plurality of processing information represents actions or states associated with the processing of substrates in a predetermined representative chamber among the plurality of chambers, and the auxiliary device comprises: a processing information collection unit that acquires a plurality of processing information of each of the plurality of chambers; and an auxiliary information generation unit that generates auxiliary information related to the maintenance operation of other chambers based on comparison information that compares the correlation between the plurality of processing information of other chambers different from the representative chamber with the representative model.

[0010] According to this embodiment, a representative model representing the correlation between a plurality of processing information of a representative chamber is generated by an information analysis device, and a plurality of processing information of each of a plurality of chambers of a substrate processing device is acquired by an auxiliary device. Since the correlation between a plurality of processing information is compared between the representative chamber and other chambers, it is possible to detect a difference in an action or state associated with processing of a substrate between the representative chamber and other chambers. In addition, auxiliary information related to maintenance work of other chambers is generated by the auxiliary device based on comparison information of comparing the correlation between a plurality of processing information between the representative chamber and other chambers. Therefore, information on the performance difference between other chambers and the representative chamber can be provided.

[0011] According to another embodiment of the present invention, an auxiliary device assists in the maintenance operation of a substrate processing device, wherein the substrate processing device has a plurality of chambers for processing substrates, wherein the auxiliary device comprises: a processing information collecting unit for acquiring a plurality of processing information, wherein the plurality of processing information represents actions or states associated with the processing of the substrates in the respective plurality of chambers; and an auxiliary information generating unit for generating auxiliary information related to the maintenance operation of the other chambers based on comparison information comparing a predetermined correlation between a plurality of processing information in a representative chamber and a correlation between a plurality of processing information in other chambers.

[0012] According to this embodiment, a plurality of processing information of each of a plurality of chambers of a substrate processing apparatus is obtained, and the correlation between the plurality of processing information is compared between a predetermined representative chamber and other chambers. Therefore, it is possible to detect a difference in an action or state associated with processing of a substrate between the representative chamber and other chambers. In addition, based on comparison information of the correlation between the plurality of processing information between the representative chamber and other chambers, auxiliary information related to maintenance work of other chambers is generated. Therefore, it is possible to provide information on the performance difference between other chambers and the representative chamber.

[0013] Preferably, the comparison information is information obtained by weighting and comparing the correlations between the plurality of processing information.

[0014] According to this embodiment, since the correlation between a plurality of processing information indicating actions or states related to substrate processing is weighted, it is possible to detect differences in actions or states that have a great impact on the performance of processing the substrate at an early stage.

[0015] Preferably, the auxiliary information generating unit calculates the correlation between the plurality of processing information after duplexing by combining the reference information predetermined for at least one target processing information among the plurality of processing information as new processing information.

[0016] According to this embodiment, object processing information that has no correlation or little correlation with other processing information can be combined with relevant reference information. Therefore, information on the performance difference between the representative chamber and other chambers can be provided for processing information that has no correlation or little correlation with other processing information.

[0017] Preferably, the auxiliary information generating unit calculates the correlation between the plurality of processing information after performing logarithmic operation on at least one object processing information among the plurality of information.

[0018] According to this embodiment, since at least one target processing information among a plurality of processing information is logarithmically processed, the accuracy of the correlation with other processing information can be improved for processing information with small changes. Therefore, the accuracy of the performance difference between the representative chamber and other chambers can be improved.

[0019] Preferably, the auxiliary device includes a representative chamber determination unit that determines, as the representative chamber, a chamber among the plurality of chambers having a correlation closest to an average correlation between the plurality of process information of the respective plurality of chambers.

[0020] According to the present embodiment, since a chamber whose operation or state related to processing of a substrate is close to an average among a plurality of chambers is determined as a representative chamber, the representative chamber can be automatically determined.

[0021] Preferably, the plurality of chambers respectively include: an ejection valve for ejecting liquid; and a flow measurement unit for measuring the flow rate of the liquid ejected from the ejection valve, and the plurality of processing information respectively include: an opening signal for indicating the opening amount input to the ejection valve in order to control the opening amount of the ejection valve; and a flow rate measured by the flow measurement unit.

[0022] According to the present embodiment, auxiliary information on maintenance work of the discharge valves of other chambers can be generated based on the difference in correlation between the open signal and the flow rate between the representative chamber and the other chambers.

[0023] Preferably, the plurality of chambers respectively include: an ejection valve for ejecting liquid; and a concentration measuring unit for measuring the concentration of the liquid, and the plurality of processing information respectively include: an opening signal for indicating the opening amount input to the ejection valve in order to control the opening amount of the ejection valve; and a concentration measured by the concentration measuring unit.

[0024] According to the present embodiment, auxiliary information on maintenance work of other chambers can be generated based on the difference in correlation between the open signal and the concentration between the representative chamber and the other chambers.

[0025] Preferably, the plurality of chambers respectively include: a concentration measuring unit for measuring the concentration of the liquid; and an indoor temperature measuring unit for measuring the temperature of the chamber, and the plurality of processing information respectively include: a concentration measured by the concentration measuring unit; and a temperature measured by the indoor temperature measuring unit.

[0026] According to the present embodiment, auxiliary information on maintenance work of other chambers can be generated based on the difference in correlation between the concentration of liquid and the temperature of the chamber between the representative chamber and the other chambers.

[0027] Preferably, the plurality of chambers respectively include: a concentration measuring unit for measuring the concentration of the liquid; and a liquid temperature measuring unit for measuring the temperature of the liquid, and the plurality of processing information respectively include: a concentration measured by the concentration measuring unit; and a temperature measured by the liquid temperature measuring unit.

[0028] According to the present embodiment, auxiliary information on maintenance work of other chambers can be generated based on the difference in correlation between the concentration of the liquid and the temperature of the liquid between the representative chamber and the other chambers.

[0029] Preferably, the auxiliary device also includes a deviation acquisition unit, which acquires deviation information as comparison information, and the deviation information represents the degree of deviation between a plurality of predicted values ​​predicted based on a correlation between a plurality of processing information representing a chamber and a plurality of processing information of other chambers and a plurality of processing information acquired for the other chambers.

[0030] According to this embodiment, since the correlation between the plurality of process information of the representative chamber is used to predict the plurality of prediction values ​​based on the plurality of process information of other chambers, the correlation between the plurality of process information can be compared between the representative chamber and the other chambers. Since the deviation information indicating the degree of deviation between the plurality of prediction values ​​and the plurality of process information of other chambers is obtained as the comparison information, the difference between the correlation between the plurality of process information of the representative chamber and the other chambers can be shown.

[0031] According to another embodiment of the present invention, a substrate processing apparatus includes the auxiliary device.

[0032] According to the present embodiment, it is possible to provide a substrate processing apparatus capable of detecting performance differences among a plurality of chambers.

[0033] According to another embodiment of the present invention, a method for comparing performance between chambers is performed by an auxiliary device that assists in maintenance operations of a substrate processing device having a plurality of chambers for processing substrates, wherein the method for comparing performance between chambers includes the following processing: a process for acquiring a plurality of processing information representing actions or states associated with processing of substrates in each of the plurality of chambers; and a process for generating auxiliary information related to maintenance operations of other chambers based on comparison information comparing a predetermined correlation between a plurality of processing information representing a chamber in the plurality of chambers with a correlation between a plurality of processing information of other chambers.

[0034] According to another embodiment of the present invention, a performance comparison program between chambers is executed by a computer of an auxiliary device that assists in the maintenance work of a substrate processing device, wherein the substrate processing device has a plurality of chambers for processing substrates, wherein the performance comparison program between chambers causes the computer to perform the following processes: a process of acquiring a plurality of processing information representing actions or states associated with the processing of substrates in each of the plurality of chambers; and a process of generating auxiliary information related to the maintenance work of other chambers based on comparison information comparing a correlation between a plurality of processing information representing a chamber predetermined in the plurality of chambers with a correlation between a plurality of processing information of other chambers.

[0035] Effects of the Invention

[0036] According to the present invention, it is possible to provide information on performance differences among a plurality of chambers included in a substrate processing apparatus. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a diagram for explaining the overall configuration of a substrate processing apparatus management system according to one embodiment of the present invention.

[0038] Figure 2 This is a conceptual diagram for explaining the operation of the substrate processing apparatus management system.

[0039] Figure 3 It is a diagram for explaining a specific calculation example of the deviation degree.

[0040] Figure 4 This is a diagram showing an example of a deviation table.

[0041] Figure 5 This is a block diagram for explaining an example of the functional structure of the substrate processing apparatus management system.

[0042] Figure 6 This is a flowchart showing an example of the flow of processing information transmission processing.

[0043] Figure 7 This is a flowchart showing an example of the flow of the model generation process.

[0044] Figure 8 This is a flowchart showing an example of the flow of inter-chamber performance comparison processing.

[0045] Fig. 9 This is a diagram showing an example of a weighting table.

[0046] Fig.10 This is a block diagram for explaining an example of the functional structure of the substrate processing apparatus management system in the second variation.

[0047] Fig.11 This is a flowchart showing an example of the flow of representative chamber determination processing.

[0048] Fig.12 This is a block diagram for explaining an example of the functional structure of the substrate processing apparatus management system in the third modification.

[0049] Fig.13 This is a diagram showing an example of a deviation table in the third variation.

[0050] Fig.14 This is a flowchart showing an example of the flow of the model generation process in the third variation.

[0051] Fig.15This is a flowchart showing an example of the flow of the inter-chamber performance comparison process in the third variation. DETAILED DESCRIPTION

[0052] Hereinafter, an auxiliary device, an inter-chamber performance comparison method, and an inter-chamber performance comparison program according to an embodiment of the present invention will be described using the accompanying drawings. In the following description, a substrate refers to a semiconductor substrate, a liquid crystal display device, an organic EL (Electro-Luminescence) display device, or a FPD (Flat Panel Display) substrate, an optical disk substrate, a magnetic disk substrate, an optical magneto-magnetic disk substrate, a photomask substrate, a ceramic substrate, or a solar cell substrate. In addition, in the following description, a person who manages a substrate processing device is referred to as a manager, and a person who performs maintenance work on the substrate processing device is referred to as a maintenance operator.

[0053] 1. Overall structure of the substrate processing device management system

[0054] First, the overall configuration of a substrate processing apparatus management system including the auxiliary apparatus according to the present embodiment will be described. Figure 1 A diagram for explaining the overall structure of a substrate processing apparatus management system according to an embodiment of the present invention. Figure 1 As shown, the substrate processing device management system 100 is composed of a substrate processing device 1, an information analysis device 3 and an auxiliary device 4. The information analysis device 3 is, for example, a server, including a CPU (central processing unit) and a memory. The auxiliary device 4 is, for example, a personal computer, including a CPU and a memory. In addition, the auxiliary device 4 can load and unload a computer-readable storage medium, namely a CD-ROM (Compact Disc Read Only Memory, read-only memory) 4c, and the auxiliary device 4 can read and execute a program recorded in the CD-ROM 4c.

[0055] The information analysis device 3 and the support device 4 are used to manage the substrate processing apparatus 1. In addition, the substrate processing apparatus 1 managed by the information analysis device 3 and the support device 4 is not limited to one, and a plurality of substrate processing apparatuses 1 may be managed.

[0056] The auxiliary device 4 of this embodiment is used to assist the maintenance work of the substrate processing device 1 performed by the maintenance operator. The auxiliary device 4 is connected to the substrate processing device 1 and the information analysis device 3 through a wired or wireless communication line or communication line network. For example, the auxiliary device 4 is connected to the substrate processing device 1 and the information analysis device 3 through a communication line network such as the Internet or a local area network. In this embodiment, the auxiliary device 4 is connected to the substrate processing device 1 and the information analysis device 3 through a wired or wireless connection.

[0057] 2. A structural example of the substrate processing apparatus 1

[0058] like Figure 1 As shown, the substrate processing device 1 is a batch type substrate cleaning device, which includes a control device 10 and a plurality of chambers C1 to Cn. Wherein n is a positive integer. A chamber is a space divided for processing a substrate. The number of chambers C1 to Cn is not limited, and here, the case where n=12 is taken as an example for explanation. In addition, in the substrate processing device 1, in addition to the plurality of chambers C1 to Cn, a display device, a sound output device, and an operating unit not shown in the figure are also provided.

[0059] The plurality of chambers C1 to Cn are respectively constituted by a plurality of components of the same type. Here, the chamber C1 is taken as an example for description. The chamber C1 includes a processing tank 111 , a substrate holding unit 112 , a lifting device 112 a , a bubbling pipe 115 , a heater 117 , and a heater driving unit 118 .

[0060] The substrate holding portion 112 is configured to hold a plurality of substrates W. The processing tank 111 is configured to accommodate a plurality of substrates W held by the substrate holding portion 112. A cleaning liquid for cleaning the substrates W is stored in the processing tank 111.

[0061] The lifting device 112a supports the substrate holding part 112 movably in the up-down direction, and moves the substrate holding part 112 in the up-down direction under the control of the control device 10. Thus, the lifting device 112a can immerse the plurality of substrates W held in the substrate holding part 112 in the cleaning liquid stored in the processing tank 111, and can lift the plurality of substrates W immersed in the cleaning liquid from the processing tank 111. The plurality of substrates W are cleaned by being immersed in the cleaning liquid. In addition, the lifting device 112a is provided with a motor (not shown) as a power source for moving the substrate holding part 112 in the up-down direction.

[0062] A chemical liquid pipe 113 and a pure water pipe 114 are connected to the treatment tank 111. The chemical liquid pipe 113 is provided with a chemical liquid valve 113a and a flow meter 124. The chemical liquid valve 113a is a control valve whose opening degree can be adjusted by the control of the control device 10.

[0063] The liquid medicine pipe 113 introduces the liquid medicine supplied from the liquid medicine supply system (not shown) into the treatment tank 111 by opening the liquid medicine valve 113a. The flow rate (supply amount per unit time) of the liquid medicine supplied to the treatment tank 111 through the liquid medicine pipe 113 changes according to the opening of the liquid medicine valve 113a. As the liquid medicine, BHF (buffered hydrofluoric acid), DHF (dilute hydrofluoric acid), hydrofluoric acid, hydrochloric acid, sulfuric acid, nitric acid, phosphoric acid, acetic acid, oxalic acid, or ammonia can be used. The flow meter 124 detects the flow rate of the liquid medicine in the downstream portion of the liquid medicine pipe 113 than the liquid medicine valve 113a, and provides the detection result to the control device 10.

[0064] A pure water valve 114a and a flow meter 125 are provided in the pure water piping 114. The pure water valve 114a is a control valve whose opening can be adjusted by the control of the control device 10. The pure water piping 114 introduces pure water supplied from a pure water supply system (not shown) into the treatment tank 111 by opening the pure water valve 114a. The flow rate (supply amount per unit time) of the pure water supplied to the treatment tank 111 through the pure water piping 114 changes according to the opening of the pure water valve 114a. The flow meter 125 detects the flow rate of pure water in the portion of the pure water piping 114 that is downstream of the pure water valve 114a, and provides the detection result to the control device 10.

[0065] The bubble tube 115 is fixed by a bubble fixing member (not shown) inside the treatment tank 111 and near the lower end thereof. The bubble tube 115 is connected to a gas pipe 116. The gas pipe 116 is provided with a gas valve 116a and a flow meter 127. The gas valve 116a is a control valve whose opening can be adjusted by the control of the control device 10.

[0066] The gas pipe 116 introduces nitrogen gas supplied from a gas supply system (not shown) into the bubbler pipe 115 in the treatment tank 111 by opening the gas valve 116a. The flow rate (supply amount per unit time) of the nitrogen gas supplied to the bubbler pipe 115 through the gas pipe 116 changes according to the opening of the gas valve 116a. The flow meter 127 detects the flow rate of nitrogen gas in the portion of the gas pipe 116 downstream of the gas valve 116a, and provides the detection result to the control device 10. In this case, the control device 10 adjusts the opening of the gas valve 116a based on the flow rate provided from the flow meter 127 so that the nitrogen gas is supplied to the bubbler pipe 115 at a predetermined flow rate.

[0067] By adjusting the opening of the liquid medicine valve 113a and the pure water valve 114a, liquid medicine and pure water are supplied in a predetermined ratio in the treatment tank 111. In this state, the gas valve 116a is further opened. Thus, nitrogen is supplied to the bubble tube 115, and a large number of bubbles are generated from the bubble tube 115. The generated bubbles rise in the treatment tank 111, and the liquid medicine and pure water supplied to the treatment tank 111 are mixed to generate a cleaning solution. In addition, other inert gases such as argon gas can be supplied to the bubble tube 115 instead of nitrogen gas.

[0068] A heater 117 is also provided inside the treatment tank 111 and near the lower end. The heater 117 has a path for the cleaning liquid to pass through, and the cleaning liquid is heated by the heater 117 while passing through the path. The heater driving unit 118 drives the heater 117 by supplying power to the heater 117. The heater thermometer 118a detects the surface temperature of the heater 117 and provides the detection result to the control device 10. The outlet thermometer 118b is provided near the outlet of the path of the heater, detects the temperature of the cleaning liquid just heated by the heater 117, and provides the detection result to the control device 10. The control device 10 determines the supply amount of power supplied to the heater 117 based on the surface temperature provided by the heater thermometer 118a and the temperature of the cleaning liquid provided by the outlet thermometer 118b, thereby controlling the heater driving unit 118.

[0069] In addition, a drain pipe is connected to the bottom of the processing tank 111. A valve (not shown) is provided on the drain pipe. By opening the valve provided on the drain pipe, the cleaning liquid in the processing tank 111 can be discharged to the outside of the chamber C1.

[0070] Furthermore, in the processing tank 111 , a liquid level meter 121 , a concentration meter 122 , a first thermometer 123 , and a second thermometer 123 a are provided as a plurality of detectors for detecting the state of the cleaning liquid stored in the processing tank 111 .

[0071] The liquid level meter 121 detects the liquid level (liquid level) of the cleaning liquid stored in the treatment tank 111, and provides the detection result to the control device 10. The concentration meter 122 detects the concentration (liquid concentration) of the cleaning liquid stored in the treatment tank 111, and provides the detection result to the control device 10. The first thermometer 123 is arranged outside the treatment tank 111 in the chamber C1, detects the temperature in the chamber C1, and provides the detection result to the control device 10. The second thermometer 123a is provided inside the treatment tank 111, detects the temperature of the cleaning liquid stored in the treatment tank 111, and provides the detection result to the control device 10.

[0072] The control device 10 is composed of, for example, a CPU (central processing unit) and a memory, and controls the operation of the lifting device 120a, the operation of the heater driving unit 118, and the opening of the liquid valve 113a, the pure water valve 114a, and the gas valve 116a. The memory of the control device 10 stores a program for executing the cleaning process of the substrate W performed by the substrate processing apparatus 1.

[0073] In addition, the control device 10 adjusts the opening of the liquid valve 113a, the pure water valve 114a, the gas valve 116a, and the valve of the drain pipe (not shown) based on the detection results of the flow meters 124 and 125, the detection results of the liquid level meter 121, and the detection results of the concentration meter 122. Thus, when the cleaning liquid having a predetermined liquid concentration is stored in the treatment tank 111, the liquid level of the cleaning liquid is maintained at a predetermined height. Based on the detection results of the liquid concentration provided by the concentration meter 122, the control device 10 feedback controls the amount of liquid supplied to the treatment tank 111 so that the liquid concentration of the cleaning liquid stored in the treatment tank 111 is within a predetermined range. For example, when the liquid concentration of the cleaning liquid detected by the concentration meter 122 is lower than the predetermined range, the control device 10 controls the liquid valve 113a to supply additional liquid to the treatment tank 111 from the liquid supply system (not shown) through the liquid piping 113.

[0074] In addition, the control device 10 controls the heater driving unit 118 based on the temperatures respectively provided from the first thermometer 123, the second thermometer 123a, the heater thermometer 118a and the outlet thermometer 118b to maintain the temperature of the cleaning liquid stored in the processing tank 111 at a predetermined temperature.

[0075] 3. Processing Information

[0076] For each of the chambers C1 to Cn included in the substrate processing apparatus 1, processing information indicating an action or state related to processing of the substrate W is determined. Figure 1 As shown by the thick solid arrow, the processing information is sent from the control device 10 of the substrate processing apparatus 1 to the auxiliary device 4 at a predetermined cycle. In addition, the processing information can also be sent from the control device 10 to the auxiliary device 4 in real time. In addition, the processing information can also be sent from the control device 10 to another computer different from the auxiliary device, and sent from the computer to the auxiliary device 4.

[0077] The processing information sent from the control device 10 of the substrate processing device 1 to the auxiliary device 4 includes "a. Chemical solution concentration", "b. Chemical solution flow rate", "c. Indoor temperature", "d. Chemical solution temperature", "e. Heater outlet temperature", "f. Heater surface temperature", "g. Concentration FB input amount", "h. Input valve opening", and "i. Heater on signal".

[0078] “a. Chemical liquid concentration” indicates the concentration of the cleaning liquid in the treatment tank 111 detected by the concentration meter 122. “b. Chemical liquid flow rate” indicates the flow rate of the chemical liquid flowing in the chemical liquid piping 113 detected by the flow meter 124. “c. Room temperature” indicates the temperature in the chamber detected by the first thermometer 123. “d. Chemical liquid temperature” indicates the temperature of the chemical liquid stored in the treatment tank 111 detected by the second thermometer 123a. “e. Heater outlet temperature” indicates the temperature of the chemical liquid near the cover outlet of the heater 117 detected by the outlet thermometer 118b. “f. Heater surface temperature” indicates the temperature of the surface of the heater 117 detected by the heater thermometer 118a. “g. Concentration FB input amount” is a value calculated by the control device 10 based on the flow rate detected by the flow meter 124, and indicates the amount of chemical liquid injected from the chemical liquid piping 113 into the treatment tank 111 so that the chemical liquid concentration of the cleaning liquid stored in the treatment tank 111 is within a predetermined range. “h. injection valve opening” indicates the opening of the chemical liquid valve 113 a provided in the chemical liquid pipe 113 . “i. heater on signal” is a signal output by the heater driving unit 118 for controlling the heater 117 .

[0079] 4. Chamber difference detection action

[0080] Figure 2 A conceptual diagram for explaining the operation of the substrate processing apparatus management system. Figure 2 In the substrate processing apparatus management system 100 of the present embodiment, a representative chamber Crp is predetermined from the plurality of chambers C1 to Cn of the substrate processing apparatus 1. Furthermore, in the substrate processing apparatus management system 100, the correlation between the plurality of processing information of the plurality of chambers C1 to Cn of the substrate processing apparatus 1 and the correlation between the plurality of processing information of the representative chamber Crp are compared, and the actions and states related to the substrate processing of the plurality of chambers C1 to Cn are determined based on the comparison result. Figure 2 In FIG. 1 , PI1 to PIn represent processing information corresponding to the plurality of chambers C1 to Cn, respectively.

[0081] The information analysis device 3 performs machine learning using the processing information PIrp corresponding to the representative cavity Crp to generate a model corresponding to the representative cavity Crp. Here, the model corresponding to the representative cavity Crp generated by the information analysis device 3 is called a representative model. Specifically, the information analysis device 3 uses the processing information PIrp to determine a plurality of combinations of two different processing information, and derives the correlation between the two processing information constituting each combination as an invariant relationship (hereinafter referred to as an invariant relationship). For example, the correlation between two processing information represents one as a function of the other as a variable, and the other as a function of the one as a variable. The invariant relationship derived by the information analysis device 3 by machine learning the plurality of processing information PIrp by the information analysis device 3 is a representative model.

[0082] The auxiliary device 4 uses the processing information PI1~PIn corresponding to the plurality of chambers C1~Cn, and for each of the plurality of chambers C1~Cn and for each of the plurality of combinations of two different processing information, compares the correlation between the two processing information constituting each combination with the invariant relationship determined in the representative model. The auxiliary device 4 compares each of the plurality of chambers C1~Cn with the representative model. Here, the comparison between chamber C1 and the representative model is used as an example for explanation. The auxiliary device 4 uses the processing information PI1 corresponding to chamber C1 to compare the correlation between the plurality of combinations of two different processing information with the invariant relationship determined in the representative model. Specifically, the auxiliary device 4 uses the processing information PI1 corresponding to chamber C1 to calculate the degree of deviation from the representative model as the deviation degree. In addition, based on the calculated deviation degree, the auxiliary device 4 calculates the degree of abnormality of chamber C1 as the abnormality score. That is, when the abnormality score is low, it means that the action of chamber C1 is close to the action of the representative chamber Crp, that is, it is acting normally. When the abnormality score is high, it means that the operation of the cavity C1 is different from the operation of the representative cavity Crp. If the operation is different from the operation of the representative cavity Crp, there is a high probability that the operation is abnormal.

[0083] <Calculation example of abnormality score>

[0084] Next, a specific example of the calculation method of the abnormality score is described. The representative model determines the correlation between a plurality of combinations of two different process information. In order to calculate the abnormality score of the chamber C1, the deviation of the process information PI1 corresponding to the chamber C1 is calculated. Figure 3 is a diagram for explaining a specific example of calculating the deviation. Figure 1The calculation example of the deviation of the combination of the processing information "h. injection valve opening" and "b. liquid medicine flow rate" is shown. In the following description, the data of "h. injection valve opening" is appropriately referred to as "h", and the data of "b. liquid medicine flow rate" is appropriately referred to as "b".

[0085] In order to calculate the deviation, reference data based on the invariable relationship between "h. injection valve opening" and "b. chemical solution flow rate" is required. Therefore, before the actual processing of the substrate W in the substrate processing device 1, the representative model generated by the information analysis device 3 is retained in the auxiliary device 4. The representative model determines the correlation between the "h" data and the "b" data when the representative chamber Crp operates normally according to the predetermined processing procedure.

[0086] For example, when the substrate processing apparatus 1 actually operates normally, the representative model is generated by the information analysis apparatus 3 based on the process information PIrp corresponding to the representative chamber Crp selected from the plurality of chambers C1 to Cn.

[0087] exist Figure 3 In the upper part, an example of the time change of the "h" data and the "b" data representing the model is shown in a graph. In the graph of the "h" data, the horizontal axis represents time, and the vertical axis represents the opening of the liquid medicine valve 113a provided in the liquid medicine piping 113. In the graph of the "b" data, the horizontal axis represents time, and the vertical axis represents the flow rate of the liquid medicine flowing in the liquid medicine piping 113 detected by the flowmeter 124. The horizontal axis (time axis) is the same between the graph of the "h" data and the graph of the "b" data.

[0088] according to Figure 3 As can be seen from the two upper graphs, as the opening value of the liquid medicine valve 113a increases, the value of the flow rate of the liquid medicine flowing in the liquid medicine piping 113 detected by the flow meter 124 also increases at a substantially constant ratio. That is, there is a correlation between the opening value of the liquid medicine valve 113 and the value of the flow rate of the liquid medicine flowing in the liquid medicine piping 113. When the representative chamber Crp operates normally, the correlation between each combination of the plurality of processing information is equal to the correlation determined in the representative model.

[0089] In this state, the substrate W is processed in the chamber C1, and the actual "h" data and "b" data are collected by the auxiliary device 4. Figure 3 In the center, an example of time changes of the “h” data and the “b” data of the chamber C1 is shown in a graph.

[0090] The correlation between the "h" data and the "b" data of chamber C1 is compared with the correlation between the "h" data and the "b" data of the representative chamber Crp. Specifically, the "b" data is predicted from the "h" data of chamber C1 based on the representative model. In other words, the "b" data is predicted from the "h" data of chamber C1 based on the correlation between the "b" data observed from the "h" data determined from the representative model. In addition, the "h" data is predicted from the "b" data of chamber C1 based on the representative model. In other words, the "h" data is predicted from the "b" data of chamber C1 based on the correlation between the "h" data observed from the "b" data determined from the representative model.

[0091] exist Figure 3 In the lower part, a graph is shown showing an example of the time variation of the "h" data and the "b" data predicted based on the representative model. Figure 3 In the lower graph, the predicted “h” data and “b” data are indicated by solid lines, and the “h” data and “b” data of the chamber C1 are indicated by dotted lines.

[0092] When chamber C1 performs the same action as the representative chamber Crp, the "h" data of chamber C1 is consistent or approximately consistent with the predicted "b" data. In addition, the "b" data of chamber C1 is consistent or approximately consistent with the predicted "h" data. However, when chamber C1 performs an action different from that of the representative chamber Crp, there is a high possibility that the "h" data of chamber C1 deviates from the predicted "h" data. In addition, there is a high possibility that the "b" data of chamber C1 deviates from the predicted "b" data. The degree of deviation is greater the greater the degree of difference between the action of chamber C1 and the action of the representative chamber Crp, and smaller the smaller the degree of difference between the action of chamber C1 and the action of the representative chamber Crp.

[0093] Therefore, in this embodiment, for the process information PI1 corresponding to the chamber C1, the difference from the predicted value predicted from the representative model is calculated as the deviation. Figure 3 In the example, when calculating the deviation at a certain moment, the auxiliary device 4 calculates the difference between the "h" data of the chamber C1 and the predicted "h" data as the deviation. In addition, the auxiliary device 4 calculates the difference between the "b" data of the chamber C1 and the predicted "b" data as the deviation.

[0094] Figure 4 : is a diagram showing an example of a deviation table. The deviation table is a table showing the deviation of each combination for all combinations of processing information. The auxiliary device 4 calculates the above deviation for all combinations of processing information. Figure 4The multiple values ​​arranged in the right row of each of the processing information "a" to "i" in the left column of the deviation table represent the deviation between the processing information predicted based on the processing information "a" to "i" in the upper column and the actually obtained processing information. The multiple values ​​arranged in the lower column of each of the processing information "a" to "i" in the upper column of the deviation table represent the deviation between the processing information predicted based on the processing information "a" to "i" in the left column and the actually obtained processing information.

[0095] For example, the value "10" in the column at the intersection of the right row of the process information "a" in the left vertical column and the lower column of the process information "b" in the upper horizontal column indicates the deviation between the predicted value of the process information "a" predicted based on the process information "b" and the process information "a" corresponding to the chamber C1. In addition, the value "11" in the column at the intersection of the lower column of the process information "a" in the upper horizontal column and the right row of the process information "b" in the left vertical column indicates the deviation between the predicted value of the process information "b" predicted based on the process information "a" and the process information "b" corresponding to the chamber C1.

[0096] Figure 4 The deviation table shown shows the plurality of deviations calculated for all combinations of processing information associated with the chamber C1. When all deviations are calculated, the auxiliary device 4 calculates the sum of the plurality of deviations calculated as the abnormality score corresponding to the chamber C1. Figure 4 In the Deviation table shown, the anomaly score is 256.

[0097] 5. Example of functional structure of auxiliary device 4

[0098] Figure 5 A block diagram for explaining an example of the functional structure of a substrate processing apparatus management system. Figure 5 The control device 10 of the substrate processing apparatus 1 includes a processing information acquisition unit 11 and a processing information transmission unit 13. The functions of the control device 10 are realized by the CPU of the control device executing a control program stored in a memory.

[0099] The processing information acquisition unit 11 acquires processing information PI1-PIn from each of the plurality of chambers C1-Cn. Here, the case of acquiring processing information PI1 from chamber C1 is taken as an example for explanation. The processing information acquisition unit 11 acquires processing information PI1 from chamber C1 at a predetermined time interval. Therefore, the plurality of processing information PI1 is time series data in which a value is determined for each moment determined at a predetermined time interval. The processing information sending unit 13 sends the processing information PI1-PIn respectively acquired from chambers C1-Cn to the auxiliary device 4. Since chambers C1-Cn process the substrate according to the processing procedure, the processing information PI1-PIn may also be time series data collected during the period when chambers C1-Cn process the substrate according to the processing procedure.

[0100] The support device 4 includes an information collecting unit 41, a comparing unit 43, an object determining unit 45, a model receiving unit 47, and a support unit 49. The functions of the support device 4 are realized by the CPU of the support device 4 executing a support information generating program stored in a memory.

[0101] The information collecting unit 41 collects processing information PI1-PIn indicating the operation and status of each of the plurality of chambers C1-Cn in processing a substrate. The information collecting unit 41 receives the plurality of processing information PI1-PIn from the control device 10, inputs the received plurality of processing information PI1-PIn to the comparison unit 43, and transmits it to the information analysis device 3.

[0102] The model receiving unit 47 receives the representative model from the information analyzing device 3, and outputs the received representative model to the comparing unit 43. The representative model determines the correlation relationship of the processing information PIrp corresponding to the representative cavity Crp.

[0103] The comparison unit 43 compares the correlation between each of the processing information PI1 to Pin corresponding to the plurality of chambers C1 to Cn with the correlation of the representative model, and outputs the comparison result to the object determination unit 45. For example, the processing information PI1 corresponding to the chamber C1 is described. The processing information PI includes a plurality of data of "a" data to "i" data. The comparison unit 43 uses the representative model to calculate the expected values ​​corresponding to the "a" data to "i" data of the processing information PI1, and calculates the difference between the "a" data to "i" data and the predicted value as the deviation. In addition, the comparison unit 43 calculates the total of the plurality of deviations calculated corresponding to the processing information PI1 as an abnormality score.

[0104] The target determination unit 45 determines the chamber to be the maintenance target based on the abnormality score calculated by the comparison unit 43. For example, the target determination unit 45 compares the abnormality score with a predetermined threshold value for each of the plurality of chambers C1 to Cn. The target determination unit 45 determines the chamber whose abnormality score is greater than the predetermined threshold value among the plurality of chambers C1 to Cn as the chamber to be the maintenance target.

[0105] The auxiliary unit 49 generates auxiliary information related to the maintenance work of the chamber determined as the maintenance object by the object determination unit 45. Here, the case where the chamber C1 is determined as the maintenance object is described as an example. The auxiliary unit 49 uses the chamber identification information for identifying the chamber C1 determined as the maintenance object as the auxiliary information, and notifies the maintenance operator. Therefore, the maintenance operator is notified that the chamber C1 needs to be maintained.

[0106] In addition, the auxiliary unit 49 displays the plurality of deviations calculated by the comparison unit 43 for the processing information PI1 for the chamber C1 as auxiliary information. Figure 4 The deviation table shown is notified to the maintenance operator as auxiliary information. Thus, the maintenance operator can be notified of information for determining which component element needs to be adjusted among the plurality of components included in the chamber C1.

[0107] In order to notify the maintenance worker of the auxiliary information, the auxiliary unit 49 may display the auxiliary information on a display unit included in the auxiliary device 4 or may send an e-mail including the auxiliary information to the maintenance worker.

[0108] according to Figure 4 The deviation table shown, for example, can grasp the deviation of the chemical solution concentration based on the deviation of the row and column of "a. Chemical solution concentration". In addition, the deviation of the chemical solution temperature can be grasped based on the deviation of the row and column of "d. Chemical solution temperature". In addition, whether the temperature rise is stable can be grasped based on the deviation of the row and column of "e. Heater outlet temperature" and "f. Heater surface temperature". In addition, whether the feedback control of the chemical solution concentration is stable can be grasped based on the deviation of the row and column of "g. Concentration FB input amount". In addition, whether the increase of the chemical solution flow rate is stable can be grasped based on the deviation of the row and column of "b. Chemical solution flow rate" and "h. Input valve opening". In addition, the delay in the timing of heater control can be grasped based on the deviation of the row and column of "i. Heater on signal".

[0109] The information analysis device 3 includes a representative information receiving unit 31, a model generating unit 33, and a model transmitting unit 35. The functions of the information analysis device 3 are realized by the CPU of the information analysis device 3 executing a model generating program stored in a memory.

[0110] The representative information receiving unit 31 receives a plurality of processing information PIrp corresponding to the representative chamber Crp. The representative chamber Crp is a chamber selected from a plurality of chambers C1 to Cn. The representative chamber Crp is selected by an administrator or a maintenance operator who manages the substrate processing device 1. For example, the substrate processing device 1 is driven to perform processing on the substrate W, and for each of the plurality of chambers C1 to Cn, the result of inspecting the substrate W processed by the chamber is taken as a processing result and stored in association with the chamber. The administrator or the maintenance operator can refer to the processing result and select the chamber with the best processing result from the plurality of chambers C1 to Cn as the representative chamber. The processing information PIrp received by the representative information receiving unit 31 is processing information corresponding to the processing result that the maintenance operator refers to for selecting the representative chamber Crp.

[0111] The model generation unit 33 generates a representative model by mechanically learning the processing information PIrp corresponding to the representative cavity Crp. Specifically, the processing information PIrp includes a plurality of data of "a" data to "i" data. The model generation unit 33 learns the correlation for each of two different groups of the plurality of data included in the processing information PIrp. The model generation unit 33 outputs the generated representative model to the model transmission unit 35. The model transmission unit 35 transmits the representative model to the auxiliary device 4.

[0112] Figure 6 2 is a flowchart showing an example of the flow of the processing information transmission process. The processing information transmission process is a process executed by the CPU of the control device 10 of the substrate processing apparatus 1 by executing a processing information transmission program stored in a memory. Figure 6 The control device 10 acquires the processing information of each of the plurality of chambers C1 to Cn (step S11). The control device 10 acquires the processing information PI1 from the chamber C1 at a predetermined cycle, for example.

[0113] In the next step S12, it is determined whether a specified time has passed. The specified time may be, for example, the time for chamber C1 to process a substrate according to the processing procedure. If the specified time has passed, the process proceeds to step S13, and if the specified time has not passed, the process returns to step S11. The processes of step S11 and step S12 are performed for each of the plurality of chambers C1 to Cn. Therefore, processing information PI1 to PIn corresponding to the plurality of chambers C1 to Cn is obtained. When a plurality of specified cycles are repeated a plurality of times within a specified time period, the processing information PI1 is a collection of processing information of the same number as the number of times the specified cycle is repeated.

[0114] In step S13, processing information PI1~PIn corresponding to the plurality of chambers C1~Cn is sent to the auxiliary device 4, and the processing proceeds to step S14. In step S14, it is determined whether the processing of the substrate processing device 1 is stopped. If the processing has stopped, the processing is terminated, and if the processing has not stopped, the processing returns to step S11. Therefore, while the substrate processing device 1 is executing the processing, processing information PI1~PIn corresponding to the plurality of chambers C1~Cn is sent to the auxiliary device 4. In addition, instead of sending the processing information PI1~PIn every prescribed time, the control device 10 may also send the processing information PI1~PIn collected so far in a summary after a period longer than the prescribed time, for example, at a time specified by the administrator of the substrate processing device 1.

[0115] Figure 7 2 is a flowchart showing an example of the flow of the model generation process. The model generation process is a process performed by the CPU of the information analysis device 3 by executing a model generation program stored in the memory. Figure 7 The CPU of the information analysis device 3 determines whether a representative model generation instruction is received (step S21). The CPU is in a standby state until a representative model generation instruction is received (no in step S21). If a model generation instruction is received (yes in step S21), the process proceeds to step S22.

[0116] In the next step S22, the processing information PI1-PIn is received, and the process proceeds to step S23. The auxiliary device 4 is requested to send the processing information PI1-PIn, and the processing information PI1-PIn sent from the auxiliary device 4 is received. The processing information PI1-Pin is the processing information collected by the auxiliary device 4 during the normal operation of the substrate processing apparatus 1.

[0117] In step S23, a representative chamber is determined, and the process proceeds to step S24. The manager or the maintenance operator determines a chamber selected from the plurality of chambers C1 to Cn as the representative chamber.

[0118] In step S24, a representative model is generated, and the process proceeds to step S25. In step S22, the process information PIrp corresponding to the representative cavity Crp determined in step S23 is extracted from the received process information PI1 to PIn. The process information PIrp is machine-learned to learn the correlation between two different "a" data to "i" data included in the process information PIrp, thereby generating a representative model. In step S25, the representative model is sent to the auxiliary device 4, and the process ends.

[0119] Figure 82 is a flowchart showing an example of the flow of the inter-chamber performance comparison process. The auxiliary information generation process is a process executed by the CPU included in the auxiliary device 4 by executing an inter-chamber performance comparison program stored in a memory.

[0120] Reference Figure 8 The CPU of the auxiliary device 4 determines whether a chamber analysis command has been received (step S31). The CPU is in a standby state until a chamber analysis command is received (No in step S31). If a chamber analysis command is received (Yes in step S31), the process proceeds to step S32.

[0121] In step S32, the representative model is received, and the process proceeds to step S33. The information analysis device 3 is requested to send the representative model, and receives the representative model sent from the information analysis device 3.

[0122] In step S33, a chamber Ck to be processed is selected from the plurality of chambers C1 to Cn, and the process proceeds to step S34. Here, k is an integer from 1 to n. In step S34, processing information PIk corresponding to the chamber Ck selected as the processing target in step S33 is selected from the plurality of processing information PI1 to PIn.

[0123] In the next step S35, the deviation between the chamber Ck selected as the processing object and the representative model is calculated. Specifically, for the "a" data to "i" data included in the processing information PIk corresponding to the chamber Ck selected as the processing object, the representative model is used to obtain the predicted value, and the difference between the predicted value and the "a" data to "i" data is calculated as the deviation. In the next step S36, the abnormality score is calculated. In step S35, the total of the multiple deviations calculated for the "a" data to "i" data included in the processing information PIk is calculated as the abnormality score.

[0124] In step S37, it is determined whether there is a chamber that was not selected as a processing target in step S33. If there is an unselected chamber, the process returns to step S33, and if there is no unselected chamber, the process proceeds to step S38.

[0125] In step S38, the chambers with abnormal scores above the threshold are extracted, and the process proceeds to step S39. In step S39, auxiliary information is generated and output, and the process ends. The auxiliary information includes chamber identification information or a deviation table for identifying chambers with abnormal scores above the threshold. In step S35, the deviation table includes deviations corresponding to the "a" data to "i" data included in the processing information calculated for the chambers with abnormal scores above the threshold.

[0126] The maintenance worker who sees the auxiliary information can know the chamber that needs maintenance from the chamber identification information included in the maintenance information. The abnormality score indicates the degree to which the chamber identified by the chamber identification information included in the maintenance information differs from the processing action and state of the representative chamber. The so-called abnormality includes an abnormality to the extent that the processing of the substrate needs to be stopped and an abnormality to the extent that the processing does not need to be stopped but needs to be improved. The maintenance worker can determine the component that becomes the maintenance object by referring to the deviation table included in the maintenance information.

[0127] 6. First Modification

[0128] In the above embodiment, the calculation Figure 4 The total of the multiple deviations shown in the deviation table is used as the abnormality score. Figure 4 Among the multiple combinations of "a" data to "i" data included in the processing information represented by the deviation table shown, when understanding the abnormality level of the substrate processing device 1, there are combinations that need to be particularly valued and combinations that do not need to be valued. In the first variation, when understanding the abnormality level of the substrate processing device 1, the combination of "a" data to "i" data included in the processing information is given a greater weight as the importance is greater to calculate the abnormality score. Specifically, multiple weighting tables corresponding to multiple combinations of multiple processing information are used.

[0129] Fig. 9 : is a diagram showing an example of a weighting table. The weighting table assigns weights of magnitude corresponding to the relationship in calculating the abnormality score to the combinations of "a" data to "i" data included in the processing information.

[0130] For example, the combination of "a. Chemical liquid concentration" and "g. Concentration FB input amount" can be said to be a combination with a very high relationship in calculating the abnormality score in order to detect the difference from the representative model. Therefore, the weight "6" is assigned. In addition, the combination of "a. Chemical liquid concentration" and any one of "b. Chemical liquid flow rate", "h. Input valve opening" and "i. Heater on signal" can be said to be a combination with the second highest relationship in calculating the abnormality score in order to detect the difference from the representative model. Therefore, the weight "5" is assigned. In addition, the combination of "a. Chemical liquid concentration" and any one of "c. Indoor temperature" and "d. Chemical liquid temperature" can be said to be a combination with a high degree of relationship in calculating the abnormality score in order to detect the difference from the representative model. Therefore, the weight "2" is assigned. Moreover, the combination of "a. Chemical liquid concentration" and any one of "e. Heater outlet temperature" and "f. Heater surface temperature" can be said to be a combination with a low relationship in calculating the abnormality score in order to detect the difference from the representative model. Therefore, the weight "1" is assigned.

[0131] In the first variation, based on Fig. 9The weights assigned to the combinations of "a" data to "i" data included in the processing information in the weighting table shown in FIG. Figure 4 The deviations determined by each combination of "a" data to "i" data included in the processing information determined in the deviation table shown in FIG. Figure 4 The deviation determined by each combination of "a" data to "i" data included in the processing information determined in the deviation table shown in FIG. 1 is changed to multiply the deviation determined by Fig. 9 The value (multiplication value) obtained by assigning weights to each combination of "a" data to "i" data included in the processing information in the weighted table shown. Then, the sum of the multiple deviations changed in consideration of the weights is calculated as the abnormality score. Thus, the calculated abnormality score is 968.

[0132] Thus, in the substrate processing apparatus management system 100 of the first variation, the abnormality score is changed to a value obtained by weighting the deviation. Thus, the maintenance operator of the substrate processing apparatus 1 can more appropriately grasp the degree of abnormality of each of the plurality of chambers C1 to Cn of the substrate processing apparatus 1 by referring to the abnormality score calculated based on the weighted deviation.

[0133] 7. Second Modification

[0134] Fig.10 1 is a block diagram for explaining an example of the functional structure of the substrate processing apparatus management system in the second modification. The substrate processing apparatus management system 100 in the second modification automatically determines a representative chamber. Fig.10 , and Figure 5 The differences from the block diagram shown are that the representative information receiving unit 31 is changed to an information receiving unit 31A and a representative determination unit 37 is added. Figure 5 The structures shown are the same, so they will not be described again here.

[0135] The information receiving unit 31A receives the processing information PI1 to PIn corresponding to the plurality of chambers C1 to Cn, respectively, and outputs the processing information PI1 to PIn to the representative determining unit 37 .

[0136] The representative determination unit 37 determines a representative chamber from the plurality of chambers C1 to Cn based on the processing information PI1 to PIn. Specifically, the average (average processing information) of the plurality of chambers C1 to Cn is calculated for the "a" data to "i" data included in the processing information according to the processing information PI1 to Pin. The representative determination unit 37 generates an average model by machine learning the average of the "a" data, the average of the "b" data to the average of the "i" data, and the average model determines the correlation between the average of the "a" data and the average of the "b" data to the average of the "i" data.

[0137] Furthermore, the representative determination unit 37 determines the model that is closest to the average model among the multiple chambers C1 to Cn as the representative model. Specifically, the average model is used to calculate the abnormality score based on the processing information PI1 to Pin. For example, when explaining the processing information PI1, the representative determination unit 37 calculates the predicted value for each of the "a" data to "i" data included in the processing information PI1 using the average model, and calculates the difference between the "a" data to "i" data and the predicted value as the deviation. The representative determination unit 37 calculates the total of the deviations calculated for the multiple combinations of the "a" data to "i" data included in the processing information as the abnormality score. The representative determination unit 37 determines the chamber with the smallest abnormality score among the multiple chambers C1 to Cn as the representative chamber.

[0138] Fig.11 1 is a flowchart showing an example of the flow of the representative chamber determination process. The representative chamber determination process is performed by the CPU of the information analysis device 3 executing a model generation program stored in a memory. Figure 7 The processing performed in step S23 of the model generation processing shown in FIG. Fig.11 The CPU of the information analysis device 3 calculates average processing information based on the processing information PI1 to Pin received in step S22 (step S51), and the process proceeds to step S52. The processing information PI1 to Pin respectively includes "a" data to "i" data. The average processing information is the average of the plurality of chambers C1 to Cn calculated for each of the "a" data to "i" data.

[0139] In step S52, an average model is generated by machine learning the average processing information. Specifically, the correlation between two different average processing information in the average processing information is machine learned to generate the average model. In step S53, a chamber Ck to be processed is selected from a plurality of chambers C1 to Cn, and the process proceeds to step S54. Here, k is an integer from 1 to n. In step S54, processing information PIk corresponding to the chamber Ck selected as the processing object in step S53 is selected from the processing information PI1 to PIn.

[0140] In the next step S55, the deviation between the chamber Ck selected as the processing object and the average model is calculated. Specifically, for each of the "a" data to "i" data included in the processing information PIk corresponding to the chamber Ck selected as the processing object, a predicted value is obtained using the average model, and the difference from the predicted value is calculated as the deviation. In the next step S56, an abnormality score is calculated. In step S55, the total of the deviations calculated for each of the "a" data to "i" data included in the processing information PIk is calculated as the abnormality score.

[0141] In step S57, it is determined whether there is a cavity that was not selected as a processing target in step S53. If there is an unselected cavity, the process returns to step S53, and if there is no unselected cavity, the process proceeds to step S58. In step S58, the cavity with the smallest abnormality score is determined as the representative cavity, and the process returns to the representative model generation process.

[0142] In the substrate processing system of the second variation, since the representative chamber is automatically determined, the manager or maintenance operator does not need to refer to the processing result to determine the representative chamber. Therefore, it is possible to easily detect the difference between chambers. In particular, the representative chamber can be determined at a stage where the processing result of the processed substrate cannot be obtained, or at a stage where the processing state after the maintenance work of the substrate processing device 1 cannot be evaluated. Thereafter, at a stage where the processing result of the processed substrate can be obtained, the manager or maintenance operator can select the representative chamber by referring to the processing result.

[0143] 8. Variation 3

[0144] The substrate processing system of the third variation performs duplication processing on the plurality of processing information, compares the correlation between the plurality of processing information of the plurality of chambers and the correlation between the plurality of processing information representing the chamber. Furthermore, the substrate processing system of the third variation performs logarithmic operation processing on the plurality of processing information to obtain the correlation between the plurality of processing information.

[0145] Fig.12 A block diagram for explaining an example of the functional structure of the substrate processing apparatus management system in the third variation. Fig.12 ,and Figure 5 The difference between the block diagram shown is that the first duplexing unit 51 and the first logarithmic operation unit 53 are added to the information analysis device 3, and the second duplexing unit 61 and the second logarithmic operation unit 63 are added to the auxiliary device 4. Figure 5 The structures shown are the same, so they will not be described again here.

[0146] The first duplexing unit 51 receives the processing information PIrp corresponding to the representative cavity Crp from the representative information receiving unit 31. The first duplexing unit 51 performs duplexing on the processing information PIrp. The duplexing is a process of combining reference information predetermined for at least one target processing information among the plurality of processing information with the plurality of processing information as new processing information.

[0147] The first duplexing unit 51 classifies the plurality of processing information PIrp corresponding to the representative chamber Crp input from the representative information receiving unit 31 into an object group and a reference group. The reference group includes at least one of the plurality of processing information PIrp. For example, one of the plurality of processing information PIrp input from the representative information receiving unit 31 may be classified as the reference group, or a plurality of the plurality of processing information PIrp may be classified as the reference group. The plurality of processing information PIrp not classified as the reference group among the plurality of processing information PIrp input from the representative information receiving unit 31 is classified as the object group.

[0148] The processing information PIrp includes "a" data to "i" data. The first duplexing unit 51 generates processing information CPIrp by combining at least one reference information of the "a" data to "i" data included in the processing information PIrp classified as the reference group with the "a" data to "i" data included in the processing information PIrp classified as the object group as new processing information.

[0149] One or more of the "a" data to "i" data included in the processing information PIrp is predetermined as the object of duplex processing, i.e., the object processing information. The object processing information is preferably the processing information that has no correlation or little correlation with any other processing information among the "a" data to "i" data included in the processing information PIrp. Hereinafter, the data included in the processing information PIrp classified as the reference group is referred to as "a'" data to "i'" data.

[0150] In this embodiment, the case where all the "a" data to "i" data included in the processing information PIrp classified as the object group are object processing information for duplex processing is described as an example. In this case, all the "a'" data to "i'" data included in the processing information PIrp classified as the reference group are reference information. Therefore, the processing information CPIrp after the duplex processing of the processing information PIrp includes 18 types of processing information, including "a" data, "a'" data to "i" data, and "i'" data.

[0151] The first logarithmic operation unit 53 inputs the processing information CPIrp after duplexing from the first duplexing unit 51. The first logarithmic operation unit 53 outputs the plurality of logarithms after logarithmically converting the "a" data, "a'" data to "i" data, and "i'" data included in the processing information CPIrp to the model generation unit 33. In addition, instead of logarithmically converting all of the "a" data, "a'" data to "i" data, and "i'" data included in the processing information CPIrp, only the processing information predetermined among the "a" data, "a'" data to "i" data, and "i'" data may be logarithmically converted.

[0152] The model generation unit 33 generates a representative model by performing machine learning on a plurality of logarithms corresponding to the processing information CPIrp input from the first logarithm calculation unit 53 .

[0153] The plurality of processing information PI1 to PIn corresponding to the plurality of chambers C1 to Cn are input from the information collecting unit 41 to the second duplexing unit 61. The second duplexing unit 61 performs duplexing on each of the plurality of processing information PI1 to Pin. Since the duplexing of each of the processing information PI1 to Pin is the same, only the duplexing of the processing information PI1 will be described here.

[0154] The second duplexing unit 61 combines the reference information predetermined for at least one object processing information among the "a" data to the "i" data included in the processing information PI1 as new processing information with the "a" data to the "i" data. The object processing information is one or more of the "a" data to the "i" data included in the processing information PI1 that are predetermined as objects for duplexing. The object processing information is the same as the object processing information determined when the representative model is generated. The reference information is the processing information PIrp representing the cavity Crp. The reference information may also be, for example, the processing information PIrp representing the cavity Crp classified into the reference group determined by the first duplexing unit 51.

[0155] In this embodiment, when generating the representative model, all the "a" data to "i" data included in the processing information PIrp classified into the object group are used as the object processing information to be processed by duplexing. Therefore, the second duplexing unit 61 uses all the "a" data to "i" data included in the processing information PI1 as the object processing information to be processed by duplexing. In addition, the second duplexing unit 61 uses all the "a'" data to "i'" data included in the processing information PIrp representing the cavity Crp as reference information.

[0156] The second duplexing unit 61 generates processing information CPI1 by combining "a'" to "i'" data included in processing information PIrp with "a" to "i" data included in processing information PI1. Processing information CPI1 includes 18 types of processing information, "a" data, "a'" to "i" data, and "i'" data.

[0157] The second logarithm operation unit 63 receives the duplexed processing information CPI1 from the second duplexing unit 61. The second logarithm operation unit 63 performs logarithmic conversion on the "a" data, "a'" data to "i" data, and "i'" data included in the processing information CPI1, and outputs the logarithms thereof to the comparison unit 43.

[0158] The comparison unit 43 compares the correlation between the processing information CPI1~CPIn corresponding to the plurality of chambers C1~Cn and the correlation of the representative model, and outputs the comparison result to the object determination unit 45. For example, the processing information CPI1 corresponding to the chamber C1 is described. The processing information CPI1 includes "a" data, "a'" data~"i" data, and "i'" data. The comparison unit 43 uses the representative model to calculate the expected value of the logarithm for the plurality of logarithms corresponding to the "a" data, "a'" data~"i" data, and "i'" data contained in the processing information CPI1, and calculates the difference between the logarithm and the corresponding predicted value as the deviation. Furthermore, the comparison unit 43 calculates the total of the plurality of deviations calculated corresponding to the processing information CPI1 as the abnormality score.

[0159] Fig.13 : is a diagram showing an example of a deviation table in the third variation. The deviation table is a table showing the deviation for each combination of all combinations of processing information. The auxiliary device 4 calculates the above deviation for all combinations of processing information. Fig.13 , the multiple values ​​arranged in the right row of each of the processing information "a" data, "a'" data to "i" data, and "i'" data in the vertical column on the left side of the deviation table represent the deviation between the processing information predicted based on the processing information "a" data, "a'" data to "i" data, and "i'" data in the horizontal column on the upper side and the actually obtained processing information. The multiple values ​​arranged in the lower column of each of the processing information "a" data, "a'" data to "i" data, and "i'" data in the horizontal column on the upper side of the deviation table represent the deviation between the processing information predicted based on the processing information "a" data, "a'" data to "i" data, and "i'" data in the vertical column on the left side and the actually obtained processing information.

[0160] Fig.14 : is a flowchart showing an example of the flow of the model generation process in the third variation. Fig.14 ,and Figure 7 The difference in the model generation process shown is that steps S61 and S62 are added between step S22 and step S23. Figure 7 The model generation process shown is the same, so it will not be repeated here.

[0161] In step S61, duplex processing is performed, and the processing proceeds to step S62. The plurality of processing information PIrp received in step S22 is classified into a target group and a reference group. Furthermore, the "a'" data to "i'" data included in the processing information PIrp classified as the reference group is used as new processing information, and the "a" data to "i" data included in the processing information PIrp classified as the target group is used as new processing information.

[0162] In step S62, the "a" data, "a'" data to "i" data, and "i'" data included in the duplexed processing information CPIrp are logarithmically converted, and the process proceeds to step S23. In step S23, the representative cavity Crp is determined, and the process proceeds to step S24.

[0163] In step 24, the following machine learning is performed: duplex processing is performed on the processing information PIrp corresponding to the representative cavity Crp, the duplex processing information CPIrp is logarithmically converted, and the plurality of logarithms after the logarithm conversion is machine learned. For the logarithms of the "a" data, "a'" data, ~ "i" data, and "i'" data included in the duplex processing information CPIrp, the correlation between two different logarithms is learned to generate a representative model.

[0164] Fig.15 FIG. 2 is a flowchart showing an example of the flow of the inter-chamber performance comparison process in the third variation. Fig.15 ,and Figure 8 The difference between the chamber performance comparison process shown is that step S71 and step S72 are added between step S34 and step S35. Figure 8 The model generation process shown is the same, so it will not be repeated here.

[0165] In step S71, duplex processing is performed, and the process proceeds to step S72. The process information PIk of the chamber Ck selected in step S34 is duplicated. The reference information is combined as new process information with the "a" data to "i" data included in the process information PIk. The reference information is the "a'" data to "i'" data included in the process information PIrp representing the chamber Crp.

[0166] In step S72, the "a" data, "a'" data to "i" data, and "i'" data included in the duplicated processing information are logarithmically converted, and the process proceeds to step S35. The processing information CPIk obtained by duplexing the processing information PIk corresponding to the chamber Ck is logarithmically converted.

[0167] In step S35, the degree of deviation between the chamber Ck selected as the processing object and the representative model is calculated. Specifically, the representative model is used to obtain the predicted value for each logarithm of the "a" data, "a'" data to "i" data, "i'" data, and "a" data to "i" data contained in the processing information CPIk corresponding to the chamber Ck selected as the processing object after duplexing, and the difference between the logarithm and the predicted value is calculated as the degree of deviation.

[0168] 9. Effects of implementation methods

[0169] The auxiliary device 4 according to the above-described embodiment can assist the maintenance work of the substrate processing apparatus 1, which has a plurality of chambers C1 to Cn for processing substrates W. The auxiliary device 4 acquires processing information PI1 to PIn, which indicates an action or state related to the processing of the substrate W in each of the plurality of chambers C1 to Cn, and generates auxiliary information related to the maintenance work of the other chambers based on comparison information comparing the correlation between the "a" data to "i" data included in the processing information of the representative chamber Crp predetermined from the plurality of chambers C1 to Cn with the correlation between the "a" data to "i" data included in the processing information of the other chambers. Since the correlation between the "a" data to "i" data included in the processing information is compared between the representative chamber Crp and the other chambers, the difference in the action or state related to the processing of the substrate W can be detected between the representative chamber Crp and the other chambers. In addition, since auxiliary information related to maintenance work of other chambers is generated based on comparison information comparing correlations between data "a" to data "i" included in processing information between the representative chamber Crp and other chambers, information indicating performance differences between other chambers and the representative chamber can be generated. As a result, auxiliary information indicating performance differences between the plurality of chambers C1 to Cn included in the substrate processing apparatus 1 can be notified.

[0170] In addition, among all the plurality of chambers C1 to Cn, the adjustment of the plurality of chambers C1 to Cn that makes the result of processing the substrate W in a good state is preferably to adjust the performance of the chambers with poor performance to be close to the performance of the chambers with good performance. In the auxiliary device 4, by selecting the chamber with good performance as the representative chamber Crp, the chamber identification information and the deviation table of the chambers with poor performance compared to the representative chamber are generated as auxiliary information. Therefore, auxiliary information for making the performance of the chambers with poor performance compared to the representative chamber close to the performance of the representative chamber can be generated.

[0171] In the auxiliary device 4 of the first variation, the comparison information is information for weighted comparison of the correlations among the "a" data to the "i" data included in the processing information. Therefore, since the correlations among the "a" data to the "i" data included in the processing information representing the actions or states associated with the processing of the substrate W are weighted, a difference in the actions or states that have a great influence on the performance of the representative chamber Crp in processing the substrate W can be detected.

[0172] In the auxiliary device 4 of the second variation, one of the plurality of chambers C1 to Cn having the closest correlation to the average correlation between the plurality of chambers C1 to Cn of the "a" data to "i" data included in the processing information is determined as the representative chamber. Therefore, from the plurality of chambers C1 to Cn, the chamber whose action or state associated with the processing of the substrate W is close to the average is determined as the representative chamber Crp, so that the representative chamber Crp can be automatically determined. In particular, even at the stage where the processing results of the substrates W processed by the plurality of chambers C1 to Cn have not yet been obtained, the representative chamber Crp can be determined.

[0173] In addition, the plurality of chambers C1 to Cn respectively include: a liquid medicine valve 113a that discharges liquid medicine; and a flow meter 124 that measures the flow rate of the liquid discharged from the liquid medicine valve 113a, and the "a" data to "i" data included in the processing information include: "h. injection valve opening", which indicates the opening amount input to the discharge valve for controlling the opening amount of the liquid medicine valve 113a; and "b. liquid medicine flow rate", which indicates the flow rate measured by the flow meter 124. Therefore, based on the difference in the correlation between "h. injection valve opening" and "b. liquid medicine flow rate" between the representative chamber Crp and the other chambers, auxiliary information related to the maintenance work of the liquid medicine valve 113a of the other chambers can be generated. The auxiliary information includes a deviation table. The maintenance operator can observe the deviation table to determine whether "b. liquid medicine flow rate" is stable, and can also determine the action delay of "h. injection valve opening".

[0174] In addition, the plurality of chambers C1 to Cn respectively include: a liquid medicine valve 113a that ejects liquid medicine; and a concentration meter 122 that measures the concentration of the liquid medicine, and the "a" data to "i" data included in the processing information include: "h. Opening of injection valve", which indicates the opening amount input to the ejection valve for controlling the opening amount of the liquid medicine valve 113a; and "a. Liquid medicine concentration", which is measured by the concentration meter 122. Therefore, based on the difference in the correlation between "h. Opening of injection valve" and "a. Liquid medicine concentration" between the representative chamber Crp and other chambers, auxiliary information related to maintenance work on other chambers can be generated. The auxiliary information includes a deviation table. The maintenance operator can observe the deviation table to determine whether the "a. Liquid medicine concentration" is stable, and can also determine the action delay of the "h. Opening of injection valve".

[0175] In addition, the plurality of chambers C1 to Cn respectively include: a concentration meter 122 for measuring the concentration of the chemical solution; and a first thermometer 123 for measuring the indoor temperature of the chamber, and the "a" data to "i" data included in the processing information include "a. Chemical solution concentration" and "c. Indoor temperature". Therefore, it is possible to generate auxiliary information related to maintenance work of other chambers based on the difference in the correlation between the chemical solution concentration and the chamber temperature between the representative chamber Crp and the other chambers. The maintenance operator can observe the deviation table to determine whether "a. Chemical solution concentration" and "c. Indoor temperature" are stable.

[0176] In addition, the plurality of chambers C1 to Cn respectively include: a concentration meter 122 that measures the concentration of the chemical solution; and a second thermometer 123a that measures the temperature of the chemical solution, and the "a" data to "i" data included in the processing information include "a. Chemical solution concentration" and "d. Chemical solution temperature". Therefore, it is possible to generate auxiliary information related to maintenance work of other chambers based on the difference in the correlation between the chemical solution concentration and the chemical solution temperature between the representative chamber Crp and the other chambers. The maintenance operator can observe the deviation table to determine whether "a. Chemical solution concentration" and "d. Chemical solution temperature" are stable.

[0177] In addition, the auxiliary device 4 acquires a deviation table including a deviation as comparison information, and the deviation indicates the degree of deviation between the predicted value predicted based on the process information of other chambers using the correlation between the "a" data to "i" data included in the process information of the representative chamber Crp and the process information of other chambers. Therefore, since the predicted values ​​of the "a" data to "i" data included in the process information of other chambers are predicted using the correlation between the "a" data to "i" data included in the process information of the representative chamber Crp, the correlation between the "a" data to "i" data included in the process information of the representative chamber Crp and the other chambers can be compared. Since the deviation table including a deviation indicating the degree of deviation between a plurality of predicted values ​​and the "a" data to "i" data included in the plurality of process information of other chambers is acquired as comparison information, the difference in the correlation between the "a" data to "i" data included in the process information between the representative chamber Crp and the other chambers can be quantitatively indicated.

[0178] In the third variation, a representative model representing the correlation between the plurality of process information representing the chamber is generated, and the correlation between the plurality of process information of each of the plurality of chambers is compared with the correlation between the plurality of process information of the representative model. Therefore, it is possible to combine the process information having no correlation or little correlation with other process information with the reference information having correlation. Therefore, it is possible to provide information on the performance difference of the representative chamber with respect to the process information having no correlation or little correlation with other process information.

[0179] In the third variation, after performing logarithmic operation on at least one of the plurality of processing information, the correlation between the plurality of processing information is calculated. Therefore, the accuracy of the correlation between the processing information with small variation and other processing information can be improved.

[0180] 10. Other Implementation Methods

[0181] (1) In the above-mentioned embodiment, the substrate processing device 1 is a substrate cleaning device, but the present invention is not limited thereto. As long as the substrate processing device 1 has a plurality of chambers, it may be a non-batch type but a single-wafer type substrate cleaning device, or it may have a structure that performs processes other than cleaning processes. In addition, the substrate processing device 1 may be a device that performs a wet etching process on the substrate W, or it may be a device that performs a flash lamp annealing (FLA) process that heats the surface of the substrate W by flashing light.

[0182] (2) The plurality of processing information may include other physical quantities in addition to or in place of the plurality of specific examples described in the above embodiment. The physical quantity may include at least one physical quantity such as the number of rotations, rotation speed, accelerations, gas flow rate, temperature, humidity, and pressure of the motor of the chamber. In addition, the plurality of processing information may include information related to the output signal of the detector provided in the motor.

[0183] (3) In the above embodiment, the auxiliary device 4 includes the auxiliary unit 49, but the present invention is not limited thereto. For example, auxiliary information may be sent from the auxiliary device 4 to the substrate processing device 1, and the auxiliary information may be displayed and outputted in the substrate processing device 1. In this case, the maintenance operator can view the auxiliary information while maintaining the substrate processing device 1.

[0184] (4) In the substrate processing apparatus management system 100 of the above embodiment, the series of processes performed by the information analysis apparatus 3 may be performed by the auxiliary apparatus 4. In addition, the series of processes performed by the information analysis apparatus 3 may be performed by the substrate processing apparatus 1. In this case, the information analysis apparatus 3 is not required.

[0185] (5) In the above embodiment, the substrate processing device 1 and the auxiliary device 4 are provided separately, but the substrate processing device 1 and the auxiliary device 4 may be provided integrally. In addition, in the above embodiment, the information analysis device 3 and the auxiliary device 4 are provided separately, but the information analysis device 3 and the auxiliary device 4 may be provided integrally.

[0186] (6) In the above-described embodiment, the auxiliary device 4 generates a representative model or an average model based on an invariant relationship, but the present invention is not limited thereto. For example, in the auxiliary device 4, a representative model or an average model may be generated by using other machine learning methods such as deep learning.

[0187] (7) In the above embodiment, the processing information PI1 to PIn is transmitted from the processing information transmitting unit 13 of the substrate processing apparatus 1 to the information collecting unit 41 of the auxiliary apparatus 4, but the present invention is not limited thereto. For example, the processing information PI1 to PIn may be transmitted via a cloud on the Internet. In this case, since the substrate processing apparatus 1 and the auxiliary apparatus 4 do not need to communicate directly, the communication load can be reduced.

[0188] (8) In the above embodiment, the auxiliary device 4 includes the model receiving unit 47 and the comparison unit 43, but the present invention is not limited thereto. For example, the auxiliary device 4 can send the processing information PI1-Pin collected by the information collecting unit 41 to the information analyzing device 3, and entrust the information analyzing device 3 to calculate the deviation and the abnormality score. In this case, the information analyzing device 3 generates a deviation table and sends the deviation table to the auxiliary device 4.

[0189] (9) The first modification example and the third modification example may be combined.

[0190] (10) In the third variation, the first duplexing unit 51 and the first logarithmic operating unit 53 are added to the information analysis device 3 , and the second duplexing unit 61 and the second logarithmic operating unit 63 are added to the support device 4 .

[0191] Instead of the above, the first duplexing unit 51 may be added to the information analysis device 3, and the second duplexing unit 61 may be added to the auxiliary device 4. In this case, the first logarithmic operation unit 53 and the second logarithmic operation unit 63 are not required. The processing information CPIrp obtained by duplexing the processing information PIrp representing the chamber Crp by the first duplexing unit 51 is input to the model generation unit 33, and the processing information CPIk obtained by duplexing the processing information PIk representing the chamber Ck by the second duplexing unit 61 is input to the comparison unit 43. In this case, the processing information that has no correlation or little correlation with other processing information can be combined with the reference information that has correlation. Therefore, for the processing information that has no correlation or little correlation with other processing information, information related to the performance difference of the representative chamber can be provided.

[0192] Furthermore, the first duplexing unit 51 may be added to the information analysis device 3 , and the second duplexing unit 61 may be added to the support device 4 , and these may be combined with the first modified example.

[0193] Alternatively, the first logarithmic operation unit 53 may be added to the information analysis device 3, and the second logarithmic operation unit 63 may be added to the auxiliary device 4. In this case, the first duplex unit 51 and the second duplex unit 61 are not required. The logarithm obtained by logarithmic conversion of the process information PIrp representing the cavity Crp by the first logarithmic operation unit 53 is input to the model generation unit 33, and the logarithm obtained by logarithmic conversion of the process information PIk of the cavity Ck by the second logarithmic operation unit 63 is input to the comparison unit 43. In this case, the accuracy of the correlation with other process information can be improved for process information with a small change.

[0194] Furthermore, the first logarithmic operation unit 53 may be added to the information analysis device 3 , and the second logarithmic operation unit 63 may be added to the support device 4 , and these may be combined with the first modified example.

[0195] 11. Correspondence between the constituent elements of the claims and the parts of the embodiments

[0196] Hereinafter, the correspondence between each constituent element of the claims and each element of the embodiment will be described. In the above embodiment, the information collecting unit 41 is an example of a processing information collecting unit, the auxiliary unit 49 is an example of an auxiliary information generating unit, and the comparing unit 43 is an example of a deviation acquiring unit. In addition, the representative determining unit 37 is an example of a representative chamber determining unit. Furthermore, the liquid medicine valve 113a is an example of a discharge valve, the flow meter 127 is an example of a flow measuring unit, the concentration meter 122 is an example of a concentration measuring unit, the first thermometer 123 is an example of a room temperature measuring unit, and the second thermometer 123a is an example of a liquid temperature measuring unit.

Claims

1. A substrate processing device management system, comprising an auxiliary device and an information analysis device, wherein the auxiliary device assists in the maintenance of the substrate processing device, wherein the substrate processing device has a plurality of chambers for processing substrates, wherein: The information analysis device includes a model generation unit that generates a representative model that represents a correlation between a plurality of processing information that represents an action or state associated with processing of a substrate in a predetermined representative chamber among the plurality of chambers. The auxiliary device comprises: A processing information collecting unit, which obtains a plurality of processing information of each of the plurality of chambers; as well as The auxiliary information generating unit generates auxiliary information related to maintenance work of another chamber different from the representative chamber based on comparison information obtained by comparing correlations between a plurality of pieces of process information of another chamber different from the representative chamber with the representative model.

2. An auxiliary device for assisting maintenance work of a substrate processing device, wherein the substrate processing device has a plurality of chambers for processing substrates, wherein: The auxiliary device comprises: a processing information collecting unit that acquires a plurality of processing information, the plurality of processing information indicating actions or states associated with processing of substrates in each of the plurality of chambers; and The auxiliary information generating unit generates auxiliary information related to maintenance work of the other chambers based on comparison information comparing correlations between the plurality of process information in a predetermined representative chamber among the plurality of chambers with correlations between the plurality of process information in other chambers.

3. The auxiliary device according to claim 2, wherein: The comparison information is information obtained by weighting and comparing the correlations between the plurality of processing information.

4. The auxiliary device according to claim 2, wherein: The auxiliary information generating unit calculates a correlation between the plurality of processing information after duplexing by combining reference information predetermined for at least one target processing information among the plurality of processing information as new processing information with the plurality of processing information.

5. The auxiliary device according to claim 4, wherein: The comparison information is information obtained by weighting and comparing the correlations between the plurality of processing information.

6. The assistive device according to claim 2, wherein: The auxiliary information generating unit calculates the correlation between the plurality of processing information after performing logarithmic operation on at least one object processing information among the plurality of information.

7. The assistive device according to claim 6, wherein: The comparison information is information obtained by weighting and comparing the correlations between the plurality of processing information.

8. The assistive device according to claim 6, wherein: The auxiliary information generating unit calculates a correlation between the plurality of processing information after duplexing by combining reference information predetermined for at least one target processing information among the plurality of processing information as new processing information with the plurality of processing information.

9. The assistive device according to claim 8, wherein: The comparison information is information obtained by weighting and comparing the correlations between the plurality of processing information.

10. The auxiliary device according to any one of claims 2 to 9, wherein: The auxiliary device includes a representative chamber determination unit that determines, as the representative chamber, one of the plurality of chambers having a correlation closest to an average correlation between the plurality of process information of the respective plurality of chambers.

11. The auxiliary device according to any one of claims 2 to 9, wherein: The plurality of chambers respectively include: a spray valve to spray liquid; and a flow rate measuring unit for measuring the flow rate of the liquid ejected from the ejection valve; The plurality of processing information respectively include: an opening signal indicating an opening amount input to the discharge valve in order to control the opening amount of the discharge valve; and a flow rate measured by the flow rate measuring unit.

12. The auxiliary device according to any one of claims 2 to 9, wherein: The plurality of chambers respectively include: a spray valve to spray liquid; and Concentration measurement unit, measures the concentration of liquid, The plurality of processing information respectively include: an opening signal indicating an opening amount input to the discharge valve in order to control the opening amount of the discharge valve; and a concentration measured by the concentration measuring unit.

13. An auxiliary device according to any one of claims 2 to 9, wherein: The plurality of chambers respectively include: a concentration measuring unit for measuring the concentration of the liquid; and Indoor temperature measurement unit, measuring the temperature of the chamber, The plurality of processing information respectively include: a concentration measured by the concentration measuring unit; and a temperature measured by the indoor temperature measuring unit.

14. The auxiliary device according to any one of claims 2 to 9, wherein: The plurality of chambers respectively include: a concentration measuring unit for measuring the concentration of the liquid; and Liquid temperature measurement unit, measures the temperature of the liquid, The plurality of processing information respectively include: a concentration measured by the concentration measuring unit; and a temperature measured by the liquid temperature measuring unit.

15. The auxiliary device according to any one of claims 2 to 9, wherein: The auxiliary device also includes a deviation acquisition unit, which acquires deviation information as the comparison information, and the deviation information represents the degree of deviation between a plurality of predicted values ​​respectively predicted based on the plurality of processing information of the other chambers using the correlation between the plurality of processing information of the representative chamber and the plurality of processing information of the other chambers.

16. A substrate processing device comprising the auxiliary device according to any one of claims 2 to 9.

17. A method for comparing performance between chambers, performed by an auxiliary device that assists in maintenance work of a substrate processing device, wherein the substrate processing device has a plurality of chambers for processing substrates, wherein: The inter-chamber performance comparison method includes the following processing: a process of acquiring a plurality of processing information indicating actions or states associated with processing of substrates in respective ones of the plurality of chambers; as well as A process for generating auxiliary information related to maintenance work of the other chamber based on comparison information comparing correlation between the plurality of process information of a predetermined representative chamber among the plurality of chambers with correlation between the plurality of process information of the other chambers.

18. A chamber performance comparison program executed by a computer of an auxiliary device, the auxiliary device assisting in maintenance work of a substrate processing device, the substrate processing device having a plurality of chambers for processing substrates, wherein: The inter-chamber performance comparison program causes the computer to perform the following processing: a process of acquiring a plurality of processing information indicating actions or states associated with processing of substrates in respective ones of the plurality of chambers; as well as A process for generating auxiliary information related to maintenance work of the other chamber based on comparison information comparing correlation between the plurality of process information of a predetermined representative chamber among the plurality of chambers with correlation between the plurality of process information of the other chambers.

Images