Supporting device, method for supporting, and program

Abstract

To provide a supporting device that allows a maintenance worker to rapidly perform a proper maintenance work on a substrate processor regardless of the degree of skills.SOLUTION: A supporting device 4 supports the maintenance work of at least one substrate processor 1. Also, the supporting device 4 acquires separation degree information. The separation degree information shows the degree of separation between plural pieces of processing information predicted on the basis of the invariant relationship among plural pieces of processing information showing operations or states related to processing of the substrate W of at least one substrate processor 1 and plural pieces of processing information actually collected from the substrate processor 1 and the actually collected pieces of processing information. The supporting device 4 generates supporting information on the maintenance work of at least one substrate processor 1 on the basis of the acquired separation degree information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a support device, a support method, and a support program for supporting maintenance work of one or more substrate processing apparatuses.

Background Art

[0002] Substrate processing apparatuses are used to perform various processes on various substrates such as semiconductor substrates. In a substrate processing apparatus, for example, a series of processes are performed on a substrate according to a predetermined processing procedure (processing recipe). In order to prevent the occurrence of processing defects of substrates due to abnormalities in the substrate processing apparatus, a data processing system for determining abnormalities in the substrate processing apparatus has been proposed (see, for example, Patent Document 1).

[0003] In that data processing system, a plurality of physical quantities related to the substrate processing apparatus are measured during the processing of the substrate, and a plurality of time-series data are generated by arranging those measurement results in time series. The plurality of time-series data includes data of physical quantities such as, for example, the flow rate of the processing liquid discharged from the nozzle and the pressure in the chamber. By comparing each time-series data with predetermined reference data, an evaluation value is calculated. Based on the calculated evaluation value, it is determined whether there is an abnormality in the time-series data.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the following explanation, those who perform maintenance work on the PCB processing equipment will be referred to as maintenance workers. Maintenance workers for the PCB processing equipment can determine whether or not an abnormality has occurred in the PCB processing equipment based on the abnormality detection results from the data processing system described above. However, inexperienced maintenance workers may be able to determine that an abnormality has occurred in the PCB processing equipment, but may not be able to identify the cause of the abnormality. Alternatively, inexperienced maintenance workers may be able to identify the cause of the abnormality, but may not be able to recognize the appropriate work required to resolve the abnormality. In these cases, maintenance workers may spend a long time performing maintenance work on the PCB processing equipment.

[0006] The object of the present invention is to provide a support device, a support method, and a support program that enable maintenance workers, regardless of their level of skill, to perform appropriate maintenance work on a substrate processing device in a short amount of time. [Means for solving the problem]

[0007] (1) An auxiliary device according to one aspect of the present invention is an auxiliary device for assisting maintenance work of a substrate processing apparatus, comprising: a deviation degree acquisition unit that acquires deviation degree information indicating the degree of deviation between a plurality of processing information predictable based on the invariant relationships between a plurality of processing information indicating the operation or state related to the processing of a substrate of the substrate processing apparatus and the plurality of processing information actually collected from the substrate processing apparatus and the plurality of processing information actually collected; and an auxiliary information generation unit that generates auxiliary information relating to maintenance work of the substrate processing apparatus based on the deviation degree information.

[0008] According to this support device, support information based on deviation degree information is generated. As a result, maintenance workers performing maintenance work on the substrate processing equipment can perform appropriate maintenance work on the substrate processing equipment in a short time, regardless of their level of skill, based on the generated support information.

[0009] (2) The substrate processing apparatus includes a plurality of components related to a plurality of processing information, and the support apparatus further includes a target determination unit that determines one or more components from the plurality of components that are subject to maintenance work as one or more maintenance target components based on deviation degree information, and the support information may include information indicating the one or more maintenance target components determined by the target determination unit.

[0010] In this case, maintenance workers can quickly identify one or more parts to be maintained based on the generated support information.

[0011] (3) For multiple processing information, multiple combinations of two different processing information are defined, each combination includes a first processing information and a second processing information, and for each combination, the second processing information actually collected from the substrate processing apparatus and the first processing information predicted based on the invariant relationship are generated as the first predicted processing information, the degree of deviation between the generated first predicted processing information and the first processing information actually collected from the substrate processing apparatus is calculated as the first deviation, and for each combination, the second processing information predicted based on the first processing information actually collected from the substrate processing apparatus and the invariant relationship is generated as the second predicted processing information, and the generated second predicted processing information and the substrate processing apparatus The degree of deviation between the second processing information actually collected and the first processing information is calculated as the second deviation degree. The deviation degree acquisition unit acquires multiple first deviation degrees calculated for each of the multiple combinations and multiple second deviation degrees calculated for each of the multiple combinations as deviation degree information. The target determination unit extracts one or more combinations from the multiple combinations in which the first deviation degree exceeds a predetermined first threshold, and one or more combinations in which the second deviation degree exceeds a predetermined second threshold. For each of the extracted one or more combinations, one or more parts that are commonly related to the first processing information and the second processing information included in that combination may be determined as one or more maintenance target parts. In this case, one or more maintenance target parts are appropriately determined based on the multiple processing information actually collected.

[0012] (4) The support device further includes a required value calculation unit that, for each of the one or more maintenance target parts determined by the target determination unit, acquires information regarding the state of the maintenance target part as it changes over time as time-series part information, and calculates a required value indicating the degree of necessity for maintenance work on the maintenance target part based on the acquired time-series part information, and the support information generation unit may, for each of the one or more maintenance target parts determined by the target determination unit, determine which of a predetermined set of required levels the required value calculated by the required value calculation unit belongs to, and include information on maintenance work for the maintenance target part predetermined according to the determined required level in the support information.

[0013] In this case, maintenance workers can quickly determine the appropriate maintenance work for each of the one or more maintenance target parts based on the generated support information.

[0014] (5) Each substrate processing apparatus is a substrate cleaning apparatus that cleans a substrate using a cleaning solution, and the multiple processing information may include at least one of the following: the amount of cleaning solution supplied to the substrate, the temperature of the cleaning solution supplied to the substrate, and the concentration of the cleaning solution supplied to the substrate. In this case, support information corresponding to the substrate cleaning apparatus is generated.

[0015] (6) A support method according to another aspect of the present invention is a support method for supporting maintenance work of a substrate processing apparatus, comprising the steps of: acquiring deviation degree information indicating the degree of deviation between a plurality of processing information that is predicted based on an invariant relationship between a plurality of processing information that indicates an operation or state related to the processing of a substrate of the substrate processing apparatus and a plurality of processing information actually collected from the substrate processing apparatus and a plurality of processing information actually collected; and generating support information relating to maintenance work of the substrate processing apparatus based on the deviation degree information.

[0016] This support method generates support information based on deviation degree information. As a result, maintenance workers performing maintenance on the substrate processing equipment can perform appropriate maintenance work on the substrate processing equipment in a short time, regardless of their level of skill, based on the generated support information.

[0017] (7) A support program according to yet another aspect of the present invention is a support program that causes a computer to execute support processing to support maintenance work of a substrate processing apparatus, the support processing including processing to acquire deviation degree information indicating the degree of deviation between a plurality of processing information that is predicted based on the invariant relationships between a plurality of processing information that indicates the operation or state related to the processing of a substrate of the substrate processing apparatus and the plurality of processing information actually collected from the substrate processing apparatus and the plurality of processing information actually collected, and processing to generate support information relating to maintenance work of the substrate processing apparatus based on the deviation degree information.

[0018] According to this support program, support information is generated based on deviation information. As a result, maintenance workers performing maintenance on the substrate processing equipment can perform appropriate maintenance work on the substrate processing equipment in a short amount of time, regardless of their skill level, based on the generated support information. [Effects of the Invention]

[0019] According to the present invention, maintenance workers can perform appropriate maintenance work on a substrate processing device in a short amount of time, regardless of their level of skill. [Brief explanation of the drawing]

[0020] [Figure 1] This figure illustrates the overall configuration of a substrate processing apparatus management system according to one embodiment of the present invention. [Figure 2] This diagram illustrates a specific example of how to calculate the degree of deviation. [Figure 3] This diagram illustrates a specific example of how to calculate an anomaly score. [Figure 4] This figure shows an example of data-related component information. [Figure 5]This is a diagram showing an example of component information over time. [Figure 6] This is a block diagram for explaining the functional configuration of an information analysis device and a support device. [Figure 7] This is a flowchart showing an example of the processing executed by the control device in FIG. 6 regarding the abnormality determination of a substrate processing apparatus. [Figure 8] This is a flowchart showing an example of the processing executed by an information analysis device to determine the abnormality of the substrate processing apparatus in FIG. 6. [Figure 9] This is a flowchart showing an example of the processing executed by a support device to support the maintenance work of the substrate processing apparatus in FIG. 6. [Figure 10] This is a flowchart showing an example of the processing executed by a support device to support the maintenance work of the substrate processing apparatus in FIG. 6.

Mode for Carrying Out the Invention

[0021] Hereinafter, a support device, a support method, and a support program according to an embodiment of the present invention will be described with reference to the drawings. In the following description, the substrate refers to a semiconductor substrate, a substrate for an FPD (Flat Panel Display) such as a liquid crystal display device or an organic EL (Electro Luminescence) display device, a substrate for an optical disk, a substrate for a magnetic disk, a substrate for a magneto-optical disk, a substrate for a photomask, a ceramic substrate, or a substrate for a solar cell, etc. Also, in the following description, a person who performs the maintenance work of the substrate processing apparatus is called a maintenance worker.

[0022] 1. Overall Configuration of Substrate Processing Apparatus Management System First, the overall configuration of the substrate processing apparatus management system, including the support device according to this embodiment, will be described. Figure 1 is a diagram illustrating the overall configuration of a substrate processing apparatus management system according to one embodiment of the present invention. As shown in Figure 1, the substrate processing apparatus management system 2 mainly consists of an information analysis device 3 and a support device 4, and is used to manage one or more (three in the example of Figure 1) substrate processing apparatuses 1. In the following description, when distinguishing between the three substrate processing apparatuses 1 shown in Figure 1, the three substrate processing apparatuses 1 will be referred to as substrate processing apparatuses 1A, 1B, and 1C, respectively. In this embodiment, substrate processing apparatuses 1A to 1C are assumed to have the same configuration.

[0023] The support device 4 according to this embodiment is used to assist maintenance workers in performing maintenance on each substrate processing device 1. The support device 4 is connected to each of the one or more substrate processing devices 1 and the information analysis device 3 by wired or wireless communication lines or a communication network. For example, the support device 4 is connected to each of the one or more substrate processing devices 1 and the information analysis device 3 via a communication network such as the Internet. In this embodiment, the support device 4 is connected to each of the one or more substrate processing devices 1 and the information analysis device 3 by wired or wireless LAN.

[0024] 2. An example configuration of the substrate processing apparatus 1A As shown in Figure 1, the substrate processing apparatus 1A is a batch-type substrate cleaning apparatus and includes a control device 100, a processing tank 111, a substrate holding unit 112, a lifting device 112a, a bubbler tube 115, a heater 117, and a heater drive unit 118. In addition to the above-mentioned components, the substrate processing apparatus 1A is also provided with a display device, an audio output device, and an operation unit (not shown).

[0025] The substrate holding section 112 is configured to hold multiple substrates W. The processing tank 111 is configured to accommodate the multiple substrates W held by the substrate holding section 112. A cleaning solution for cleaning the substrates W is stored in the processing tank 111.

[0026] The lifting device 112a supports the substrate holder 112 so that it can move vertically, and moves the substrate holder 112 vertically under the control of the control device 100. This allows the lifting device 112a to immerse the multiple substrates W held by the substrate holder 112 in the cleaning solution stored in the processing tank 111, and to lift the multiple substrates W immersed in the cleaning solution from the processing tank 111. The multiple substrates W are cleaned by being immersed in the cleaning solution. The lifting device 112a is also equipped with a motor (not shown) as a power source for moving the substrate holder 112 vertically.

[0027] The treatment tank 111 is connected to a chemical solution piping 113 and a pure water piping 114. The chemical solution piping 113 is equipped with a chemical solution valve 113a and a flow meter 124. The chemical solution valve 113a is a control valve whose opening degree can be adjusted by the control device 100.

[0028] The chemical piping 113 guides the chemical supplied from a chemical supply system (not shown) to the treatment tank 111 when the chemical valve 113a is opened. The flow rate (amount supplied per unit time) of the chemical supplied to the treatment tank 111 through the chemical piping 113 changes according to the degree of opening of the chemical valve 113a. Examples of chemicals used include BHF (buffered hydrofluoric acid), DHF (dilute hydrofluoric acid), hydrofluoric acid, hydrochloric acid, sulfuric acid, nitric acid, phosphoric acid, acetic acid, oxalic acid, or ammonia. The flow meter 124 detects the flow rate of the chemical in the portion of the chemical piping 113 downstream of the chemical valve 113a and provides the detection result to the control device 100.

[0029] The pure water piping 114 is equipped with a pure water valve 114a and a flow meter 125. The pure water valve 114a is a control valve whose opening degree can be adjusted by the control device 100.

[0030] The pure water piping 114 guides pure water supplied from a pure water supply system (not shown) to the treatment tank 111 when the pure water valve 114a is opened. The flow rate (amount supplied per unit time) of pure water supplied to the treatment tank 111 through the pure water piping 114 changes according to the degree to which the pure water valve 114a is opened. The flow meter 125 detects the flow rate of pure water in the part of the pure water piping 114 downstream of the pure water valve 114a and provides the detection result to the control device 100.

[0031] A bubbler pipe 115 is fixed inside the processing tank 111, near its lower end, by a bubbler fixing device (not shown). A gas pipe 116 is connected to the bubbler pipe 115. The gas pipe 116 is equipped with a gas valve 116a, a flow meter 126, and a pressure gauge 127. The gas valve 116a is a control valve whose opening degree can be adjusted by the control device 100.

[0032] When the gas valve 116a is opened, the gas piping 116 guides nitrogen gas supplied from a gas supply system (not shown) to the bubbler pipe 115 in the treatment tank 111. The flow rate (amount supplied per unit time) of nitrogen gas supplied to the bubbler pipe 115 through the gas piping 116 changes according to the degree to which the gas valve 116a is opened.

[0033] The flow meter 126 detects the flow rate of nitrogen gas in the portion of the gas piping 116 downstream of the gas valve 116a and provides the detection result to the control device 100. In this case, the control device 100 adjusts the opening of the gas valve 116a based on the flow rate provided by the flow meter 126 so that nitrogen gas is supplied to the bubbler tube 115 at a predetermined flow rate. The pressure gauge 127 also detects the internal pressure in the portion of the gas piping 116 downstream of the gas valve 116a and provides the detection result to the control device 100.

[0034] By adjusting the opening of the chemical valve 113a and the pure water valve 114a, the chemical solution and pure water are supplied to the treatment tank 111 in predetermined proportions. In this state, the gas valve 116a is further opened. This supplies nitrogen gas to the bubbler tube 115, generating a large amount of bubbles from the bubbler tube 115. As the generated bubbles rise in the treatment tank 111, the chemical solution and pure water supplied to the treatment tank 111 are mixed, and a cleaning solution is produced. Note that other inert gases such as argon gas may be supplied to the bubbler tube 115 instead of nitrogen gas.

[0035] A heater 117 is further provided inside the processing tank 111, near its lower end. The heater drive unit 118 drives the heater 117 by supplying power to it. The amount of power supplied from the heater drive unit 118 to the heater 117 is controlled by the control device 100.

[0036] Furthermore, a drain pipe is connected to the bottom of the processing tank 111. A valve (not shown) is provided in the drain pipe. When the valve in the drain pipe is opened, the cleaning liquid inside the processing tank 111 is discharged to the outside of the substrate processing device 1A.

[0037] The processing tank 111 is further equipped with a liquid level gauge 121, a concentration meter 122, and a thermometer 123 as multiple detectors for detecting the state of the cleaning liquid stored in the processing tank 111.

[0038] The liquid level gauge 121 detects the liquid level of the cleaning solution stored in the treatment tank 111 and provides the detection result to the control device 100. The concentration meter 122 detects the concentration of the cleaning solution stored in the treatment tank 111 and provides the detection result to the control device 100. The thermometer 123 detects the temperature of the cleaning solution stored in the treatment tank 111 and provides the detection result to the control device 100.

[0039] The control device 100 consists of, for example, a CPU (Central Processing Unit) and memory, and controls the operation of the lifting device 112a, the operation of the heater drive unit 118, and the opening degrees of the chemical valve 113a, the pure water valve 114a, and the gas valve 116a. The memory of the control device 100 stores a substrate processing program for executing the substrate cleaning process of the substrate W by the substrate processing device 1A.

[0040] Furthermore, the control device 100 adjusts the opening of the chemical 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, 125, and 126, the liquid level meter 121, and the concentration meter 122. As a result, the liquid level of the cleaning solution, which has a predetermined chemical concentration, is maintained at a predetermined height while it is stored in the treatment tank 111. The control device 100 also controls the heater drive unit 118 based on the temperature supplied by the thermometer 123 so that the temperature of the cleaning solution stored in the treatment tank 111 is maintained at a predetermined temperature.

[0041] Furthermore, the control device 100 has an emergency stop function that stops the operation of the substrate processing device 1A if a person enters a predetermined space inside the substrate processing device 1A or if a predetermined detector (for example, a concentration meter 122) installed inside the substrate processing device 1A is not functioning.

[0042] 3. Processing Information Each substrate processing apparatus 1 is configured with multiple pieces of processing information indicating the operation or state related to the processing of the substrate W, which is used to detect abnormalities in the substrate processing apparatus 1. These processing pieces of information are transmitted from the control device 100 of each substrate processing apparatus 1 to the information analysis device 3 of the substrate processing apparatus management system 2 at predetermined intervals, as shown by the thick solid arrows in Figure 1.

[0043] As shown in the outlet in Figure 1, the processing information transmitted from the substrate processing apparatus 1 to the information analysis apparatus 3 includes: a. liquid level, b. chemical valve opening, c. chemical valve open / close signal, d. chemical concentration, e. cleaning solution temperature, f. chemical flow rate, g. nitrogen gas flow rate, and h. nitrogen gas pressure.

[0044] "a. Liquid level" indicates the liquid level of the cleaning solution in the treatment tank 111 as detected by the liquid level gauge 121. "b. Chemical valve opening" indicates the opening degree of the chemical valve 113a provided in the chemical piping 113. "c. Chemical valve opening / closing signal" is a signal given from the control device 100 to the chemical valve 113a to command the opening or closing of the chemical valve 113a.

[0045] "d. Chemical concentration" indicates the concentration of the cleaning solution in the treatment tank 111 as detected by the concentration meter 122. "e. Cleaning solution temperature" indicates the temperature of the cleaning solution in the treatment tank 111 as detected by the thermometer 123. "f. Chemical flow rate" indicates the flow rate of the chemical solution flowing through the chemical solution piping 113 as detected by the flow meter 124.

[0046] "g. Nitrogen gas flow rate" indicates the flow rate of nitrogen gas flowing through the gas pipe 116 as detected by the flow meter 126. "h. Nitrogen gas pressure" indicates the pressure of nitrogen gas in the gas pipe 116 as detected by the pressure gauge 127.

[0047] 4. Detection of abnormalities in the substrate processing device 1 by the information analysis device 3 The information analysis device 3 in Figure 1 is, for example, a server and includes a CPU and memory. The information analysis device 3 collects multiple processing information transmitted from each substrate processing device 1. In the information analysis device 3, multiple combinations of two different processing information are predetermined for the multiple processing information transmitted from each substrate processing device 1 to the information analysis device 3. A predetermined invariant relationship (hereinafter referred to as the invariant relationship) is maintained between the two processing information that constitute each combination.

[0048] Here, we assume a scenario where inappropriate substrate processing is performed due to a malfunction in the substrate processing device 1. In this case, the relationship between two processing information components that constitute at least one of the multiple combinations deviates from an invariant relationship.

[0049] Therefore, the information analysis device 3 calculates multiple deviation degrees, which represent the degree of discrepancy between the relationships between multiple combinations of the multiple processing information actually collected and the multiple invariant relationships predetermined for those multiple processing information. Furthermore, based on the calculated multiple deviation degrees, the information analysis device 3 calculates the degree of abnormality of the substrate processing device 1 as an abnormality score. A specific example of the method for calculating the abnormality score will be described later.

[0050] Furthermore, as shown by the thick dashed arrow in Figure 1, the information analysis device 3 transmits the calculated abnormal score for each substrate processing device 1 to that substrate processing device 1. The transmission of the abnormal score is performed each time the information analysis device 3 calculates an abnormal score. At this time, each substrate processing device 1 stores the abnormal score transmitted from the information analysis device 3.

[0051] Furthermore, the information analysis device 3 determines whether the abnormality score for each substrate processing device 1 exceeds a predetermined abnormality detection threshold. If the abnormality score exceeds the abnormality detection threshold, the information analysis device 3 sends an alarm to the substrate processing device 1 corresponding to that abnormality score, as shown by the wavy dotted arrow in Figure 1. In the example in Figure 1, the information analysis device 3 sends an alarm only to substrate processing device 1C among the substrate processing devices 1A to 1C. At this time, the substrate processing device 1C that receives the alarm outputs an alarm.

[0052] In this embodiment, the abnormality score (degree of abnormality) is lower for abnormalities that do not require action by maintenance personnel, and higher for abnormalities that do require action by maintenance personnel.

[0053] A state with a low abnormality score is one in which all of the processing conditions fall within the range predicted to be normal based on the invariant relationships corresponding to each of the above combinations.

[0054] On the other hand, a high abnormality score includes, for example, a state in which the actual temporal change of "d. chemical solution concentration" is significantly larger than the temporal change predicted based on the temporal change of "f. chemical solution flow rate". The continuation of this state can lead to, for example, processing failures of the substrate W due to the inability to adjust the chemical solution concentration of the cleaning solution, generation of harmful gases, and damage to components of the substrate processing apparatus 1.

[0055] Furthermore, a high abnormality score includes, for example, a state in which the actual value of "a. liquid level" differs significantly from the temporal change predicted based on the temporal change of "g. nitrogen gas flow rate". The persistence of this state can lead to, for example, inadequate processing of the substrate W due to the inability to ensure that the substrate W is immersed in the cleaning solution, generation of harmful gases, and damage to the components of the substrate processing apparatus 1.

[0056] 5. Specific examples of methods for calculating anomaly scores As described above, the information analysis device 3 has defined multiple combinations of two different processing information. A deviation degree is calculated for each combination in order to calculate the anomaly score. Figure 2 is a diagram illustrating a specific example of deviation degree calculation. Here, we will explain an example of deviation degree calculation corresponding to the combination of "b. Chemical valve opening" and "f. Chemical flow rate" in Figure 1. In the following explanation, the data for "b. Chemical valve opening" will be referred to as "b" data as appropriate, and the data for "f. Chemical flow rate" will be referred to as "f" data as appropriate.

[0057] To calculate the degree of deviation, information indicating the invariant relationship between "b. chemical valve opening" and "f. chemical flow rate" is required. In the following explanation, information indicating the invariant relationship between two pieces of processing information will be referred to as invariant information. Invariant information is preferably generated by machine learning, for example.

[0058] Assume that machine learning is performed to obtain invariant information between "b. chemical valve opening" and "f. chemical flow rate". In this case, the information analysis device 3 is given "b" data and "f" data when the substrate processing device 1 is operating ideally (operating normally) according to the recipe, before the actual processing of the substrate W in each substrate processing device 1.

[0059] The upper part of Figure 2 shows graphs illustrating examples of the time-dependent changes in normal "b" data and normal "f" data. In the "b" data graph, the horizontal axis represents time, and the vertical axis represents the opening degree of the chemical valve 113a in Figure 1. In the "f" data graph, the horizontal axis represents time, and the vertical axis represents the flow rate of the chemical in the portion of the chemical piping 113 downstream of the chemical valve 113a in Figure 1. The horizontal axis (time axis) is common to both the "b" data graph and the "f" data graph.

[0060] As shown in the two upper graphs of Figure 2, it can be seen that as the opening of the chemical valve 113a increases, the flow rate of the chemical solution flowing through the chemical pipe 113 also increases at a nearly constant rate. In this case, the relationship between the normal "b" data and the normal "f" data represents an invariant relationship. Thus, when the substrate processing device 1 is operating normally, the relationship between data in each combination of multiple processing information is equivalent to an invariant relationship. Therefore, the information analysis device 3 is pre-inputted with multiple normal processing information. As a result, the invariant relationship for each combination of multiple processing information is modeled by machine learning, and invariant information is generated. Consequently, the invariant relationship that fits each substrate processing device 1 is stored in the information analysis device 3.

[0061] In addition to the examples above, invariant information may also be generated by simulations assuming that the substrate processing device 1 is operating normally, or it may be determined by the administrator managing each substrate processing device 1.

[0062] With the invariant information stored in the information analysis device 3, the substrate W is processed in each substrate processing device 1, and the actual "b" data and "f" data are collected by the information analysis device 3. In the middle section of Figure 2, an example of the time-dependent changes in the actually collected "b" data and "f" data is shown in a graph.

[0063] When actual "b" data is collected, "f" data is predicted based on pre-stored invariant information. Conversely, when actual "f" data is collected, "b" data is predicted based on pre-stored invariant information. The lower part of Figure 2 shows a graph illustrating an example of the temporal changes in the predicted "b" and "f" data based on invariant information. In the graph in the lower part of Figure 2, the predicted "b" and "f" data are shown as solid lines, while the actually collected "b" and "f" data are shown as dotted lines.

[0064] When the substrate processing device 1 is operating normally, the actual "b" data and the predicted "b" data will match or nearly match. Similarly, the actual "f" data and the predicted "f" data will match or nearly match. However, if an abnormality occurs in the substrate processing device 1, there is a high probability that the actual "b" data and the predicted "b" data will diverge. Similarly, there is a high probability that the actual "f" data and the predicted "f" data will diverge. The degree of this divergence is considered to be greater the greater the degree of abnormality in the substrate processing device 1, and smaller the less severe the abnormality in the substrate processing device 1.

[0065] Therefore, in this embodiment, the difference between the data of the processing information actually collected and the data of the processing information predicted is calculated as the degree of deviation. In the example in Figure 2, the information analysis device 3 calculates the degree of deviation as the difference between the actual "b" data and the predicted "b" data when calculating the degree of deviation at a certain point in time. The score calculation unit 32 also calculates the degree of deviation as the difference between the actual "f" data and the predicted "f" data.

[0066] In the following explanation, the processing information "a. liquid level", "b. chemical valve opening", "c. chemical valve open / close signal", "d. chemical concentration", "e. cleaning fluid temperature", "f. chemical flow rate", "g. nitrogen gas flow rate", and "h. nitrogen gas pressure" will be referred to as processing information "a", "b", "c", "d", "e", "f", "g", and "h", respectively.

[0067] Figure 3 is a diagram illustrating a specific example of calculating an anomaly score. The information analysis device 3 calculates the above deviation for all combinations of multiple processing information. The multiple values ​​in the rows to the right of each of the processing information "a" to "h" in the left vertical column of Figure 3 represent the deviation between the processing information predicted from each of the processing information "a" to "h" in the upper horizontal column and the processing information actually obtained. The multiple values ​​in the columns below each of the processing information "a" to "h" in the upper horizontal column of Figure 3 represent the deviation between the processing information predicted from each of the processing information "a" to "h" in the left vertical column and the processing information actually obtained.

[0068] For example, the value "52" in the column at the intersection of the rightmost row of processing information "a" in the left vertical column and the lowermost column of processing information "g" in the upper horizontal column represents the degree of deviation between the processing information "a" predicted from processing information "g" and the processing information "a" actually obtained. Similarly, the value "50" in the column at the intersection of the lowermost column of processing information "a" in the upper horizontal column and the rightmost row of processing information "g" in the left horizontal column represents the degree of deviation between the processing information "g" predicted from processing information "a" and the processing information "g" actually obtained.

[0069] Figure 3 shows the multiple deviations calculated for all combinations of multiple processing information. Once all deviations have been calculated, the information analysis device 3 calculates the sum of the calculated deviations as the anomaly score. In the example in Figure 3, the anomaly score is 102.

[0070] 6. Support for maintenance work on the substrate processing device 1 in the support device 4. The support device 4 in Figure 1 is, for example, a personal computer and includes a CPU and memory. The support device 4 also includes a display unit 4a and an operation unit 4b. Multiple maintenance workers, each responsible for multiple board processing devices 1, can understand the degree of abnormality in their respective board processing devices 1 by checking the abnormality score transmitted from the information analysis device 3. In addition, each maintenance worker can understand that a serious abnormality has occurred in their board processing device 1 by receiving an alarm from the information analysis device 3.

[0071] However, even if each maintenance worker can grasp the degree of abnormality in the substrate processing device 1, they may not be able to identify the cause of the abnormality. Alternatively, an inexperienced maintenance worker may be able to identify the cause of the abnormality, but may not be able to recognize the appropriate work to resolve the abnormality. In these cases, each maintenance worker will spend a long time performing maintenance on the substrate processing device.

[0072] Therefore, as shown by the thick dotted arrows in Figure 1, the information analysis device 3 according to this embodiment transmits each of the multiple deviation degrees calculated for each substrate processing device 1 to the support device 4 along with a combination of two processing information corresponding to that deviation degree. The support device 4 then generates support information for each substrate processing device 1 based on the multiple deviation degrees received from the information analysis device 3, data-related component information described later, and time-series component information described later, to assist in the maintenance work of the substrate processing device 1. Furthermore, as shown by the thick dashed arrows in Figure 1, the support device 4 provides the generated support information to the substrate processing device 1 corresponding to that support information.Specific examples of support information and its generation method will be described below.

[0073] The memory of the support device 4 stores data-related component information and time-dependent component information in advance in order to generate the above-mentioned support information. The data-related component information is information that indicates each of the multiple processing information collected by the information analysis device 3 and one or more components related to that processing information. The data-related component information is determined in advance by a maintenance worker of the board processing device 1 or a manager who manages the board processing device 1, for example, before board processing in the board processing device 1. Specifically, the data-related component information is generated and updated by the maintenance worker or manager operating the operation unit of the board processing device 1 or the operation unit 4b of the support device 4.

[0074] Figure 4 shows an example of data-related component information. According to the data-related component information in Figure 4, the components related to processing information "a" are shown to be a liquid level gauge 121, a chemical valve 113a, and a bubbler fixing device. The components related to processing information "b" are shown to be a chemical valve 113a and a chemical piping 113. The component related to processing information "c" is shown to be a chemical valve 113a.

[0075] Furthermore, chemical piping 113 and concentration meter 122 are shown as components related to processing information "d". Chemical piping 113, heater 117 and thermometer 123 are shown as components related to processing information "e". Chemical piping 113 is shown as a component related to processing information "f".

[0076] Furthermore, the components related to processing information "g" are shown as a bubbler tube 115, a bubbler fixture, a gas flow meter 126, and gas piping 116. The components related to processing information "h" are shown as a bubbler tube 115, a bubbler fixture, and gas piping 116.

[0077] Time-dependent component information is information about the deterioration state that changes over time for each of several components related to at least a portion of the processing information in the data-related component information. In the support device 4, the time-dependent component information is updated to the latest state at predetermined intervals.

[0078] Figure 5 shows an example of component information over time. The component information in Figure 5 includes, for each of the multiple components listed in the data-related component information in Figure 4, information about the deterioration state of that component, including "related processing information," "elapsed time," "estimated number of years," "number of failures," and "number of operations."

[0079] "Related processing information" indicates the processing information related to each component, and the relationship between the component and the processing information related to that component is the same as the relationship between each processing information and component shown in the data-related component information in Figure 4. "Elapsed time" is information indicating the elapsed time from the time each component was attached to the substrate processing device 1. "Expected lifespan" is information indicating the expected lifespan in years for each component. "Number of failures" is information indicating the number of failures that have occurred in components of the same type (same model) as the component in question from the time the component in question was put into use until the present. "Number of operational components" is information indicating the total number of components of the same type (same model) as the component in question that are currently operational.

[0080] A specific example of generating support information will be explained. In this embodiment, the support device 4 stores one or more deviation threshold values, which are common or individually determined for each of the multiple deviation values ​​provided by the information analysis device 3. Each deviation threshold value is determined so that it is possible to determine whether or not a predetermined degree of abnormality has occurred in the components related to the two pieces of processing information used to calculate the corresponding deviation value.

[0081] The support device 4 determines whether each of the multiple deviations provided by the information analysis device 3 exceeds the corresponding deviation threshold. If there is a deviation that exceeds the deviation threshold, the support device 4 determines the component that is commonly related to the two processing information used to calculate the deviation and the data-related component information as the component to be maintained.

[0082] For example, let's assume that a common deviation threshold for the multiple deviations in Figure 3 is set to "40". In this case, the deviation of "52" between the processing information "a" predicted from processing information "g" and the processing information "a" actually obtained exceeds the deviation threshold of "40". Also, the deviation of "50" between the processing information "g" predicted from processing information "a" and the processing information "g" actually obtained also exceeds the deviation threshold of "40". On the other hand, all other deviations are "0", so they do not exceed the deviation threshold of "40". As a result, in the example of multiple deviations in Figure 3, the component "bubbler fixing device", which is related to processing information "a" and processing information "g", is determined to be a component to be maintained, based on the data-related component information in Figure 4.

[0083] Next, the support device 4 calculates the degree of need for maintenance work for each of the determined one or more maintenance target parts as the maintenance requirement value. The maintenance requirement value is calculated based on the time-lapse information of the maintenance target parts, for example, by using the following formula (1).

[0084] Maintenance requirement value = ((Elapsed time / Estimated number of years) + (Number of failures / Number of operational units)) × Weight ... (1) In formula (1) above, the "weight" is determined, for example, for each maintenance target component, according to the type of abnormality that is expected to occur if the maintenance target component is damaged or missing. Types of abnormalities include "chemical leakage," "circuit board damage," and "processing time delay." In this case, "chemical leakage" is highly likely to affect the health of maintenance workers of the circuit board processing device 1. Therefore, maintenance target components that may cause "chemical leakage" due to damage or missing are assigned a high weight (e.g., "3"). On the other hand, "circuit board damage" is unlikely to affect the health of maintenance workers of the circuit board processing device 1. Therefore, maintenance target components that may cause "circuit board damage" due to damage or missing are assigned a medium weight (e.g., "2"). On the other hand, "processing time delay" does not affect the health of maintenance workers of the circuit board processing device 1 and is unlikely to cause damage to the circuit board processing device 1 and the circuit board. Therefore, maintenance target components that may cause "processing time delay" due to damage or missing are assigned a low weight (e.g., "1").

[0085] Subsequently, the support device 4 generates support information for each of the one or more maintenance target components, including instructions for maintenance work corresponding to that component, based on the calculated maintenance requirement value, and transmits it to the substrate processing device 1.

[0086] Specifically, the support device 4 determines, for each of the one or more maintenance target parts, which of the predetermined levels (for example, three levels: large, medium, and small) the calculated maintenance requirement belongs to. Such level classification can be achieved, for example, by setting multiple different reference values ​​for the maintenance requirement.

[0087] When the component to be maintained is the "liquid level gauge 121" and the maintenance requirement level is "high", the support device 4 generates support information, for example, "instructions for maintenance work to replace the liquid level gauge 121". Furthermore, in this case, the support device 4 may also generate support information, such as "work information for presenting the procedure for replacing the liquid level gauge 121 to the maintenance worker" and "report information for creating a report regarding the replacement of the liquid level gauge 121".

[0088] Furthermore, when the component to be maintained is the "liquid level gauge 121" and the maintenance requirement level is "medium," the support device 4 generates support information including, for example, "instructions for maintenance work to perform a detailed operational check of the liquid level gauge 121." In this case, the support device 4 may also generate support information including "work information to present the detailed operational check procedure for the liquid level gauge 121 to the maintenance worker" and "report information to create a report regarding the operational check of the liquid level gauge 121," etc.

[0089] Furthermore, when the component to be maintained is the "liquid level gauge 121" and the maintenance requirement level is "low," the support device 4 generates support information including, for example, "instructions for maintenance work to perform a simple operational check of the liquid level gauge 121." In this case, the support device 4 may also generate support information including, for example, "work information to present the procedure for a simple operational check of the liquid level gauge 121 to the maintenance worker."

[0090] The support information described above is transmitted from the support device 4 to each substrate processing device 1. In this case, the support information is presented to the maintenance worker in each substrate processing device 1 via a display device or audio output device. As a result, the maintenance worker of the substrate processing device 1 can easily and quickly understand, based on the received support information, which components in the substrate processing device 1 should be serviced and what kind of maintenance work should be performed.

[0091] 7. An example of the functional configuration and operation of the substrate processing device management system 2. Figure 6 is a block diagram illustrating the functional configuration of the information analysis device 3 and the support device 4. Figure 7 is a flowchart showing an example of the processing performed by the control device 100 in Figure 6 regarding abnormality detection of the substrate processing device 1. Figure 8 is a flowchart showing an example of the processing performed by the information analysis device 3 to determine abnormality of the substrate processing device 1 in Figure 6. Figures 9 and 10 are flowcharts showing an example of the processing performed by the support device 4 to assist in maintenance work on the substrate processing device 1 in Figure 6.

[0092] In the following explanation, we assume that the substrate processing apparatus management system 2 manages only one substrate processing apparatus 1. Therefore, the series of processes shown in Figures 8 to 10 will be executed only for the substrate processing apparatus 1 shown in Figure 6.

[0093] As explained using Figure 1, the substrate processing apparatus 1 includes a control device 100. As shown in Figure 7, the control device 100 transmits a plurality of processing information generated within the substrate processing apparatus 1 during the processing of the substrate W to the information analysis device 3 at predetermined intervals (step S10). At this time, the control device 100 may store the plurality of processing information in association with their transmission times.

[0094] Next, the control device 100 determines whether or not it has received an abnormal score from the information analysis device 3 (step S11). If no abnormal score is received, the control device 100 repeats the determination in step S11. If an abnormal score is received, the control device 100 stores the received abnormal score in association with its reception time (step S12).

[0095] Furthermore, the control device 100 determines whether or not it has received an alarm from the information analysis device 3 (step S13). If no alarm is received, the control device 100 proceeds to step S15, which will be described later. If an alarm is received, the control device 100 outputs the alarm in the form of video or sound using the display device or audio output device of the substrate processing device 1 (step S14).

[0096] Furthermore, the control device 100 determines whether or not it has received support information from the support device 4 (step S15). If support information is not received, the control device 100 returns to step S10. If support information is received, the control device 100 presents instructions for maintenance work corresponding to the part to be maintained to the maintenance worker via a display device or voice output device based on the received support information (step S16). After that, the control device 100 returns to step S10.

[0097] As shown in Figure 6, the information analysis device 3 includes an information collection unit 31, a score calculation unit 32, a score transmission unit 33, and an alarm transmission unit 34. The memory of the information analysis device 3 stores an abnormality determination program for determining abnormalities in the substrate processing device 1. The CPU of the information analysis device 3 executes the abnormality determination program, thereby realizing the functions of the components (31-34) of the information analysis device 3. Some or all of the components (31-34) of the information analysis device 3 in Figure 6 may be realized by hardware such as electronic circuits.

[0098] As shown in Figure 8, the information collection unit 31 first collects multiple processing information transmitted from the substrate processing device 1 (step S20). Next, the score calculation unit 32 calculates multiple deviations from the collected processing information (step S21) and transmits the calculated deviations to the support device 4 (step S22). At this time, the score calculation unit 32 stores the multiple deviations calculated in step S22 in the memory of the information analysis device 3.

[0099] Next, the score calculation unit 32 calculates an abnormal score for the substrate processing device 1 based on a plurality of deviation degrees stored in the memory of the information analysis device 3 (step S23), and transmits the calculated abnormal score to the substrate processing device 1 (step S24).

[0100] The memory of the information analysis device 3 stores the above-mentioned abnormality detection threshold, which is set in advance according to the substrate processing device 1. The alarm transmission unit 34 then determines whether the abnormality score calculated in step S23 exceeds the abnormality detection threshold (step S25). If the abnormality score does not exceed the abnormality detection threshold, the alarm transmission unit 34 returns to step S21. On the other hand, if the abnormality score exceeds the abnormality detection threshold, the alarm transmission unit 34 sends an alarm to the substrate processing device 1 (step S26) and returns to step S20.

[0101] As shown in Figure 6, the support device 4 includes a deviation degree acquisition unit 41, a target determination unit 42, a required value calculation unit 43, a level determination unit 44, an instruction generation unit 45, a first storage unit 46, a second storage unit 47, a third storage unit 48, and an information update unit 49. The memory of the support device 4 stores a maintenance support program for assisting with maintenance work on the substrate processing device 1. The CPU of the support device 4 executes the maintenance support program, thereby realizing the functions of the components (41-49) of the support device 4. Some or all of the components (41-49) of the support device 4 in Figure 6 may be realized by hardware such as electronic circuits.

[0102] The first storage unit 46 stores data-related component information (Figure 4) corresponding to the substrate processing device 1 shown in Figure 6 before the substrate processing is started by the substrate processing device 1 shown in Figure 6. The second storage unit 47 stores time-dependent component information (Figure 5) corresponding to the substrate processing device 1 shown in Figure 6 before the substrate processing is started by the substrate processing device 1 shown in Figure 6. Furthermore, the third storage unit 48 stores instructions for multiple maintenance tasks, each of which corresponds to multiple levels of maintenance requirements for multiple components of the substrate processing device 1, before the substrate processing is started by the substrate processing device 1 shown in Figure 6.

[0103] As described above, data-related component information is determined by maintenance workers or managers. Furthermore, time-dependent component information changes over time. Therefore, as shown in Figures 9 and 10, the information update unit 49 determines whether or not there has been a change in the data-related component information stored in the first storage unit 46 (step S30). This determination is made based on whether or not a change in the data-related component information has been ordered by maintenance workers or managers.

[0104] If there are no changes to the data-related component information, the information update unit 49 proceeds to step S32, which will be described later. On the other hand, if there are changes to the data-related component information, the information update unit 49 updates the data-related component information stored in the first storage unit 46 with the new data-related component information after the change (step S31).

[0105] Next, the information update unit 49 updates the time-series component information stored in the second storage unit 47 (step S32). This update process includes updating the elapsed time, the number of failures, and the number of operational units based on the current time.

[0106] Next, the deviation degree acquisition unit 41 determines whether it has received multiple deviation degrees from the information analysis device 3 for the substrate processing device 1 shown in Figure 6 (step S33). The memory of the support device 4 stores one or more deviation degree thresholds that have been set in advance according to the substrate processing device 1. In this example, it is assumed that the one or more deviation degree thresholds are a common value. If the deviation degree acquisition unit 41 does not receive multiple deviation degrees in step S33, it returns to step S30. On the other hand, if the deviation degree acquisition unit 41 receives multiple deviation degrees in step S33, it determines whether each of those deviation degrees exceeds a predetermined deviation degree threshold and extracts the deviation degrees that exceed the deviation degree threshold (step S34).

[0107] Next, the target determination unit 42 determines the parts to be maintained based on the extracted deviation degrees and the data-related part information stored in the first storage unit 46 (step S35). Specifically, for each of the one or more deviation degrees extracted in step S34, the target determination unit 42 determines the parts to be maintained that are commonly related to the two pieces of processing information used to calculate the deviation degree.

[0108] Next, the required value calculation unit 43 calculates the required maintenance value for the maintenance target component based on the determined maintenance target component and the time-dependent component information stored in the second storage unit 47 (step S36). Specifically, for each of the one or more maintenance target components determined in step S35, the required maintenance value is calculated using the time-dependent component information of the maintenance target component and a predetermined calculation formula (for example, formula (1) above).

[0109] Next, the instruction generation unit 45 generates support information corresponding to the maintenance target component based on the maintenance requirement value calculated in step S36 (step S37). Specifically, first, the level determination unit 44 in Figure 6 determines which of the predetermined levels the calculated maintenance requirement value belongs to for each of the one or more maintenance target components. Then, for each of the one or more maintenance target components, the instruction unit 45 extracts the maintenance work instruction content corresponding to the maintenance requirement value level from the multiple maintenance work instruction contents stored in the third storage unit 48 and generates support information. Finally, the instruction generation unit 45 transmits the generated support information to the substrate processing device 1 in Figure 6 (step S38) and returns the process to step S30.

[0110] In the example above, the series of processes shown in Figure 8 are performed only on one substrate processing device 1 in Figure 6. In contrast, when the substrate processing device management system 2 manages multiple substrate processing devices 1, the series of processes shown in Figure 8 are performed sequentially or in parallel on multiple substrate processing devices 1, for example.

[0111] Furthermore, the series of processes shown in Figures 9 and 10 are performed only on one substrate processing apparatus 1 shown in Figure 6. In contrast, when the substrate processing apparatus management system 2 manages multiple substrate processing apparatuses 1, the series of processes shown in Figures 9 and 10 are performed sequentially or in parallel on multiple substrate processing apparatuses 1, for example.

[0112] 8. Effects of the Embodiment In the information analysis device 3, for each of the one or more substrate processing devices 1, the degree of abnormality of the substrate processing device 1 is calculated as an abnormality score based on the invariant relationships between multiple processing information and the multiple processing information actually collected. If the abnormality score exceeds the abnormality judgment threshold, an alarm is sent to the substrate processing device 1. When calculating the abnormality score, for each of the multiple predetermined combinations of two different processing information, the degree of deviation between one processing information predicted based on the invariant information and the processing information actually collected is calculated.

[0113] In the support device 4, one or more maintenance target parts are appropriately determined from among the multiple parts constituting the substrate processing device 1, based on the multiple deviation degrees calculated by the information analysis device 3 and data-related component information.

[0114] Furthermore, for each of the one or more determined maintenance target components, a maintenance requirement value is calculated based on the component information over time, and support information is generated according to the level of the calculated maintenance requirement value. As a result, maintenance workers of the PCB processing apparatus 1 can easily identify the maintenance target components based on the generated support information, regardless of their skill level. In addition, maintenance workers can perform appropriate maintenance work on the PCB processing apparatus 1 in a short amount of time.

[0115] 9. Other Embodiments (1) In the above embodiment, the multiple substrate processing apparatuses 1A to 1C in Figure 1 have the same configuration, but the present invention is not limited thereto. Some or all of the multiple substrate processing apparatuses 1A to 1C may have different configurations from each other. Also, at least one of the multiple substrate processing apparatuses 1A to 1C in Figure 1 may be a single-wafer type substrate cleaning apparatus instead of a batch type, or it may have a configuration that performs processing other than cleaning. For example, the substrate processing apparatus 1 may be other substrate processing apparatus such as a coating apparatus, a developing apparatus, a heating apparatus, a cooling apparatus, or a transport apparatus.

[0116] (2) In the substrate processing apparatus management system 2 according to the above embodiment, the series of processes performed by the information analysis device 3 may be performed by the support device 4. Alternatively, the series of processes performed by the information analysis device 3 may be performed by one or more substrate processing apparatus 1. In this case, the information analysis device 3 becomes unnecessary.

[0117] (3) In the substrate processing apparatus management system 2 according to the above embodiment, it is not necessary for an abnormal score to be transmitted from the information analysis device 3 to the substrate processing apparatus 1.

[0118] (4) In the substrate processing apparatus management system 2 according to the above embodiment, the degree of necessity for maintenance work on the components to be maintained is classified into levels, and a maintenance requirement value is calculated in order to determine the instruction for maintenance work according to the level, but the present invention is not limited thereto.

[0119] The required maintenance values ​​do not necessarily need to be calculated. In this case, support information may be generated that includes instructions for multiple possible maintenance tasks for the determined maintenance target parts.

[0120] Alternatively, the maintenance requirement may be calculated based on other conditions instead of using the above formula (1). For example, the maintenance requirement may be "elapsed time," "number of failures," or the value obtained by dividing "elapsed time" by "expected number of years."

[0121] (5) The multiple processing information may include, in addition to or in place of, the multiple specific examples described in the above embodiment, at least one physical quantity from among the temperature in the processing chamber where the substrate W is housed, the pressure in the processing chamber where the substrate W is housed, the pressure of the gas discharged from the processing chamber where the substrate W is housed, and the moving speed of the substrate being transported by the robot. The multiple processing information may also include information regarding at least one of the drive pulse signals that drive the robot transporting the substrate W, and the output signals of a detector provided on the robot transporting the substrate W.

[0122] (6) In the above embodiment, the first storage unit 46 of the support device 4 stores data-related component information corresponding to each of the one or more substrate processing devices 1. The second storage unit 47 of the support device 4 stores time-series component information corresponding to each of the one or more substrate processing devices 1. Furthermore, the third storage unit 48 of the support device 4 stores instructions for multiple maintenance operations.

[0123] However, the present invention is not limited to the above examples. Some or all of the above data-related component information, time-dependent component information, and instructions for multiple maintenance tasks may be stored on another server located outside the support device 4. Alternatively, some or all of the data-related component information, time-dependent component information, and instructions for multiple maintenance tasks may be stored in one or more substrate processing devices 1, or in the information analysis device 3. In this case, each of the target determination unit 42, required value calculation unit 43, and instruction generation unit 45 of the support device 4 acquires the information necessary to achieve the function from outside the support device 4.

[0124] (7) The support device 4 according to the above embodiment may have an instruction output device that outputs instructions for maintenance work based on support information. In this case, the instruction output device may be, for example, a printer that prints the contents of the maintenance work instructions on paper, or a portable terminal that has a display unit that displays the contents of the maintenance work instructions and is configured to be able to communicate wirelessly with the CPU of the support device 4. Alternatively, the instruction output device may be an audio output device that announces the contents of the maintenance work instructions.

[0125] (8) When report information is generated as support information in the support device 4, the support device 4 may have a report output device that outputs reports on various maintenance tasks based on the support information. In this case, the report output device may be, for example, a printer that prints the report information on paper, or a portable terminal that has a display unit for displaying the report information and is configured to be able to communicate wirelessly with the CPU of the support device 4. Alternatively, the report output device may be an audio output device that announces the report information.

[0126] 10. Correspondence between each component of the claim and each part of the embodiment The following describes examples of the correspondence between each component of the claims and each element of the embodiments, but the present invention is not limited to the following examples. Various other elements having the configuration or function described in the claims can also be used as each component of the claims.

[0127] In the above embodiment, the substrate processing apparatus 1, 1A to 1C are examples of substrate processing apparatuses, the support apparatus 4 is an example of a support apparatus, the deviation degree acquisition unit 41 is an example of a deviation degree acquisition unit, the level determination unit 44 and the instruction generation unit 45 are examples of support information generation units, the target determination unit 42 is an example of a target determination unit, the required value calculation unit 43 is an example of a required value calculation unit, and the CPU and memory of the support apparatus 4 are examples of a computer. [Explanation of Symbols]

[0128] 1, 1A~1C...Substrate processing device, 2...Substrate processing device management system, 3...Information analysis device, 4...Support device, 4a...Display unit, 4b...Operation unit, 31...Information collection unit, 32...Score calculation unit, 33...Score transmission unit, 34...Alarm transmission unit, 41...Degree of deviation acquisition unit, 42...Target determination unit, 43...Required value calculation unit, 44...Level determination unit, 45...Instruction generation unit, 46...First memory unit, 47...Second memory unit, 48...Third memory unit, 49...Information Update unit, 100…Control device, 111…Processing tank, 112…Substrate holder, 112a…Lifting device, 113…Chemical solution piping, 113a…Chemical solution valve, 114…Pure water piping, 114a…Pure water valve, 115…Bubbler tube, 116…Gas piping, 116a…Gas valve, 117…Heater, 118…Heater drive unit, 121…Liquid level gauge, 122…Concentration meter, 123…Thermometer, 124~126…Flow meter, 127…Pressure gauge, W…Substrate

Claims

1. A support device for supporting a maintenance operation of a substrate processing apparatus, comprising: a deviation degree acquiring unit that acquires deviation degree information that indicates an invariant relationship between a plurality of pieces of processing information that indicate an operation or state related to substrate processing of the substrate processing apparatus and a degree of deviation between a plurality of pieces of processing information predicted based on a plurality of pieces of processing information actually collected from the substrate processing apparatus and the plurality of pieces of processing information actually collected; a support information generating unit configured to generate support information related to a maintenance operation of the substrate processing apparatus based on the deviation degree information.

2. the substrate processing apparatus includes a plurality of components associated with the plurality of processing information; The support device further includes a target determination unit that determines one or more parts to be subjected to the maintenance work among the plurality of parts as one or more maintenance target parts based on the deviation degree information, The support device according to claim 1 , wherein the support information includes information indicating one or more maintenance target parts determined by the target determination unit.

3. A plurality of combinations of two different pieces of processing information are determined for the plurality of pieces of processing information; Each combination includes first processing information and second processing information; For each combination, the second processing information actually collected from the substrate processing apparatus and the first processing information predicted based on the invariant relationship are generated as first predicted processing information, and a degree of deviation between the generated first predicted processing information and the first processing information actually collected from the substrate processing apparatus is calculated as a first deviation degree; For each combination, the first processing information actually collected from the substrate processing apparatus and the second processing information predicted based on the invariant relationship are generated as second predicted processing information, and a degree of deviation between the generated second predicted processing information and the second processing information actually collected from the substrate processing apparatus is calculated as a second deviation degree; the deviation degree acquisition unit acquires, as the deviation degree information, a plurality of first deviation degrees calculated for the plurality of combinations and a plurality of second deviation degrees calculated for the plurality of combinations, The target determination unit is extracting, from the plurality of combinations, one or more combinations in which the first deviation degree exceeds a predetermined first threshold value and one or more combinations in which the second deviation degree exceeds a predetermined second threshold value; The support device according to claim 2 , further comprising: a support device for supporting a maintenance target component that is provided to the maintenance target component and a support device for supporting the maintenance target component, the support device being configured to support the maintenance target component and the support device being configured to support the maintenance target component.

4. The system further includes a required value calculation unit that acquires information on a state of the maintenance target part that changes over time as aging part information for each of the one or more maintenance target parts determined by the target determination unit, and calculates a required value indicating a degree of necessity of the maintenance work for the maintenance target part based on the acquired aging part information; The support information generation unit 4. The support device according to claim 2 or 3, further comprising: a support unit for supporting one or more maintenance target parts determined by said target determination unit, said support unit determining to which of a plurality of predetermined necessary levels a necessary value calculated by said necessary value calculation unit belongs; and said support information includes information on a maintenance operation for said maintenance target part that is predetermined according to the determined necessary level.

5. Each of the substrate processing apparatuses is a substrate cleaning apparatus that cleans a substrate using a cleaning liquid, The support device according to any one of claims 1 to 4, wherein the plurality of processing information includes at least one of an amount of cleaning liquid supplied to the substrate, a temperature of the cleaning liquid supplied to the substrate, and a concentration of the cleaning liquid supplied to the substrate.

6. A method for supporting maintenance work of a substrate processing apparatus, comprising: acquiring deviation degree information indicating an invariant relationship between a plurality of pieces of processing information indicating an operation or state related to substrate processing of the substrate processing apparatus and a degree of deviation between a plurality of pieces of processing information predicted based on a plurality of pieces of processing information actually collected from the substrate processing apparatus and the plurality of pieces of processing information actually collected; generating support information relating to a maintenance operation of the substrate processing apparatus based on the deviation information.

7. A support program for causing a computer to execute a support process for supporting a maintenance operation of a substrate processing apparatus, The support process includes: acquiring deviation degree information indicating an invariant relationship between a plurality of pieces of processing information indicating an operation or state related to the processing of a substrate in the substrate processing apparatus and a degree of deviation between a plurality of pieces of processing information predicted based on a plurality of pieces of processing information actually collected from the substrate processing apparatus and the plurality of pieces of processing information actually collected; and generating support information relating to a maintenance operation of the substrate processing apparatus based on the deviation information.

Images