Information processing apparatus, inference apparatus, machine learning apparatus, information processing method, inference method, and machine learning method

By obtaining the action status information of the substrate processing device and using machine learning models to predict the status of the cleaning tool, the problem of not being able to grasp the status of the cleaning tool in detail in the prior art is solved, and the management accuracy and service life of the cleaning tool are improved.

CN119054052APending Publication Date: 2024-11-29EBARA CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202380031327.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-30
Filing Date
2023-03-02
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The prior art cannot grasp the state of the cleaning tool in detail, especially when the operation state of the substrate processing device changes, the state of the cleaning tool cannot be accurately predicted by insufficient cumulative usage times and time management.

Method used

The information processing device obtains the operation status information of the substrate processing device, including the state of the substrate holding part, the cleaning fluid supply part and the cleaning tool cleaning part, and uses the machine learning model to predict the state of the cleaning tool, and combines the operation status information of the substrate processing device to predict the cleaning. The status of the tool.

Benefits of technology

It is possible to properly predict the state of the cleaning tool according to the operating state of the substrate processing device, improve the management accuracy of the state of the cleaning tool, avoid unnecessary replacement and extend service life.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119054052A_ABST
    Figure CN119054052A_ABST
Patent Text Reader

Abstract

An information processing apparatus (5) according to the present invention is provided with an information acquisition unit (500) that acquires operation state information as an operation state when the substrate processing apparatus operates, and a state prediction unit (501), the substrate processing apparatus being provided with: a substrate holding unit that holds a substrate; a cleaning fluid supply unit that supplies a substrate cleaning fluid to the substrate; a substrate cleaning unit that rotatably supports the cleaning tool and cleans the substrate by bringing the cleaning tool into contact with the substrate; and a cleaning tool cleaning unit that cleans the cleaning tool with a cleaning tool cleaning fluid, the operation state information including substrate holding unit state information, cleaning fluid supply unit state information, substrate cleaning unit state information, and cleaning tool cleaning unit state information. The state prediction unit predicts cleaning tool state information corresponding to the operation state information by inputting the operation state information acquired by the information acquisition unit (500) into a learning model that learns the correlation between the operation state information and the cleaning tool state information by machine learning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to an information processing device, an inference device, a machine learning device, an information processing method, an inference method and a machine learning method. Background Art

[0002] A substrate processing device that performs various processes on substrates such as semiconductor wafers is known as a substrate processing device that performs chemical mechanical polishing (CMP). For example, the substrate processing device rotates a polishing table with a polishing pad and supplies a polishing liquid (slurry) to the polishing pad from a liquid supply nozzle, and presses the substrate against the polishing pad through a polishing head called a top ring to chemically and mechanically polish the substrate. Then, in order to remove foreign matter such as polishing chips attached to the polished substrate, a substrate cleaning fluid is supplied to the polished substrate and the substrate is contacted with a cleaning tool for friction cleaning, and the substrate is further dried, thereby completing a series of processes and transferring to the processing of the next substrate.

[0003] When the above series of treatments are repeated, the cleaning tool will gradually become worn and contaminated, so it is necessary to replace the cleaning tool. However, the replacement period of the cleaning tool is managed, for example, by the cumulative number of times the cleaning tool has been used and the cumulative usage time (for example, refer to Patent Document 1).

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: Japanese Patent Application Laid-Open No. 10-242092

[0007] (Problem to be solved by the invention)

[0008] In Patent Document 1, the cumulative number of times and the cumulative time of use of the cleaning tool are calculated by accumulating the number of times and the time when the cleaning tool contacts the substrate through a counter and a timing unit. However, because the state of the cleaning tool changes not only according to the operating state of the substrate processing device when the cleaning tool contacts the substrate, but also when the cleaning tool does not contact the substrate, for example, when the cleaning tool is cleaned (self-cleaned) by a cleaning fluid, it still changes according to the operating state of the substrate processing device. Therefore, it is impossible to grasp the state of the cleaning tool in detail by only managing the cumulative number of times and the cumulative time of use.

[0009] On the other hand, in order to use the cleaning part to clean the substrate, the action state of each part of the substrate processing device (for example, a substrate holding part that holds the substrate; a cleaning fluid supply part that supplies a substrate cleaning fluid to the substrate; a substrate cleaning part that makes a cleaning tool contact the substrate to clean the substrate; and a cleaning tool cleaning part that cleans the cleaning tool with a cleaning tool cleaning fluid) is an element that affects the state of the cleaning tool, and the cleaning tool is complicated and interacts with each other. Therefore, it is difficult to correctly analyze how each action state will affect the state of the cleaning tool. Summary of the invention

[0010] In view of the above problems, the present invention aims to provide an information processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method that can appropriately predict the state of a cleaning tool according to the operation state of a substrate processing device.

[0011] (Methods to solve the problem)

[0012] In order to achieve the above object, an information processing device according to one embodiment of the present invention comprises:

[0013] An information acquisition unit, which acquires action status information as an action status of a substrate processing device when the substrate processing device is in action, wherein the substrate processing device comprises a substrate holding unit, a cleaning fluid supply unit, a substrate cleaning unit and a cleaning tool cleaning unit, wherein the substrate holding unit holds a substrate, the cleaning fluid supply unit supplies a substrate cleaning fluid to the substrate, the substrate cleaning unit supports a cleaning tool so as to be rotatable and makes the cleaning tool contact the substrate to clean the substrate, and the cleaning tool cleaning unit cleans the cleaning tool with a cleaning tool cleaning fluid, wherein the action status information comprises: substrate holding unit status information indicating a status of the substrate holding unit, cleaning fluid supply unit status information indicating a status of the cleaning fluid supply unit, substrate cleaning unit status information indicating a status of the substrate cleaning unit, and cleaning tool cleaning unit status information indicating a status of the cleaning tool cleaning unit; and

[0014] A state prediction unit, which inputs the action state information obtained by the information acquisition unit into a learning model, thereby predicting cleaning tool state information corresponding to the action state information. The learning model learns the correlation between the action state information and the cleaning tool state information through machine learning. The cleaning tool state information represents the state of the cleaning tool when the substrate processing device operates in the action state indicated by the action state information.

[0015] Effects of the Invention

[0016] When an information processing device using one embodiment of the present invention is used, the state of the cleaning tool can be appropriately predicted based on the action state of the substrate processing device by inputting action state information including substrate holding unit state information, cleaning fluid supply unit state information, substrate cleaning unit state information, and cleaning tool cleaning unit state information into a learning model to predict the cleaning tool state information corresponding to the action state information.

[0017] Problems, structures, and effects other than those described above will become apparent from the modes for carrying out the invention described later. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 1 is a diagram showing the overall configuration of an example of the substrate processing system 1 .

[0019] Figure 2 It is a plan view showing an example of the substrate processing apparatus 2 .

[0020] Figure 3 It is a perspective view showing an example of the first polishing section 22A to the fourth polishing section 22D.

[0021] Figure 4 It is a perspective view showing an example of the first roll sponge cleaning section 24A and the second roll sponge cleaning section 24B.

[0022] Figure 5 It is a perspective view showing an example of the first pen-shaped sponge cleaning unit 24C and the second pen-shaped sponge cleaning unit 24D.

[0023] Figure 6 It is a perspective view showing an example of the first drying section 24E and the second drying section 24F.

[0024] Figure 7 It is a block diagram showing an example of the substrate processing apparatus 2 .

[0025] Figure 8 It is a diagram showing a hardware configuration of an example of the computer 900 .

[0026] Fig. 9 It is a data structure diagram showing an example of the production history information 30 managed by the database device 3.

[0027] Fig.10 2 is a data structure diagram showing an example of the cleaning test information 31 managed by the database device 3 .

[0028] Fig.11 It is a block diagram showing an example of the machine learning device 4 according to the first embodiment.

[0029] Fig.12 FIG. 1 is a diagram showing an example of the first learning model 10A and the first learning data 11A.

[0030] Fig.13 This is a flowchart showing an example of a machine learning method performed by the machine learning device 4 .

[0031] Fig.14 This is a block diagram showing an example of the information processing device 5 according to the first embodiment.

[0032] Fig.15 This is a functional explanation diagram showing an example of the information processing device 5 according to the first embodiment.

[0033] Fig.16 This is a flowchart showing an example of an information processing method implemented by the information processing device 5 .

[0034] Fig.17 It is a block diagram showing an example of a machine learning device 4a according to the second embodiment.

[0035] Fig.18 FIG. 1 is a diagram showing an example of the second learning model 10B and the second learning data 11B.

[0036] Fig.19 This is a block diagram showing an example of the information processing device 5a functioning as the information processing device 5a according to the second embodiment.

[0037] Fig. 20 This is a functional explanatory diagram showing an example of an information processing device 5a according to the second embodiment. DETAILED DESCRIPTION

[0038] Hereinafter, embodiments for implementing the present invention will be described with reference to the drawings. Hereinafter, the scope necessary for the description to achieve the purpose of the present invention is schematically shown, and the description will be mainly based on the scope necessary for the description of this part of the present invention, and the omitted description belongs to the known technology.

[0039] (First Implementation Method)

[0040] Figure 1 1 is an overall configuration diagram showing an example of a substrate processing system 1. The substrate processing system 1 of the present embodiment functions as a system for managing a series of substrate processing as follows: a chemical mechanical polishing process (hereinafter referred to as a "polishing process") in which a substrate W such as a semiconductor wafer (hereinafter referred to as a "wafer") is pressed against a polishing pad to polish the surface of the wafer W flatly; a cleaning process in which the surface of the wafer W is cleaned by bringing the polished wafer W into contact with a cleaning tool; and the like.

[0041] The substrate processing system 1 is mainly composed of: a substrate processing device 2, a database device 3, a machine learning device 4, an information processing device 5 and a user terminal device 6. Each device 2 to 6 is, for example, a general-purpose or special-purpose computer (see the following description). Figure 8 ) and connected to a wired or wireless network 7, and can send and receive various data ( Figure 1 In addition, the number of each device 2 to 6 and the connection structure of the network 7 are not limited to Figure 1 The examples may also be changed appropriately.

[0042] The substrate processing apparatus 2 is composed of a plurality of units, and is an apparatus for performing a series of substrate processing on one or more wafers W, such as loading, grinding, cleaning, drying, film thickness measurement, unloading, etc. At this time, the substrate processing apparatus 2 controls the operation of each unit while referring to the apparatus setting information 265 composed of a plurality of apparatus parameters set in each unit, and the substrate processing plan information 266 that determines the operation status of the grinding process, the cleaning process, the drying process, etc.

[0043] The substrate processing apparatus 2 sends various reports R to the database apparatus 3, the user terminal apparatus 6, etc. in accordance with the operation of each unit. The various reports R include, for example, process information for determining the wafer W to be the target when performing substrate processing, apparatus status information indicating the status of each unit when performing each processing, event information detected by the substrate processing apparatus 2, and operation information of the user (operator, production manager, maintenance manager, etc.) on the substrate processing apparatus 2.

[0044] The database device 3 is a device for managing production history information 30 and cleaning test information 31. The production history information 30 is about the history of using the cleaning tool for production to process the substrate, and the cleaning test information 31 is about the history of using the cleaning tool for the test to perform the cleaning process (hereinafter referred to as "cleaning test"). In addition, in addition to the above, the database device 3 can also store device setting information 265 and substrate processing plan information 266, and at this time, the substrate processing device 2 can also refer to this information.

[0045] When the substrate processing apparatus 2 processes the substrate using the cleaning tool for production, the database device 3 receives various reports R from the substrate processing apparatus 2 at any time and registers them in the production history information 30 , thereby storing the reports R about the substrate processing in the production history information 30 .

[0046] When the substrate processing device 2 uses the cleaning tool for the test to perform the cleaning test, the database device 3 receives various reports R (including at least the device status information) from the substrate processing device 2 at any time, logs them in the cleaning test information 31, and logs the test results of the cleaning test accordingly, thereby storing the report R and the test results of the cleaning test in the cleaning test information 31. The cleaning test can also be performed by the substrate processing device 2 for production, or by a cleaning test device for the test (not shown) that can reproduce the same cleaning process as the substrate processing device 2. Various cleaning tool measuring devices (not shown) are set in the cleaning tool for the test and the cleaning test device. The various cleaning tool measuring devices are used to measure the weight, moisture content, hardness, and cleanliness of the cleaning tool as the cleaning tool, and the measured values ​​of the cleaning tool measuring devices are logged in the cleaning test information 31 as the test results.

[0047] The machine learning device 4 acts as a main body in the learning phase of machine learning, for example, obtains a part of the cleaning test information 31 from the database device 3 as the first learning data 11A, and generates a first learning model 10A for use by the information processing device 5 through machine learning. The learned first learning model 10A is provided to the information processing device 5 via the network 7 and the recording medium.

[0048] The information processing device 5 acts as the main body of the inference stage of machine learning, and uses the first learning model 10A generated by the machine learning device 4 to predict the state of the cleaning tool when the cleaning tool for production is used to perform the cleaning process caused by the substrate processing device 2, and sends the cleaning tool state information as the prediction result to the database device 3, the user terminal device 6, etc. The information processing device 5 can predict the cleaning tool state information after the cleaning process is performed (post-prediction processing), during the cleaning process (real-time prediction processing), or before the cleaning process is performed (pre-prediction processing).

[0049] The user terminal device 6 is a terminal device used by the user, and may be a fixed device or a portable device. The user terminal device 6 accepts various input operations via a display screen such as an application program or a web browser, and displays various information (e.g., notification events, substrate status information, production history information 30, processing test information 31, etc.) via the display screen.

[0050] (Substrate processing device 2)

[0051] Figure 22 is a top view showing an example of a substrate processing apparatus 2. The substrate processing apparatus 2 is configured by including a loading / unloading unit 21, a polishing unit 22, a substrate transport unit 23, a processing unit 24, a film thickness measuring unit 25, and a control unit 26 inside a frame 20 which is roughly rectangular in plan view. The loading / unloading unit 21 and the polishing unit 22, the substrate transport unit 23, and the processing unit 24 are divided by a first partition wall 200A, and the substrate transport unit 23 and the processing unit 24 are divided by a second partition wall 200B.

[0052] (Loading / unloading unit)

[0053] The loading / unloading unit 21 comprises: a first front loading section 210A to a fourth front loading section 210D for loading a wafer cassette (FOUP, etc.) that can store multiple wafers W in the up-down direction; a transfer robot 211 that can move up and down along the storage direction (up-down direction) of the wafers W stored in the wafer cassette; and a horizontal moving mechanism section 212 that enables the transfer robot 211 to move along the arrangement direction (short side direction of the frame 20) of the first front loading section 210A to the fourth front loading section 210D.

[0054] The transfer robot 211 is configured to be able to access the wafer cassettes loaded on the first front loading section 210A to the fourth front loading section 210D, the substrate transfer unit 23 (specifically, the elevator 232 described later), the processing unit 24 (specifically, the first drying section 24E and the second drying section 24F described later), and the film thickness measurement unit 25, and is provided with upper and lower two-stage arms (not shown) for transferring wafers W between them. The lower arm is used when transferring wafers W before processing, and the upper arm is used when transferring wafers W after processing. When transferring wafers W to the substrate transfer unit 23 and the processing unit 24, a shutter (not shown) provided on the first partition wall 200A is opened and closed.

[0055] (Grinding unit)

[0056] The polishing unit 22 includes first to fourth polishing sections 22A to 22D that respectively perform polishing (planarization) on the wafer W. The first to fourth polishing sections 22A to 22D are arranged side by side along the longitudinal direction of the frame 20 .

[0057] Figure 3 1 is a perspective view showing an example of the first to fourth polishing sections 22A to 22D. The first to fourth polishing sections 22A to 22D have the same basic configuration and function.

[0058] The first grinding section 22A to the fourth grinding section 22D respectively include: a grinding table 220 that rotatably supports a grinding pad 2200 having a grinding surface; a top ring (grinding head) 221 that holds a wafer W and is used to press the wafer W against the grinding pad 2200 on the grinding table 220 for grinding; a grinding fluid supply nozzle 222 that supplies grinding fluid to the grinding pad 2200; a dresser 223 that rotatably supports a dressing disk 2230 and makes the dressing disk 2230 contact the grinding surface of the grinding pad 2200 to dress the grinding pad 2200; and an atomizer 224 that sprays a cleaning fluid on the grinding pad 2200.

[0059] The polishing table 220 includes a rotational movement mechanism 220 b that is supported by a polishing table shaft 220 a and drives the polishing table 220 to rotate about its axis, and a temperature control mechanism 220 c that controls the surface temperature of the polishing pad 2200 .

[0060] The top ring 221 includes: a rotational movement mechanism portion 221c which is supported by a top ring shaft 221a which is movable in the up-down direction and drives the top ring 221 to rotate around its axis; a vertical movement mechanism portion 221d which moves the top ring 221 in the up-down direction; and a rocking movement mechanism portion 221e which rotates (rocks) the top ring 221 around the support shaft 221b as a rotation center.

[0061] The polishing fluid supply nozzle 222 includes: a swing movement mechanism 222b supported by a support shaft 222a, which makes the polishing fluid supply nozzle 222 rotate around the support shaft 222a; a flow rate adjustment unit 222c for adjusting the flow rate of the polishing fluid; and a temperature adjustment mechanism 222d for adjusting the temperature of the polishing fluid. The polishing fluid is a polishing liquid (slurry) or pure water, and may also contain a chemical liquid, or a dispersant may be added to the polishing liquid.

[0062] The dresser 223 includes: a rotational movement mechanism portion 223c which is supported by a dresser shaft 223a which can move in the up-down direction and drives the dresser 223 to rotate around its axis; a vertical movement mechanism portion 223d which moves the dresser 223 in the up-down direction; and a rocking movement mechanism portion 223e which rotates the dresser 223 around the support shaft 223b as the rotation center.

[0063] The atomizer 224 includes: a swing mechanism 224b that is supported by a support shaft 224a and rotates the atomizer 224 around the support shaft 224a; and a flow rate adjustment unit 224c that adjusts the flow rate of a cleaning fluid. The cleaning fluid is a mixed fluid of a liquid (e.g., pure water) and a gas (e.g., nitrogen) or a liquid (e.g., pure water).

[0064] The wafer W is held by suction on the lower surface of the top ring 221 , and after being moved to a predetermined polishing position on the polishing table 220 , the top ring 221 presses the polishing surface of the polishing pad 2200 to which the polishing fluid is supplied from the polishing fluid supply nozzle 222 , for polishing.

[0065] (Substrate transport unit)

[0066] like Figure 2 As shown, the substrate transport unit 23 includes: a first linear conveyor 230A and a second linear conveyor 230B that can be horizontally moved along the arrangement direction of the first grinding section 22A to the fourth grinding section 22D (the length direction of the frame 20); a swing conveyor 231 arranged between the first linear conveyor 230A and the second linear conveyor 230B; an elevator 232 arranged on the side of the loading / unloading unit 21; and a temporary placement table 233 for the chip W arranged on the side of the processing unit 24.

[0067] The first linear conveyor 230A is disposed adjacent to the first polishing section 22A and the second polishing section 22B, and is a mechanism for transferring the wafer W between four transfer positions (first transfer position TP1 to fourth transfer position TP4 in order from the loading / unloading unit 21 side). The second transfer position TP2 is a position for transferring the wafer W to the first polishing section 22A, and the third transfer position TP3 is a position for transferring the wafer W to the second polishing section 22B.

[0068] The second linear conveyor 230B is disposed adjacent to the third polishing section 22C and the fourth polishing section 22D, and is a mechanism for transferring the wafer W between three transfer positions (the fifth transfer position TP5 to the seventh transfer position TP7 in order from the loading / unloading unit 21 side). The sixth transfer position TP6 is a position for transferring the wafer W to the third polishing section 22C, and the seventh transfer position TP7 is a position for transferring the wafer W to the fourth polishing section 22D.

[0069] The swing conveyor 231 is arranged adjacent to the fourth transfer position TP4 and the fifth transfer position TP5, and has an arm that can move between the fourth transfer position TP4 and the fifth transfer position TP5. The swing conveyor 231 is a mechanism for transferring the wafer W between the first linear conveyor 230A and the second linear conveyor 230B, and temporarily placing the wafer W on the temporary placement table 233. The elevator 232 is arranged adjacent to the first transfer position TP1, and is a mechanism for transferring the wafer W to the transfer robot 211 of the loading / unloading unit 21. When transferring the wafer W, the shutter (not shown) provided on the first partition wall 200A is opened and closed.

[0070] (Processing unit)

[0071] Processing unit 24 Figure 2As shown, as a substrate cleaning device using a roller sponge 2400, a first roller sponge cleaning section 24A and a second roller sponge cleaning section 24B are provided on two upper and lower steps; as a substrate cleaning device using a pen-shaped sponge 2401, a first pen-shaped sponge cleaning section 24C and a second pen-shaped sponge cleaning section 24D are provided on two upper and lower steps; as a substrate drying device for drying a wafer W after cleaning, a first drying section 24E and a second drying section 24F are provided on two upper and lower steps; and a first conveying section 24G and a second conveying section 24H for conveying the wafer W. In addition, the number and arrangement of the roller sponge cleaning sections 24A, 24B, the pen-shaped sponge cleaning sections 24C, 24D, the drying sections 24E, 24F, and the conveying sections 24G, 24H are not limited to Figure 2 For example, the positions of the roller sponge cleaning parts 24A and 24B and the pen-shaped sponge cleaning parts 24C and 24D may be exchanged.

[0072] The processing unit 24 includes the first roller sponge cleaning unit 24A and the second roller sponge cleaning unit 24B, the first conveying unit 24G, the first pen-shaped sponge cleaning unit 24C and the second pen-shaped sponge cleaning unit 24D, the second conveying unit 24H, and the first drying unit 24E and the second drying unit 24F, respectively, along the first linear conveyor 230A and the second linear conveyor 230B in a divided state. The processing unit 24 sequentially performs: a primary cleaning process by one or both of the first roller sponge cleaning unit 24A and the second roller sponge cleaning unit 24B; a secondary cleaning process by one or both of the first pen-shaped sponge cleaning unit 24C and the second pen-shaped sponge cleaning unit 24D; and a drying process by one or both of the first drying unit 24E and the second drying unit 24F on the wafer W after the polishing process. In addition, the processing order of each part 24A to 24H of the processing unit 24 may be appropriately changed, and a part of the processing may be omitted. For example, the cleaning process of the roller sponge cleaning parts 24A and 24B may be omitted, and the cleaning process of the pen sponge cleaning parts 24C and 24D may be started. In addition, the processing unit 24 may perform a polishing cleaning process by replacing one of the roller sponge cleaning parts 24A and 24B and the pen sponge cleaning parts 24C and 24D or by further including a polishing cleaning part (not shown). In addition, the processing unit 24 of the present embodiment is described with respect to the case where the wafer W is placed horizontally and held (horizontally held), but the wafer W may be held vertically or tilted.

[0073] The roller sponge 2400 and the pen sponge 2401 are made of synthetic resin such as PVA and nylon and have a porous structure. The roller sponge 2400 and the pen sponge 2401 function as cleaning tools for friction cleaning of the wafer W and are replaceably mounted on the first roller sponge cleaning section 24A and the second roller sponge cleaning section 24B, and the first pen sponge cleaning section 24C and the second pen sponge cleaning section 24D.

[0074] The first transfer unit 24G includes a first transfer robot 246A that can move in the up-down direction. The first transfer robot 246A is configured to be able to access the temporary table 233 of the substrate transfer unit 23, the first roller sponge cleaning unit 24A and the second roller sponge cleaning unit 24B, and the first pen-shaped sponge cleaning unit 24C and the second pen-shaped sponge cleaning unit 24D, and includes upper and lower two-stage arms for transferring the wafer W therebetween. For example, the lower arm is used when transferring the wafer W before cleaning, and the upper arm is used when transferring the wafer W after cleaning. When transferring the wafer W to the temporary table 233, a shutter (not shown) provided on the second partition wall 200B is opened and closed.

[0075] The second transfer unit 24H includes a second transfer robot 246B movable in the vertical direction. The second transfer robot 246B is configured to access the first and second pen-shaped sponge cleaning units 24C and 24D, and the first and second drying units 24E and 24F, and includes an arm for transferring wafers W therebetween.

[0076] Figure 4 1 is a perspective view showing an example of the first roller sponge cleaning unit 24A and the second roller sponge cleaning unit 24B. The first roller sponge cleaning unit 24A and the second roller sponge cleaning unit 24B have the same basic structure and function. Figure 4 In the example, the first roll sponge cleaning unit 24A and the second roll sponge cleaning unit 24B include a pair of roll sponges 2400 disposed one above the other so as to sandwich the cleaned surface (front surface and back surface) of the wafer W.

[0077] The first roller sponge cleaning section 24A and the second roller sponge cleaning section 24B respectively include: a substrate holding section 241 for holding the chip W; a cleaning fluid supplying section 242 for supplying a substrate cleaning fluid to the chip W; a substrate cleaning section 240 for rotatably supporting the roller sponge 2400 and making the roller sponge 2400 contact the chip W to clean the chip W; a cleaning tool cleaning section 243 for cleaning the roller sponge 2400 with a cleaning tool cleaning fluid (self-cleaning); and an environmental sensor 244 for measuring the internal space state of the frame 20 performing the cleaning process.

[0078] The substrate holding unit 241 includes a substrate holding mechanism 241 a for holding a plurality of side edge portions of the wafer W and a substrate rotating mechanism 241 b for rotating the wafer W around a third rotation axis perpendicular to the surface of the wafer W to be cleaned. Figure 4 The substrate holding mechanism 241a includes four rollers, at least one of which is movable in a holding direction or a separation direction relative to the side edge of the wafer W, and the substrate rotating mechanism 241b drives and rotates at least one of the rollers.

[0079] The cleaning fluid supply unit 242 includes: a cleaning fluid supply nozzle 242a for supplying a substrate cleaning fluid to the cleaning surface of the wafer W; a rocking movement mechanism unit 242b for causing the cleaning fluid supply nozzle 242a to rotate; a flow rate regulating unit 242c for regulating the flow rate and pressure of the substrate cleaning fluid; and a temperature regulating mechanism unit 242d for regulating the temperature of the substrate cleaning fluid. The substrate cleaning fluid may also be any one of pure water (rinsing liquid), a chemical liquid, and a mixture of these (for example, the concentration can be adjusted by adjusting the flow rate of pure water and the chemical liquid through the flow rate regulating unit 242c). The cleaning fluid supply nozzle 242a may be configured as follows: Figure 4 As shown, a nozzle for pure water and a nozzle for chemical solution may be provided separately. In addition, the substrate cleaning fluid may be a liquid, a double fluid of a mixture of liquid and gas, or may contain a solid such as dry ice.

[0080] The substrate cleaning unit 240 includes: a cleaning tool rotating mechanism unit 240a that rotates the roller sponge 2400 around a first rotation axis parallel to the surface to be cleaned of the wafer W; a vertical movement mechanism unit 240b that moves at least one of the pair of roller sponges 2400 in the vertical direction in order to change the height of the pair of roller sponges 2400 and the distance between the two; and a linear movement mechanism unit 240c that moves the pair of roller sponges 2400 in a linear direction in the horizontal direction. The vertical movement mechanism unit 240b and the linear movement mechanism unit 240c function as a cleaning tool moving mechanism unit that moves the relative position of the roller sponge 2400 and the surface to be cleaned of the wafer W.

[0081] The cleaning tool cleaning section 243 is arranged at a position that does not interfere with the wafer W, and includes: a cleaning tool cleaning tank 243a that can store and discharge a cleaning tool cleaning fluid; a cleaning tool cleaning plate 243b that is received in the cleaning tool cleaning tank 243a and presses the roller sponge 2400; a flow rate regulating section 243c that regulates the flow rate and pressure of the cleaning tool cleaning fluid supplied to the cleaning tool cleaning tank 243a; and a flow rate regulating section 243d that regulates the flow rate and pressure of the cleaning tool cleaning fluid that flows inside the roller sponge 2400 and is discharged to the outside from the outer peripheral surface of the roller sponge 2400. The cleaning tool cleaning fluid may also be any one of pure water (rinsing liquid), chemical liquid, and a mixture thereof (for example, the concentration can be adjusted by adjusting the flow rate of pure water and chemical liquid through the flow rate regulating section 243c).

[0082] The environmental sensor 244 includes, for example, a temperature sensor 244a, a humidity sensor 244b, an air pressure sensor 244c, an oxygen concentration sensor 244d, and a microphone (sound sensor) 244e. In addition, the environmental sensor 244 may also include a camera (image sensor) that can capture the surface, temperature distribution, airflow distribution, etc. of the wafer W and the roller sponge 2400 during or before and after the cleaning process. The camera's capture object is not limited to visible light, and may also be infrared light, ultraviolet light, etc.

[0083] In one cleaning process of the first roller sponge cleaning section 24A and the second roller sponge cleaning section 24B, the wafer W is rotated by the substrate rotating mechanism section 241b while being held by the substrate holding mechanism section 241a. Then, while the substrate cleaning fluid is supplied from the cleaning fluid supply nozzle 242a to the cleaned surface of the wafer W, the roller sponge 2400 rotated about the axis by the cleaning tool rotating mechanism section 240a cleans the wafer W by sliding contact with the cleaned surface of the wafer W. Then, the substrate cleaning section 240 moves the roller sponge 2400 to the cleaning tool cleaning tank 243a, for example, rotates the roller sponge 2400, or presses the roller sponge 2400 on the cleaning tool cleaning plate 243b, and supplies the cleaning tool cleaning fluid to the roller sponge 2400 through the flow rate regulating section 243d to clean the roller sponge 2400.

[0084] Figure 5 1 is a perspective view showing an example of the first pen-shaped sponge cleaning unit 24C and the second pen-shaped sponge cleaning unit 24D. The first pen-shaped sponge cleaning unit 24C and the second pen-shaped sponge cleaning unit 24D have the same basic structure and function.

[0085] The first pen-type sponge cleaning unit 24C and the second pen-type sponge cleaning unit 24D are respectively provided with: a substrate holding unit 241 for holding a wafer W; a cleaning fluid supply unit 242 for supplying a substrate cleaning fluid to the wafer W; a substrate cleaning unit 240 for rotatably supporting a pen-type sponge 2401 and bringing the pen-type sponge 2401 into contact with the wafer W to clean the wafer W; a cleaning tool cleaning unit 243 for cleaning (self-cleaning) the pen-type sponge 2401 with a cleaning tool cleaning fluid; and an environmental sensor 244 for measuring the internal space state of the rack 20 for performing cleaning processing. The cleaning fluid supply unit 242 corresponds to a processing fluid supply unit for supplying a substrate cleaning fluid as a substrate processing fluid. Hereinafter, the pen-type sponge cleaning units 24C and 24D will be mainly described as being different from the roller sponge cleaning units 24A and 24B.

[0086] The substrate holding unit 241 includes a substrate holding mechanism 241 c that holds a plurality of side edge portions of the wafer W and a substrate rotating mechanism 241 d that rotates the wafer W around a third rotation axis perpendicular to the surface of the wafer W to be cleaned. Figure 5 In the example, the substrate holding mechanism 241c is four chucks, and at least one chuck is configured to be movable in a holding direction or a separation direction relative to the side edge of the wafer W, and the substrate rotating mechanism 241d drives the support shafts connected to the four chucks to rotate.

[0087] The cleaning fluid supply unit 242 and Figure 4 The device is similarly configured to include a cleaning fluid supply nozzle 242a, a swing movement mechanism 242b, a flow rate adjustment section 242c, and a temperature adjustment mechanism 242d.

[0088] The substrate cleaning unit 240 includes a cleaning tool rotating mechanism 240d for rotating the pen-shaped sponge 2401 around a second rotation axis perpendicular to the surface to be cleaned of the wafer W, a vertical movement mechanism 240e for moving the pen-shaped sponge 2401 in the vertical direction, and a swing movement mechanism 240f for rotating the pen-shaped sponge 2401 in the horizontal direction. The vertical movement mechanism 240e and the swing movement mechanism 240f function as a cleaning tool moving mechanism for moving the relative position of the pen-shaped sponge 2401 and the surface to be cleaned of the wafer W.

[0089] The cleaning tool cleaning section 243 is arranged at a position that does not interfere with the chip W, and comprises: a cleaning tool cleaning tank 243e that can store and discharge a cleaning tool cleaning fluid; a cleaning tool cleaning plate 243f that is accommodated in the cleaning tool cleaning tank 243e and presses the pen-shaped sponge 2401; a flow regulating section 243g that regulates the flow rate and pressure of the cleaning tool cleaning fluid supplied to the cleaning tool cleaning tank 243e; and a flow regulating section 243h that regulates the flow rate and pressure of the cleaning tool cleaning fluid that flows through the inner side of the pen-shaped sponge 2401 and is discharged to the outside from the outer surface of the pen-shaped sponge 2401.

[0090] The environment sensor 244 includes, for example, a temperature sensor 244a, a humidity sensor 244b, an air pressure sensor 244c, an oxygen concentration sensor 244d, and a microphone (sound sensor) 244e. In addition, the environment sensor 244 may also include a camera (image sensor) that can capture images of the surface, temperature distribution, airflow distribution, etc. of the wafer W and the pen-shaped sponge 2401 during or before and after the cleaning process. The camera's capture object is not limited to visible light, and may also be infrared light, ultraviolet light, etc.

[0091] In the secondary cleaning process of the first pen-type sponge cleaning unit 24C and the second pen-type sponge cleaning unit 24D, the wafer W is rotated by the substrate rotating mechanism unit 241d while being held by the substrate holding mechanism unit 241c. Then, the pen-type sponge 2401 rotated about the axis by the cleaning tool rotating mechanism unit 240d cleans the wafer W by sliding contact with the cleaned surface of the wafer W while the substrate cleaning fluid is supplied from the cleaning fluid supply nozzle 242a. Then, the substrate cleaning unit 240 moves the pen-type sponge 2401 to the cleaning tool cleaning tank 243e, for example, rotates the pen-type sponge 2401 or presses it on the cleaning tool cleaning plate 243f, and supplies the cleaning tool cleaning fluid to the pen-type sponge 2401 through the flow rate adjustment unit 243h to clean the pen-type sponge 2401.

[0092] Figure 6 24E and 24F are perspective views showing an example of the first drying section 24E and the second drying section 24F. The first drying section 24E and the second drying section 24F have the same basic configuration and function.

[0093] The first drying section 24E and the second drying section 24F respectively include: a substrate holding section 241 for holding the wafer W; a drying fluid supply section 245 for supplying a substrate drying fluid to the wafer W; and an environmental sensor 244 for measuring the internal space state of the rack 20 for performing the drying process.

[0094] The substrate holding unit 241 includes a substrate holding mechanism 241 e that holds a plurality of side edge portions of the wafer W and a substrate rotating mechanism 241 f that rotates the wafer W about a third rotation axis that is perpendicular to the surface of the wafer W to be cleaned.

[0095] The drying fluid supply unit 245 includes: a drying fluid supply nozzle 245a for supplying the substrate drying fluid to the cleaned surface of the chip W; an up-and-down moving mechanism unit 245b for moving the drying fluid supply nozzle 245a in the up-and-down direction; a shaking moving mechanism unit 245c for rotating the drying fluid supply nozzle 245a in the horizontal direction; a flow rate regulating unit 245d for regulating the flow rate and pressure of the substrate drying fluid; and a temperature regulating mechanism unit 245e for regulating the temperature of the substrate drying fluid. The up-and-down moving mechanism unit 245b and the shaking moving mechanism unit 245c function as a drying fluid supply nozzle moving mechanism unit for moving the relative position of the drying fluid supply nozzle 245a and the cleaned surface of the chip W. The substrate drying fluid is, for example, IPA vapor and pure water (rinsing liquid). The drying fluid supply nozzle 245a is Figure 6 As shown, a nozzle for IPA vapor and a nozzle for pure water may be provided separately. In addition, the substrate drying fluid may be a liquid, a double fluid of a mixture of liquid and gas, or may include a solid such as dry ice.

[0096] The environmental sensor 244 includes, for example, a temperature sensor 244a, a humidity sensor 244b, an air pressure sensor 244c, an oxygen concentration sensor 244d, and a microphone (sound sensor) 244e. In addition, the environmental sensor 244 may also include a camera (image sensor) that can capture the surface, temperature distribution, airflow distribution, etc. of the wafer W during or before and after the drying process.

[0097] In the drying process performed by the first drying section 24E and the second drying section 24F, the wafer W is rotated by the substrate rotating mechanism 241f while being held by the substrate holding mechanism 241e. Then, while the substrate drying fluid is supplied from the drying fluid supply nozzle 245a to the cleaned surface of the wafer W, the drying fluid supply nozzle 245a moves to the side edge side (radially outward) of the wafer W. Then, the wafer W is rotated at high speed by the substrate rotating mechanism 241d to dry the wafer W.

[0098] in addition, Figures 4 to 6 The specific structure of the substrate rotating mechanism 241b, 241d, the up and down moving mechanism 240b, 240e, 245b, the linear moving mechanism 240c, the shaking moving mechanism 240f, 242b, 245c, and the cleaning tool rotating mechanism 240a, 240d is omitted, but it is composed of a suitable combination of modules for generating driving force, such as motors and air cylinders; driving force transmission mechanisms, such as linear guides, ball screws, gears, belts, couplings, and bearings; and sensors, such as linear sensors, encoder sensors, limit sensors, and torque sensors. Figures 4 to 6The specific structure of the flow regulating parts 243c, 243d, 243g, 243h, and 245d is omitted, but it is composed of modules for regulating the fluid, such as a proper combination of pumps, valves, regulators, and sensors such as flow sensors, pressure sensors, liquid level sensors, temperature sensors, fluid concentration sensors, and fluid particle sensors. Figures 4 to 6 The specific structure of the temperature control mechanism parts 242d and 245e is omitted, but it is composed of, for example, a module for adjusting temperature (contact or non-contact) such as a heater and a heat exchanger; and sensors such as a temperature sensor and a current sensor.

[0099] (Film thickness measurement unit)

[0100] The film thickness measuring unit 25 is a measuring device for measuring the film thickness of the wafer W before or after polishing, and is composed of, for example, an optical film thickness measuring device, an eddy current film thickness measuring device, etc. The transfer robot 211 transfers the wafer W to each film thickness measuring module.

[0101] (Control Unit)

[0102] Figure 7 2 is a block diagram showing an example of the substrate processing apparatus 2. The control unit 26 is electrically connected to each unit 21 to 25, and functions as a control unit that controls each unit 21 to 25. The control system (module, sensor, sequencer) of the processing unit 24 is described below as an example, but since the basic configuration and functions of the other units 21, 23 to 25 are also the same, the description is omitted.

[0103] The processing unit 24 includes: a plurality of modules 2471 to 247r which are respectively arranged in each subunit of the processing unit 24 (for example, the first roller sponge cleaning section 24A and the second roller sponge cleaning section 24B, the first pen-shaped sponge cleaning section 24C and the second pen-shaped sponge cleaning section 24D, the first drying section 24E and the second drying section 24F, the first and second conveying sections 24G, 24H, etc.) and serve as control objects; a plurality of sensors 2481 to 248s which are respectively arranged in the plurality of modules 2471 to 247r and detect data (detection values) required for controlling each module 2471 to 247r; and a sequence generator 249 which controls the action of each module 2471 to 247r based on the detection values ​​of each sensor 2481 to 248s.

[0104] The sensors 2481 to 248s of the processing unit 24 include, for example: a sensor for detecting the holding pressure of the substrate holding mechanism 241a, 241c when the substrate is held; a sensor for detecting the rotation speed of the substrate holding mechanism 241a, 241c; a sensor for detecting the rotation torque of the substrate rotating mechanism 241b, 241d; a sensor for detecting the flow rate of the substrate cleaning fluid; a sensor for detecting the pressure of the substrate cleaning fluid; a sensor for detecting the position coordinates of the cleaning fluid supply unit 242 that can be converted to the dripping position of the substrate cleaning fluid; a sensor for detecting the temperature of the substrate cleaning fluid; a sensor for detecting the concentration of the substrate cleaning fluid; a sensor for detecting the rotation speed of the cleaning tool rotating mechanism 240a; a sensor for detecting the rotation torque of the cleaning tool rotating mechanism 240a; a sensor for detecting the A sensor for detecting the position coordinates of the moving mechanism unit (up and down moving mechanism unit 240b, 240e, linear moving mechanism unit 240c, and shaking moving mechanism unit 240f); a sensor for detecting the moving speed of the cleaning tool moving mechanism unit; a sensor for detecting the moving torque of the cleaning tool moving mechanism unit; a sensor for detecting the pressing load when the cleaning tool (roller sponge 2400, pen sponge 2401) is brought into contact with the chip W or the cleaning plate 243b, 243f of the cleaning tool; a sensor for detecting the flow rate of the cleaning fluid of the cleaning tool; a sensor for detecting the pressure of the cleaning fluid of the cleaning tool; a sensor for detecting the cleanliness of the cleaning fluid of the cleaning tool (for example, the concentration of microparticles contained in the waste liquid of the cleaning tool cleaning tank 243a, 243e, the particle diameter, and the number of particles per particle diameter); an environmental sensor 244, etc.

[0105] The control unit 26 includes a control unit 260, a communication unit 261, an input unit 262, an output unit 263, and a storage unit 264. The control unit 26 is, for example, a general-purpose or dedicated computer (see the following). Figure 8 ) and constituted.

[0106] The communication unit 261 is connected to the network 7 and functions as a communication interface for sending and receiving various data. The input unit 262 receives various input operations, and the output unit 263 outputs various information via a display screen, a signal tower light, or a buzzer, and functions as a user interface.

[0107] The storage unit 264 stores various programs (operating system (OS), application programs, web browsers, etc.) and data (device setting information 265, substrate processing plan information 266, etc.) used when the substrate processing device 2 operates. The device setting information 265 and the substrate processing plan information 266 are data that can be edited by the user via the display screen.

[0108] The control unit 260 obtains the detection values ​​of multiple sensors 2181~218q, 2281~228s, 2381~238u, 2481~248w, 2581~258y (hereinafter referred to as the "sensor group") through multiple sequence generators 219, 229, 239, 249, 259 (hereinafter referred to as the "sequencer group"), and performs a series of substrate processing such as loading, grinding, cleaning, drying, film thickness measurement, and unloading by coordinating multiple modules 2171~217p, 2271~227r, 2371~237t, 2471~247v, 2571~257x (hereinafter referred to as the "module group")

[0109] (Hardware Configuration of Each Device)

[0110] Figure 8 1 is a diagram showing an example of a hardware configuration of a computer 900. The control unit 26, the database device 3, the machine learning device 4, the information processing device 5, and the user terminal device 6 of the substrate processing apparatus 2 are respectively configured by a general-purpose or dedicated computer 900.

[0111] Computer 900 Figure 8 As shown, its main components include a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) unit 922, an external device I / F unit 924, an I / O (input and output) device I / F unit 926, and a media input and output unit 928. In addition, the above components can be appropriately omitted depending on the purpose of using the computer 900.

[0112] The processor 912 is composed of one or more arithmetic processing devices (CPU (Central Processing Unit)), MPU (Micro-processing unit), DSP (digital signal processor), GPU (Graphics Processing Unit), etc., and acts as a control unit that controls the entire computer 900. The memory 914 stores various data and programs 930, and is composed of, for example, a volatile memory (DRAM, SRAM, etc.) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0113] The input device 916 is composed of, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and plays the function of an input unit. The output device 917 is composed of, for example, a voice (sound) output device, a vibration device, etc., and plays the function of an output unit. The display device 918 is composed of, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and plays the function of a display unit. The input device 916 and the display device 918, such as a touch panel display, can also be integrally constructed. The storage device 920 is composed of, for example, an HDD, an SSD (Solid State Drive), etc., and plays the function of a storage unit. The storage device 920 stores various data required for the execution of the operating system and the program 930.

[0114] The communication I / F unit 922 is connected to a network 940 such as the Internet or an enterprise network (or may be connected to a network 940) via wired or wireless communication. Figure 1 The I / F section 926 is connected to an I / O device 960 such as various sensors and actuators, and functions as a communication section for sending and receiving various signals and data such as sensor detection signals and control signals for actuators with the I / O device 960. The media input / output section 928 is composed of a drive device such as a digital optical drive (DVD drive) and a CD drive, and reads and writes data to a medium (permanent storage medium) 970 such as a DVD and a CD.

[0115] In the computer 900 having the above-mentioned structure, the processor 912 calls the program 930 stored in the storage device 920 to the memory 914 for execution, and controls each part of the computer 900 via the bus 910. In addition, the program 930 can also be stored in the memory 914 instead of the storage device 920. The program 930 can also be recorded in the medium 970 in the form of an installable file or an executable file, and provided to the computer 900 via the media input and output unit 928. The program 930 can also be provided to the computer 900 by downloading through the communication I / F unit 922 and through the network 940. In addition, the computer 900 can also realize various functions realized by the execution of the program 930 by the processor 912 with hardware such as FPGA (programmable gate array) and ASIC (application specific integrated circuit).

[0116] The computer 900 is an electronic device of any type, such as a fixed computer or a portable computer. The computer 900 may be a client computer, a server computer, or a cloud computer. The computer 900 may also be applied to devices other than the devices 2 to 6 .

[0117] (Production history information 30)

[0118] Fig. 9 2 is a data structure diagram showing an example of the production history information 30 managed by the database device 3. The production history information 30 is a table in which reports R obtained when substrate processing is performed using the cleaning tool (roller sponge 2400, pen sponge 2401) for production are classified and registered, and includes, for example, a wafer history table 300 for each wafer W and a cleaning history table 301 for device status information during cleaning processing. In addition to the above, the production history information 30 also includes a polishing history table for device status information during polishing processing, a drying history table for device status information during drying processing, an event history table for event information, and an operation history table for operation information, etc., but detailed descriptions are omitted.

[0119] Each record of the wafer history table 300 includes, for example, a wafer ID, a cassette number, a slot number, the start time and end time of each process, a unit ID used, and the like. Fig. 9 Although the polishing step, the cleaning step, and the drying step are exemplified, the other steps can be registered in the same manner.

[0120] Each record of the cleaning history table 301 includes, for example, the chip ID, substrate holding unit status information, cleaning fluid supply unit status information, substrate cleaning unit status information, cleaning tool cleaning unit status information, device internal environment information, processing performance information, etc.

[0121] The substrate holder state information is information indicating the state of the substrate holder 241 during the cleaning process. The substrate holder state information is, for example, detection values ​​of sensors (or command values ​​to modules) sampled at predetermined time intervals by a sensor group (or module group) included in the substrate holder 241 .

[0122] The cleaning fluid supply unit state information is information indicating the state of the cleaning fluid supply unit 242 during the cleaning process. The cleaning fluid supply unit state information is, for example, the detection value of each sensor (or the command value to each module) sampled at a predetermined time interval by the sensor group (or module group) of the cleaning fluid supply unit 242.

[0123] The substrate cleaning unit state information is information indicating the state of the substrate cleaning unit 240 during cleaning processing. The substrate cleaning unit state information is, for example, detection values ​​of sensors (or command values ​​to modules) sampled at predetermined time intervals by a sensor group (or module group) included in the substrate cleaning unit 240.

[0124] The cleaning tool cleaning unit state information is information indicating the state of the cleaning tool cleaning unit 243 during cleaning processing. The cleaning tool cleaning unit state information is, for example, detection values ​​of each sensor (or command value to each module) sampled at a predetermined time interval by a sensor group (or module group) of the cleaning tool cleaning unit 243.

[0125] The in-device environment information is information indicating the state of the internal space of the substrate processing apparatus 2 formed by the frame 20. The internal space of the substrate processing apparatus 2 is a space where the processing unit 24 is arranged, and the in-device environment information is, for example, the detection value of each sensor sampled at a predetermined time interval by the environmental sensor 244. In addition, when the internal space of the substrate processing apparatus 2 is divided by each subunit (for example, the first roller sponge cleaning section 24A and the second roller sponge cleaning section 24B, the first pen-type sponge cleaning section 24C and the second pen-type sponge cleaning section 24D, the first drying section 24E and the second drying section 24F) provided by the processing unit 24, each subunit of the processing unit 24 is provided with an environmental sensor 244, and each subunit of the processing unit 24 obtains the in-device environment information.

[0126] The processing result information is information indicating the results of the cleaning process and includes the cumulative number of wafers W used and the cumulative usage time when the cleaning tool (roller sponge 2400, pen sponge 2401) is used for cleaning since the cleaning tool was replaced.

[0127] By referring to the cleaning history table 301, the time series data of each sensor (or the time series data of each module) can be extracted as the apparatus state of the substrate processing apparatus 2 when the cleaning process is performed on the wafer W specified by the wafer ID.

[0128] (Cleaning test information 31)

[0129] Fig.10 3 is a data structure diagram showing an example of the cleaning test information 31 managed by the database device 3. The cleaning test information 31 includes a cleaning test table 310 in which reports R and test results obtained when a cleaning test is performed using a cleaning tool for a test and a cleaning test device are classified and registered.

[0130] In each record of the cleaning test table 310, for example, a test ID, substrate holding unit status information, cleaning fluid supply unit status information, substrate cleaning unit status information, cleaning tool cleaning unit status information, device internal environment information, processing effectiveness information, test result information, etc. are registered. The substrate holding unit status information, cleaning fluid supply unit status information, substrate cleaning unit status information, cleaning tool cleaning unit status information, device internal environment information, and processing effectiveness information of the cleaning test table 310 are information indicating the status of each part in the cleaning test, and because their data structure is the same as that of the cleaning history table 301, detailed description is omitted.

[0131] The test result information is information indicating the state of the test cleaning tool during the cleaning process in the cleaning test. The test result information is a measurement value sampled at a predetermined time interval by the test cleaning tool and a cleaning tool measuring device provided in the cleaning test apparatus. Fig.10 The test result information shown includes the weight, moisture content, hardness, and cleanliness of the cleaning tool at each time t1, t2, ..., ...tm, ..., tn during the cleaning process from the start of the cleaning process to the end. In addition, the test result information may also be the measured value of the measurement result of the cleaning tool measuring device as described above, or it may be the information of the image processing results obtained by performing image processing on each image taken by the camera provided as the environmental sensor 244 or the camera mounted on the optical microscope and the scanning electron microscope (SEM) at a prescribed time interval, and the experimental analysis results obtained by the experimenter. In addition, the test result information may also be the information collected from a single cleaning test that is continuously performed from the start of the cleaning process to the end, or it may be the information collected through multiple cleaning tests by repeatedly performing the cleaning test from the start of the cleaning process to the arrival of the prescribed time while gradually extending the prescribed time.

[0132] By referring to the cleaning test table 310, in the cleaning test identified by the test ID, it is possible to extract time series data (or time series data of each module) representing the state of the substrate cleaning device (substrate holding part 241, cleaning fluid supply part 242, substrate cleaning part 240, and cleaning tool cleaning part 243) when the cleaning process is performed using the cleaning tool used in the test, and time series data representing the state of the cleaning tool used in the test at that time.

[0133] (Machine Learning Device 4)

[0134] Fig.11 1 is a block diagram showing an example of the machine learning device 4 according to the first embodiment. The machine learning device 4 includes a control unit 40 , a communication unit 41 , a learning data storage unit 42 , and a learned model storage unit 43 .

[0135] The control unit 40 functions as a learning data acquisition unit 400 and a machine learning unit 401. The communication unit 41 is connected to external devices (e.g., substrate processing device 2, database device 3, information processing device 5, user terminal device 6, cleaning test device (not shown) etc.) via the network 7, and functions as a communication interface for sending and receiving various data.

[0136] The learning data acquisition unit 400 is connected to an external device via the communication unit 41 and the network 7, and acquires the first learning data 11A composed of the action state information as input data and the cleaning tool state information as output data. The first learning data 11A is data used as teacher data (training data), inspection data, and test data in teacher learning. In addition, the cleaning tool state information is data used as a correct answer label in teacher learning.

[0137] The learning data storage unit 42 is a database that stores a plurality of sets of first learning data 11A acquired by the learning data acquisition unit 400. The specific configuration of the database constituting the learning data storage unit 42 may be appropriately designed.

[0138] The machine learning unit 401 performs machine learning using the plurality of sets of first learning data 11A stored in the learning data storage unit 42. That is, the machine learning unit 401 inputs the plurality of sets of first learning data 11A into the first learning model 10A, and causes the first learning model 10A to learn the correlation between the action state information and the cleaning tool state information included in the first learning data 11A, thereby generating a learned first learning model 10A.

[0139] The learned model storage unit 43 is a database that stores the learned first learning model 10A (specifically, the adjusted weighted parameter group) generated by the machine learning unit 401. The learned first learning model 10A stored in the learned model storage unit 43 is provided to the real system (for example, the information processing device 5) via the network 7 and the recording medium. Fig.11 Although the learning data storage unit 42 and the learned model storage unit 43 are shown as separate storage units, they may be configured as a single storage unit.

[0140] In addition, the number of the first learning models 10A stored in the learned model storage unit 43 is not limited to one, and multiple learning models with different conditions may be stored, for example, machine learning methods, types of wafers W (size, thickness, film type, etc.), types of cleaning tools, differences in the structure of the substrate cleaning device (substrate holding unit 241, cleaning fluid supply unit 242, substrate cleaning unit 240, and cleaning tool cleaning unit 243), types of substrate cleaning fluid and cleaning tool cleaning fluid, types of data included in the action state information, types of data included in the cleaning tool state information, etc. In this case, multiple types of learning data having data corresponding to multiple learning models with different conditions may be stored in the learning data storage unit 42.

[0141] Fig.12 1 is an example diagram showing a first learning model 10A and first learning data 11A. The first learning data 11A used for machine learning of the first learning model 10A is composed of action state information and cleaning tool state information. The first learning model 10A and the first learning data 11A of this embodiment are prepared at least for the roller sponge cleaning parts 24A and 24B using the roller sponge 2400 and the pen sponge cleaning parts 24C and 24D using the pen sponge 2401. However, since the basic data structure is the same, they are described together below.

[0142] The action status information constituting the first learning data 11A includes: substrate holding unit status information indicating the status of the substrate holding unit 241 during the cleaning process of the chip W performed by the substrate processing device 2; cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit 242; substrate cleaning unit status information indicating the status of the substrate cleaning unit 240; and cleaning tool cleaning unit status information indicating the status of the cleaning tool cleaning unit 243.

[0143] The substrate holding unit state information included in the operation state information includes: the number of substrates held when the substrate holding mechanism 241a, 241c holds the substrate, the holding pressure when the substrate holding mechanism 241a, 241c holds the substrate, the rotation speed of the substrate holding mechanism 241a, 241c, the rotation torque of the substrate rotating mechanism 241b, 241d, and at least one of the conditions of the substrate holding mechanism 241a, 241c. The condition of the substrate holding mechanism 241a, 241c, for example, indicates the degree of consumption and contamination of the substrate holding mechanism 241a, 241c set based on the use of the substrate holding mechanism 241a, 241c (use time, pressure during use, whether or not it is replaced). The condition of the substrate holding mechanism 241a, 241c, for example, may also change over time during the cleaning process.

[0144] The cleaning fluid supply unit status information included in the operation status information includes at least one of the flow rate of the substrate cleaning fluid, the pressure of the substrate cleaning fluid, the dripping position of the substrate cleaning fluid, the temperature of the substrate cleaning fluid, and the concentration of the substrate cleaning fluid. When the substrate cleaning fluid is a plurality of types of fluids, the cleaning fluid supply unit status information may include the flow rate, pressure, dripping position, temperature and concentration of each fluid.

[0145] The substrate cleaning unit status information included in the action status information includes: the rotation speed of the cleaning tool rotating mechanism 240a, the rotation torque of the cleaning tool rotating mechanism 240a, the position coordinates of the cleaning tool moving mechanism (up and down moving mechanism 240b, 240e, linear moving mechanism 240c, shaking moving mechanism 240f), the moving speed of the cleaning tool moving mechanism, the moving torque of the cleaning tool moving mechanism, the pressing load when the cleaning tool contacts the wafer W, and at least one of the conditions of the cleaning tool. The condition of the cleaning tool indicates the condition of the cleaning tool at a time point before the object time point in the cleaning tool status information, for example, the consumption degree and contamination degree of the cleaning tool set based on the use of the cleaning tool (use time, pressing load during use, replacement, rotation speed of the wafer W, number of wafers processed, image of the surface of the cleaning tool taken). The condition of the cleaning tool may also change over time during the cleaning process, for example.

[0146] The cleaning tool cleaning part status information included in the action status information includes: the rotation speed of the cleaning tool rotating mechanism part 240a, the rotation torque of the cleaning tool rotating mechanism part 240a, the position coordinates of the cleaning tool moving mechanism part (up and down moving mechanism part 240b, 240e, linear moving mechanism part 240c, shaking moving mechanism part 240f), the moving speed of the cleaning tool moving mechanism part, the moving torque of the cleaning tool moving mechanism part, the pressing load when the cleaning tool contacts the cleaning plates 243b, 243f of the cleaning tool, the flow rate of the cleaning fluid of the cleaning tool, the pressure of the cleaning fluid of the cleaning tool, and at least one of the cleanliness of the cleaning fluid of the cleaning tool (the discharge side of the cleaning tool cleaning tank 243a, 243e).

[0147] In addition, the operation status information may further include device internal environment information indicating the spatial environment in which the cleaning process is performed, and the device internal environment information included in the operation status information includes at least one of the temperature, humidity, air pressure, airflow, oxygen concentration, and sound of the internal space (each subunit of the processing unit 24) formed by the rack 20. In addition, the operation status information may further include processing effectiveness information indicating the effectiveness of the cleaning process, and the processing effectiveness information included in the operation status information includes, for example, at least one of the cumulative number of wafers W used when the cleaning tool is used for cleaning after the cleaning tool is replaced, and the cumulative use time.

[0148] The cleaning tool status information constituting the first learning data 11A is information indicating the status of the cleaning tool when the substrate processing device 2 operates in the operation state indicated by the operation state information. The cleaning tool status information of the present embodiment is situation information indicating the status of the cleaning tool. The situation information includes, for example, at least one of the weight, moisture content, hardness, and cleanliness of the cleaning tool at the target time point included in the cleaning process period from the start of the cleaning process to the end (the time required for the cleaning process of each wafer). During the cleaning process, for example, it includes: the action of the substrate cleaning unit 240 bringing the cleaning tool into contact with the wafer W to clean the wafer W; the action of the cleaning fluid supply unit 242 supplying the substrate cleaning fluid; and the action of the cleaning tool cleaning unit 243 cleaning the cleaning tool with the cleaning tool cleaning fluid.

[0149] The learning data acquisition unit 400 acquires the first learning data 11A by referring to the cleaning test information 31 and, if necessary, accepting an input operation from the user through the user terminal device 6. For example, the learning data acquisition unit 400 acquires the substrate holding unit state information, the cleaning fluid supply unit state information, the substrate cleaning unit state information, and the cleaning tool cleaning unit state information (time series data of each sensor respectively provided in the substrate holding unit 241, the cleaning fluid supply unit 242, the substrate cleaning unit 240, and the cleaning tool cleaning unit 243) when performing the cleaning test identified by the test ID by referring to the cleaning test table 310 of the cleaning test information 31 as the operation state information.

[0150] In addition, the present embodiment describes obtaining the action status information as follows: Fig.12 The case of the time series data of the sensor group shown in the figure, however, can also be appropriately changed according to the structure of the substrate cleaning device (substrate holding part 241, cleaning fluid supply part 242, substrate cleaning part 240, and cleaning tool cleaning part 243). In addition, the action state information can also use the command value to the module, or can use the parameter converted from the detection value of the sensor or the command value to the module, or can use the parameter calculated based on the detection values ​​of multiple sensors. Furthermore, the action state information can also be obtained as time series data during the entire cleaning process, or as time series data during an object period that is part of the cleaning process, or as time point data at a specific object time point. As mentioned above, when the definition of the action state information is changed, it is only necessary to appropriately change the data structure of the input data in the first learning model 10A and the first learning data 11A.

[0151] Furthermore, the learning data acquisition unit 400 acquires the test result information (time series data of the cleaning tool measuring device) when the cleaning test identified by the same test ID is performed by referring to the cleaning test table 310 of the cleaning test information 31. Fig.10 )) as the cleaning tool state information corresponding to the above-mentioned operation state information. In the case where the cleaning tool measuring device is a measuring device that can measure the surface of the cleaning tool, the learning data acquisition unit 400 acquires the surface measurement value as the cleaning tool state information.

[0152] In addition, in this embodiment, the cleaning tool status information is Fig.12 The situation information shown is explained, but it can also include at least one of the weight, moisture content, hardness, and cleanliness of the cleaning tool. In addition, the cleaning tool status information can also be calculated by substituting the measured value of the cleaning tool measuring device into the prescribed calculation formula. Furthermore, when the action status information is obtained as time series data during the entire cleaning process or time series data during an object period of a part of the cleaning process, the cleaning tool status information can also be obtained as time series data during the entire cleaning process or time series data during the object period, or as time point data at the end time of the cleaning process or time point data at the object time point. In addition, when the action status information is obtained as time point data at a specific object time point, the cleaning tool status information can also be obtained as time point data at its specific object time point. As mentioned above, when the definition of the cleaning tool status information is changed, it is only necessary to appropriately change the data structure of the output data in the first learning model 10A and the first learning data 11A.

[0153] The first learning model 10A adopts a neural network-like structure, and includes an input layer 100, an intermediate layer 101, and an output layer 102. Synapses (not shown) connecting neurons are laid between the layers, and each synapse has a corresponding weight. The weight parameter group composed of the weights of each synapse is adjusted by machine learning.

[0154] The input layer 100 has a number of neurons corresponding to the action state information as input data, and each value of the action state information is input to each neuron. The output layer 102 has a number of neurons corresponding to the cleaning tool state information as output data, and the prediction result (inference result) of the cleaning tool state information relative to the action state information is output as output data. When the first learning model 10A is composed of a regression model, the cleaning tool state information is output as a numerical value normalized in a specified range (for example, 0 to 1). In addition, when the first learning model 10A is composed of a classification model, the cleaning tool state information is output as a score (correctness) for each level, and is output as a numerical value normalized in a specified range (for example, 0 to 1).

[0155] (Machine Learning Methods)

[0156] Fig.13This is a flowchart showing an example of a machine learning method performed by the machine learning device 4 .

[0157] First, in step S100, the learning data acquisition unit 400 acquires a desired amount of first learning data 11A from the cleaning test information 31, etc., and stores the acquired first learning data 11A in the learning data storage unit 42 as a preliminary preparation for starting machine learning. The amount of the first learning data 11A prepared at this time can be set in consideration of the inference accuracy required for the first learning model 10A finally obtained.

[0158] Next, in step S110, the machine learning unit 401 prepares a first learning model 10A before learning in order to start machine learning. The first learning model 10A before learning prepared at this time is composed of Fig.12 The illustrated neural network model is constructed, and the weight of each synapse is set to an initial value.

[0159] Next, in step S120 , the machine learning unit 401 acquires, for example, one set of first learning data 11A at random from the plurality of sets of first learning models 10A stored in the learning data storage unit 42 .

[0160] Next, in step S130, the machine learning unit 401 inputs the action state information (input data) included in a set of the first learning data 11A into the input layer 100 of the prepared first learning model 10A before learning (or during learning). As a result, the cleaning tool state information (output data) is output from the output layer 102 of the first learning model 10A as an inference result, but the output data is generated by the first learning model 10A before learning (or during learning). Therefore, the output data output as the inference result of the state before learning (or during learning) represents information different from the cleaning tool state information (correct answer label) included in the first learning data 11A.

[0161] Next, in step S140, the machine learning unit 401 compares the cleaning tool state information (correct answer label) included in the first learning data 11A obtained in step S120 with the cleaning tool state information (output data) output from the output layer as the inference result in step S130, and performs machine learning by adjusting the weight of each synapse (backward propagation). Thus, the machine learning unit 401 causes the first learning model 10A to learn the correlation between the action state information and the cleaning tool state information.

[0162] Secondly, in step S150, the machine learning unit 401 determines whether the specified learning end conditions are met based on, for example, an evaluation value of an error function based on the cleaning tool status information (correct answer label) contained in the first learning data 11A and the cleaning tool status information (output data) output as a result of inference; and the remaining number of unlearned first learning data 11A stored in the learning data storage unit 42.

[0163] In step S150, if the machine learning unit 401 determines that the learning end condition is not satisfied and continues the machine learning (No in step S150), the process returns to step S120 and performs the process of steps S120 to S140 multiple times on the first learning model 10A being learned using the first learning data 11A that has not been learned. On the other hand, in step S150, if the machine learning unit 401 determines that the learning end condition is satisfied and ends the machine learning (Yes in step S150), the process proceeds to step S160.

[0164] Then, in step S160, the machine learning unit 401 stores the first learning model 10A (adjusted weight parameter group) generated by adjusting the weights corresponding to each synapse in the learned model storage unit 43, and ends. Fig.13 In the machine learning method, step S100 corresponds to a learning data storage step, steps S110 to S150 correspond to a machine learning step, and step S160 corresponds to a learning model storage step.

[0165] As described above, when the machine learning device 4 and the machine learning method of the present embodiment are used, a first learning model 10A can be provided, which can predict (infer) cleaning tool status information representing the state of the cleaning tool (roller sponge 2400, pen sponge 2401) from action status information including substrate holding part status information, cleaning fluid supply part status information, substrate cleaning part status information, and cleaning tool cleaning part status information.

[0166] (Information processing device 5)

[0167] Fig.14 This is a block diagram showing an example of the information processing device 5 according to the first embodiment. Fig.15 1 is a functional explanatory diagram showing an example of the information processing device 5 according to the first embodiment. The information processing device 5 includes a control unit 50 , a communication unit 51 , and a learned model storage unit 52 .

[0168] The control unit 50 functions as an information acquisition unit 500, a state prediction unit 501, and an output processing unit 502. The communication unit 51 is connected to an external device (e.g., substrate processing device 2, database device 3, machine learning device 4, user terminal device 6, etc.) via a network 7, and functions as a communication interface for sending and receiving various data.

[0169] The information acquisition unit 500 is connected to an external device via the communication unit 51 and the network 7 to acquire operation status information including substrate holding unit status information, cleaning fluid supply unit status information, substrate cleaning unit status information, and cleaning tool cleaning unit status information.

[0170] For example, in the case of "post-prediction processing" of the cleaning tool status information for the wafer W that has been subjected to the cleaning process, the information acquisition unit 500 obtains the substrate holding unit status information, the cleaning fluid supply unit status information, the substrate cleaning unit status information, and the cleaning tool cleaning unit status information during the cleaning process of the wafer W as the operation status information by referring to the cleaning history table 301 of the production history information 30. In the case of "real-time prediction processing" of the cleaning tool status information for the wafer W during the cleaning process, the information acquisition unit 500 obtains the substrate holding unit status information, the cleaning fluid supply unit status information, the substrate cleaning unit status information, and the cleaning tool cleaning unit status information during the cleaning process of the wafer W as the operation status information at any time by receiving the report R on the device status information from the substrate processing device 2 that performs the cleaning process at any time. In the case of "pre-prediction processing" of the cleaning tool status information of the chip W before the cleaning process, the information acquisition unit 500 receives the substrate processing plan information 266 from the substrate processing device 2 scheduled to perform the cleaning process, and simulates the device status information of the substrate processing device 2 when it is in action according to the substrate processing plan information 266, thereby obtaining the substrate holding part status information, the cleaning fluid supply part status information, the substrate cleaning part status information, and the cleaning tool cleaning part status information when the chip W is cleaned as the action status information.

[0171] As described above, the state prediction unit 501 predicts the cleaning tool state information (situation information in this embodiment) by inputting the action state information obtained by the information acquisition unit 500 as input data into the first learning model 10A. The cleaning tool state information indicates the state of the cleaning tool when the substrate processing device 2 has been operating in the action state indicated by the action state information.

[0172] The learned model storage unit 52 is a database storing the learned first learning model 10A used by the state prediction unit 501. In addition, the number of first learning models 10A stored in the learned model storage unit 52 is not limited to one. For example, depending on the machine learning method, the type of wafer W (size, thickness, film type, etc.), the type of cleaning tool, the difference in the structure of the substrate cleaning device (substrate holding unit 241, cleaning fluid supply unit 242, substrate cleaning unit 240, and cleaning tool cleaning unit 243), the type of substrate cleaning fluid and cleaning tool cleaning fluid, the type of data included in the action state information, the type of data included in the cleaning tool state information, etc., a plurality of learned models with different conditions may be stored and selectively used. In this embodiment, at least two first learning models 10A corresponding to the roller sponge cleaning unit 24A and 24B using the roller sponge 2400 and the pen sponge cleaning unit 24C and 24D using the pen sponge 2401 are stored in the learned model storage unit 52. In addition, the learned model storage unit 52 may also be replaced by a storage unit of an external computer (eg, a server-type computer or a cloud-type computer). In this case, the state prediction unit 501 only needs to access the external computer.

[0173] The output processing unit 502 performs output processing for outputting the cleaning tool status information generated by the status prediction unit 501. For example, the output processing unit 502 may send the cleaning tool status information to the substrate processing device 2 and the user terminal device 6, thereby displaying a display screen based on the cleaning tool status information on the substrate processing device 2 and the user terminal device 6, or may send the cleaning tool status information to the database device 3 and log the cleaning tool status information in the production history information 30.

[0174] (Information Processing Method)

[0175] Fig.16 1 is a flowchart showing an example of an information processing method implemented by the information processing device 5. Next, an operation example when a user operates the user terminal device 6 to perform "post-event prediction processing" on the cleaning tool status information for a specific wafer W will be described.

[0176] First, in step S200 , when the user performs an input operation to input a wafer ID of a wafer W to be a prediction target into the user terminal device 6 , the user terminal device 6 transmits the wafer ID to the information processing device 5 .

[0177] Next, in step S210, the information acquisition unit 500 of the information processing device 5 receives the wafer ID sent in step S200. In step S211, the information acquisition unit 500 uses the wafer ID received in step S210 to refer to the cleaning history table 301 of the production history information 30, and acquires the operation status information when the cleaning process is performed on the wafer W specified by the wafer ID.

[0178] Next, in step S220 , the state prediction unit 501 inputs the operation state information acquired in step S211 as input data into the first learning model 10A, thereby generating cleaning tool state information corresponding to the operation state information as output data, and predicting the state of the cleaning tool.

[0179] Next, in step S230, the output processing unit 502 performs output processing for outputting the cleaning tool status information generated in step S220, and sends the cleaning tool status information to the user terminal device 6. In addition, in addition to the user terminal device 6 or in place of the user terminal device 6, the sending object of the cleaning tool status information may also be the database device 3.

[0180] Next, in step S240, when the user terminal device 6 receives the cleaning tool status information sent in step S230 as a response to the sending process of step S200, the user terminal device 6 displays a display screen based on the cleaning tool status information, so that the user can visually confirm the status of the cleaning tool. In the above-mentioned information processing method, steps S210 and S211 are equivalent to the information acquisition process, step S220 is equivalent to the status prediction process, and step S230 is equivalent to the output processing process.

[0181] As described above, when the information processing device 5 and the information processing method of the present embodiment are used, the action status information including the substrate holding part status information, the cleaning fluid supply part status information, the substrate cleaning part status information, and the cleaning tool cleaning part status information in the cleaning process is input into the first learning model 10A to predict the cleaning tool status information (situation information) corresponding to the action status information. Therefore, the state of the cleaning tool can be appropriately predicted according to the action state of the substrate processing device 2.

[0182] (Second Implementation Method)

[0183] The second embodiment differs from the first embodiment in that the cleaning tool status information is at least one of the remaining life information indicating the remaining life of the cleaning tool (roller sponge 2400, pen sponge 2401) and the cleaning quality information indicating the cleaning quality of the cleaning tool. Hereinafter, the machine learning device 4a and the information processing device 5a of the second embodiment are mainly described in terms of the parts that are different from the first embodiment.

[0184] Fig.17 It is a block diagram showing an example of a machine learning device 4a according to the second embodiment. Fig.18 FIG. 2 is a diagram showing an example of the second learning model 10B and the second learning data 11B. The second learning data 11B is used for machine learning of the second learning model 10B.

[0185] The cleaning tool status information constituting the second learning data 11B includes: at least one of the remaining life information indicating the remaining life of the cleaning tool and the cleaning quality information indicating the cleaning quality of the cleaning tool. The remaining life of the cleaning tool is determined by, for example, the number of times the cleaning tool can be used before reaching the end of its life and the usable time, for example, it can be set according to the impact on the cleaning quality. The cleaning quality of the cleaning tool is determined according to the cleaning degree of the wafer W when the cleaning tool is used for cleaning processing, for example, it can also be information about the particles present in the wafer W, and can also include the surface distribution state of the particles and the total number of particles. In addition, the action state information constituting the second learning data 11B is the same as the first embodiment, so the description is omitted.

[0186] The learning data acquisition unit 400 acquires the second learning data 11B by referring to the cleaning test information 31 and accepting the input operation of the user through the user terminal device 6 when necessary. In the cleaning test information 31, for example, as test result information, there are recorded: remaining life information, which is set to "0" when the life of the cleaning tool is reached when the cleaning process is repeatedly performed using the cleaning tool and the cleaning test device for the test, and is set to a larger value as it goes back in time; and cleaning quality information measured by measuring instruments such as an optical microscope and a scanning electron microscope (SEM). Then, the learning data acquisition unit 400 acquires the test result information when performing the cleaning test identified by the test ID from the cleaning test table 310 of the cleaning test information 31, thereby acquiring the remaining life information and the cleaning quality information.

[0187] The machine learning unit 401 inputs a plurality of sets of second learning data 11B into the second learning model 10B, and generates a learned second learning model 10B by causing the second learning model 10B to learn the correlation between the action state information and the cleaning tool state information (at least one of the remaining life information and the cleaning quality information) contained in the second learning data 11B.

[0188] Fig.19 This is a block diagram showing an example of the information processing device 5a functioning as the information processing device 5a according to the second embodiment. Fig. 20 This is a functional explanatory diagram showing an example of an information processing device 5a according to the second embodiment.

[0189] The information acquisition unit 500 acquires the operation status information including the substrate holding unit status information, the cleaning fluid supply unit status information, the substrate cleaning unit status information, and the cleaning tool cleaning unit status information, similarly to the first embodiment.

[0190] As described above, the state prediction unit 501 predicts the cleaning tool state information (at least one of the remaining life information and the cleaning quality information) by inputting the action state information obtained by the information acquisition unit 500 as input data into the second learning model 10B. The cleaning tool state information represents the state of the cleaning tool when the substrate processing device 2 operates in the action state indicated by the action state information.

[0191] The output processing unit 502 performs output processing for outputting the cleaning tool status information (at least one of the remaining life information and the cleaning quality information) generated by the status prediction unit 501, similarly to the first embodiment. For example, the output processing unit 502 may display a display screen based on the cleaning tool status information on the substrate processing device 2 and the user terminal device 6 by sending the cleaning tool status information to the substrate processing device 2 and the user terminal device 6, or may log the cleaning tool status information in the production history information 30 by sending the cleaning tool status information to the database device 3. At this time, the output processing unit 502 may also send information indicating the replacement notice of the cleaning tool, the procedure book of the replacement operation, the time required for the replacement operation, the price of the replacement parts, etc. to the substrate processing device 2 and the user terminal device 6, for example, when the remaining life of the cleaning tool displayed by the remaining life information is lower than the prescribed forecast reference number and forecast reference time, or when the cleaning quality displayed by the cleaning quality information is lower than the prescribed reference quality. In addition, when the substrate processing device 2 has the function of automatically replacing cleaning tools, the output processing unit 502 can also send an instruction for automatically replacing cleaning tools to the substrate processing device 2, and can also send an instruction to order replacement parts for the cleaning tools to an inventory management device (no icon) that manages the inventory of cleaning tools.

[0192] As described above, when the information processing device 5a and the information processing method of the present embodiment are used, the action status information including the substrate holding part status information, the cleaning fluid supply part status information, the substrate cleaning part status information, and the cleaning tool cleaning part status information in the cleaning process is input into the second learning model 10B to predict the cleaning tool status information (at least one of the remaining life information and the cleaning quality information) corresponding to the action status information. Therefore, the state of the cleaning tool can be appropriately predicted according to the action state of the substrate processing device 2.

[0193] (Other embodiments)

[0194] The present invention is not limited to the above-described embodiments, and can be implemented with various modifications within the scope of the present invention, all of which are included in the technical concept of the present invention.

[0195] In the above embodiment, the database device 3, the machine learning device 4, and the information processing device 5 are described as being composed of different devices, but the three devices may be composed of a single device, or any two of the three devices may be composed of a single device. In addition, at least one of the machine learning device 4 and the information processing device 5 may also be incorporated into the control unit 26 of the substrate processing device 2 or the user terminal device 6.

[0196] The above embodiment describes that the substrate processing device 2 includes various units 21 to 25, but the substrate processing device 2 only needs to have at least a cleaning function (roller sponge cleaning parts 24A, 24B or pen sponge cleaning parts 24C, 24D) in the processing unit 24, and other units may be omitted.

[0197] The above embodiment describes the case where a quasi-neural network is used as a learning model for implementing machine learning based on the machine learning unit 401, but other machine learning models may also be used. Other machine learning models include, for example, tree-based models such as decision trees and regression trees, ensemble learning such as bagging and boosting, recursive neural networks, stacked neural networks, neural network types such as LSTM (including deep learning), hierarchical clustering, non-hierarchical clustering, clustering types such as the k-nearest neighbor method and the k-means method, multivariate analysis such as principal component analysis, factor analysis, logistic regression, support vector machines, etc.

[0198] (Machine learning programs and information processing programs)

[0199] Each unit of the machine learning device 4 of the present invention may be provided in the form of a program (machine learning program) for making the computer 900 function; and a program (machine learning program) for making the computer 900 execute each step of the machine learning method. In addition, each unit of the information processing device 5 of the present invention may be provided in the form of a program (information processing program) for making the computer 900 function; and a program (information processing program) for making the computer 900 execute each step of the information processing method of the above-mentioned embodiment.

[0200] (Inference device, inference method and inference program)

[0201] The present invention is not only provided in the form of an information processing device 5 (information processing method or information processing program) based on the above-mentioned embodiment, but can also be provided in the form of an inference device (inference method or inference program) used to infer the state information of the cleaning tool. In this case, the inference device (inference method or inference program) may include a memory and a processor, wherein the processor performs a series of processes. The so-called series of processes includes: information acquisition processing (information acquisition process) for obtaining action state information; and inference processing (inference process), when the action state information is obtained through the information acquisition processing, the cleaning tool state information (situation information, remaining life information or cleaning quality information) is inferred, and the cleaning tool state information indicates the state of the cleaning tool when the substrate processing device operates in the action state indicated by the action state information.

[0202] By providing it in the form of an inference device (inference method or inference program), it can be applied to various devices more easily than when an information processing device is installed. Those skilled in the art can understand that when the inference device (inference method or inference program) infers the cleaning tool status information, the learning model generated by the machine learning device and machine learning method of the above embodiment can also be used to apply the inference method implemented by the status prediction unit.

[0203] Industrial Applicability

[0204] The present invention can be utilized in an information processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method.

[0205] Explanation of symbols

[0206] 1: Substrate processing system 2: Substrate processing device 3: Database device 4, 4a: Machine learning device 5, 5a: Information processing device 6: User terminal device 7: Network 10A: First learning model 10B: Second learning model 11A: First learning data 11B: Second learning data 20: Rack 21: Loading / unloading unit 22: Polishing unit 22A to 22D: Polishing unit 23: Substrate conveying unit 24: Processing unit 24A, 24B: First and second roller sponge cleaning units 24C, 24D: First and second pen-type sponge cleaning units 24E, 24F: First and second drying units 24G, 24H: First and second conveying units 25: Film thickness measuring unit 26: Control unit 30: Production history information 31: Cleaning test information 40: Control unit 41: Communication unit 42: Learning data storage unit 43: Learning Learning completed model storage unit 50: control unit 51: communication unit 52: learning completed model storage unit 220: polishing table 221: top ring 222: polishing fluid supply nozzle 223: dresser 224: atomizer 240: substrate cleaning unit 241: substrate holding unit 242: cleaning fluid supply unit 243: cleaning tool cleaning unit 244: environmental sensor 245: drying fluid supply unit 260: control unit 21: communication unit 262: input unit 263: output unit 264: storage unit 300: chip history table 301: cleaning history table 310: cleaning test table 400: learning data acquisition unit 401: machine learning unit 500: information acquisition unit 501: state prediction unit 502: output processing unit 900: computer 2200: polishing pad 2230: dressing disk 2400: roller sponge 2401: pen-shaped sponge.

Claims

1. An information processing device, characterized in that: have: an information acquisition unit, the information acquisition unit acquiring operation status information as an operation status of a substrate processing device when the substrate processing device is in operation, the substrate processing device comprising a substrate holding unit, a cleaning fluid supply unit, a substrate cleaning unit and a cleaning tool cleaning unit, the substrate holding unit holding a substrate, the cleaning fluid supply unit supplying a substrate cleaning fluid to the substrate, the substrate cleaning unit supporting a cleaning tool so as to be rotatable and making the cleaning tool contact the substrate to clean the substrate, the cleaning tool cleaning unit cleaning the cleaning tool with a cleaning tool cleaning fluid, the operation status information comprising: substrate holding unit status information indicating a status of the substrate holding unit, cleaning fluid supply unit status information indicating a status of the cleaning fluid supply unit, substrate cleaning unit status information indicating a status of the substrate cleaning unit, and cleaning tool cleaning unit status information indicating a status of the cleaning tool cleaning unit; and A state prediction unit, which inputs the action state information obtained by the information acquisition unit into a learning model, thereby predicting cleaning tool state information corresponding to the action state information. The learning model learns the correlation between the action state information and the cleaning tool state information through machine learning. The cleaning tool state information represents the state of the cleaning tool when the substrate processing device operates in the action state indicated by the action state information.

2. The information processing device according to claim 1, wherein: The substrate cleaning unit comprises: a cleaning tool rotating mechanism that rotates the cleaning tool around a first rotation axis parallel to the cleaned surface of the substrate or a second rotation axis perpendicular to the cleaned surface; and a cleaning tool moving mechanism, which moves the relative position between the cleaning tool and the cleaned surface; The substrate cleaning unit status information included in the operation status information includes: The rotation speed of the cleaning tool rotating mechanism, The rotation torque of the cleaning tool rotating mechanism, The position coordinates of the cleaning tool moving mechanism, The moving speed of the cleaning tool moving mechanism, The moving torque of the cleaning tool moving mechanism, a pressing load when the cleaning tool is brought into contact with the substrate, and At least one of the conditions of the cleaning tool.

3. The information processing device according to claim 2, wherein: The cleaning tool cleaning part status information included in the action status information includes: The rotation speed of the cleaning tool rotating mechanism, The rotation torque of the cleaning tool rotating mechanism, The position coordinates of the cleaning tool moving mechanism, The moving speed of the cleaning tool moving mechanism, The moving torque of the cleaning tool moving mechanism, a pressing load when the cleaning tool contacts the cleaning plate of the cleaning tool, The flow rate of the cleaning fluid of the cleaning tool, The pressure of the cleaning fluid of the cleaning tool, and The cleaning tool cleans at least one of the cleanliness of the fluid.

4. The information processing device according to any one of claims 1 to 3, characterized in that: The substrate holding portion comprises: a substrate rotating mechanism that rotates the substrate around a third rotation axis that is perpendicular to a surface to be cleaned of the substrate; and a substrate holding mechanism portion, the substrate holding mechanism portion holding a side edge portion of the substrate, The substrate holding unit state information included in the operation state information includes: The number of substrates held when the substrate holding mechanism holds the substrates, The holding pressure when the substrate holding mechanism holds the substrate, The rotation speed of the substrate rotating mechanism, The rotation torque of the substrate rotating mechanism, and At least one of the conditions of the substrate holding mechanism portion.

5. The information processing device according to any one of claims 1 to 4, characterized in that: The cleaning fluid supply unit status information included in the operation status information includes: The flow rate of the substrate cleaning fluid, The pressure of the substrate cleaning fluid, the dropping position of the substrate cleaning fluid, The temperature of the substrate cleaning fluid, and At least one of the concentrations of the substrate cleaning fluid.

6. The information processing device according to any one of claims 1 to 5, characterized in that: The operation status information further includes device internal environment information, and the device internal environment information represents the environment of the space where the substrate is cleaned by the cleaning tool. The device internal environment information included in the action status information includes: The temperature of the space, The humidity of the space, The air pressure of the space, the airflow of the space, The oxygen concentration of the space, and At least one of the sounds of the space.

7. The information processing device according to any one of claims 1 to 6, characterized in that: The cleaning tool status information is status information indicating the status of the cleaning tool. The situation information includes: The weight of the cleaning tool, The moisture content of the cleaning tool, The hardness of the cleaning tool, and At least one of the cleanliness of the cleaning tool.

8. The information processing device according to any one of claims 1 to 6, characterized in that: The cleaning tool status information includes: Remaining life information indicating the remaining life of the cleaning tool; and At least one of the cleaning quality information indicating the cleaning quality of the cleaning tool.

9. An inference device comprising a memory and a processor, characterized in that: The processor performs the following processing: an information acquisition process, wherein the information acquisition process acquires operation status information as an operation status of a substrate processing device when the substrate processing device is in operation, the substrate processing device comprising a substrate holding portion, a cleaning fluid supply portion, a substrate cleaning portion, and a cleaning tool cleaning portion, the substrate holding portion holding a substrate, the cleaning fluid supply portion supplying a substrate cleaning fluid to the substrate, the substrate cleaning portion supporting a cleaning tool so as to be rotatable and making the cleaning tool contact the substrate to clean the substrate, the cleaning tool cleaning portion cleaning the cleaning tool with a cleaning tool cleaning fluid, the operation status information comprising: substrate holding portion status information indicating a status of the substrate holding portion, cleaning fluid supply portion status information indicating a status of the cleaning fluid supply portion, substrate cleaning portion status information indicating a status of the substrate cleaning portion, and cleaning tool cleaning portion status information indicating a status of the cleaning tool cleaning portion; and and an inference process that, when the operation state information is acquired by the information acquisition process, infers cleaning tool state information indicating a state of the cleaning tool when the substrate processing apparatus operates in the operation state indicated by the operation state information.

10. A machine learning device, characterized in that: have: a learning data storage unit, the learning data storage unit storing a plurality of sets of learning data, the learning data consisting of action state information and cleaning tool state information, the action state information being an action state of a substrate processing device when the substrate processing device is in action, the substrate processing device comprising a substrate holding unit, a cleaning fluid supply unit, a substrate cleaning unit and a cleaning tool cleaning unit, the substrate holding unit holding a substrate, the cleaning fluid supply unit supplying a substrate cleaning fluid to the substrate, the substrate cleaning unit supporting a cleaning tool so as to be rotatable and making the cleaning tool contact the substrate to clean the substrate, the cleaning tool cleaning unit cleaning the cleaning tool with the cleaning tool cleaning fluid, the action state information comprising: substrate holding unit state information indicating a state of the substrate holding unit, cleaning fluid supply unit state information indicating a state of the cleaning fluid supply unit, substrate cleaning unit state information indicating a state of the substrate cleaning unit, and cleaning tool cleaning unit state information indicating a state of the cleaning tool cleaning unit, the cleaning tool state information indicating a state of the cleaning tool when the substrate processing device is in action in the action state indicated by the action state information; a machine learning unit, which inputs a plurality of sets of the learning data into a learning model so that the learning model learns the correlation between the action state information and the cleaning tool state information; as well as A learned model storage unit stores the learned model in which the correlation is learned by the machine learning unit.

11. An information processing method, characterized in that: have: an information acquisition step, wherein the information acquisition step acquires operation status information as an operation status of a substrate processing device when the substrate processing device is in operation, the substrate processing device comprising a substrate holding portion, a cleaning fluid supply portion, a substrate cleaning portion, and a cleaning tool cleaning portion, the substrate holding portion holding a substrate, the cleaning fluid supply portion supplying a substrate cleaning fluid to the substrate, the substrate cleaning portion supporting a cleaning tool so as to be rotatable and making the cleaning tool contact the substrate to clean the substrate, the cleaning tool cleaning portion cleaning the cleaning tool with a cleaning tool cleaning fluid, the operation status information comprising: substrate holding portion status information indicating a status of the substrate holding portion, cleaning fluid supply portion status information indicating a status of the cleaning fluid supply portion, substrate cleaning portion status information indicating a status of the substrate cleaning portion, and cleaning tool cleaning portion status information indicating a status of the cleaning tool cleaning portion; and A state prediction process, in which the action state information obtained through the information acquisition process is input into a learning model to predict the cleaning tool state information corresponding to the action state information. The learning model learns the correlation between the action state information and the cleaning tool state information through machine learning. The cleaning tool state information represents the state of the cleaning tool when the substrate processing device operates in the action state indicated by the action state information.

12. An inference method, executed by an inference device having a memory and a processor, characterized in that: The processor performs the following steps: an information acquisition step, wherein the information acquisition step acquires operation status information as an operation status of a substrate processing device when the substrate processing device is in operation, the substrate processing device comprising a substrate holding portion, a cleaning fluid supply portion, a substrate cleaning portion, and a cleaning tool cleaning portion, the substrate holding portion holding a substrate, the cleaning fluid supply portion supplying a substrate cleaning fluid to the substrate, the substrate cleaning portion supporting a cleaning tool so as to be rotatable and making the cleaning tool contact the substrate to clean the substrate, the cleaning tool cleaning portion cleaning the cleaning tool with a cleaning tool cleaning fluid, the operation status information comprising: substrate holding portion status information indicating a status of the substrate holding portion, cleaning fluid supply portion status information indicating a status of the cleaning fluid supply portion, substrate cleaning portion status information indicating a status of the substrate cleaning portion, and cleaning tool cleaning portion status information indicating a status of the cleaning tool cleaning portion; and and an inference step of inferring cleaning tool state information indicating a state of the cleaning tool when the substrate processing apparatus operates in the operation state indicated by the operation state information, when the operation state information is acquired by the information acquisition step.

13. A machine learning method, characterized in that: have: a learning data storage step, wherein the learning data storage step stores a plurality of sets of learning data in a learning data storage unit, wherein the learning data is composed of action state information and cleaning tool state information, wherein the action state information is an action state of a substrate processing device when the substrate processing device is in action, wherein the substrate processing device comprises a substrate holding unit, a cleaning fluid supply unit, a substrate cleaning unit, and a cleaning tool cleaning unit, wherein the substrate holding unit holds a substrate, the cleaning fluid supply unit supplies a substrate cleaning fluid to the substrate, the substrate cleaning unit supports a cleaning tool so as to be rotatable and makes the cleaning tool contact the substrate to clean the substrate, and the cleaning tool cleaning unit cleans the cleaning tool with a cleaning tool cleaning fluid, wherein the action state information comprises: substrate holding unit state information indicating a state of the substrate holding unit, cleaning fluid supply unit state information indicating a state of the cleaning fluid supply unit, substrate cleaning unit state information indicating a state of the substrate cleaning unit, and cleaning tool cleaning unit state information indicating a state of the cleaning tool cleaning unit, wherein the cleaning tool state information indicates a state of the cleaning tool when the substrate processing device is in action in the action state indicated by the action state information; A machine learning step, wherein the machine learning step inputs a plurality of sets of the learning data into a learning model so that the learning model learns the correlation between the action state information and the cleaning tool state information; as well as A learned model storage step is performed to store the learned model having learned the correlation in the machine learning step in a learned model storage unit.

Citation Information

Patent Citations

  • Substrate cleaning equipment

    JP1998242092A