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

The information processing device quickly and accurately diagnoses substrate processing apparatuses by comparing processing numbers and device information, addressing the challenge of identifying causes for deviations in substrate processing rates.

JP2024159211APending Publication Date: 2024-11-08EBARA CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2023075056
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Identifying the cause of deviations in the number of substrates processed per unit time in a substrate processing apparatus is difficult due to the intricate relationship between various parameter groups and mechanical mechanisms, requiring advanced knowledge and extensive experience.

Method used

An information processing device and method that utilize a reference processing number and device information to diagnose the state of a substrate processing apparatus by comparing it with a reference device, generating diagnostic information to identify and address differences.

Benefits of technology

Enables quick and accurate diagnosis of the substrate processing apparatus state by identifying the cause of processing number deviations, facilitating timely countermeasures.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024159211000001_ABST
    Figure 2024159211000001_ABST
Patent Text Reader

Abstract

To provide an information processing device that enables a state of a substrate processing device to be speedily and accurately diagnosed.SOLUTION: An information processing device 5A comprises: a reference information acquisition part 501 which acquires, as reference information 10-A, a reference processed sheet number WPH-A and reference device information 11-A of a reference device equivalent to a substrate processing device 2 as a reference; a comparison information acquisition part 502 which acquires, as comparison information 10-B, a comparison processed sheet number WPH-B and comparison device information 11-B of a comparison device equivalent to the substrate processing device 2 as an object of comparison of the reference device; and a diagnostic processing part 503A which generates diagnostic information 16 including at least one of the cause of generation of a difference between the reference processed sheet number WPH-A and the comparison processed sheet number WPH-B and measures to eliminate the difference based upon the reference information 10-A and the comparison information 10-B.SELECTED DRAWING: Figure 20
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 technology]

[0002] As one of substrate processing apparatuses that perform various substrate processing on substrates such as semiconductor wafers, a substrate processing apparatus that performs chemical mechanical polishing (CMP) processing is known. Such substrate processing apparatuses include, for example, a polishing unit that performs a polishing processing on the substrate, a finishing unit that performs a finishing processing (e.g., a cleaning processing or a drying processing) on ​​the substrate after the polishing processing, and a transport unit that performs a transport processing to transport the substrate between each unit, and are configured to perform a series of processing by sequentially operating each unit (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2007-301690 A Summary of the Invention [Problem to be solved by the invention]

[0004] The number of substrates processed per unit time (number of substrates processed per unit time) is used as an index for managing the operation of a substrate processing apparatus. In the substrate processing apparatus, various mechanical mechanisms of each unit work in cooperation with each other while referring to various parameter groups such as apparatus setting information and recipe information. Therefore, when the actual value of the number of substrates processed per unit time deviates from the target value of the number of substrates processed per unit time, it is necessary to identify the cause, such as which of the various parameter groups is affecting the deviation, or which of the various mechanical groups is affecting the deviation, and take measures to deal with the cause, as a task for diagnosing the state of the substrate processing apparatus. However, since various parameter groups and mechanisms are intricately related to each other, it is difficult to identify the cause and take measures quickly and accurately, as a result of the need for advanced knowledge and abundant experience.

[0005] 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 enable quick and accurate diagnosis of the condition of a substrate processing device. [Means for solving the problem]

[0006] In order to achieve the above object, an information processing device according to one aspect of the present invention comprises: 1. An information processing apparatus for diagnosing a state of a substrate processing apparatus including a substrate processing unit that performs substrate processing on a substrate, and a transport processing unit that performs a transport processing for transporting a substrate before and after the substrate processing, a reference information acquiring unit that acquires, as reference information, a reference processed number indicating the number of substrates processed per unit time when a reference processing operation in which the substrate processing and the transport processing are repeated is performed in a reference apparatus corresponding to the reference substrate processing apparatus, and reference apparatus information regarding the reference apparatus when the reference processing operation is performed; a comparison processing number indicating the number of substrates processed per unit time when a comparison processing operation in which the substrate processing and the transport processing are repeated is performed in a comparison apparatus corresponding to the substrate processing apparatus to be compared with the reference apparatus; a comparison information acquisition unit that acquires comparison device information related to the comparison device as comparison information; The system is equipped with a diagnostic processing unit that generates diagnostic information including at least one of a cause when a difference occurs between the reference number of sheets processed and the comparative number of sheets processed, and a measure to eliminate the difference, based on the reference information acquired by the reference information acquisition unit and the comparative information acquired by the comparative information acquisition unit. Effect of the Invention

[0007] According to an information processing apparatus according to an aspect of the present invention, a diagnostic processing unit generates diagnostic information including at least one of a cause of a difference between the reference processing number and the comparative processing number based on reference information including a reference processing number and reference processing number information in a reference processing apparatus corresponding to a reference substrate processing apparatus and a comparison information including a comparative processing number and comparison processing number information in a comparison processing apparatus corresponding to a substrate processing apparatus to be compared with the reference apparatus, and a measure to eliminate the difference. Therefore, when a difference occurs between the reference processing number and the comparative processing number, the condition of the substrate processing apparatus can be diagnosed quickly and accurately.

[0008] Other objects, configurations and effects will become apparent from the detailed description of the invention described below. [Brief description of the drawings]

[0009] [Figure 1] 1 is an overall configuration diagram showing an example of a substrate processing system 1. FIG. [Diagram 2] 1 is a schematic plan view showing an example of a substrate processing apparatus 2. FIG. [Diagram 3] 2 is a schematic diagram showing an example of a transfer route (first half) of a wafer W in the substrate processing apparatus 2. FIG. [Figure 4]1 is a schematic diagram showing an example of a transfer route (latter half) of a wafer W in the substrate processing apparatus 2. FIG. [Diagram 5] FIG. 2 is a perspective view showing an example of first to fourth polishing units 22A to 22D. [Figure 6] FIG. 11 is a perspective view showing an example of first finishing units 230A, 230B that perform a roll sponge cleaning process. [Figure 7] FIG. 11 is a perspective view showing an example of second finishing units 231A and 231B that perform a pen sponge cleaning process. [Figure 8] FIG. 13 is a perspective view showing an example of third finishing units 232A, 232B that perform drying processing. [Figure 9] 2 is a schematic side view showing an example of the transport section 24 (second transport units 241A, 241B and a transfer robot 243). FIG. [Figure 10] 1 is a schematic side view showing an example of the transport section 24 (third transport units 242A, 242B and a transfer robot 243). FIG. [Figure 11] FIG. 2 is a block diagram showing an example of a substrate processing apparatus 2. [Figure 12] 9 is a hardware configuration diagram showing an example of a computer 900. [Figure 13] 2 is a data configuration diagram showing an example of production history information 30 managed by a database device 3. FIG. [Figure 14] 2 is a data structure diagram showing an example of test information 31 managed by a database device 3. FIG. [Figure 15] 2 is a data configuration diagram showing an example of simulation information 32 managed by a database device 3. FIG. [Figure 16] FIG. 2 is a block diagram showing an example of a machine learning device 4. [Figure 17] FIG. 2 is a diagram showing an example of a learning model 18 and learning data 17. [Figure 18] 4 is a flowchart showing an example of a machine learning method performed by the machine learning device 4. [Figure 19] FIG. 2 is a block diagram showing an example of an information processing device 5A according to the first embodiment. [Figure 20] FIG. 2 is a functional explanatory diagram showing an example of an information processing device 5A according to the first embodiment. [Figure 21] 11 is a flowchart showing an example of an information processing method by the information processing device 5A according to the first embodiment. [Figure 22] FIG. 11 is a block diagram showing an example of an information processing device 5B according to a second embodiment. [Figure 23] 13 is a flowchart showing an example of an information processing method by an information processing device 5B according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment for carrying out the present invention will be described with reference to the drawings. In the following, the scope necessary for the explanation to achieve the object of the present invention will be shown in a schematic manner, and the scope necessary for the explanation of the relevant part of the present invention will be mainly explained, and the parts that are omitted will be explained as being related to the publicly known technology.

[0011] (First embodiment) FIG. 1 is an overall configuration diagram showing an example of a substrate processing system 1. The substrate processing system 1 according to this embodiment mainly includes a substrate processing apparatus 2, a database device 3, a machine learning device 4, an information processing device 5A, and a user terminal device 6. Each of the devices 2 to 6 is, for example, configured as a general-purpose or dedicated computer (see FIG. 12 described later), and is connected to a wired or wireless network 7 so as to be able to transmit and receive various data (FIG. 1 shows transmission and reception of some data by dashed arrows). The number of the devices 2 to 6 and the connection configuration of the network 7 are not limited to the example of FIG. 1, and may be changed as appropriate.

[0012] The substrate processing apparatus 2 includes a substrate processing unit (described in detail below) that performs various substrate processing on a substrate (hereinafter referred to as a "wafer") W such as a semiconductor wafer, and a transport processing unit (described in detail below) that transports the wafer W. In this embodiment, the substrate processing apparatus 2 includes a polishing unit and a finishing unit as the substrate processing units, and performs a chemical mechanical polishing process (hereinafter referred to as a "polishing process"), a finishing process, a transport processing, etc. on the wafer W by operating the polishing unit, the finishing unit, and the transport processing unit. At that time, the substrate processing apparatus 2 controls the operations of the polishing unit, the finishing unit, and the transport processing unit while referring to apparatus setting information 12 that defines the operation contents of the polishing unit, the finishing unit, and the transport processing unit, and recipe information 13 that defines the processing contents of the polishing process and the finishing process. The substrate processing apparatus 2 then executes a processing operation (automatic operation) that repeats the polishing process, the finishing process, the transport processing, etc. on a plurality of wafers W.

[0013] The substrate processing apparatus 2 transmits various reports R to the database apparatus 3 and the like in response to the execution of processing operations. The various reports R include, for example, process information specifying the wafer W and the time of each process when the processing operation was performed, apparatus information 11 including the state and setting values ​​of each part of the substrate processing apparatus 2 when the processing operation was performed, and operation information of the operator on the substrate processing apparatus 2. The apparatus information 11 includes, for example, apparatus setting information 12, recipe information 13, consumables information 14, event information 15, and the like. Details of each piece of information will be described later.

[0014] The database device 3 is a device that manages production history information 30 related to a history of processing operations (automatic operation) performed using the substrate processing apparatus 2 for actual production, test information 31 related to test results when a test operation (test operation) similar to the processing operation is performed using a test device (not shown), and simulation information 32 related to simulation results when a simulation operation (simulation operation) similar to the processing operation is performed using a simulation device (not shown). The test device may be substituted with the substrate processing apparatus 2 for actual production, or may be a dedicated device capable of testing the processing operation. The simulation device may be substituted with the database device 3, or may be a dedicated device capable of simulating the processing operation.

[0015] The production history information 30 includes information on the actual production substrate processing apparatus 2 when the processing operation is performed. Various reports R transmitted from the production substrate processing apparatus 2 are registered. In the test information 31, various reports R (test results) transmitted from the test apparatus when a test operation is performed in accordance with predetermined test conditions and test conditions are registered. In the simulation information 32, simulation results and simulation conditions transmitted from the simulation apparatus when a simulation operation is performed in accordance with predetermined simulation conditions are registered. The simulation results include, for example, information similar to the report R.

[0016] The machine learning device 4 is a device that operates as a subject of the learning phase of machine learning. The machine learning device 4, for example, refers to the production history information 30, the test information 31, and the simulation information 32 registered in the database device 3, and acquires a plurality of sets of learning data 17. Then, the machine learning device 4 generates a learning model 18 used in the information processing device 5A by machine learning, based on the plurality of sets of learning data 17. The trained learning model 18 is provided to the information processing device 5A via the network 7, a recording medium, or the like.

[0017] The information processing device 5A is a device that operates as a subject of the inference phase of machine learning and diagnoses the state of the substrate processing device 2 by using the learning model 18 provided from the machine learning device 4. The information processing device 5A generates diagnostic information as a result of diagnosing the state of the substrate processing device 2. The substrate processing device 2 to be diagnosed may be the substrate processing device 2 before being shipped from an assembly factory of the substrate processing device 2, or may be the substrate processing device 2 installed on a production line after being shipped from the assembly factory.

[0018] The user terminal device 6 is a terminal device used by an operator, and may be a stationary 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., event notifications, device information 11, production history information 30, test information 31, simulation information 32, diagnosis information, etc.) via the display screen.

[0019] (Substrate processing equipment) Fig. 2 is a schematic plan view showing an example of the substrate processing apparatus 2. Figs. 3 and 4 are schematic views showing an example of a transport route of the wafer W in the substrate processing apparatus 2. The substrate processing apparatus 2 is configured to include a load / unload section 21, a polishing section 22, a finishing section 23, a substrate transport section 24, and a control unit 25 inside a housing 20 having a substantially rectangular shape in a plan view.

[0020] (Load / Unload section) The load / unload section 21 includes first and second front load sections 210A, 210B on which wafer cassettes (substrate cassettes such as FOUPs) capable of storing a large number of wafers W in the vertical direction are placed at wafer cassette positions LL1, LL2, and a supply / discharge robot 211 that supplies and discharges the wafers W.

[0021] The supply and discharge robot 211 is configured to be movable horizontally along the short side direction of the housing 20, and is also configured to be movable up and down and in a rotational direction. The supply and discharge robot 211 has two hands (not shown), one on top and one on bottom, for transferring the wafer W. One hand is used when transferring the wafer W before the polishing process, and the other hand is used when transferring the wafer W after the finishing process. The hand is configured to be extendable and retractable, for example, and capable of turning the wafer W upside down.

[0022] The supply / discharge robot 211 performs a substrate supply process PT1 as a transfer process PT for the wafer W, which takes out the wafer W before polishing from a wafer cassette and supplies it to the first transfer unit 240, and a wafer W after finishing is transferred to a finishing section 23 (a third finishing unit 240 in this embodiment). The substrate is then received from the wafer cassette (32A, 232B) and placed in a wafer cassette (substrate discharge process PT10).

[0023] (polishing section) The polishing section 22 includes a plurality of (four in this embodiment) polishing units 22A-22D each performing a polishing process PP of a wafer W. In this embodiment, the first to fourth polishing units 22A-22D are arranged in line along the longitudinal direction of the housing 20, and perform the polishing process PP of the wafer W in parallel at polishing positions LP1-LP4. The first to fourth polishing units 22A-22D are configured to be accessible to polishing unit transfer positions LT1-LT4 for transferring the wafer W. The polishing unit transfer positions LT1-LT4 are set individually for the first to fourth polishing units 22A-22D.

[0024] 5 is a perspective view showing an example of the first to fourth polishing units 22A to 22D. In this embodiment, the first to fourth polishing units 22A to 22D will be described assuming that they have the same basic configuration and functions.

[0025] Each of the first to fourth polishing units 22A to 22D includes a polishing table 220 that rotatably supports a polishing pad 2200 having a polishing surface, a top ring (substrate holding part) 221 that rotatably holds a wafer W and polishes the wafer W while pressing it against the polishing pad 2200 on the polishing table 220, a polishing fluid supply part 222 that supplies a polishing fluid to the polishing pad 2200, a dresser 223 that rotatably supports a dresser disk 2230 and brings the dresser disk 2230 into contact with the polishing surface of the polishing pad 2200 to dress the polishing pad 2200, and an atomizer 224 that sprays a cleaning fluid onto the polishing pad 2200.

[0026] The polishing table 220 is supported by a polishing table shaft 220a and includes a rotational movement mechanism 220b that rotates the polishing table 220 about its axis, and a temperature adjustment mechanism 220c that adjusts the surface temperature of the polishing pad 2200.

[0027] The top ring 221 is supported by a top ring shaft 221a that is movable in the vertical direction, and includes a rotational movement mechanism 221c that rotates the top ring 221 about its axis, a vertical movement mechanism 221d that moves the top ring 221 in the vertical direction, and a swinging movement mechanism 221e that swings (swings) the top ring 221 about the support shaft 221b. The rotational movement mechanism 221c, the vertical movement mechanism 221d, and the swinging movement mechanism 221e function as a substrate moving mechanism that moves the relative positions of the polishing pad 2200 and the polished surface of the wafer W.

[0028] The polishing fluid supply unit 222 includes a polishing fluid supply nozzle 222a that supplies a polishing fluid to the polishing surface of the polishing pad 2200, a swinging movement mechanism 222c that is supported by a support shaft 222b and moves the polishing fluid supply nozzle 222a in a swinging motion around the support shaft 222b, a flow rate adjustment unit 222d that adjusts the flow rate of the polishing fluid, and a temperature adjustment mechanism 222e that adjusts the temperature of the polishing fluid. The polishing fluid is a polishing liquid (slurry) or pure water, and may further include a chemical solution or may be a polishing liquid to which a dispersant has been added.

[0029] The dresser 223 is supported by a dresser shaft 223a that can move in the vertical direction, and is equipped with a rotational movement mechanism 223c that rotates the dresser 223 around its axis, a vertical movement mechanism 223d that moves the dresser 223 in the vertical direction, and a swinging movement mechanism 223e that moves the dresser 223 in a swinging motion around the support shaft 223b.

[0030] The atomizer 224 is supported by a support shaft 224a and rotates around the support shaft 224a. The cleaning fluid is a mixture of a liquid (e.g., pure water) and a gas (e.g., nitrogen gas) or a liquid (e.g., pure water).

[0031] In the polishing process PP, the top ring 221 moves to the polishing unit transfer positions LT1 to LT4, and receives the unpolished wafer W from the second transfer units 241A and 241B by suction-holding the unpolished wafer W on the lower surface of the top ring 221. Next, the top ring 221 moves to the polishing positions LP1 to LP4 on the polishing table 220, and presses the wafer W against the polishing surface of the polishing pad 2200 to which a polishing fluid is supplied from the polishing fluid supply nozzle 222a, thereby polishing the wafer W. Then, when the polishing process PP is completed, the top ring 221 moves to the polishing unit transfer positions LT1 to LT4, and transfers the polished wafer W to the second transfer units 241A and 241B.

[0032] (Finishing section) The finishing section 23 includes a plurality of finishing units 230A-232A, 230B-232B (in this embodiment, a total of six, three types each arranged in two upper and lower stages) each performing a finishing process PC on the wafer W. In this embodiment, the first to third finishing units 230A-232A are arranged in the upper stage along the longitudinal direction of the housing 20, and the first to third finishing units 230B-232B having the same configuration are arranged in the lower stage along the longitudinal direction of the housing 20. The first to third finishing units 230A-232A, 230B-232B perform the finishing processes PC in the order of their arrangement (the order of the finishing steps) at finishing positions LC1-LC3, respectively.

[0033] The first finishing units 230A and 230B perform a roll sponge cleaning process (first finishing process PC1) as the finishing process PC of the most upstream process, which uses a roll sponge 2300 to clean the wafer W after the polishing process. The second finishing units 231A and 231B perform a pen sponge cleaning process (second finishing process PC2) as the finishing process PC of the most downstream process, which uses a pen sponge 2310 to clean the wafer W after the roll sponge cleaning process. The third finishing units 232A and 232B perform a drying process (third finishing process PC3) as the finishing process PC of the most downstream process, which dries the wafer W after the pen sponge cleaning process. Note that the finishing process PC may start with the pen sponge cleaning process, for example, omitting the roll sponge cleaning process.

[0034] The roll sponge 2300 and the pen sponge 2310 are made of a synthetic resin such as PVA or nylon, and have a porous structure. The roll sponge 2300 and the pen sponge 2310 function as cleaning tools for scrubbing the wafer W, and are replaceably attached to the first finishing units 230A and 230B and the second finishing units 231A and 231B, respectively.

[0035] The finishing section 23 may include a finishing unit (not shown) that performs a buff cleaning process for cleaning the wafer W using a buff instead of or in addition to any of the first and second finishing units 230A, 230B, 230A, 231A, 231B, or any of the first and second finishing units 230A, 230B, 230A, 231A, 231B may be omitted. In this embodiment, the first to third finishing units 230A to 232A, 230B to 232B are described as holding the wafer W horizontally (horizontally holding), but they may hold the wafer W vertically or at an angle.

[0036] 6 is a perspective view showing an example of first finishing units 230A and 230B for performing roll sponge cleaning processing. The first finishing units 230A and 230B include a substrate holder 2301 for holding a wafer W, a cleaning fluid supply unit 2302 for supplying a substrate cleaning fluid to the wafer W, and a cleaning fluid supply unit 2303 for rotatably supporting a roll sponge 2300 and for cleaning the roll sponge 2300 on the wafer. The apparatus includes a substrate cleaning unit 2303 that cleans the wafer W by contacting the roll sponge 2300 with a cleaning tool cleaning fluid, and a cleaning tool cleaning unit 2304 that cleans (self-cleaning) the roll sponge 2300 with a cleaning tool cleaning fluid. The substrate cleaning fluid may be either pure water (rinsing liquid) or a chemical liquid, or may be a liquid, or may be a two-fluid mixture of a liquid and a gas, or may contain a solid such as dry ice. The cleaning tool cleaning fluid may be either pure water (rinsing liquid) or a chemical liquid.

[0037] In the roll sponge cleaning process by the first finishing units 230A and 230B, the wafer W is rotated while being held at the first finishing position LC1 by the substrate holding part 2301. Then, with a substrate cleaning fluid being supplied from a cleaning fluid supply part 2302 to the surface of the wafer W to be cleaned, the roll sponge 2300 rotated about its axis by the substrate cleaning part 2303 comes into sliding contact with the surface of the wafer W to be cleaned, thereby cleaning the wafer W.

[0038] 7 is a perspective view showing an example of second finishing units 231A and 231B for performing a pen sponge cleaning process. The second finishing units 231A and 231B include a substrate holding unit 2311 for holding a wafer W, a cleaning fluid supply unit 2312 for supplying a substrate cleaning fluid to the wafer W, a substrate cleaning unit 2313 for rotatably supporting a pen sponge 2310 and bringing the pen sponge 2310 into contact with the wafer W to clean the wafer W, and a cleaning tool cleaning unit 2314 for cleaning (self-cleaning) the pen sponge 2310 with a cleaning tool cleaning fluid.

[0039] In the pen sponge cleaning process by the second finishing units 231A, 231B, the wafer W is rotated while being held at the second finishing position LC2 by the substrate holding part 2311. Then, with a substrate cleaning fluid being supplied from the cleaning fluid supply part 2312 to the surface of the wafer W to be cleaned, the pen sponge 2310 rotated about its axis by the substrate cleaning part 2313 comes into sliding contact with the surface of the wafer W to be cleaned, thereby cleaning the wafer W.

[0040] 8 is a perspective view showing an example of third finishing units 232A, 232B that perform drying processing. The third finishing units 232A, 232B include a substrate holder 2321 that holds the wafer W, and a drying fluid supply unit 2322 that supplies a substrate drying fluid to the wafer W. The substrate drying fluid is, for example, IPA vapor and pure water (rinsing liquid), and may be a liquid, a two-fluid mixture of liquid and gas, or a fluid containing a solid such as dry ice.

[0041] In the drying process by the third finishing units 232A, 232B, the wafer W is rotated while being held at the third finishing position LC3 by the substrate holding part 2321. Then, with a substrate drying fluid being supplied from the drying fluid supply part 2322 to the surface to be cleaned of the wafer W, the drying fluid supply part 2322 is moved to the side edge part (radial outer side) of the wafer W. Thereafter, the wafer W is dried by being rotated at high speed.

[0042] (Substrate transport section) Fig. 9 is a schematic side view showing an example of the transport section 24 (second transport units 241A, 241B and transfer robot 243). Fig. 10 is a schematic side view showing an example of the transport section 24 (third transport units 242A, 242B and transfer robot 243). The substrate transport section 24 is composed of a plurality of transport processing units that can select a transport route when transporting a substrate in a transport process.

[0043] 2, the substrate transport section 24 includes a first transport unit 240, second transport units 241A and 241B, third transport units 242A and 242B, and a transfer robot 243. In this embodiment, the second transport units include a second transport unit 241A arranged on the side of the first and second polishing units 22A and 22B (hereinafter referred to as the "right side"), and a second transport unit 241B arranged on the side of the third and fourth polishing units 22C and 22D (hereinafter referred to as the "left side"). Also, the third transport unit includes a second transport unit 241B arranged on the upper stage. The third transport unit 242A is disposed on the upper stage, and the third transport unit 242B is disposed on the lower stage.

[0044] The first transport unit 240 is disposed between the polishing section 22 and the finishing section 23, and is configured to be movable horizontally along the longitudinal direction of the housing 20 between a first transport start position LS1 and a first transport end position LE1.

[0045] The first transfer unit 240 performs a pre-polishing transfer process PT2 as a transfer process PT for the wafer W, in which the pre-polishing wafer W supplied by the supply / discharge robot 211 is transferred from a first transfer start position LS1 to a first transfer end position LE1.

[0046] The second transport units 241A and 241B are disposed on the polishing section 22 side and configured to be movable horizontally along the longitudinal direction of the housing 20 and to be movable vertically.

[0047] The second transport unit 241A on the right side is equipped with multiple transport mechanisms 2410A-2412A (in this embodiment, a total of three arranged in three upper and lower tiers) that move horizontally independently between the transfer robot transfer position LR1 and the polishing unit transfer positions LT1, LT2, a first pusher mechanism 2413A that is arranged at the polishing unit transfer position LT1 and moves in the vertical direction, and a second pusher mechanism 2414B that is arranged at the polishing unit transfer position LT2 and moves in the vertical direction.

[0048] The second transport unit 241B on the left side is equipped with multiple transport mechanisms 2410B-2412B (in this embodiment, a total of three arranged in three upper and lower tiers) that move horizontally independently between the transfer robot transfer position LR2 and the polishing unit transfer positions LT3, LT4, a first pusher mechanism 2413B that is arranged at the polishing unit transfer position LT3 and moves in the vertical direction, and a second pusher mechanism 2414B that is arranged at the polishing unit transfer position LT4 and moves in the vertical direction.

[0049] Each of the multiple transport mechanisms 2410A-2412A, 2410B-2412B in the second transport units 241A, 241B performs a transport process PT for the wafer W, which includes a pre-polishing process load process PT4 for transporting the wafer W before the polishing process from the transfer robot transfer positions LR1, LR2 to the polishing unit transfer positions LT1-LT4, and a post-polishing process unload process PT5 for transporting the wafer W after the polishing process from the polishing unit transfer positions LT1-LT4 to the transfer robot transfer positions LR1, LR2.

[0050] The third conveying units 242A, 242B are arranged on the finishing section 23 side and are configured to be movable horizontally along the longitudinal direction of the housing 20 between the third conveying start position LS3, the first finishing position LC1, the second finishing position LC2, and the third finishing position LC3.

[0051] The third transfer unit 242A at the upper stage includes a wafer station 2420A for holding a polished wafer W and allowing the wafer W to wait thereon, and a transfer mechanism 2421A for moving horizontally between the wafer station 2420A and the first to third finishing units 230A to 232A. The third transfer unit 242B at the lower stage includes a wafer station 2420B for holding a polished wafer W and allowing the wafer W to wait thereon, and a transfer mechanism 2421B for moving horizontally between the wafer station 2420B and the first to third finishing units 230B to 232B. The transfer mechanisms 2421A and 2421B include a pair of left and right hands 2422 and 2423 for transferring the wafer W. One hand 2422 is used when transferring a wafer W that has been polished but is not yet finished, and the other hand 2433 is used when transferring a wafer W that has been finished. The hands 2422 and 2433 are, for example, The wafer W can be folded upside down and can be turned upside down.

[0052] The transport mechanisms 2421A, 2421B in the third transport units 242A, 242B perform transport processes PT for the wafer W, including a post-polishing transport process PT7 in which the wafer W after the polishing process is transported from the third transport start position LS3 to the finishing section 23 (in this embodiment, the first finishing position LC1 of the first finishing units 230A, 230B), and during-finishing transport processes PT8, PT9 in which the wafer W undergoing finishing process is transported between each finishing unit. In this embodiment, the third transport units 242A, 242B perform the following finishing transport processes: a first finishing transport process PT8 for transporting a wafer W undergoing finishing processing from the first finishing unit 230A, 230B (first finishing position LC1) to the second finishing unit 231A, 231B (second finishing position LC2), and a second finishing transport process PT9 for transporting a wafer W undergoing finishing processing from the second finishing unit 231A, 231B (second finishing position LC2) to the third finishing unit 232A, 232B (third finishing position LC3).

[0053] The transfer robot 243 is configured to be movable in the vertical direction and to be movable in the rotation direction. The transfer robot 243 includes a hand 2430 for receiving and transferring the wafer W. The hand 2430 is configured to be, for example, extendable and capable of turning the wafer W upside down.

[0054] The transfer robot 243 performs the following transport processes PT for the wafer W: a pre-polishing process transfer process PT3 in which the transfer robot 243 receives the wafer W before the polishing process from the first transfer unit 240 at the first transfer end position LE1 and transfers it to the second transfer units 241A, 241B at the transfer robot transfer positions LR1, LR2; and a post-polishing process transfer process PT6 in which the transfer robot 243 receives the wafer W after the polishing process from the second transfer units 241A, 241B at the transfer robot transfer positions LR1, LR2 and transfers it to the third transfer units 242A, 242B at the third transfer start position LS3.

[0055] (Control Unit) 11 is a block diagram showing an example of the substrate processing apparatus 2. The control unit 25 is electrically connected to each of the sections 21 to 24, and functions as a control section that comprehensively controls each of the sections 21 to 24. In the following, the control systems (modules, sensors, sequencers) of the polishing section 22, the finishing section 23, and the substrate transport section 24 will be described as examples, but the loading / unloading section 21 will not be described because it has the same basic configuration and functions.

[0056] The polishing section 22 includes a plurality of modules 227 to be controlled, which are arranged in each substrate processing unit (in this embodiment, the first to fourth polishing units 22A to 22D), a plurality of sensors 228 arranged in each of the modules 227 to detect data (detection values) required for controlling each module 227, and a sequencer 229 that controls the operation of each module 227 based on the detection values ​​of each sensor 228.

[0057] The finishing section 23 includes a plurality of modules 237 to be controlled, which are arranged in each substrate processing unit (in this embodiment, the first to third finishing units 230A to 232A, 230B to 232B), a plurality of sensors 238 arranged in each of the plurality of modules 237 to detect data (detection values) required for controlling each module 237, and a sequencer 239 that controls the operation of each module 237 based on the detection values ​​of each sensor 238.

[0058] The substrate transport unit 24 is arranged in each transport processing unit (in this embodiment, the first transport unit 240, the second transport units 241A and 241B, the third transport units 242A and 242B, and the transfer robot 243) and stores a plurality of modules 247 to be controlled, and data required for controlling each module 247 that is arranged in each of the plurality of modules 247. The system includes a plurality of sensors 248 that detect data (detection values), and a sequencer 249 that controls the operation of each module 247 based on the detection values ​​of each sensor 248.

[0059] The modules 227, 237, 247 include rotary motors, linear motors, air actuators, hydraulic actuators, etc. provided in each part to perform rotary motion and linear motion. The modules 227, 237, 247 are appropriately combined with driving force transmission mechanisms such as linear guides, ball screws, gears, belts, couplings, bearings, etc. according to the function of each part. The sensors 228, 238, 248 include, for example, linear sensors, encoder sensors, limit sensors, torque sensors, acceleration sensors, angular velocity sensors, current sensors, flow sensors, pressure sensors, vibration sensors, temperature sensors, proximity sensors, etc.

[0060] The control unit 25 includes a control unit 250, a communication unit 251, an input unit 252, an output unit 253, and a storage unit 254. The control unit 25 is configured, for example, by a general-purpose or dedicated computer (see FIG. 12 described later).

[0061] The communication unit 251 is connected to the network 7 and functions as a communication interface for transmitting and receiving various data. The input unit 252 accepts various input operations, and the output unit 253 functions as a user interface by outputting various information via a display screen, signal tower lighting, and buzzer sound.

[0062] The storage unit 254 stores various programs (operating system (OS), control programs, application programs, web browser, etc.) and data (apparatus information 11, etc.) used in the operation of the substrate processing apparatus 2.

[0063] The control unit 250 acquires detection values ​​of the multiple sensors 218, 228, 238, 248 (hereinafter referred to as the "sensor group") via the multiple sequencers 219, 229, 239, 249 (hereinafter referred to as the "sequencer group"), and causes the multiple modules 217, 227, 237, 247 (hereinafter referred to as the "module group") to operate in cooperation with each other. The substrate processing apparatus 2 controls each unit 21-24 by the control unit 250, and performs a polishing process PP, a finishing process PC, a transport process PT, etc., sequentially on the multiple wafers W in the wafer cassette, thereby performing an automatic operation.

[0064] The device information 11 includes, for example, device setting information 12, recipe information 13, consumables information 14, and event information 15. The device information 11 is data that is displayed via a display screen and can be edited by an operator.

[0065] The equipment setting information 12 is information that defines the operation content of the substrate processing apparatus 2 when the substrate processing apparatus 2 executes a processing operation (automatic operation) of repeating substrate processing and transport processing for multiple wafers W. The equipment setting information 12 has multiple equipment setting items, and defines the operation content of the substrate processing apparatus 2 by setting setting values ​​for each of the multiple equipment setting items.

[0066] The apparatus setting items include, for example, the coordinate values, moving speed, moving acceleration, timer time, etc. of each transport processing unit. The apparatus setting items also include the coordinate values, moving speed, moving acceleration, timer time, etc. of each substrate processing unit (in this embodiment, the polishing units 22A-22D and the finishing units 230A-232A, 230B-232B). The apparatus setting items may also include the version of a control program for controlling the operation of the substrate processing apparatus 2.

[0067] The recipe information 13 is information indicating the processing contents of the polishing process PP and the finishing process PC. The recipe information 13 has a plurality of recipe setting items, and a set value is set for each of the plurality of recipe setting items. By setting each of these, the process contents of the polishing process PP and the finishing process PC are determined. Note that the recipe information 13 may be set for each wafer W, or may be set for each of a plurality of wafers constituting a lot.

[0068] Recipe setting items for the polishing process PP include, for example, the table rotation speed of the polishing table 220, the top ring pressing time of the top ring 221, the wafer pressing load, the wafer rotation speed, the amount of polishing fluid supplied by the polishing fluid supply unit 222, the supply timing, the dresser operation time of the dresser 223, the atomizer operation time of the atomizer 224, etc.

[0069] Recipe setting items for the finishing process PC include, for example, roll sponge operation time, roll sponge rotation speed, wafer rotation speed, supply amount and supply timing of substrate cleaning fluid in the roll sponge cleaning process (first finishing process PC1), pen sponge operation time, pen sponge rotation speed, wafer rotation speed, supply amount and supply timing of substrate cleaning fluid in the pen sponge cleaning process (second finishing process PC2), wafer rotation speed, drying operation time, wafer rotation speed, supply amount and supply timing of substrate drying fluid in the drying process (third finishing process PC3), etc.

[0070] The consumable information 14 is information that defines, for each consumable item, the consumption state of the consumables used in the substrate processing apparatus 2 when a processing operation is performed. The consumables include, but are not limited to, the polishing pad 2200, the roll sponge 2300, the pen sponge 2310, etc. The consumable items include, for example, the number of uses, the usage time, and the pressure when used of the polishing pad 2200, the number of uses, the usage time, and the pressure when used of the roll sponge 2300, and the number of uses, the usage time, and the pressure when used of the pen sponge 2310.

[0071] The event information 15 is information that defines, for each event item, the content of an event that occurs in the substrate processing apparatus 2 when a processing operation is performed. Examples of event items include, but are not limited to, an occurring event ID and an occurring unit ID. The occurring event ID identifies the type (actuator malfunction, sensor abnormality detection, etc.) and the level (abnormal stop, warning operation) of an event that occurs in the substrate processing apparatus 2 by the event ID. The occurring unit ID identifies the unit in which the event occurs by the unit ID.

[0072] (Hardware configuration of each device) 12 is a hardware configuration diagram showing an example of a computer 900. Each of the control unit 25 of the substrate processing apparatus 2, the database device 3, the machine learning device 4, the information processing device 5A, and the user terminal device 6 is configured by a general-purpose or dedicated computer 900.

[0073] 12, the computer 900 includes, as its main components, 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 / output) device I / F unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the application of the computer 900.

[0074] The processor 912 is composed of one or more arithmetic processing devices (such as a central processing unit (CPU), a micro-processing unit (MPU), a digital signal processor (DSP), a graphics processing unit (GPU), or a neural processing unit (NPU)) and operates as a control unit that controls the entire computer 900. The memory 914 stores various data and programs 930 and includes, for example, a volatile memory (DRAM, SRAM, etc.) that functions as a main memory and a non-volatile memory (ROM, ), flash memory, etc.

[0075] The input device 916 is, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The output device 917 is, for example, a sound (audio) output device, a vibration device, etc., and functions as an output unit. The display device 918 is, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit. The input device 916 and the display device 918 may be integrally configured, such as a touch panel display. The storage device 920 is, for example, a HDD, an SSD, etc., and functions as a storage unit. The storage device 920 stores various data necessary for the execution of the operating system and the program 930.

[0076] The communication I / F unit 922 is connected to a network 940 (which may be the same as the network 7 in FIG. 1) such as the Internet or an intranet by wire or wirelessly, and functions as a communication unit that transmits and receives data to and from other computers according to a predetermined communication standard. The external device I / F unit 924 is connected to an external device 950 such as a camera, a printer, a scanner, a reader / writer by wire or wirelessly, and functions as a communication unit that transmits and receives data to and from the external device 950 according to a predetermined communication standard. The I / O device I / F unit 926 is connected to an I / O device 960 such as various sensors and actuators, and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, between the I / O device 960. The media input / output unit 928 is composed of, for example, a drive device such as a DVD drive or a CD drive, a memory card slot, and a USB connector, and reads and writes data from and to a medium (non-temporary storage medium) 970 such as a DVD, a CD, a memory card, or a USB memory.

[0077] In the computer 900 having the above configuration, the processor 912 calls up the program 930 stored in the storage device 920 into the memory 914, executes the program, and controls each unit of the computer 900 via the bus 910. The program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded in the medium 970 in an installable file format or an executable file format, and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by downloading the program 930 via the communication I / F unit 922 over the network 940. In addition, the computer 900 may realize various functions realized by the processor 912 executing the program 930, for example, with hardware such as an FPGA or an ASIC.

[0078] The computer 900 is, for example, a desktop computer or a portable computer, and is an electronic device of any type. The computer 900 may be a client computer, a server computer, or a cloud computer, or may be, for example, an embedded computer called a control panel, a controller (including a microcomputer, a programmable logic controller, and a sequencer). The computer 900 may also be applied to devices other than the devices 2 to 6.

[0079] (Production history information 30) 13 is a data configuration diagram showing an example of production history information 30 managed by the database device 3. The production history information 30 includes, for example, a wafer history table 300 relating to the wafer W and the time of each process, an equipment information table 301 relating to equipment information 11, and an operation history table 302 relating to operation information, as tables in which reports R acquired when processing operations are performed in the substrate processing apparatus 2 for this production are classified and registered.

[0080] Each record in the wafer history table 300 includes, for example, a wafer ID, a device ID, a cassette ID, and The process time, the start time, the end time, the ID of the unit used, etc. are registered. Note that, although polishing process, cleaning process, and drying process are exemplified in Fig. 13, other processes are also registered in the same manner. The unit used ID specifies the unit used in each process by the unit ID, and the unit ID is associated with a unit type (e.g., conveying process, polishing process, roll sponge cleaning process, pen sponge cleaning process, drying process, etc.) that indicates the type of the unit.

[0081] In each record of the equipment information table 301, for example, a wafer ID, and the equipment setting information 12, recipe information 13, consumables information 14, event information 15, etc., included in the equipment information 11 are registered. The equipment setting information 12, recipe information 13, consumables information 14, and event information 15 may be registered as they are, or information indicating a reference destination of the information may be registered.

[0082] In each record of the operation history table 302, for example, an apparatus ID, an operation time, user operation information, etc. are registered. The user operation information includes, for example, the edited contents when the operator edits the apparatus setting information 12 and the recipe information 13 (for example, the edited apparatus setting items or recipe setting items, and the setting values ​​before and after the edit, etc.). In addition, the user operation information includes, for example, the replacement contents when the operator replaces a consumable item (for example, the type of the replaced consumable item).

[0083] In the production history information 30, by referring to the wafer history table 300, it is possible to calculate, for example, the number of wafers W processed per unit time (hereinafter referred to as "number of wafers processed per unit time WPH") when processing operations are performed on a plurality of wafers W. By referring to the equipment information table 301 and the operation history table 302 associated with each other by the wafer ID and the equipment ID, it is possible to acquire various information when processing operations are performed.

[0084] (Exam Information 31) 14 is a data configuration diagram showing an example of the test information 31 managed by the database device 3. The test information 31 includes a test table 310 in which test conditions and test results obtained when a test operation is performed by the test device are classified and registered.

[0085] Each record of the test table 310 includes, for example, a test ID, test conditions, a first number of sheets processed per unit time WPH-1, first equipment information 11-1, a second number of sheets processed per unit time WPH-2, second equipment information 11-2, test diagnosis information, and the like.

[0086] The test conditions are conditions that are changed between the first test operation and the second test operation when the first test operation and the second test operation are performed in the test device. For example, the test conditions include device setting change contents when a setting value for a specific (may be multiple) device setting item included in the device setting information 12 is changed, recipe change contents when a setting value for a specific (may be multiple) recipe setting item included in the recipe information 13 is changed, consumable replacement contents when a specific (may be multiple) consumable item is replaced, and mechanical change contents when a mechanical adjustment value (e.g., stroke amount of an air actuator, etc.) of a specific module 217, 227, 237, 247 is changed as a mechanical adjustment item that can be mechanically adjusted.

[0087] In the test device, by performing a first test operation before the setting values ​​or adjustment values ​​in the test conditions are changed or before the consumables are replaced, the number of sheets processed per unit time WPH and device information 11 at that time are registered as the first number of sheets processed per unit time WPH-1 and first device information 11-1. Also, in the test device, by performing a second test operation after the setting values ​​or mechanical adjustment values ​​in the test conditions are changed or after the consumables are replaced, the number of sheets processed per unit time WPH and device information 11 at that time are registered as the second number of sheets processed per unit time WPH-2 and second device information 11-1. It will be registered as 1-2.

[0088] The test diagnostic information includes at least one of a cause when a difference occurs between the first number of wafers processed per unit time WPH-1 and the second number of wafers processed per unit time WPH-2, and a countermeasure for eliminating the difference. In this case, the test diagnostic information may include at least one of a cause classification result in which the causes are classified into a plurality of cause types, and a countermeasure classification result in which the countermeasures are classified into a plurality of countermeasure types. The cause types include at least one of a cause caused by the apparatus setting information 12, a cause caused by the recipe information 13, a cause caused by consumables, and a mechanical cause of the substrate processing apparatus 2. The countermeasure types include at least one of a countermeasure related to the apparatus setting information 12, a countermeasure related to the recipe information 13, a countermeasure related to consumables, and a mechanical cause of the substrate processing apparatus 2.

[0089] In addition, the test diagnosis information may include at least one of cause items identified as cause-related items by at least one of equipment setting items, recipe setting items, consumable items, and mechanical adjustment items, and at least one of countermeasure items identified as countermeasure-related items by at least one of equipment setting items, recipe setting items, consumable items, and mechanical adjustment items.

[0090] The test diagnosis information is registered based on the test conditions. For example, when the device setting change contents are registered as the test conditions, the cause type is classified as a cause caused by the device setting information 12, and the cause item is identified by the device setting item changed by the device setting change contents. When the recipe change contents are registered as the test conditions, the cause type is classified as a cause caused by the recipe information 13, and the cause item is identified by the recipe setting item changed by the recipe change contents. When the consumable replacement contents are registered as the test conditions, the cause type is classified as a cause caused by the consumable, and the cause item is identified by the consumable item changed in the consumable replacement. When the mechanical change contents are registered as the test conditions, the cause type is classified as a mechanical cause, and the cause item is identified by the mechanical adjustment item changed by the mechanical change contents. The test diagnosis information may be input by an operator by accepting an input operation by the operator via the user terminal device 6.

[0091] (Simulation information 32) 15 is a data configuration diagram showing an example of the simulation information 32 managed by the database device 3. The simulation information 32 includes a simulation table 320 in which the simulation conditions and the simulation results acquired when a simulation operation is performed by the simulation device are classified and registered.

[0092] Each record of the simulation table 320 includes, for example, a simulation ID, a simulation condition, a first processing number per unit time WPH-1, a first device information 11-1, a second processing number per unit time WPH-2, a second device information 11-2, and simulation diagnosis information.

[0093] The simulation conditions are conditions that are changed between the first simulation operation and the second simulation operation when the first simulation operation and the second simulation operation are performed in the simulation device. For example, the simulation conditions include device setting change contents when a setting value for a specific (may be multiple) device setting item included in the device setting information 12 is changed, recipe change contents when a setting value for a specific (may be multiple) recipe setting item included in the recipe information 13 is changed, consumable replacement contents when a specific (may be multiple) consumable item is replaced, and mechanical change contents when a mechanical adjustment value (e.g., stroke amount of an air actuator, etc.) of a specific module 217, 227, 237, 247 is changed as a mechanical adjustment item that can be mechanically adjusted.

[0094] In the simulation device, by performing a first simulation operation before the setting values ​​or adjustment values ​​in the simulation conditions are changed or before the consumables are replaced, the number of sheets processed per unit time WPH and device information 11 at that time are registered as the first number of sheets processed per unit time WPH-1 and the first device information 11-1. Also, by performing a second simulation operation after the setting values ​​or mechanical adjustment values ​​in the simulation conditions are changed or after the consumables are replaced, the number of sheets processed per unit time WPH and device information 11 at that time are registered as the second number of sheets processed per unit time WPH-2 and the second device information 11-2.

[0095] The simulation diagnostic information includes at least one of the cause of a difference between the first number of sheets processed per unit time WPH-1 and the second number of sheets processed per unit time WPH-2 and a measure to eliminate the difference. The simulation diagnostic information is registered based on the simulation conditions, as in the test table 310, but may also be input by an operator by receiving an input operation by the operator via the user terminal device 6. Note that the data structure of the simulation diagnostic information is similar to that of the test diagnostic information in the test table 310, and therefore a detailed description thereof will be omitted.

[0096] (Machine Learning Device 4) 16 is a block diagram showing an example of the machine learning device 4. The machine learning device 4 includes a control unit 40, a communication unit 41, a learning data storage unit 42, a trained model storage unit 43, an input unit 44, and an output unit 45.

[0097] 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., the substrate processing apparatus 2, the database device 3, the information processing device 5A, the user terminal device 6, a simulation device (not shown), etc.) via the network 7, and functions as a communication interface for transmitting and receiving various data. The input unit 44 accepts various input operations, and the output unit 45 functions as a user interface by outputting various information via a display screen or voice.

[0098] The learning data acquisition unit 400 acquires learning data 17 consisting of reference information 10-A and comparison information 10-B as input data, and diagnostic information 16 as output data. The learning data 17 is data used as teacher data (training data), verification data, and test data in supervised learning. The diagnostic information 16 is data used as a correct answer label in supervised learning.

[0099] The learning data acquiring unit 400 acquires the learning data 17, for example, by referring to the production history information 30, the test information 31, or the simulation information 32 of the database device 3. For example, the learning data acquiring unit 400 detects the operation time when the setting value of the equipment setting information 12 or the recipe information 13 is changed or the consumables are replaced in the operation history table 302, and acquires the number of wafers processed per unit time WPH and the equipment information 11 before those times as reference information 10-A and the number of wafers processed per unit time WPH and the equipment information 11 after those times as comparison information 10-B from the wafer history table 300 and the equipment information table 301. Then, the learning data acquiring unit 400 acquires the learning data 17 by accepting the diagnosis information 16 for the reference information 10-A and the comparison information 10-B as an input operation by the operator via the user terminal device 6, for example.

[0100] The learning data acquisition unit 400 also acquires learning data 17 from a specific record in the test table 310 by acquiring the first number of sheets processed per unit time WPH-1 and the first device information 11-1 as reference information 10-A, the second number of sheets processed per unit time WPH-2 and the second device information 11-2 as comparison information 10-B, and the test diagnosis information as diagnosis information 16. The learning data acquisition unit 400 acquires learning data 17 from a specific record in the simulation table 320 by setting the first number of sheets processed per unit time WPH-1 and the first device information 11-1 as reference information 10-A, the second number of sheets processed per unit time WPH-2 and the second device information 11-2 as comparison information 10-B, and acquiring simulation diagnostic information as diagnostic information 16.

[0101] The learning data storage unit 42 is a database that stores a plurality of sets of learning data 17 acquired by the learning data acquisition unit 400. The specific configuration of the database that constitutes the learning data storage unit 42 may be designed as appropriate.

[0102] The machine learning unit 401 performs machine learning using multiple sets of learning data 17 stored in the learning data storage unit 42. That is, the machine learning unit 401 inputs multiple sets of learning data 17 to the learning model 18, and generates a trained learning model 18 by having the learning model 18 learn the correlation between the reference information 10-A and the comparison information 10-B included in the learning data 17, and the diagnostic information 16.

[0103] The trained model storage unit 43 is a database that stores the trained learning model 18 (specifically, a group of adjusted weight parameters) generated by the machine learning unit 401. The trained learning model 18 stored in the trained model storage unit 43 is provided to an actual system (e.g., information processing device 5A) via the network 7, a recording medium, or the like. Note that, although the learning data storage unit 42 and the trained model storage unit 43 are shown as separate storage units in FIG. 16, they may be configured as a single storage unit.

[0104] 17 is a diagram showing an example of a learning model 18 and learning data 17. The learning data 17 used for machine learning of the learning model 18 is composed of reference information 10-A and comparison information 10-B as input data, and diagnostic information 16 as output data.

[0105] The reference information 10-A constituting the input data of the learning data 17 includes a reference number of sheets to be processed WPH-A and reference apparatus information 11-A.

[0106] The reference processing number WPH-A is the number of wafers processed per unit time WPH when a reference processing operation corresponding to a processing operation is performed in a reference apparatus corresponding to the reference substrate processing apparatus 2. When the learning data acquisition unit 400 acquires the learning data 17 from the test information 31 or the simulation information 32, the first processing number WPH-1 per unit time corresponds to the reference processing number WPH-A.

[0107] The reference device information 11-A is device information 11 related to the reference device when the reference processing operation was executed. When the learning data acquisition unit 400 acquires the learning data 17 from the test information 31 or the simulation information 32, the first device information 11-1 corresponds to the reference device information 11-A. The reference device information 11-A includes at least one of the device setting information 12, the recipe information 13, the consumables information 14, and the event information 15, similar to the first device information 11-1.

[0108] The comparison information 10-B constituting the input data of the learning data 17 includes a comparison processing number WPH-B and comparison apparatus information 11-B.

[0109] The comparison processing number WPH-B is the number of wafers processed per unit time WPH when a comparison processing operation corresponding to the processing operation is performed in a comparison apparatus corresponding to the substrate processing apparatus 2 to be compared with the reference apparatus. When the learning data acquisition unit 400 acquires the learning data 17 from the test information 31 or the simulation information 32, the second processing number WPH-2 per unit time is the number of wafers processed per unit time WPH. This corresponds to several WPH-B.

[0110] The comparison device information 11-B is device information 11 related to the comparison device when the comparison process operation is executed. When the learning data acquisition unit 400 acquires the learning data 17 from the test information 31 or the simulation information 32, the second device information 11-2 corresponds to the comparison device information 11-B. The comparison device information 11-B includes at least one of the device setting information 12, the recipe information 13, the consumable information 14, and the event information 15, similar to the second device information 11-2.

[0111] The diagnostic information 16 constituting the output data of the learning data 17 includes at least one of the cause of a difference between the reference number of sheets processed WPH-A and the comparison number of sheets processed WPH-B and a measure to eliminate the difference. In other words, the diagnostic information 16 indicates the cause in the comparison device when the comparison number of sheets processed WPH-B is less or more than the reference number of sheets processed WPH-A, and the measure in the comparison device to make the comparison number of sheets processed WPH-B closer to the reference number of sheets processed WPH-A. When the learning data acquisition unit 400 acquires the learning data 17 from the test information 31 or the simulation information 32, the test diagnostic information and the simulation diagnostic information correspond to the diagnostic information 16.

[0112] In this case, the diagnostic information 16 may include at least one of a cause classification result in which causes are classified into a plurality of cause types and a countermeasure classification result in which countermeasures are classified into a plurality of countermeasure types, similar to the test diagnostic information and the simulation diagnostic information. The cause types include at least one of causes caused by the equipment setting information 12, causes caused by the recipe information 13, causes caused by consumables, and mechanical causes of the substrate processing apparatus 2. The countermeasure types include at least one of countermeasures related to the equipment setting information 12, countermeasures related to the recipe information 13, countermeasures related to consumables, and mechanical causes of the substrate processing apparatus 2.

[0113] The diagnostic information 16 may also include at least one of the cause items identified as the cause-related items by at least one of the device setting items, recipe setting items, consumable items, and mechanical adjustment items, and at least one of the countermeasure items identified as the countermeasure-related items by at least one of the device setting items, recipe setting items, consumable items, and mechanical adjustment items. In this case, the diagnostic information 16 may indicate a plurality of cause items and countermeasure items in order of the degree of relevance to the cause or countermeasure.

[0114] The learning model 18 employs, for example, a neural network structure, and includes an input layer 180, an intermediate layer 181, and an output layer 182. Synapses (not shown) that connect each neuron are laid between each layer, and each synapse is associated with a weight. A weight parameter group consisting of the weights of each synapse is adjusted by machine learning.

[0115] The input layer 180 has neurons in a number corresponding to the reference information 10-A and the comparison information 10-B as input data, and each parameter value included in the reference information 10-A and the comparison information 10-B is input to each neuron. The output layer 182 has neurons in a number corresponding to the diagnostic information 16 as output data, and the prediction result (inference result) of the diagnostic information 16 for the reference information 10-A and the comparison information 10-B is output as output data.

[0116] The number of learning models 18 stored in the trained model storage unit 43 is not limited to one, and multiple learning models 18 with different conditions, such as machine learning techniques, differences in the mechanisms of the substrate processing apparatus 2, types of data included in the reference information 10-A and the comparison information 10-B, types of data included in the diagnostic information 16, etc., may be stored. In this case, the learning data storage unit 42 stores data structures each corresponding to a multiple number of learning models 18 with different conditions. It is only necessary to store a plurality of types of learning data 17 that correspond to the plurality of types of learning data 17.

[0117] (Machine learning methods) FIG. 18 is a flowchart showing an example of a machine learning method performed by the machine learning device 4.

[0118] First, in step S100, the learning data acquisition unit 400 acquires a desired number of learning data 17 as a preparation for starting machine learning, and stores the acquired learning data 17 in the learning data storage unit 42. The number of learning data 17 to be prepared here may be set in consideration of the inference accuracy required for the learning model 18 to be finally obtained.

[0119] Next, in step S110, in order to start machine learning, the machine learning unit 401 prepares a pre-learning learning model 18. The pre-learning learning model 18 prepared here is configured with a neural network model, and the weights of each synapse are set to initial values.

[0120] Next, in step S120, the machine learning unit 401 acquires, for example, one set of learning data 17 at random from the multiple sets of learning data 17 stored in the learning data storage unit .

[0121] Next, in step S130, the machine learning unit 401 inputs the input data (reference information 10-A and comparison information 10-B) included in one set of learning data 17 to the input layer 180 of the prepared learning model 18 before learning (or during learning). As a result, output data (diagnostic information 16) is output as an inference result from the output layer 182 of the learning model 18, but the output data is generated by the learning model 18 before learning (or during learning). Therefore, in the state before learning (or during learning), the output data output as an inference result indicates information different from the correct label (diagnostic information 16) included in the learning data 17.

[0122] Next, in step S140, the machine learning unit 401 performs machine learning by comparing the correct label included in the set of learning data 17 acquired in step S120 with the output data output from the output layer 182 as an inference result in step S130 and performing a process of adjusting the weight of each synapse (backpropagation). In this way, the machine learning unit 401 causes the learning model 18 to learn the correlation between the input data and the output data.

[0123] Next, in step S150, the machine learning unit 401 determines whether a predetermined learning termination condition has been satisfied, for example, based on an evaluation value of an error function based on the correct label included in the learning data 17 and the output data output as the inference result, or the remaining number of unlearned learning data 17 stored in the learning data memory unit 42.

[0124] In step S150, if the machine learning unit 401 determines that the learning end condition is not satisfied and that machine learning is to be continued (No in step S150), the process returns to step S120, and performs the processes of steps S120 to S140 multiple times on the learning model 18 being trained, using untrained learning data 17. On the other hand, in step S150, if the machine learning unit 401 determines that the learning end condition is satisfied and that machine learning is to be terminated (Yes in step S150), the process proceeds to step S160.

[0125] Then, in step S160, the machine learning unit 401 stores the trained learning model 18 (adjusted weight parameter group) generated by adjusting the weights associated with each synapse in the trained model storage unit 43, and ends the series of machine learning methods shown in FIG. 18. In the machine learning method, step S100 is a learning data storage step, step S11 is a learning data storage step, and step S20 is a learning data storage step. Steps S10 to S150 correspond to the machine learning process, and step S160 corresponds to the learned model storage process.

[0126] As described above, according to the machine learning device 4 and machine learning method of this embodiment, a learning model 18 can be provided that can predict (infer) diagnostic information 16 including at least one of the cause of a difference between the reference processing number WPH-A and the comparative processing number WPH-B and measures to eliminate the difference, from reference information 10-A including a reference processing number WPH-A and reference device information 11-A in a reference device corresponding to the reference substrate processing device 2, and comparison information 10-B including a comparative processing number WPH-B and comparative device information 11-B in a comparative device corresponding to the substrate processing device 2 to be compared with the reference device.

[0127] (Information processing device 5A) Fig. 19 is a block diagram showing an example of an information processing device 5A according to the first embodiment. Fig. 20 is a functional explanatory diagram showing an example of the information processing device 5A according to the first embodiment. The information processing device 5A includes a control unit 50, a communication unit 51, and a storage unit 52.

[0128] The control unit 50 functions as a diagnostic condition receiving unit 500, a reference information acquiring unit 501, a comparison information acquiring unit 502, a diagnostic processing unit 503A, and an output processing unit 504. The communication unit 51 is connected to external devices (e.g., the substrate processing apparatus 2, the database device 3, the machine learning device 4, and the user terminal device 6) via the network 7, and functions as a communication interface for transmitting and receiving various data. The storage unit 52 stores various programs (such as an operating system and an information processing program) and data (such as the learning model 18) used in the operation of the information processing apparatus 5A.

[0129] The diagnostic condition receiving unit 500 receives diagnostic conditions for diagnosing the state of the substrate processing apparatus 2. The diagnostic conditions include, for example, a reference apparatus designation condition and a comparison apparatus designation condition. For example, the diagnostic condition receiving unit 500 displays a display screen for inputting diagnostic conditions on the user terminal device 6, and receives the diagnostic conditions in response to an input operation by an operator on the display screen. The diagnostic condition receiving unit 500 may automatically receive pre-set diagnostic conditions for each predetermined time period or each number of processed wafers.

[0130] The reference apparatus designation conditions specify a reference apparatus corresponding to the reference substrate processing apparatus 2 and a reference processing operation performed in the reference apparatus. The reference apparatus designation conditions are designated by, for example, (A1) a combination of an apparatus ID and a date and time, (A2) a combination of an apparatus ID and a wafer ID, (A3) a test ID, (A4) a simulation ID, etc.

[0131] The comparison apparatus designation condition specifies a comparison apparatus corresponding to the substrate processing apparatus 2 to be compared with the reference apparatus, and a comparison processing operation executed in the comparison apparatus. The comparison apparatus designation condition is designated by, for example, (B1) a combination of an apparatus ID and date and time, (B2) a combination of an apparatus ID and a wafer ID, (B3) a test ID, (B4) a simulation ID, etc.

[0132] Therefore, various diagnoses can be realized by the reference device designation conditions and the comparison device designation conditions. For example, in a shipping inspection at an assembly factory of the substrate processing apparatus 2, or in an inspection on a production line, a substrate processing apparatus 2 (or a plurality of substrate processing apparatuses 2) that meets the design specifications of the substrate processing apparatus 2 is designated as the reference device in the above (A3) or (A4), and the substrate processing apparatus 2 to be inspected is designated as the comparison device in the above (B1) or (B2), so that a shipping inspection or an inspection can be performed according to the occurrence of an operational error. In this case, a substrate processing apparatus 2 (or a plurality of substrate processing apparatuses 2) that has passed the inspection or a substrate processing apparatus 2 that meets the design specifications of the substrate processing apparatus 2 may be designated as the reference device in the above (A1) or (A2). In addition, when checking the change over time of the substrate processing apparatus 2, In this case, for example, a substrate processing apparatus 2 (or a plurality of substrate processing apparatuses 2) from a past time point is designated as a reference apparatus in the above (A1) or (A2), and a substrate processing apparatus 2 at the present time is designated as a comparison apparatus in the above (A1) or (A2), so that a change over time can be confirmed. Furthermore, when evaluating the accuracy of a test apparatus or a simulation apparatus, for example, a substrate processing apparatus 2 (or a plurality of substrate processing apparatuses 2) that satisfies the design specifications of the substrate processing apparatus 2 is designated as a reference apparatus in the above (A1) or (A2), and a test apparatus or a simulation apparatus to be evaluated is designated as a comparison apparatus in the above (B3) or (B4), so that the accuracy of the test apparatus or the simulation apparatus can be evaluated. When a plurality of substrate processing apparatuses 2 are designated as reference apparatuses, the reference information 10-A may be obtained by performing calculations such as an average value, a maximum value, and a minimum value for the plurality of substrate processing apparatuses 2.

[0133] The reference information acquiring unit 501 acquires, as the reference information 10-A, a reference number of sheets WPH-A processed when a reference processing operation is performed in the reference device, and reference device information 11-A related to the reference device when the reference processing operation is performed. That is, the reference information 10-A includes the reference number of sheets WPH-A processed and the reference device information 11-A. The reference information acquiring unit 501 acquires the reference information 10-A by, for example, referring to the production history information 30, the test information 31, or the simulation information 32 of the database device 3 based on the reference device designation condition among the diagnostic conditions accepted by the diagnostic condition accepting unit 500.

[0134] The comparison information acquisition unit 502 acquires, as the comparison information 10-B, the comparison processing number WPH-B when the comparison processing operation is executed in the comparison device, and the comparison device information 11-B related to the comparison device when the comparison processing operation is executed. That is, the comparison information 10-B includes the comparison processing number WPH-B and the comparison device information 11-B. The comparison information acquisition unit 502 acquires the comparison information 10-B by, for example, referring to the production history information 30, the test information 31, or the simulation information 32 of the database device 3 based on the comparison device designation condition among the diagnostic conditions accepted by the diagnostic condition acceptance unit 500.

[0135] The diagnostic processing unit 503A generates diagnostic information 16 based on the reference information 10-A acquired by the reference information acquisition unit 501 and the comparison information 10-B acquired by the comparison information acquisition unit 502, which includes at least one of the cause of a difference between the reference processing count WPH-A and the comparison processing count WPH-B and measures to resolve the difference.

[0136] In this embodiment, the diagnostic processing unit 503A generates diagnostic information 16 for the reference information 10-A and the comparison information 10-B by inputting the reference information 10-A acquired by the reference information acquisition unit 501 and the comparison information 10-B acquired by the comparison information acquisition unit 502 to the learning model 18. The diagnostic information 16 may include at least one of a cause classification result and a countermeasure classification result, or may include at least one of a cause item and a countermeasure item. In this case, the diagnostic information 16 may indicate multiple cause items and countermeasure items in order of the degree of relevance to the cause or countermeasure.

[0137] The storage unit 52 stores a trained learning model 18 used by the diagnostic processing unit 503A. The number of learning models 18 stored in the storage unit 52 is not limited to one, and a plurality of trained models with different conditions, such as machine learning techniques, differences in the mechanisms of the substrate processing apparatus 2, types of data included in the reference information 10-A and the comparison information 10-B, and types of data included in the diagnostic information 16, may be stored and used selectively or in parallel. The storage unit 52 may be substituted by a storage unit of an external computer (e.g., a server-type computer or a cloud-type computer), and in that case, the diagnostic processing unit 503A may access the external computer.

[0138] The output processing unit 504 performs an output process for outputting the diagnostic information 16 generated by the diagnostic processing unit 503A. For example, the output processing unit 504 transmits the diagnostic information 16 to the user terminal device 6, so that the user terminal device 6 displays a display screen based on the diagnostic information 16. The output processing unit 504 may store the diagnostic information 16 in the storage unit 52.

[0139] (Information processing method) 21 is a flowchart showing an example of an information processing method by the information processing device 5A according to the first embodiment. In the following, an operation example in which an operator operates the user terminal device 6 to diagnose the state of a specific substrate processing device 2 will be described.

[0140] First, in step S200, when the operator performs an input operation to input diagnostic conditions to the user terminal device 6, the user terminal device 6 transmits the diagnostic conditions to the information processing device 5A.

[0141] Next, in step S210, the diagnostic condition receiving section 500 of the information processing device 5A receives the diagnostic conditions transmitted in step S200.

[0142] Next, in step S220, the reference information acquisition unit 501 acquires reference information 10-A including a reference processing quantity WPH-A and reference device information 11-A by referring to the production history information 30, the test information 31, or the simulation information 32 of the database device 3 based on the reference device designation conditions among the diagnostic conditions received in step S210.

[0143] Next, in step S230, the comparison information acquisition unit 502 acquires comparison information 10-B including the comparison processing number WPH-B and comparison device information 11-B by referring to the production history information 30, test information 31, or simulation information 32 of the database device 3 based on the comparison device designation conditions among the diagnostic conditions received in step S210.

[0144] Next, in step S240, the diagnostic processing unit 503A inputs the reference information 10-A acquired in step S220 and the comparison information 10-B acquired in step S230 as input data into the learning model 18, thereby generating diagnostic information 16 for the reference information 10-A and the comparison information 10-B as output data, and diagnosing the state of the comparison device relative to the reference device.

[0145] Next, in step S250, the output processing unit 504 transmits the diagnostic information 16 generated in step S240 to the user terminal device 6 as an output process for outputting the diagnostic information 16. Note that the destination of the diagnostic information 16 may be the database device 3 in addition to or instead of the user terminal device 6.

[0146] Then, in step S260, when the user terminal device 6 receives the diagnostic information 16 transmitted in step S250 as a response to the transmission process in step S200, the user terminal device 6 displays a display screen based on the diagnostic information 16, allowing the operator to check the diagnosis result of the comparison device against the reference device. In the above information processing method, step S210 corresponds to a diagnostic condition receiving step, S220 corresponds to a reference information obtaining step, S230 corresponds to a comparison information obtaining step, step S240 corresponds to a diagnostic processing step, and step S250 corresponds to an output processing step.

[0147] As described above, according to the information processing apparatus 5A and the information processing method of this embodiment, reference information 10-A including the reference number of processed substrates WPH-A and the reference apparatus information 11-A in the reference apparatus corresponding to the substrate processing apparatus 2 serving as the reference, and comparison information including the comparative number of processed substrates WPH-B and the comparative apparatus information 11-B in the comparative apparatus corresponding to the substrate processing apparatus 2 to be compared with the reference apparatus are provided. By inputting the reference information 10-A and the comparison information 10-B into the learning model 18, diagnosis information 16 for the reference information 10-A and the comparison information 10-B is generated, so that the state of the substrate processing apparatus 2 can be diagnosed quickly and accurately.

[0148] Second Embodiment 22 is a block diagram showing an example of an information processing device 5B according to the second embodiment. The information processing device 5B according to the second embodiment differs from the information processing device 5A according to the first embodiment in that a diagnostic processing unit 503B generates diagnostic information 16 using a rule model 19. Other configurations and operations of the information processing device 5B are similar to those of the first embodiment, so the same reference numerals are used and detailed descriptions are omitted. Note that in the second embodiment, at least one of the database device 3 and the machine learning device 4 may be omitted.

[0149] The diagnostic processing unit 503B generates diagnostic information 16 for the reference information 10-A and the comparison information 10-B from the reference information 10-A acquired by the reference information acquisition unit 501 and the comparison information 10-B acquired by the comparison information acquisition unit 502, based on the rule model 19 stored in the storage unit 52. Note that the storage unit 52 may be substituted by a storage unit of an external computer, and in that case, the diagnostic processing unit 503B may access the external computer.

[0150] Specifically, the diagnostic processing unit 503B acquires at least one of the following: a difference value for each device setting item when the device setting information 12 included in the reference device information 11-A is compared with the device setting information 12 included in the comparison device information 11-B in units of setting values ​​set for each device setting item; a difference value for each recipe setting item when the recipe information 13 included in the reference device information 11-A is compared with the recipe information 13 included in the comparison device information 11-B in units of setting values ​​set for each recipe setting item; a difference value for each consumable item when the consumable information 14 included in the reference device information 11-A is compared with the consumable information 14 included in the comparison device information 11-B in units of consumable items; and a difference value for each event item when the event information 15 included in the reference device information 11-A is compared with the event information 15 included in the comparison device information 11-B in units of event items.

[0151] Then, the diagnostic processing unit 503B generates diagnostic information 16 for the reference information 10-A and the comparison information 11B based on at least one of the difference values ​​for each device setting item, the difference values ​​for each recipe setting item, the difference values ​​for each consumable item, and the difference values ​​for each event item.

[0152] The rule model 19 stores conditional expressions and logical expressions for branching and determining causes and measures according to, for example, the magnitude relationship between the difference values ​​for each device setting item, the difference values ​​for each recipe setting item, the difference values ​​for each consumable item, and the difference values ​​for each event item. Therefore, the diagnostic processing unit 503B generates diagnostic information 16 by applying the difference values ​​for each device setting item, the difference values ​​for each recipe setting item, and the difference values ​​for each consumable item acquired from the reference device information 11-A and the comparison device information 11-B to the conditional expressions and logical expressions of the rule model 19.

[0153] 23 is a flowchart showing an example of an information processing method by the information processing device 5B according to the second embodiment. The information processing method according to the second embodiment differs from the information processing device 5A according to the first embodiment in that in step S241 (diagnosis processing step), the diagnosis processing unit 503B generates diagnosis information 16 from the reference information 10-A acquired in step S220 and the comparison information 10-B acquired in step S230 based on the rule model 19. Since the rest are the same as those in the first embodiment, the same reference numerals are used and detailed description is omitted.

[0154] As described above, according to the information processing device 5B and the information processing method according to the present embodiment, the reference Diagnostic information 16 for the reference information 10-A and comparison information 10-B is generated from reference information 10-A including a reference number of processed wafers WPH-A and reference apparatus information 11-A in a reference apparatus corresponding to the substrate processing apparatus 2 that is to be compared with the reference apparatus, and comparison information 10-B including a comparative number of processed wafers WPH-B and comparison apparatus information 11-B in a comparison apparatus corresponding to the substrate processing apparatus 2 that is to be compared with the reference apparatus, so that the condition of the substrate processing apparatus 2 can be diagnosed quickly and accurately.

[0155] (Other embodiments) The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present invention, all of which are included in the technical concept of the present invention.

[0156] In the above embodiment, the database device 3, the machine learning device 4, the information processing devices 5A and 5B, and the user terminal device 6 are described as being configured as separate devices, but the four devices may be configured as a single device, or any two or three of the four devices may be configured as a single device. In addition, at least one of the machine learning device 4 and the information processing devices 5A and 5B may be incorporated into the control unit 25 of the substrate processing device 2 or the user terminal device 6. For example, the learning model 18 or the rule model 19 may be stored in the storage unit 62 of the user terminal device 6, and the control unit 60 of the user terminal device 6 may function as the diagnostic condition receiving unit 500, the reference information acquiring unit 501, the comparison information acquiring unit 502, and the diagnostic processing units 503A and 503B.

[0157] In the above embodiment, the substrate processing apparatus 2 has been described as performing a chemical mechanical polishing process as a polishing process, but the substrate processing apparatus 2 may perform a physical mechanical polishing process instead of a chemical mechanical polishing process. Also, the substrate processing apparatus 2 has been described as performing a polishing process and a finishing process of the wafer W as a substrate processing, but the substrate processing apparatus 2 may perform either the polishing process or the finishing process, or may perform another substrate processing instead of or in addition to the polishing process and the finishing process.

[0158] In the above embodiment, the substrate processing apparatus 2 includes each substrate processing unit (polishing unit, finishing unit) and each transport processing unit as shown in FIG. 2. In contrast, the number, arrangement, upstream-downstream relationship, parallel relationship, and serial relationship of each substrate processing unit and each transport processing unit as the configuration of the substrate processing apparatus 2 are not limited to the example of FIG. 2, and may be changed as appropriate. For example, the number of polishing units may be one or more, and the number of finishing units may be one or more. In addition, as the number of transport processing units, the number of supply and discharge robots may be one or more, the number of first to third transport robots may be one or more, and the number of transfer robots may be one or more. In addition, the positions for transferring the wafer W between each substrate processing unit and each transport processing unit, the positions for temporarily waiting the wafer W, etc. may be changed as appropriate, and the number of them may be added as appropriate. In such a case, the data configuration of the input data and the output data in the learning data 17 and the learning model 18 may be changed according to the configuration of each processing unit.

[0159] In the above embodiment, a case has been described in which a neural network is used as a learning model for implementing machine learning by the machine learning unit 401, but other machine learning models may be used. Examples of other machine learning models include tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, recurrent neural networks, convolutional neural networks, and neural network types such as LSTM (including deep learning). (including hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, k-means, etc.) Examples of the method include multivariate analysis such as filtering, principal component analysis, factor analysis, logistic regression, and support vector machine. Furthermore, the machine learning algorithm used by the machine learning unit 401 may employ reinforcement learning instead of supervised learning.

[0160] (Machine learning programs and information processing programs) The present invention can also be provided in the form of a program (machine learning program) that causes the computer 900 to function as each unit included in the machine learning device 4, or a program (machine learning program) that causes the computer 900 to execute each step included in the machine learning method. Moreover, the present invention can also be provided in the form of a program (information processing program) that causes the computer 900 to function as each unit included in the information processing devices 5A and 5B, or a program (information processing program) that causes the computer 900 to execute each step included in the information processing method according to the above embodiment.

[0161] (Inference device, inference method, and inference program) The present invention can be provided not only in the form of the information processing device 5A (information processing method or information processing program) according to the above embodiment, but also in the form of an inference device (inference method or inference program) used to infer diagnostic information. In this case, the inference device (inference method or inference program) can include a memory and a processor, and the processor executes a series of processes. The series of processes includes a reference information acquisition process (reference information acquisition step) for acquiring a reference processing number and reference device information as reference information 10-A, a comparison information acquisition process (comparison information acquisition step) for acquiring a comparison processing number and comparison device information as comparison information 10-B, and an inference process (inference step) for inferring diagnostic information 16 based on the reference information 10-A and the comparison information 10-B when the reference information acquisition process acquires the reference information 10-A and the comparison information 10-B.

[0162] By providing it in the form of an inference device (inference method or inference program), it can be easily applied to various devices compared to the case where a safety support device is implemented. It can be naturally understood by those skilled in the art that when the inference device (inference method or inference program) infers diagnostic information, the inference method implemented by the diagnostic information generation unit may be applied using a trained learning model generated by the machine learning device and machine learning method according to the above embodiment. [Explanation of symbols]

[0163] 1... substrate processing system, 2... substrate processing apparatus, 3... database device, 4...machine learning device, 5A, 5B...information processing device, 6...user terminal device, 7…Network, 10-A...Standard information, 10-B...Comparison information, 11...Device information, 11-1: First device information, 11-2: Second device information 11-A...Reference device information, 11-B...Comparison device information, 12 ... device setting information, 13 ... recipe information, 14 ... consumables information, 15 ... event information, 16...Diagnostic information, 17...Learning data, 18...Learning model, 19...Rule model 20...housing, 21...load / unload unit, 22...polishing unit, 23: substrate transport unit, 24: finishing unit, 25: control unit, 30...Production history information, 31...Test information, 32...Simulation information, 40: control unit, 41: communication unit, 42: learning data storage unit, 43: learning model storage unit, 44...input section, 45...output section, 50: control unit, 51: communication unit, 52: storage unit, 60: control unit, 62: storage unit, 400...learning data acquisition unit, 401...machine learning unit, 500: diagnostic condition receiving unit, 501: reference information acquiring unit, 502: comparison information acquiring unit, 503...diagnosis processing unit, 503A, 503B...diagnosis processing units WPH: number of sheets processed per unit time WPH-1: first number of sheets processed per unit time; WPH-2: second number of sheets processed per unit time; WPH-A: Reference processing volume, WPH-B: Comparison processing volume

Claims

1. 1. An information processing apparatus for diagnosing a state of a substrate processing apparatus including a substrate processing unit that performs substrate processing on a substrate, and a transport processing unit that performs a transport processing for transporting a substrate before and after the substrate processing, a reference information acquiring unit that acquires, as reference information, a reference processed number indicating the number of substrates processed per unit time when a reference processing operation in which the substrate processing and the transport processing are repeated is performed in a reference apparatus corresponding to the reference substrate processing apparatus, and reference apparatus information regarding the reference apparatus when the reference processing operation is performed; a comparison information acquisition unit that acquires, as comparison information, a comparison processing number indicating the number of substrates processed per unit time when a comparison processing operation is performed in a comparison apparatus corresponding to the substrate processing apparatus to be compared with the reference apparatus, in which the substrate processing and the transport processing are repeated, and comparison apparatus information regarding the comparison apparatus when the comparison processing operation is performed; a diagnostic processing unit that generates diagnostic information including at least one of a cause of a difference between the reference number of sheets processed and the comparative number of sheets processed based on the reference information acquired by the reference information acquisition unit and the comparative information acquired by the comparative information acquisition unit and a measure to eliminate the difference. Information processing device.

2. The reference device information is device setting information that defines the operation content of the reference device when the reference processing operation is executed by setting values ​​for each of a plurality of device setting items; recipe information that defines the processing content of the substrate processing when the reference processing operation is executed by setting a setting value for each of a plurality of recipe setting items; Consumable item information that defines, for each of the consumable items, a state of a consumable item used in the reference device when the reference processing operation is executed; and the event information includes at least one event item that defines the content of an event that occurred in the reference device when the reference processing operation was executed, for each event item; The comparison device information is device setting information that defines the operation content of the comparison device when the comparison processing operation is executed by setting values ​​for each of a plurality of device setting items; recipe information that defines the processing content of the substrate processing when the comparison processing operation is performed by setting a setting value for each of a plurality of recipe setting items; Consumable item information that defines, for each of the consumable items, a consumption state of the consumable items used in the comparison device when the comparison processing operation is performed; and the event information includes at least one event item that defines the content of an event that occurred in the reference device when the reference processing operation was executed, for each event item; The information processing device according to claim 1 .

3. The diagnostic information includes: A cause classification result in which the cause is classified into a plurality of cause types; and At least one countermeasure classification result in which the countermeasures are classified into a plurality of countermeasure types is included; The cause type is: A cause caused by the device setting information; A cause caused by the recipe information; Causes attributable to the consumables; and at least one of the mechanical causes of the substrate processing apparatus; The countermeasure type is: Measures regarding the device setting information; Measures regarding the recipe information Measures regarding said consumables, and At least one of the mechanical measures of the substrate processing apparatus, The information processing device according to claim 2 .

4. The diagnostic information includes: A cause item identified as at least one of the device setting items, the recipe setting items, the consumable items, and the mechanical adjustment items that can be mechanically adjusted in the substrate processing apparatus as the items related to the cause. The item related to the measure includes at least one of the device setting item, the recipe setting item, the consumable item, and the mechanical adjustment item, and the measure item identified in the at least one of the device setting item, the recipe setting item, the consumable item, and the mechanical adjustment item. The information processing device according to claim 3 .

5. The diagnostic processing unit: a difference value for each device setting item when the device setting information included in the reference device information and the device setting information included in the comparison device information are compared in units of setting values ​​set for each device setting item; a difference value for each recipe setting item when the recipe information included in the reference apparatus information and the recipe information included in the comparison apparatus information are compared in units of setting values ​​set for each recipe setting item; a difference value for each consumable item when the consumable information included in the reference device information and the consumable information included in the comparison device information are compared for each consumable item; and acquiring at least one difference value for each event item when comparing the event information included in the reference device information with the event information included in the comparison device information for each event item; generating the diagnosis information for the reference information and the comparison information based on at least one of a difference value for each device setting item, a difference value for each recipe setting item, a difference value for each consumable item, and a difference value for each event item; The information processing device according to claim 2 .

6. The diagnostic processing unit: The reference information acquired by the reference information acquisition unit and the comparison information acquired by the comparison information acquisition unit are input to a learning model that has been trained by machine learning to learn correlations between the reference information and the comparison information, and the diagnosis information, thereby generating the diagnosis information for the reference information and the comparison information. The information processing device according to claim 1 .

7. A memory and a processor, 1. An inference device for diagnosing a state of a substrate processing apparatus including a substrate processing unit that performs substrate processing on a substrate, and a transport processing unit that performs transport processing to transport the substrate before and after the substrate processing, a reference information acquisition process for acquiring, as reference information, a reference processed number indicating the number of substrates processed per unit time when a reference processing operation in which the substrate processing and the transport processing are repeated is performed in a reference apparatus corresponding to the reference substrate processing apparatus, and reference apparatus information regarding the reference apparatus when the reference processing operation is performed; a comparison information acquisition process for acquiring, as comparison information, a comparison processing number indicating the number of substrates processed per unit time when a comparison processing operation is performed in a comparison apparatus corresponding to the substrate processing apparatus to be compared with the reference apparatus, in which the substrate processing and the transport processing are repeated, and comparison apparatus information regarding the comparison apparatus when the comparison processing operation is performed; The reference information is acquired in the reference information acquisition process, and the comparison information is acquired in the comparison information acquisition process. when the information is acquired, an inference process is executed to infer diagnostic information including at least one of a cause of a difference occurring between the reference processed number and the comparative processed number and a measure for eliminating the difference, based on the reference information and the comparative information. Reasoning device.

8. 1. A machine learning device that generates a learning model for diagnosing a state of a substrate processing device including a substrate processing unit that performs substrate processing on a substrate, and a transport processing unit that performs a transport processing for transporting a substrate before and after the substrate processing, a learning data storage unit that stores a plurality of sets of learning data each composed of input data and output data; a machine learning unit that inputs a plurality of sets of the learning data to the learning model, thereby causing the learning model to learn a correlation between the input data and the output data; A trained model storage unit that stores the trained model in which the correlation is trained by the machine learning unit, The input data is Reference information including a reference processing number indicating the number of substrates processed per unit time when a reference processing operation in which the substrate processing and the transport processing are repeated is performed in a reference apparatus corresponding to the substrate processing apparatus serving as a reference, and reference apparatus information regarding the reference apparatus when the reference processing operation is performed; and the comparison information including a comparison processing number indicating the number of substrates processed per unit time when a comparison processing operation is performed in a comparison apparatus corresponding to the substrate processing apparatus to be compared with the reference apparatus, the comparison processing operation repeating the substrate processing and the transport processing, and comparison apparatus information regarding the comparison apparatus when the comparison processing operation is performed; The output data is the diagnostic information including at least one of a cause of a difference between the reference processing number and the comparative processing number and a measure to eliminate the difference; Machine learning device.

9. 1. An information processing method for diagnosing a state of a substrate processing apparatus including a substrate processing unit that performs substrate processing on a substrate, and a transport processing unit that performs transport processing to transport a substrate before and after the substrate processing, comprising: a reference information acquiring step of acquiring, as reference information, a reference processed number indicating the number of substrates processed per unit time when a reference processing operation in which the substrate processing and the transport processing are repeated is performed in a reference apparatus corresponding to the substrate processing apparatus serving as a reference, and reference apparatus information regarding the reference apparatus when the reference processing operation is performed; a comparison information acquiring step of acquiring, as comparison information, a comparison processing number indicating the number of substrates processed per unit time when a comparison processing operation is performed in a comparison apparatus corresponding to the substrate processing apparatus to be compared with the reference apparatus, in which the substrate processing and the transport processing are repeated, and comparison apparatus information regarding the comparison apparatus when the comparison processing operation is performed; a diagnostic processing step of generating diagnostic information including at least one of a cause of a difference between the reference number of sheets processed and the comparative number of sheets processed based on the reference information acquired by the reference information acquiring step and the comparative information acquired by the comparative information acquiring step and a measure to eliminate the difference, Information processing methods.

10. A memory and a processor, 1. An inference method executed by an inference device for diagnosing a state of a substrate processing apparatus including a substrate processing unit that performs substrate processing on a substrate, and a transport processing unit that performs transport processing for transporting the substrate before and after the substrate processing, comprising: The substrate processing and the transfer processing are performed in a reference apparatus corresponding to the reference substrate processing apparatus. a reference information acquiring step of acquiring, as reference information, a reference processing number indicating the number of substrates processed per unit time when a reference processing operation in which a process is repeated is performed, and reference apparatus information regarding the reference apparatus when the reference processing operation is performed; a comparison information acquiring step of acquiring, as comparison information, a comparison processing number indicating the number of substrates processed per unit time when a comparison processing operation is performed in a comparison apparatus corresponding to the substrate processing apparatus to be compared with the reference apparatus, in which the substrate processing and the transport processing are repeated, and comparison apparatus information regarding the comparison apparatus when the comparison processing operation is performed; and when the reference information is acquired in the reference information acquisition step and the comparison information is acquired in the comparison information acquisition step, an inference step is executed of inferring diagnostic information including at least one of a cause of a difference occurring between the reference number of sheets processed and the comparison number of sheets processed and a measure for eliminating the difference, based on the reference information and the comparison information. Reasoning method.

11. 1. A machine learning method for generating a learning model for diagnosing a state of a substrate processing apparatus including a substrate processing unit that performs substrate processing on a substrate, and a transport processing unit that performs a transport processing for transporting a substrate before and after the substrate processing, comprising: a learning data storage step of storing a plurality of sets of learning data, each set being composed of input data and output data, in a learning data storage unit; a machine learning process of inputting a plurality of sets of the learning data into the learning model to allow the learning model to learn a correlation between the input data and the output data; A trained model storage step of storing the trained model in a trained model storage unit, the trained model having the correlation trained by the machine learning step; The input data is Reference information including a reference processing number indicating the number of substrates processed per unit time when a reference processing operation in which the substrate processing and the transport processing are repeated is performed in a reference apparatus corresponding to the substrate processing apparatus serving as a reference, and reference apparatus information regarding the reference apparatus when the reference processing operation is performed; and the comparison information including a comparison processing number indicating the number of substrates processed per unit time when a comparison processing operation is performed in a comparison apparatus corresponding to the substrate processing apparatus to be compared with the reference apparatus, the comparison processing operation repeating the substrate processing and the transport processing, and comparison apparatus information regarding the comparison apparatus when the comparison processing operation is performed; The output data is the diagnostic information including at least one of a cause of a difference between the reference processing number and the comparative processing number and a measure to eliminate the difference; Machine learning methods.

Citation Information

Patent Citations

  • Management system of semiconductor manufacturing apparatus

    JP2000269108A

  • Substrate processing apparatus and quality assurance method therefor

    JP2017112212A

  • Substrate processing device, analysis method, display device and program

    JP2022151509A

  • Information processing device, inference device, machine learning device, information processing method, inference method, and machine learning method

    JP2023055161A

  • Polishing device

    JP2007301690A