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

Abstract

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, capable of properly predicting a cleaning tool state according to an operating state of a substrate processing device.SOLUTION: In a substrate processing system, an information processing device 5 comprises: an information acquisition unit 500; and a state prediction unit 501. A substrate processing device comprises: a substrate holding unit for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; a substrate cleaning unit for rotatably supporting a cleaning tool, bringing the cleaning tool into contact with the substrate to clean the substrate; and a cleaning tool cleaning unit for cleaning the cleaning tool with a cleaning tool cleaning fluid. The information acquisition unit acquires operating state information including substrate holding unit state information, cleaning fluid supply unit state information, substrate cleaning unit state information, and cleaning tool cleaning unit state information as operating states of when the substrate processing device is operated.SELECTED DRAWING: Figure 15

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 Regarding machine learning methods. [Background technology]

[0002] Chemical machinery is one of the substrate processing equipment that performs various processes on substrates such as semiconductor wafers. Polishing (CMP: Chemical Mechanical Polishing) process In the substrate processing apparatus, for example, a polishing apparatus having a polishing pad is used. While rotating the table, a polishing liquid (slurry) is supplied to the polishing pad from the liquid supply nozzle. In this state, the substrate is pressed against the polishing pad by a polishing head called a top ring. The substrate is chemically and mechanically polished. After polishing, the polishing debris adhering to the substrate is removed. In order to remove foreign matter, a cleaning tool is brought into contact with the polished substrate while supplying a substrate cleaning fluid. The series of processes is completed by cleaning the substrate with a scrub and then drying it, and the next substrate is processed. To carry out.

[0003] Repeating the above process will gradually cause wear and contamination of the cleaning equipment. Therefore, the cleaning tool needs to be replaced, but the replacement period depends on, for example, the cumulative number of uses of the cleaning tool. The number of batteries and the cumulative usage time were used as the basis for management (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 10-242092 Summary of the Invention [Problem to be solved by the invention]

[0005] In Patent Document 1, the cumulative number of uses and cumulative usage time of the cleaning tool are recorded by a counter or a timing unit. It is calculated by accumulating the number of times and time that the cleaning tool is in contact with the substrate. The state of the tool varies depending on the operating state of the substrate processing apparatus when the cleaning tool is in contact with the substrate. In addition, when the cleaning tool is not in contact with the substrate, e.g., when the cleaning tool is immersed in cleaning tool cleaning fluid, The temperature also fluctuates depending on the operating state of the substrate processing apparatus when cleaning (self-cleaning). Therefore, it is not possible to grasp the condition of cleaning tools in detail by managing only the cumulative number of uses and cumulative usage time. cannot be done.

[0006] On the other hand, in order to clean the substrate using the cleaning unit, each unit (for example, a substrate holder for holding the plate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; a substrate cleaning unit that cleans a substrate by contacting the substrate with a cleaning tool cleaning fluid; The operating condition of the cleaning tool cleaning unit is a factor that affects the condition of the cleaning tool. It is complex and interacts with each other, so it is important to understand how each operating state affects the condition of the cleaning tool. It is difficult to accurately analyze how this will affect the future.

[0007] In view of the above-mentioned problems, the present invention provides a method for appropriately controlling the state of a cleaning tool according to the operating state of a substrate processing apparatus. Information processing device, inference device, machine learning device, information processing method, and inference that enable prediction The present invention aims to provide a method for machine learning. [Means for solving the problem]

[0008] In order to achieve the above object, an information processing device according to one aspect of the present invention comprises: a substrate holder for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; and rotatably supporting the cleaning tool and bringing the cleaning tool into contact with the substrate to clean the substrate. A substrate cleaning unit and a cleaning tool cleaning unit for cleaning the cleaning tool with a cleaning tool cleaning fluid. A substrate holding unit state indicating the state of the substrate holding unit as the operating state when the processing apparatus is operated. cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit; and cleaning tool cleaning unit status information indicating the state of the cleaning tool cleaning unit. an information acquisition unit that acquires operation status information including the The operating state information and the operating state indicated by the operating state information are used to determine whether the substrate processing apparatus is operating in the operating state indicated by the operating state information. The correlation between the cleaning tool status information indicating the status of the cleaning tool when it was made and the cleaning tool status information is learned by machine learning. inputting the operation state information acquired by the information acquisition unit into the learning model generated by the learning unit; and a state prediction unit that predicts the cleaning tool state information in response to the operating state information. [Effects of the Invention]

[0009] According to an information processing apparatus of one aspect of the present invention, the substrate holder status information, the cleaning fluid supply unit status information, and the like are stored in the information processing apparatus. The operating status information including the state information, the substrate cleaning unit state information, and the cleaning tool cleaning unit state information is used in the learning model. By inputting the information into the database, the cleaning tool status information for the relevant operating status information is predicted. The state of the cleaning tool can be appropriately predicted depending on the operating state of the substrate processing apparatus.

[0010] Problems, configurations, and effects other than those described above will become apparent from the detailed description of the invention that follows. can be. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is an overall configuration diagram showing an example of a substrate processing system 1. FIG. [Figure 2] FIG. 2 is a plan view showing an example of a substrate processing apparatus 2. [Figure 3] FIG. 2 is a perspective view showing an example of first to fourth polishing sections 22A to 22D. [Figure 4] FIG. 2 is a perspective view showing an example of first and second roll sponge cleaning units 24A and 24B. [Figure 5] 10 is a perspective view showing an example of first and second pen sponge cleaning units 24C and 24D. FIG. [Figure 6] FIG. 2 is a perspective view showing an example of first and second drying sections 24E and 24F. [Figure 7] FIG. 2 is a block diagram showing an example of a substrate processing apparatus 2. [Figure 8] FIG. 9 is a hardware configuration diagram showing an example of a computer 900. [Figure 9] 3 is a data configuration diagram showing an example of production history information 30 managed by the database device 3. FIG. [Figure 10] 3 is a data configuration diagram showing an example of cleaning test information 31 managed by the database device 3. FIG. [Figure 11] FIG. 2 is a block diagram showing an example of a machine learning device 4 according to the first embodiment. [Figure 12] 1 is a diagram showing an example of a first learning model 10A and first learning data 11A. FIG. [Figure 13] 10 is a flowchart showing an example of a machine learning method performed by the machine learning device 4. [Figure 14] 1 is a block diagram showing an example of an information processing device 5 according to a first embodiment. [Figure 15] FIG. 2 is a functional explanatory diagram illustrating an example of an information processing device 5 according to the first embodiment. [Figure 16] 10 is a flowchart showing an example of an information processing method by the information processing device 5. [Figure 17] FIG. 10 is a block diagram showing an example of a machine learning device 4a according to a second embodiment. [Figure 18]10A and 10B are diagrams showing examples of a second learning model 10B and second learning data 11B. [Figure 19] FIG. 10 is a block diagram showing an example of an information processing device 5a that functions as an information processing device 5a according to a second embodiment. [Figure 20] FIG. 10 is a functional explanatory diagram showing an example of an information processing device 5a according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment for carrying out the present invention will be described with reference to the drawings. The scope necessary for the explanation to achieve the object of the present invention is shown schematically, and the relevant part of the present invention is explained. The scope necessary for clarity will be mainly explained, and the parts that will be omitted will be explained based on the publicly known technology. It shall be.

[0013] (First embodiment) 1 is a diagram showing an overall configuration of an example of a substrate processing system 1. The processing system 1 includes a polishing pad that presses a substrate (hereinafter referred to as a "wafer") W such as a semiconductor wafer against the polishing pad. A chemical mechanical polishing process (hereinafter referred to as "polishing process") is performed to polish the surface of the wafer W to a flat surface by attaching a solder paste to the surface. The surface of the wafer W is cleaned by bringing the polished wafer W into contact with the cleaning tool. It functions as a system for managing a series of substrate processes including cleaning processes.

[0014] The substrate processing system 1 mainly comprises a substrate processing apparatus 2 and a database device. The system includes a machine learning device 3, a machine learning device 4, an information processing device 5, and a user terminal device 6. 6 is, for example, a general-purpose or dedicated computer (see FIG. 8 described later), It is connected to a wired or wireless network 7 and transmits various data (only some of the data is shown in Fig. 1). The number of devices 2 to 6 is shown by the dashed arrows. The connection configuration of the network 7 is not limited to the example in FIG. 1 and may be changed as appropriate.

[0015] The substrate processing apparatus 2 is composed of a plurality of units and performs a series of processes for one or a plurality of wafers W. The substrate processing includes, for example, loading, polishing, cleaning, drying, film thickness measurement, unloading, etc. In this case, the substrate processing apparatus 2 is an apparatus for performing the processing set for each unit. The equipment setting information 265 is made up of a plurality of equipment parameters, and the polishing process, cleaning process, drying process The operation of each unit is controlled while referring to the substrate recipe information 266 that determines the operating state of the process. do.

[0016] The substrate processing apparatus 2 stores various reports R in a database according to the operation of each unit. 3, and transmits it to the user terminal device 6, etc. Various reports R include, for example, process information for identifying the wafer W to be processed when each process is performed, Device status information indicating the status, event information detected by the substrate processing apparatus 2, and the substrate processing apparatus 2 It includes operation information of users (operators, production managers, maintenance managers, etc.) for the system.

[0017] The database device 3 stores information related to the history of substrate processing performed using the production cleaning tool. The production history information 30 and the test cleaning tool are used to test the cleaning process (hereinafter referred to as the "cleaning test"). This is a device that manages cleaning test information 31 relating to the history of when the cleaning test was performed. In addition to the above, the database device 3 stores device setting information 265 and substrate recipe information 266. In this case, the substrate processing apparatus 2 may refer to the information. You may do so.

[0018] The database device 3 stores the information on the substrate processing apparatus 2 that has processed the substrate using the cleaning tool for production. At the same time, various reports R are received from the substrate processing apparatus 2 at any time and registered in the production history information 30. As a result, the production history information 30 accumulates reports R relating to the substrate processing.

[0019] The database device 3 stores the information that the substrate processing apparatus 2 has performed a cleaning test using a test cleaning tool. At this time, various reports R (including at least apparatus status information) are received from the substrate processing apparatus 2 as needed. The cleaning test result is registered in the cleaning test information 31. By doing so, the cleaning test information 31 accumulates reports R and test results related to the cleaning test. The cleaning test may be performed in the substrate processing apparatus 2 for production or in the same equipment as the substrate processing apparatus 2. Such cleaning processes may be performed in a reproducible test cleaning test apparatus (not shown). The cleaning tools and cleaning test equipment are equipped with the condition of the cleaning tools, such as the weight of the cleaning tool, Various cleaning tool measuring instruments (not shown) are provided to measure water content, hardness, and cleanliness. The measurement values ​​of the cleaning tool measuring device are registered in the cleaning test information 31 as test results.

[0020] The machine learning device 4 operates as a subject of the learning phase of machine learning, for example, A part of the cleaning test information 31 is acquired from the cleaning device 3 as first learning data 11A, and the information is processed. The first learning model 10A used in the processing device 5 is generated by machine learning. The first learning model 10A is provided to the information processing device 5 via the network 7, a recording medium, etc. will be done.

[0021] The information processing device 5 operates as the subject of the inference phase of machine learning, and The first learning model 10A generated by the above is used to estimate the cleaning process by the substrate processing apparatus 2. When cleaning is performed using a cleaning tool for cleaning, the state of the cleaning tool is predicted and the predicted result is The cleaning tool status information is transmitted to the database device 3, the user terminal device 6, etc. The timing when the cleaning tool status information is predicted by the device 5 is after the cleaning process has been performed (post-prediction process). It can be performed before the cleaning process (real-time prediction process), or during the cleaning process (real-time prediction process). It may be performed before the cleaning process is performed (advance prediction process).

[0022] The user terminal device 6 is a terminal device used by a user, and may be a stationary device or a portable device. The user terminal device 6 may be a mobile device. It accepts various input operations via the display screen of a web browser, etc., and also Various information (e.g., event notifications, cleaning tool status information, production history information, cleaning test Display information 31, etc.

[0023] (Substrate processing device 2) 2 is a plan view showing an example of the substrate processing apparatus 2. The substrate processing apparatus 2 has a substantially rectangular shape in a plan view. A load / unload unit 21 and a polishing unit 22 are housed inside a housing 20 having a shape similar to that of the , a substrate transport unit 23, a finishing unit 24, a film thickness measurement unit 25, and a control unit The load / unload unit 21 and the polishing unit 26 are included. 2. The first partition wall 200A separates the substrate transport unit 23 from the finishing unit 24. The substrate transport unit 23 and the finishing unit 24 are separated by a second partition wall 200B. It's more compartmentalized.

[0024] (load / unload unit) The load / unload unit 21 is a wafer container that can store a large number of wafers W in the vertical direction. First to fourth front loading sections 210A to 210D on which sets (FOUPs, etc.) are placed and can move up and down along the storage direction (vertical direction) of the wafers W stored in the wafer cassette. The arrangement of the transport robot 211 and the first to fourth front loading sections 210A to 210D A horizontal movement mechanism that moves the transport robot 211 along the horizontal direction (the short side direction of the housing 20). and a unit 212.

[0025] The transport robot 211 is connected to each of the first to fourth front loading sections 210A to 210D. The wafer cassette placed thereon, the substrate transport unit 23 (specifically, the lifter 232 described later), A finishing unit 24 (specifically, first and second drying sections 24E and 24F, which will be described later), and The film thickness measuring unit 25 is configured to be accessible, and the wafer W is transferred between them. The lower hand receives the wafer W before processing. The upper hand is used when transferring the wafer W after processing, and the lower hand is used when transferring the wafer W after processing. When the wafer W is delivered to the wafer transfer unit 23 or the finishing unit 24, the first A shutter (not shown) provided on the partition wall 200A is opened and closed.

[0026] (Polishing unit) The polishing unit 22 includes first to fourth polishing units each performing a polishing process (flattening) of the wafer W. The first to fourth grinding sections 22A to 22D are provided on the housing 20. are arranged side by side along the longitudinal direction.

[0027] 3 is a perspective view showing an example of the first to fourth polishing sections 22A to 22D. The four polishing units 22A to 22D have the same basic configuration and function.

[0028] Each of the first to fourth polishing units 22A to 22D includes a polishing pad 2200 having a polishing surface. a polishing table 220 that rotatably supports the wafer W; A top ring (polishing head) is used to polish the polishing head while pressing it against the polishing pad 2200 on the bull 220. a polishing fluid supply nozzle 222 for supplying a polishing fluid to the polishing pad 2200; , the dresser disk 2230 is rotatably supported, and the dresser disk 2230 is A dressing pad is brought into contact with the polishing surface of the polishing pad to dress the polishing pad. and an atomizer 224 that sprays a cleaning fluid onto the polishing pad 2200.

[0029] The polishing table 220 is supported by a polishing table shaft 220a, and its axial circumference is a rotational movement mechanism 220b for rotating the polishing table 220, and a polishing pad 220 The temperature adjusting mechanism 220c adjusts the surface temperature of the heater 220.

[0030] The top ring 221 is supported by a top ring shaft 221a that is movable in the vertical direction. a rotational movement mechanism 221c configured to rotate the top ring 221 around its axis; A vertical movement mechanism 221d that moves the top ring 221 in the vertical direction, and a support shaft 2 The swinging movement mechanism 2 swings (swings) the top ring 221 around the center of the swing. 21e and is equipped.

[0031] The polishing fluid supply nozzle 222 is supported by a support shaft 222a. A swinging movement mechanism 222 that swings and moves the polishing fluid supply nozzle 222 around 2a. b, a flow rate adjusting unit 222c for adjusting the flow rate of the polishing fluid, and a temperature adjusting unit 222b for adjusting the temperature of the polishing fluid. The polishing fluid is a polishing liquid (slurry) or pure water, and further, The polishing liquid may contain a chemical solution, or may be a polishing liquid to which a dispersant has been added.

[0032] The dresser 223 is supported by a dresser shaft 223a that is movable in the vertical direction. a rotational movement mechanism 223c for rotating the dresser 223 around the axis of the dresser 223; 3 in the vertical direction, and a vertical movement mechanism 223d that moves the support shaft 223b in the vertical direction. and a swing movement mechanism 223e for swinging the dresser 223.

[0033] The atomizer 224 is supported by a support shaft 224a and rotates around the support shaft 224a. a swinging movement mechanism 224b for swinging the atomizer 224 around the center of rotation; The cleaning fluid is a mixture of liquid (e.g., pure water) and gas. The gas may be a mixture of a gas (e.g., nitrogen gas) or a liquid (e.g., pure water).

[0034] The wafer W is held by suction on the lower surface of the top ring 221 and is placed on the polishing table 220. After the wafer is moved to a predetermined polishing position, a polishing fluid is supplied from the polishing fluid supply nozzle 222. The polishing surface of the pad 2200 is pressed by the top ring 221 to perform polishing. .

[0035] (Substrate transport unit) As shown in FIG. 2, the substrate transport unit 23 is The first and second linear actuators are horizontally movable along the direction of the arrangement (the longitudinal direction of the housing 20). Transporters 230A, 230B and first and second linear transporters 230A, 2 30B, a swing transporter 231 and a load / unload unit The lifter 232 arranged on the 21 side and the temporary placement of the wafer W arranged on the finishing unit 24 side It is equipped with a support 233.

[0036] The first linear transporter 230A is adjacent to the first and second polishing sections 22A and 22B. The four transfer positions (first to fourth positions from the load / unload unit 21 side) are arranged in this order. The second transfer position is a mechanism for transferring the wafer W between the fourth transfer positions TP1 to TP4. The transfer position TP2 is a position where the wafer W is transferred to the first polishing section 22A. The transfer position TP3 is a position where the wafer W is handed over to the second polishing section 22B.

[0037] The second linear transporter 230B is adjacent to the third and fourth polishing sections 22C and 22D. The transfer positions are arranged in three positions (the fifth to sixth positions from the load / unload unit 21 side). The sixth transfer mechanism is a mechanism for transferring wafers W between seventh transfer positions TP5 to TP7. The transfer position TP6 is a position where the wafer W is transferred to the third polishing section 22C. The transfer position TP7 is a position where the wafer W is handed over to the fourth polishing section 22D.

[0038] The swing transporter 231 is adjacent to the fourth and fifth transfer positions TP4 and TP5. and a hand that is movable between the fourth and fifth transfer positions TP4 and TP5. The swing transporter 231 is connected to the first and second linear transporters 230. The wafer W is transferred between 230A and 230B, and the wafer W is temporarily placed on the temporary placement table 233. The lifter 232 is disposed adjacent to the first transfer position TP1 and is used to This is a mechanism for transferring the wafer W between the transfer robot 211 of the unload unit 21 and the transfer robot 211 . When the wafer W is transferred, a shutter (not shown) provided on the first partition wall 200A is opened and closed. can be.

[0039] (Finishing unit) As shown in FIG. 2, the finishing unit 24 is a substrate cleaning unit using a roll sponge 2400. The device includes first and second roll sponge cleaning units 24A and 24B arranged in two stages, one above the other. The substrate cleaning device using the pen sponge 2401 is a first and second device arranged in two stages, one above the other. The second pen sponge cleaning units 24C and 24D and the substrate drying unit for drying the wafer W after cleaning are provided. The drying unit includes first and second drying units 24E and 24F arranged in two stages, one above the other, and a wafer transport unit. The roll sponge cleaning unit 2 4A, 24B, pen sponge cleaning units 24C, 24D, drying units 24E, 24F, and conveyance The number and arrangement of the sections 24G and 24H are not limited to the example shown in FIG. 2 and may be changed as appropriate. Swap the positions of the roller sponge cleaning units 24A and 24B and the pen sponge cleaning units 24C and 24D. It may be possible.

[0040] The finishing unit 24 has first and second sections 24A to 24H, each of which is partitioned. Along two linear transporters 230A, 230B, for example, first and second roll Sponge cleaning units 24A, 24B, first transport unit 24G, first and second pen sponge cleaning the first and second drying sections 24C and 24D, the second conveying section 24H, and the first and second drying sections 24E and 24F. The finishing unit 24 is arranged in the order of furthest from the load / unload unit 21. The first and second roll sponge cleaning units 24A and 24B clean the wafer W after polishing. The first and second pen sponge cleaning units 24C, 2 4D, and the first and second drying units 24E, 24 The drying process is performed by either one or both of the parts 24 of the finishing unit 24. The order of the processes from A to 24H may be changed as appropriate, or some of the processes may be omitted. For example, the cleaning process by the roll sponge cleaning units 24A and 24B may be omitted and the cleaning process by the pen sponge cleaning unit 24B may be omitted. The cleaning process may start with the cleaning units 24C and 24D. Either the roll sponge cleaning units 24A and 24B or the pen sponge cleaning units 24C and 24D Alternatively or in addition to this, a buff cleaning unit (not shown) may be provided to perform the buff cleaning process. Furthermore, in this embodiment, the respective parts 24A to 24B of the finishing unit 24 H will be explained for the case where the wafer W is held horizontally (horizontally held), It may be held vertically or at an angle.

[0041] Roll sponge 2400 and pen sponge 2401 are made of synthetic resins such as PVA and nylon. The roll sponge 2400 and the pen sponge 2401 are made of , which functions as a cleaning tool for scrubbing the wafer W, and the first and second roll sponges The pen sponge cleaning units 24A and 24B, and the first and second pen sponge cleaning units 24C and 24D They can be installed interchangeably.

[0042] The first transfer section 24G includes a first transfer robot 246A that is movable in the vertical direction. The first transfer robot 246A transfers the temporary table 233 of the substrate transfer unit 23, the first and second The roll sponge cleaning units 24A and 24B, and the first and second pen sponge cleaning units 2 4C, 24D and configured to be accessible to the wafer W therebetween. For example, the lower hand is used to transfer the wafer W before cleaning. The upper hand is used when transferring the wafer W after cleaning. When the wafer W is delivered to the second partition wall 200B, a shutter (not shown) is opened. (shown in the figure) is opened and closed.

[0043] The second transfer section 24H includes a second transfer robot 246B that is movable in the vertical direction. The second transfer robot 246B is configured to transfer the first and second pen sponge cleaning units 24C and 24D, and the first and second drying sections 24E, 24F are accessible. A hand is provided for transferring the wafer W between the two.

[0044] FIG. 4 is a perspective view showing an example of the first and second roll sponge cleaning units 24A and 24B. The first and second roll sponge cleaning units 24A and 24B have the same basic configuration and functions. In the example of FIG. 4, the first and second roll sponge cleaning units 24A and 24B are A pair of roll sponges 2 arranged above and below to sandwich the surface to be cleaned (front and back) It has 400.

[0045] Each of the first and second roll sponge cleaning units 24A and 24B has a base for holding the wafer W. a plate holder 241, a cleaning fluid supply unit 242 for supplying a substrate cleaning fluid to the wafer W, and a roll The sponge 2400 is rotatably supported and the roll sponge 2400 is attached to the wafer W. A substrate cleaning unit 240 for cleaning the wafer W by contacting it with the substrate, and a roll sponge 2400 for cleaning the cleaning tool. The cleaning tool cleaning unit 243 performs cleaning (self-cleaning) with a fluid, and the hand cleaning unit 244 performs cleaning. and an environmental sensor 244 for measuring the condition of the interior space of the housing 20.

[0046] The substrate holding unit 241 includes a substrate holding mechanism 241a that holds the side edge of the wafer W at multiple locations. a substrate rotation mechanism for rotating the wafer W around a third rotation axis perpendicular to the surface of the wafer W to be cleaned; In the example of FIG. 4, the substrate holding mechanism 241a is composed of four rollers. At least one roller is movable in a holding direction or a separating direction relative to the side edge of the wafer W. The substrate rotation mechanism 241b rotates and drives at least one roller.

[0047] The cleaning fluid supply unit 242 supplies a substrate cleaning fluid to the surface of the wafer W to be cleaned. a nozzle 242a, and a swinging movement mechanism 242 that moves the cleaning fluid supply nozzle 242a in a swiveling manner; b, a flow rate adjusting unit 242c that adjusts the flow rate and pressure of the substrate cleaning fluid, and a temperature adjusting unit 242b that adjusts the temperature of the substrate cleaning fluid. The substrate cleaning fluid is pure water (rinse liquid), chemical liquid, and a mixture thereof (for example, by adjusting the flow rate of the pure water and the chemical liquid by the flow rate adjusting unit 242c) The cleaning fluid supply nozzle 242a may be either one of the following, as shown in FIG. A nozzle for pure water and a nozzle for chemical liquid may be provided separately. The body may be liquid, a two-fluid mixture of liquid and gas, or a solid material such as dry ice. It may also contain such solids.

[0048] The substrate cleaning unit 240 rotates a roll sponge around a first rotation axis parallel to the surface of the wafer W to be cleaned. a cleaning tool rotation mechanism 240a that rotates the pair of roll sponges 2400; In order to change the thickness and the distance between them, at least one of the pair of roll sponges 2400 a vertical movement mechanism 240b for moving the pair of roll sponges 2400 in the vertical direction; and a linear movement mechanism 240c that moves the vertical movement mechanism 240b in a straight line. The linear movement mechanism 240c adjusts the relative position between the roll sponge 2400 and the surface of the wafer W to be cleaned. It functions as a cleaning tool moving mechanism that moves the cleaning tool.

[0049] The cleaning tool cleaning unit 243 is disposed at a position where it does not interfere with the wafer W, and stores a cleaning tool cleaning fluid. and a cleaning tool cleaning tank 243a that can store and discharge cleaning tools. A cleaning tool cleaning plate 243b onto which the sponge 2400 is pressed, and a cleaning tool cleaning tank 243a are provided. A flow rate adjusting unit 243c adjusts the flow rate and pressure of the supplied cleaning fluid, and a roll sponge The cleaning fluid flows through the inside of the roll sponge 2400 and is discharged to the outside from the outer periphery of the roll sponge 2400. and a flow rate adjusting unit 243d for adjusting the flow rate and pressure of the cleaning tool cleaning fluid. , pure water (rinse liquid), chemical liquid and mixture thereof (for example, pure water by the flow rate adjusting unit 243c and the concentration can be adjusted by adjusting the flow rate of the chemical solution).

[0050] The environmental sensor 244 includes, for example, a temperature sensor 244a, a humidity sensor 244b, and an air pressure sensor. The sensor 244c, the oxygen concentration sensor 244d, and the microphone (sound sensor) 244e are provided. The environment sensor 244 detects the temperature of the wafer W or the load during, before, and after the cleaning process. A camera (image sensor) that can capture the surface of the Lusponge 2400, temperature distribution, airflow distribution, etc. The object of the camera is not limited to visible light, but may also be infrared light, ultraviolet light, etc. good.

[0051] In the primary cleaning process by the first and second roll sponge cleaning units 24A and 24B, the wafer W is rotated by the substrate rotation mechanism 241b while being held by the substrate holding mechanism 241a. Then, the cleaning fluid is supplied from the cleaning fluid supply nozzle 242a to the surface of the wafer W to be cleaned. The roll spot rotated around the axis by the cleaning tool rotation mechanism 240a in a state where the cleaning tool is supplied The wafer W is cleaned by the scrubbing brush 2400 sliding in contact with the surface to be cleaned of the wafer W. The plate cleaning unit 240 moves the roll sponge 2400 to the cleaning tool cleaning tank 243a, for example. For example, the roll sponge 2400 may be rotated, pressed against the cleaning tool cleaning plate 243b, or The amount adjusting unit 243d supplies the cleaning fluid to the roll sponge 2400, The foam sponge 2400 is cleaned.

[0052] FIG. 5 is a perspective view showing an example of the first and second pen sponge cleaning units 24C and 24D. The first and second pen sponge cleaning units 24C and 24D have the same basic configuration and functions.

[0053] Each of the first and second pen sponge cleaning units 24C and 24D is configured to a holder 241, a cleaning fluid supply unit 242 for supplying a substrate cleaning fluid to the wafer W, and a pen spot The pen sponge 2401 is rotatably supported and the pen sponge 2401 is brought into contact with the wafer W. a substrate cleaning unit 240 for cleaning the wafer W by using a cleaning tool cleaning fluid; A cleaning tool cleaning unit 243 that performs cleaning (self-cleaning) and a housing where the cleaning process is performed. The pen sponge 20 is provided with an environmental sensor 244 for measuring the state of the internal space of the pen sponge 20. Regarding the cleaning units 24C and 24D, the differences from the roll sponge cleaning units 24A and 24B are as follows: Explain to your heart.

[0054] The substrate holding unit 241 includes a substrate holding mechanism 241c that holds the side edge of the wafer W at multiple locations. a substrate rotation mechanism for rotating the wafer W around a third rotation axis perpendicular to the surface of the wafer W to be cleaned; In the example of FIG. 5, the substrate holding mechanism 241c is four chucks. At least one chuck is movable in a holding direction or a separating direction relative to the side edge of the wafer W. The substrate rotating mechanism 241d is configured to be movable, and the substrate rotating mechanism 241d has a support shaft connected to four chucks. The device is driven to rotate.

[0055] The cleaning fluid supply unit 242 has the same configuration as that shown in FIG. 4, and includes a cleaning fluid supply nozzle 242a , a swing movement mechanism 242b, a flow rate regulator 242c, and a temperature regulation mechanism 242d.

[0056] The substrate cleaning unit 240 rotates the pen sponge 2 around a second rotation axis perpendicular to the surface of the wafer W to be cleaned. The cleaning tool rotation mechanism 240d rotates the pen sponge 2401, and the pen sponge 2401 moves up and down. and a vertical movement mechanism 240e for rotating the pen sponge 2401 in the horizontal direction. The vertical movement mechanism 240e and the vertical movement mechanism 240f are provided. f is a cleaning tool movement that moves the relative position between the pen sponge 2401 and the surface of the wafer W to be cleaned. It functions as a mechanical part.

[0057] The cleaning tool cleaning unit 243 is disposed at a position where it does not interfere with the wafer W, and stores a cleaning tool cleaning fluid. and a cleaning tool cleaning tank 243e that can store and discharge cleaning tools. A cleaning tool cleaning plate 243f onto which the sponge 2401 is pressed, and a cleaning tool cleaning tank 243e are supplied with the cleaning tool cleaning material. a flow rate adjusting unit 243g for adjusting the flow rate and pressure of the cleaning fluid; The cleaning fluid flows through the inside of 401 and is discharged to the outside from the outer surface of the pen sponge 2401. and a flow rate adjusting unit 243h that adjusts the flow rate and pressure of the fluid.

[0058] The environmental sensor 244 includes, for example, a temperature sensor 244a, a humidity sensor 244b, and an air pressure sensor. The sensor 244c, the oxygen concentration sensor 244d, and the microphone (sound sensor) 244e are provided. The environment sensor 244 detects the temperature of the wafer W or the pen during, before, and after the cleaning process. A camera (image sensor) capable of photographing the surface temperature distribution and airflow distribution of the sponge 2401 The object of the camera is not limited to visible light, but may be infrared light, ultraviolet light, etc. .

[0059] In the secondary cleaning process by the first and second pen sponge cleaning units 24C and 24D, the wafer W is rotated by the substrate rotation mechanism 241d while being held by the substrate holding mechanism 241c. Then, the cleaning fluid is sprayed onto the surface of the wafer W to be cleaned from the cleaning fluid supply nozzle 242a. In the supplied state, the pen sponge is rotated around the axis by the cleaning tool rotation mechanism 240d. The wafer W is cleaned by the sliding contact of 2401 with the surface to be cleaned of the wafer W. The cleaning unit 240 moves the pen sponge 2401 to the cleaning tool cleaning tank 243e, and The sponge 2401 is rotated, pressed against the cleaning tool cleaning plate 243f, and the flow rate adjusting part 243h supplies the cleaning fluid to the pen sponge 2401, 2401 is cleaned.

[0060] 6 is a perspective view showing an example of the first and second drying sections 24E and 24F. The drying units 24E and 24F of the second embodiment have the same basic configuration and functions.

[0061] Each of the first and second drying sections 24E and 24F includes a substrate holder 241 for holding a wafer W. a drying fluid supply unit 245 for supplying a substrate drying fluid to the wafer W; and an environmental sensor 244 for measuring the condition of the interior space of the housing 20.

[0062] The substrate holding unit 241 includes a substrate holding mechanism 241e that holds the side edge of the wafer W at multiple locations. a substrate rotation mechanism for rotating the wafer W around a third rotation axis perpendicular to the surface of the wafer W to be cleaned; and a section 241f.

[0063] The drying fluid supply unit 245 supplies a substrate drying fluid to the surface of the wafer W to be cleaned. a nozzle 245a and a vertical movement mechanism for moving the dry fluid supply nozzle 245a in the vertical direction; 245b, and a swinging movement mechanism 2 that swings and moves the dry fluid supply nozzle 245a in the horizontal direction. 45c, a flow rate adjusting unit 245d for adjusting the flow rate and pressure of the substrate drying fluid, and The temperature control mechanism 245e controls the temperature of the vertical movement mechanism 245b. The mechanism 245c changes the relative position between the drying fluid supply nozzle 245a and the surface of the wafer W to be cleaned. The drying fluid supply nozzle is moved by the IP A steam and pure water (rinse liquid), and the drying fluid supply nozzle 245a is Alternatively, a nozzle for IPA vapor and a nozzle for pure water may be provided separately. The plate drying fluid may be a liquid, or a two-fluid mixture of a liquid and a gas, or a dryer. It may also include a solid object such as a chair.

[0064] The environmental sensor 244 includes a temperature sensor 244a, a humidity sensor 244b, and an air pressure sensor 244c. 4c, an oxygen concentration sensor 244d, and a microphone (sound sensor) 244e. The environmental sensor 244 measures the surface temperature and temperature of the wafer W during, before, and after the drying process. It may also be equipped with a camera (image sensor) that can photograph the fabric, airflow distribution, etc.

[0065] In the drying process by the first and second drying sections 24E and 24F, the wafer W is held by the substrate holding mechanism The substrate is rotated by the substrate rotation mechanism 241f while being held by the substrate rotation mechanism 241e. In a state where the substrate drying fluid is supplied from the drying fluid supply nozzle 245a to the surface to be cleaned of the wafer W, The drying fluid supply nozzle 245a is moved toward the side edge of the wafer W (outward in the radial direction). Thereafter, the wafer W is dried by being rotated at high speed by the substrate rotation mechanism 241f. can be.

[0066] 4 to 6, the substrate rotation mechanism 241b, 241d, the vertical movement mechanism 240 b, 240e, 245b, linear movement mechanism 240c, swing movement mechanism 240f, 242b , 245c, and the cleaning tool rotation mechanism parts 240a, 240d are omitted. For example, modules for generating driving force such as motors and air cylinders, and linear guides and ball screws The drive force transmission mechanism, such as gears, belts, couplings, and bearings, and the linear sensor and encoder It is configured by appropriately combining sensors such as a stator sensor, a limit sensor, and a torque sensor. 4 to 6, the components of the flow rate adjusting units 243c, 243d, 243g, 243h, and 245d are Although the physical configuration is omitted, it may include, for example, pumps, valves, regulators, and other fluid adjusting devices. Modules and flow sensors, pressure sensors, liquid level sensors, temperature sensors, fluid concentration sensors, The sensor is configured by appropriately combining sensors such as a particle sensor. Although the specific configuration of the temperature adjustment mechanism parts 242d and 245e is omitted, for example, a heater, a heat exchanger, Modules for temperature control (contact or non-contact) of converters, etc., temperature sensors, current sensors, etc. It is configured by appropriately combining the above sensors.

[0067] (film thickness measurement unit) The film thickness measuring unit 25 is a measuring unit for measuring the film thickness of the wafer W before or after the polishing process. These devices are, for example, optical film thickness measuring devices, eddy current film thickness measuring devices, etc. The wafer W is delivered to and received from the module by a transfer robot 211.

[0068] (control unit) 7 is a block diagram showing an example of the substrate processing apparatus 2. The control unit 26 controls each unit. A control unit electrically connected to the units 21 to 25 and controlling the units 21 to 25 in an integrated manner. The control system (modules, sensors, sequencers) of the finishing unit 24 will be explained below. The explanation will be given using the example of the sensor, but the other units 21 to 23 and 25 also share the same basic structure and functions. Therefore, the explanation will be omitted.

[0069] The finishing unit 24 includes sub-units (for example, first and second sub-units) and second roll sponge cleaning units 24A, 24B, first and second pen sponge cleaning units 24 C, 24D, first and second drying sections 24E, 24F, first and second conveying sections 24G, 24 H, etc.) and a plurality of modules 2471 to 247 to be controlled. r and, Multiple modules 2471-247 r Each module is placed in 47 r A plurality of sensors 2481 to 248 detect data (detected values) necessary for the control of s and, Each sensor 2481~248 s Based on the detected value, each module 2471 to 247 r How it works and a sequencer 249 for controlling the above.

[0070] Finishing unit 24 sensors 2481-248 s For example, the substrate holding mechanism 241 a, 241c, a sensor for detecting the holding pressure when holding the substrate, the substrate holding mechanism part 241 a, a sensor for detecting the rotation speed of 241c, a rotation torque of the substrate rotation mechanism parts 241b, 241d a sensor for detecting the flow rate of the substrate cleaning fluid; a sensor for detecting the pressure of the substrate cleaning fluid a sensor for detecting the position coordinates of the cleaning fluid supply unit 242 which can be converted into a dropping position of the substrate cleaning fluid; a sensor for detecting the temperature of the substrate cleaning fluid; a sensor for detecting the concentration of the substrate cleaning fluid; a sensor for detecting the number of rotations of the cleaning tool rotation mechanism 240a; a sensor for detecting the rotation torque of the cleaning tool moving mechanism (up and down moving mechanism 240b, 240e) , a sensor for detecting the position coordinates of the linear movement mechanism 240c, the swing movement mechanism 240f, A sensor that detects the movement speed of the cleaning tool movement mechanism and a sensor that detects the movement torque of the cleaning tool movement mechanism The sensor and cleaning tools (roll sponge 2400, pen sponge 2401) are placed on the wafer W or a sensor for detecting a pressing load when the cleaning tool cleaning plates 243b and 243f are brought into contact with the cleaning tool cleaning plates; Sensor for detecting the flow rate of a fluid, sensor for detecting the pressure of a cleaning tool cleaning fluid, The cleanliness of the cleaning tool (for example, the concentration of particles contained in the wastewater from the cleaning tool cleaning tanks 243a and 243e) These include sensors for detecting the particle size, particle diameter, and number of particles per particle diameter, and an environmental sensor 244.

[0071] The control unit 26 includes a control unit 260, a communication unit 261, an input unit 262, an output unit 263, and and a storage unit 264. The control unit 26 is, for example, a general-purpose or dedicated computer. (See Figure 8 below.)

[0072] The communication unit 261 is connected to the network 7 and is a communication interface for transmitting and receiving various data. The input unit 262 accepts various input operations and outputs The unit 263 outputs various information via a display screen, a signal tower light, and a buzzer sound. This functions as a user interface.

[0073] The storage unit 264 stores various programs (operating programs) used in the operation of the substrate processing apparatus 2. Operating systems (OS), application programs, web browsers, etc.) and data (devices The device setting information 265 and the substrate recipe information 266 are stored. The recipe information 266 is data that can be edited by the user via the display screen.

[0074] The control unit 260 controls a plurality of sequencers 219, 229, 239, 249, and 259 (hereinafter, A plurality of sensors 2181 to 218 q, 2281-228 s , 2381-238 u , 2481-248 w , 2581-258 y (hereinafter referred to as "sensor group" ") and a plurality of modules 2171 to 217 p , 227 1~227 r , 2371-237 t , 2471-247 v , 2571-257 x (below, By operating these modules in cooperation with each other, loading, polishing, cleaning, drying, film deposition, A series of substrate processes such as thickness measurement and unloading are performed.

[0075] (Hardware configuration of each device) 8 is a hardware configuration diagram showing an example of the computer 900. The control unit 26, the database device 3, the machine learning device 4, the information processing device 5, and the user Each of the user terminal devices 6 is configured by a general-purpose or dedicated computer 900 .

[0076] As shown in FIG. 8, 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 a device 918, a storage device 920, a communication I / F (interface) unit 922, an external device an I / O (input / output) device I / F unit 924, an I / O (input / output) device I / F unit 926, and a media input / output unit 928. The above components may be configured differently depending on the purpose for which the computer 900 is used. It may be omitted as appropriate.

[0077] The processor 912 may include one or more central processing units (CPUs). processing unit), MPU (micro-processing unit) , DSP (digital signal processor), GPU (Graph The entire computer 900 is composed of The memory 914 stores various data and programs 930. volatile memory (DRAM, SRAM, etc.) that stores data and functions as a main memory, It consists of non-volatile memory (ROM), flash memory, etc.

[0078] The input device 916 is configured with, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc. The output device 917 is, for example, a sound (audio) output device, a The display device 918 is configured with a display device, etc., and functions as an output unit. , LCD displays, OLED displays, electronic paper, projectors, etc. The input device 916 and the display device 918 function as a touch panel. The storage device 920 may be integrated with the display. For example, it is composed of HDD, SSD (Solid State Drive), etc., and serves as a storage unit. The storage device 920 functions as an operating system and a program 930. Stores various data required for execution.

[0079] The communication I / F unit 922 is connected to a network 940 (see FIG. 1) by wire or wirelessly, and It functions as a communication unit that sends and receives data to and from other computers according to the standard. The external device I / F unit 924 is connected to an external device 95 such as a camera, a printer, a scanner, a reader / writer, etc. 0 by wire or wirelessly, and transmits data to and receives data from an external device 950 in accordance with a predetermined communication standard. The I / O device I / F unit 926 functions as a communication unit that transmits and receives various sensors. The I / O device 960 is connected to the I / O device 960 such as a sensor or an actuator. For example, various signals and data such as detection signals from sensors and control signals to actuators are The media input / output unit 928 functions as a communication unit that transmits and receives data. It consists of a drive device such as a drive or CD drive, and media such as DVDs and CDs (non-temporary) The data is read from and written to the storage medium 970.

[0080] In the computer 900 having the above configuration, the processor 912 A program 930 stored in 920 is called from memory 914 and executed, and a bus 910 is used. The program 930 controls each part of the computer 900 through the storage device. The program 930 may be stored in the memory 914 instead of the device 920. The file is recorded on the medium 970 in a downloadable or executable file format. The program 93 may be provided to the computer 900 via the media input / output unit 928. 0 is downloaded via the network 940 via the communication I / F unit 922. The computer 900 may be provided with a processor 9 12 executes the program 930, various functions are realized by, for example, FPGA, A It may also be realized by hardware such as SIC.

[0081] The computer 900 may be, for example, a desktop computer or a portable computer. The computer 900 is a client computer. Alternatively, a server-type computer or a cloud-type computer may be used. 0 may also be applied to devices other than devices 2 to 6.

[0082] (Production history information 30) FIG. 9 is a data structure showing an example of the production history information 30 managed by the database device 3. The production history information 30 includes cleaning tools for this production (roll sponge 2400, pence The report R obtained when substrate processing was performed using Sponge 2401 was classified. The tables to be registered include, for example, a wafer history table 300 for each wafer W, The cleaning history table 301 includes information on the state of the equipment during the cleaning process. In addition to the above, the history information 30 includes a polishing history table relating to the device status information in the polishing process. a drying history table relating to device status information in the drying process; an event table relating to event information; The system includes an input history table and an operation history table related to operation information, but detailed explanations are omitted. Abbreviated.

[0083] Each record in the wafer history table 300 includes, for example, a wafer ID, a cassette number, a sequence number, and a The lot number, start time, end time of each process, unit ID used, etc. are registered. 9 shows examples of the polishing process, cleaning process, and drying process, but the same applies to other processes. It will be registered.

[0084] Each record in the cleaning history table 301 contains, for example, a wafer ID, substrate holder status information, and , cleaning fluid supply unit status information, substrate cleaning unit status information, cleaning tool cleaning unit status information, and device internal environment information. Information such as transaction information and processing results information is registered.

[0085] The substrate holder state information is information that indicates the state of the substrate holder 241 during the cleaning process. The substrate holder status information may be, for example, a group of sensors (or a group of modules) included in the substrate holder 241. ) is sampled at a predetermined time interval by each sensor (or each module) command value).

[0086] The cleaning fluid supply unit status information is information indicating the status of the cleaning fluid supply unit 242 during the cleaning process. The cleaning fluid supply unit status information is, for example, a sensor group ( or a group of modules) at predetermined time intervals. (command value to each module).

[0087] The substrate cleaning unit status information is information that indicates the status of the substrate cleaning unit 240 during the cleaning process. The substrate cleaning unit status information may be, for example, information from a group of sensors (or a group of modules) included in the substrate cleaning unit 240. ) is sampled at a predetermined time interval by each sensor (or each module) command value).

[0088] The cleaning tool cleaning unit status information is information indicating the status of the cleaning tool cleaning unit 243 during the cleaning process. The cleaning tool cleaning unit status information is, for example, a sensor group (or module) included in the cleaning tool cleaning unit 243. The detected values ​​of each sensor (or each module) sampled at a predetermined time interval by the (command value to the controller).

[0089] The internal environment information of the substrate processing apparatus 2 is the state of the internal space formed by the housing 20. The internal space of the substrate processing apparatus 2 is a space in which the finishing unit 24 is disposed. The internal environment information of the device is sampled at predetermined time intervals by the environment sensor 244, for example. The detected values ​​of the sensors are shown in Table 1. The inner space of the substrate processing apparatus 2 is Each sub-unit included in the cleaning unit 24 (for example, the first and second roll sponge cleaning units 24A, 24B, first and second pen sponge cleaning units 24C, 24D, first and second drying units 24 If the temperature is separated by a space between the finishing unit 24 and the temperature sensor 24F, the environmental sensor 244 The internal environment information is provided to each sub-unit of the finishing unit 24. is obtained every

[0090] The processing result information is information showing the results of the cleaning process. After the sponge 2400 and the pen sponge 2401 are replaced, the cleaning tool is used to perform the cleaning process. This includes the cumulative number of wafers W used and the cumulative usage time when the process was performed.

[0091] By referring to the cleaning history table 301, for the wafer W identified by the wafer ID, The time series data ( or time series data for each module) can be extracted.

[0092] (Cleaning test information 31) FIG. 10 is a data table showing an example of the cleaning test information 31 managed by the database device 3. The cleaning test information 31 is a diagram showing the cleaning test performed using the cleaning tools and cleaning test equipment. The cleaning test table in which the report R obtained when the test was carried out and the test results are classified and registered. Equipped with Bull 310.

[0093] Each record in the cleaning test table 310 includes, for example, a test ID, substrate holder status information, Cleaning fluid supply unit status information, substrate cleaning unit status information, cleaning tool cleaning unit status information, and device internal environment information The cleaning test table 310 has a substrate holding section. status information, cleaning fluid supply unit status information, substrate cleaning unit status information, cleaning tool cleaning unit status information, The environmental information and processing performance information are information that indicates the state of each part in the cleaning test. The data structure is the same as that of the cleaning history table 301, so a detailed description will be omitted.

[0094] The test result information is the condition of the test cleaning equipment when the cleaning process is performed in the cleaning test. The test result information is information indicating the cleaning tool used for the test and the cleaning tool measurement data provided in the cleaning test device. The test results shown in Figure 10 are measurements taken at specified time intervals using a measuring device. The information is stored at each time t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11, t12, t13, t14, t15, t16, t17, t18, t19, t19, t20, t21, t22, t23, t24, t25 Measurement of the weight, moisture content, hardness, and cleanliness of the cleaning tools at 2, ..., ...tm, ..., tn The test result information includes values ​​V1 to V4. The measurement may be a measurement result obtained by a camera or optical sensor installed as the environmental sensor 244. The test cleaning tool is scanned using a camera mounted on a scanning electron microscope (SEM). The images were taken at time intervals, and the results of image processing were then processed for each image. The test result information may be based on the results of an experiment analyzed by the person in charge of the cleaning process. The data may be collected in a single cleaning test, which is carried out continuously from start to finish, or A cleaning test is conducted from the start of the cleaning process until the specified time is reached, gradually increasing the specified time. The data may be collected from multiple cleaning tests by repeating the same procedure.

[0095] By referring to the cleaning test table 310, in the cleaning test identified by the test ID, The substrate cleaning device (substrate holder 241, cleaning tool) when the cleaning process was performed using the test cleaning tool A timeline showing the status of the purified fluid supply unit 242, the substrate cleaning unit 240, and the cleaning tool cleaning unit 243 The column data (or time series data for each module) and the status of the cleaning tool for the test at that time are shown. It is possible to extract time series data.

[0096] (Machine Learning Device 4) FIG. 11 is a block diagram showing an example of a machine learning device 4 according to the first embodiment. The learning device 4 includes a control unit 40, a communication unit 41, a learning data storage unit 42, and a learned model. It is equipped with a rule storage unit 43.

[0097] The control unit 40 functions as a learning data acquisition unit 400 and a machine learning unit 401. The unit 41 communicates with an external device (for example, the substrate processing apparatus 2, the database device) via the network 7. device 3, an information processing device 5, a user terminal device 6, a cleaning test device (not shown), etc. It functions as a communication interface for sending and receiving various types of data.

[0098] The learning data acquisition unit 400 is connected to an external device via the communication unit 41 and the network 7. The data is composed of operation status information as input data and cleaning tool status information as output data. The first training data 11A is obtained by supervised learning. It is used as teacher data (training data), validation data, and test data in learning. In addition, cleaning tool status information is used as a correct label in supervised learning. This is the data used.

[0099] The learning data storage unit 42 stores the first learning data acquired by the learning data acquisition unit 400. 11A. The specific configuration of the database may be designed as appropriate.

[0100] The machine learning unit 401 uses a plurality of sets of first learning data stored in the learning data storage unit 42. That is, the machine learning unit 401 performs machine learning using the first learning model. A plurality of sets of first training data 11A are input to the rule 10A, and the first training data 11A is The first learning model 10A learns the correlation between the operating status information and the cleaning tool status information. This generates a trained first learning model 10A.

[0101] The trained model storage unit 43 stores the trained first learning model generated by the machine learning unit 401. A database that stores the training model 10A (specifically, the adjusted weight parameters) The trained first learning model 10A stored in the trained model storage unit 43 is provided to a real system (for example, information processing device 5) via a network 7 or a recording medium, etc. In FIG. 11, the learning data storage unit 42 and the trained model storage unit 43 are separate units. Although shown as storage units, these may be comprised of a single storage unit.

[0102] The number of first learning models 10A stored in the learned model storage unit 43 is limited to one. The method is not limited to a specific one, and may be, for example, a machine learning method, a type of wafer W (size, thickness, film type, etc.), a cleaning tool, etc. The type of substrate cleaning device (substrate holder 241, cleaning fluid supply unit 242, substrate cleaning unit 240, Also, differences in the mechanism of the cleaning tool cleaning unit 243), the type of substrate cleaning fluid and cleaning tool cleaning fluid, and operation The type of data included in the status information, the type of data included in the cleaning tool status information, etc. A plurality of learning models with different conditions may be stored. In this case, the learning data storage unit 42 includes a plurality of types of data structures each corresponding to a plurality of learning models with different conditions. It is sufficient that the learning data of the class is stored.

[0103] FIG. 12 is a diagram showing an example of a first learning model 10A and first learning data 11A. The first learning data 11A used for machine learning of the first learning model 10A is a set of data representing the behavior of the first learning model 10A. In this embodiment, the first learning model 10A and The first learning data 11A is a roll sponge cleaning unit using a roll sponge 2400. 24A and 24B, and a pen sponge cleaning unit 2 using a pen sponge 2401. At least two types are available, one for 4C and one for 24D, but the basic data structure is are common to all of the above, so they will be explained together below.

[0104] The operation state information constituting the first learning data 11A is generated by the substrate processing apparatus 2. Substrate holder status information indicating the status of the substrate holder 241 during the cleaning process of the wafer W, cleaning flow cleaning fluid supply unit status information indicating the status of the substrate supply unit 242, and The cleaning tool cleaning unit status information includes the board cleaning unit status information and the cleaning tool cleaning unit status information indicating the status of the cleaning tool cleaning unit 243. .

[0105] The substrate holding unit status information included in the operation status information is the status of the substrate holding mechanism units 241a and 241c. The number of holding points when holding a substrate, when the substrate holding mechanism parts 241a and 241c hold a substrate, the holding pressure, the rotation speed of the substrate holding mechanism parts 241a and 241c, the substrate rotation mechanism part 241b, The rotation torque of 241d and the condition of the substrate holding mechanism parts 241a and 241c are low. The conditions of the substrate holding mechanism parts 241a and 241c include, for example, Usage status of the substrate holding mechanism parts 241a and 241c (usage time, pressure during use, whether or not they have been replaced) 4 indicates the degree of wear and dirt of the substrate holding mechanism parts 241a and 241c set based on the above. The condition of the substrate holding mechanism parts 241a and 241c changes over time during cleaning processing, for example. It may also be something that

[0106] The cleaning fluid supply unit status information included in the operation status information includes the flow rate of the substrate cleaning fluid, the substrate cleaning flow rate, The pressure of the substrate, the drip position of the substrate cleaning fluid, the temperature of the substrate cleaning fluid, and the concentration of the substrate cleaning fluid. When the substrate cleaning fluid is a plurality of types of fluid, the cleaning fluid supply unit The status information may include the flow rate, pressure, drop position, temperature, and concentration of each fluid.

[0107] The substrate cleaning unit status information included in the operation status information includes the rotation speed of the cleaning tool rotation mechanism 240a, The rotation torque of the cleaning tool rotation mechanism 240a, the cleaning tool movement mechanism (vertical movement mechanism 240b, 240e, the linear movement mechanism 240c, the swing movement mechanism 240f), the position coordinates of the cleaning tool movement The moving speed of the mechanism, the moving torque of the cleaning tool moving mechanism, and the time when the cleaning tool is brought into contact with the wafer W The cleaning tool condition includes at least one of the pressing load and the cleaning tool condition. The condition of the cleaning tool at a time point before the target time point in the cleaning tool status information is For example, the usage status of the cleaning tool (usage time, pressure load during use, replacement The setting is based on the presence or absence of the cleaning tool, the rotation speed of the wafer W, the number of wafers processed, and an image of the surface of the cleaning tool. The condition of the cleaning tool indicates the degree of wear and dirt of the cleaning tool. It may be something that changes over time.

[0108] The cleaning tool cleaning unit status information included in the operation status information is the rotation speed of the cleaning tool rotation mechanism 240a. , the rotation torque of the cleaning tool rotation mechanism 240a, the cleaning tool movement mechanism (vertical movement mechanism 240b , 240e, the linear movement mechanism 240c, the swing movement mechanism 240f), the position coordinates of the cleaning tool movement the moving speed of the moving mechanism, the moving torque of the cleaning tool moving mechanism, the cleaning tool cleaning plate 243b, 243f, the pressure when contacting the cleaning tool cleaning fluid, the flow rate of the cleaning tool cleaning fluid, And, the cleanliness of the cleaning tool cleaning fluid (discharge side of the cleaning tool cleaning tanks 243a, 243e) is at least Also includes one.

[0109] The operating status information further includes internal environment information indicative of the environment of the space in which the cleaning process is performed. The internal environment information included in the operating state information may be formed by the housing 20. The temperature, humidity, air pressure, air flow, etc. of the internal space (each sub-unit of the finishing unit 24) The operational status information includes at least one of oxygen concentration and sound. The operation status information may further include processing history information indicating For example, when the cleaning tool is replaced and then the cleaning process is performed using the replaced cleaning tool, the wafer W The information includes at least one of the cumulative number of sheets used and the cumulative usage time.

[0110] The cleaning tool state information constituting the first learning data 11A is the operation state indicated by the operation state information. This is information indicating the state of the cleaning tool when the substrate processing apparatus 2 operates. The cleaning tool status information is condition information that indicates the condition of the cleaning tool. The cleaning information may be, for example, the cleaning period from the start to the end of the cleaning process (wafer 1 The weight, moisture content, and The cleaning process includes at least one of hardness and cleanliness. 40 performs an operation of bringing the cleaning tool into contact with the wafer W to clean the wafer W, and the cleaning fluid supply unit 242 An operation of supplying a substrate cleaning fluid and a cleaning tool cleaning unit 243 cleaning the cleaning tool with the cleaning tool cleaning fluid. Cleaning actions are included.

[0111] The learning data acquisition unit 400 refers to the cleaning test information 31 and, if necessary, By accepting an input operation by the user through the user terminal device 6, the first learning data 11A For example, the learning data acquisition unit 400 acquires the cleaning test table of the cleaning test information 31. By referring to the table 310, the substrate holder when the cleaning test specified by the test ID was performed can be identified. Status information, cleaning fluid supply unit status information, substrate cleaning unit status information, and cleaning tool cleaning unit status information (Substrate holding unit 241, cleaning fluid supply unit 242, substrate cleaning unit 240, and cleaning tool cleaning unit 2 The time series data of each sensor included in each of the sensors 43 is acquired as operation status information.

[0112] In this embodiment, the operational status information is calculated based on the time-series data of the sensor group as shown in FIG. The case where the substrate cleaning device (substrate holder 241, cleaning fluid supply supply unit 242, substrate cleaning unit 240, and cleaning tool cleaning unit 243) may be appropriately changed depending on the configuration. Also, as the operation status information, a command value to the module may be used, or a sensor A parameter converted from a detected value or a command value to the module may be used. Parameters calculated based on the detected values ​​of the sensors may also be used. may be acquired as time series data for the entire cleaning treatment period, or for a part of the cleaning treatment period. It may be acquired as time series data for a certain period of time, or as point-in-time data at a specific point in time. As described above, when changing the definition of the operational status information, Data configuration of input data in the first learning model 10A and the first learning data 11A can be changed appropriately.

[0113] Furthermore, the learning data acquisition unit 400 refers to the cleaning test table 310 of the cleaning test information 31. By checking the test result information (for cleaning) when a cleaning test identified by the same test ID was conducted, The time series data of the cleaning tool measuring equipment (Fig. 10) is used to calculate the cleaning tool status information for the above operating status information. The cleaning tool measuring device is a measuring device that can measure the entire surface of the cleaning tool. In this case, the learning data acquisition unit 400 acquires planar measurement values ​​as cleaning tool state information. do.

[0114] In this embodiment, the cleaning tool status information is condition information as shown in FIG. In this case, the weight, moisture content, hardness and cleanliness of the cleaning tool are taken into consideration. The cleaning tool status information may include one of the following: Furthermore, the operation status information may be, for example, a cleaning process period. Obtained as time-series data for the entire period or for a target period that is part of the cleaning treatment period. If so, the cleaning tool status information is time-series data for the entire cleaning process period or the target period. It may be acquired as time series data, or as point-in-time data at the end of the cleaning process or at a target point in time. Alternatively, the operational status information may be acquired as time point data, for example, at a specific target time point. If the cleaning tool status information is acquired as point-in-time data at a specific time, the cleaning tool status information is As described above, the definition of the cleaning tool status information may be obtained as time point data at a certain time. When changing the first learning model 10A and the first learning data 11A, The data structure of the force data may be changed as appropriate.

[0115] The first learning model 10A is, for example, a model that employs a neural network structure. It has an input layer 100, an intermediate layer 101, and an output layer 102. Each neuron is connected to a synapse (not shown), and each synapse has a weight. The weight parameters of each synapse are assigned to each other. It is adjusted by practice.

[0116] The input layer 100 has neurons whose number corresponds to the motion state information as input data. Each value of the motion state information is input to each neuron. The output layer 102 outputs the output data The number of neurons corresponds to the cleaning tool state information as The prediction result (inference result) of the state information is output as output data. When OA is configured as a regression model, the cleaning tool status information is calculated based on a predetermined range (e.g., 0 The first learning model 10A outputs the normalized values ​​(1) to (1). When configured as a class model, the cleaning tool status information is represented by a score (accuracy) for each class. Then, the values ​​are output as normalized numbers within a predetermined range (for example, 0 to 1).

[0117] (machine learning methods) FIG. 13 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 starts machine learning. As a preliminary preparation for this, a desired number of first learning data 11A is collected from the cleaning test information 31, etc. The acquired first learning data 11A is stored in the learning data storage unit . The number of first learning data 11A prepared here is determined based on the number of the first learning data 11A finally obtained. This setting should be made taking into account the inference accuracy required for Model 10A.

[0119] Next, in step S110, the machine learning unit 401 starts the learning The first learning model 10A before learning is prepared. A is composed of the neural network model shown in Figure 12, and each synapse The weights are set to their initial values.

[0120] Next, in step S120, the machine learning unit 401 performs the following steps: For example, one set of first learning data is randomly selected from the plurality of sets of first learning data 11A stored in the memory. Obtain the data 11A.

[0121] Next, in step S130, the machine learning unit 401 performs a first set of learning data 1 The operation status information (input data) included in 1A is used as the first data before (or during) learning. The input layer 100 of the first learning model 10A is then input. The output layer 102 outputs cleaning tool status information (output data) as an inference result. The data is generated by a first learning model 10A before (or during) learning. Therefore, before (or during) learning, the output data output as the inference result is is information different from the cleaning tool state information (correct label) included in the first learning data 11A. Shows.

[0122] Next, in step S140, the machine learning unit 401 performs the The cleaning tool state information (correct label) included in the acquired set of first learning data 11A, In step S130, the cleaning tool status information (output data) is output as an inference result from the output layer. The weights of each synapse are adjusted (backpropagation) by comparing the input data with the input data. By this, the machine learning unit 401 performs machine learning by integrating the operation state information and the washing The first learning model 10A is made to learn the correlation with the cleaning tool state information.

[0123] Next, in step S150, the machine learning unit 401 performs a process of determining whether a predetermined learning termination condition is met. Whether or not the cleaning tool has been detected is determined based on, for example, the cleaning tool state information (correct answer label) included in the first learning data 11A. The error function based on the cleaning tool status information (output data) and the inference result The evaluation value and the unlearned first learning data 11A stored in the learning data storage unit 42 The decision is based on the remaining number.

[0124] In step S150, the machine learning unit 401 determines that the learning termination condition is not satisfied, If it is determined that machine learning should be continued (No in step S150), the process returns to step S120. The processes of steps S120 to S140 are performed on the first learning model 10A during learning. The first training data 11A is used for multiple times. When the machine learning unit 401 determines that the learning termination condition is met and that the machine learning is to be terminated, If so (Yes in step S150), the process proceeds to step S160.

[0125] Then, in step S160, the machine learning unit 401 calculates the The trained first learning model 10A (adjusted weights) generated by adjusting the weights The trained model storage unit 43 stores the trained model (parameter group) and performs the series of machine learning methods shown in FIG. In the machine learning method, step S100 is a learning data storage step, step Steps S110 to S150 correspond to the machine learning process, and step S160 corresponds to the learned model storage process. Correct.

[0126] As described above, according to the machine learning device 4 and the machine learning method of this embodiment, cleaning fluid supply unit status information, substrate cleaning unit status information, and cleaning tool cleaning unit status information From the operational status information including the cleaning tool (roll sponge 2400, pen sponge 2401), A first learning model 10A capable of predicting (inferring) cleaning tool status information indicating the status of the cleaning tool. can be provided.

[0127] (Information processing device 5) FIG. 14 is a block diagram showing an example of the information processing device 5 according to the first embodiment. 5 is a functional explanatory diagram showing an example of an information processing device 5 according to the first embodiment. The device 5 includes a control unit 50, a communication unit 51, and a trained model storage unit 52.

[0128] The control unit 50 functions as an information acquisition unit 500, a state prediction unit 501, and an output processing unit 502. The communication unit 51 communicates with external devices (for example, the substrate processing apparatus 2, the data processing apparatus 3, the data processing apparatus 4, the data processing apparatus 5, the data processing apparatus 6, the data processing apparatus 7, the data processing apparatus 8, the data processing apparatus 9, the data processing apparatus 10, the data processing apparatus 11, the data processing apparatus 12, the data processing apparatus 13, the data processing apparatus 14, the data processing apparatus 15, the data processing apparatus 16, The system is connected to various devices (e.g., a database device 3, a machine learning device 4, and a user terminal device 6) and stores various data. It functions as a communication interface for sending and receiving data.

[0129] The information acquisition unit 500 is connected to an external device via the communication unit 51 and the network 7. Plate holder status information, cleaning fluid supply status information, substrate cleaning unit status information, and cleaning tool cleaning unit Obtain operational status information including status information.

[0130] For example, the "post-prediction" of the cleaning tool status information for the wafer W after the cleaning process has already been performed When the "processing" is performed, the information acquisition unit 500 acquires the cleaning history table 30 of the production history information 30. 1, the substrate holder status information when the cleaning process is performed on the wafer W can be obtained. cleaning fluid supply unit status information, substrate cleaning unit status information, and cleaning tool cleaning unit status information. The cleaning tool status for the wafer W during the cleaning process is acquired as information on the operation status. When performing "real-time prediction processing" of information, the information acquisition unit 500 performs the cleaning processing. By receiving a report R on the device status information from the substrate processing device 2 at any time, The status information of the substrate holder during the cleaning process on the wafer W, the cleaning fluid supply The state information of the cleaning tool cleaning unit, the state information of the substrate cleaning unit, and the state information of the cleaning tool cleaning unit are stored as the operation state information. The cleaning tool status information for the wafer W before the cleaning process is acquired as needed. When the cleaning process is to be performed, the information acquiring unit 500 receives the information from the substrate processing apparatus 2 that is to perform the cleaning process. The substrate recipe information 266 is received from the By simulating the device status information during operation, the cleaning The substrate holder status information, cleaning fluid supply status information, and substrate cleaning unit status information when processing is performed are stored. The operation status information includes the cleaning tool cleaning unit status information and the cleaning tool cleaning unit status information.

[0131] As described above, the state prediction unit 501 uses the operation state information acquired by the information acquisition unit 500. is input as input data to the first learning model 10A, the operation state information Cleaning tool status information indicating the status of the cleaning tool when the substrate processing apparatus 2 is operated in the operating state (in this embodiment) In this embodiment, condition information is predicted.

[0132] The trained model storage unit 52 stores the trained first trained model used in the state prediction unit 501. The trained model storage unit 52 stores the trained model 10A. The number of first learning models 10A to be used is not limited to one, and may be, for example, a machine learning technique, a wafer Type of W (size, thickness, film type, etc.), type of cleaning tool, substrate cleaning device (substrate holding unit 241, Differences in the mechanisms of the cleaning fluid supply unit 242, the substrate cleaning unit 240, and the cleaning tool cleaning unit 243; The type of substrate cleaning fluid and cleaning tool cleaning fluid, the type of data included in the operating status information, the type of cleaning tool Multiple trained models with different conditions, such as the type of data included in the state information, are stored. In this embodiment, the trained model storage unit 52 stores the following: The roll sponge 2400 corresponds to the roll sponge cleaning units 24A and 24B. , and those corresponding to the pen sponge cleaning units 24C and 24D using the pen sponge 2401. At least two types of first learning models 10A are stored. 52 is an external computer (e.g., a server computer or a cloud computer) In this case, the state prediction unit 501 may be substituted by the storage unit of the external computer. You just need to access the data.

[0133] The output processing unit 502 outputs the cleaning tool state information generated by the state prediction unit 501. For example, the output processing unit 502 outputs the cleaning tool status information to the substrate processing apparatus. 2 or the user terminal device 6, a display screen based on the cleaning tool status information is displayed on the substrate processing The cleaning tool status information may be displayed on the management device 2 or the user terminal device 6, or may be stored in a database. By transmitting the cleaning tool status information to the device 3, the cleaning tool status information may be registered in the production history information 30.

[0134] (Information processing method) FIG. 16 is a flowchart showing an example of an information processing method by the information processing device 5. Below, the user operates the user terminal device 6 to input cleaning tool status information for a specific wafer W. An example of the operation when the "post-event prediction process" is performed will be described.

[0135] First, in step S200, the user inputs the target of prediction to the user terminal device 6. When an input operation is performed to input a wafer ID that identifies a wafer W, the user terminal device 6 The wafer ID is transmitted to the information processing device 5.

[0136] Next, in step S210, the information acquisition unit 500 of the information processing device 5 In step S211, the information acquisition unit 5 receives the wafer ID transmitted by the wafer ID acquisition unit 5. 00 is used to calculate the cleaning history data of the production history information 30 using the wafer ID received in step S210. By referring to the table 301, the cleaning process is performed on the wafer W identified by the wafer ID. Obtain the operating status information when this is done.

[0137] Next, in step S220, the state prediction unit 501 calculates the state obtained in step S211. The motion state information is input as input data to the first learning model 10A, and the motion is Generates cleaning tool status information for the operation status information as output data and predicts the status of the cleaning tool. do.

[0138] Next, in step S230, the output processing unit 502 outputs the As an output process for outputting the cleaning tool status information, the cleaning tool status information is transmitted to the user terminal. The cleaning tool status information may be sent to the user terminal device 6 in addition to or instead of the user terminal device 6. In addition, the database device 3 may also be used.

[0139] Next, in step S240, the user terminal device 6 executes the transmission process of step S200. When the cleaning tool status information transmitted in step S230 is received as a response to the By displaying the display screen based on the cleaning tool status information, the status of the cleaning tool can be easily displayed by the user. In the above information processing method, steps S210 and S211 are information acquisition steps. Step S220 corresponds to a state prediction step, and step S230 corresponds to an output processing step.

[0140] As described above, according to the information processing device 5 and the information processing method of this embodiment, the cleaning process In the above, the substrate holder status information, the cleaning fluid supply unit status information, and the substrate cleaning unit status information are Operation status information including cleaning tool cleaning unit status information is input to the first learning model 10A. Since the cleaning tool status information (condition information) corresponding to the operation status information is predicted, The state of the cleaning tool can be appropriately predicted depending on the operating state of the substrate processing apparatus 2.

[0141] (Second embodiment) In the second embodiment, the cleaning tool status information is stored in the cleaning tool (roll sponge 2400, pen sponge, Remaining life information indicating the remaining life of the cleaning tool (2401) and cleaning quality information indicating the cleaning quality of the cleaning tool. The second embodiment differs from the first embodiment in that there is at least one. The machine learning device 4a and the information processing device 5a will be described, focusing on the differences from the first embodiment. explain.

[0142] FIG. 17 is a block diagram showing an example of a machine learning device 4a according to the second embodiment. 18 is a diagram showing an example of a second learning model 10B and second learning data 11B. The second learning data 11B is used for machine learning of the second learning model 10B.

[0143] The cleaning tool status information constituting the second learning data 11B is a remaining lifespan indicating the remaining lifespan of the cleaning tool. and cleaning quality information indicating the cleaning quality of the cleaning tool. The lifespan is determined, for example, by the number of times or duration that the cleaning tool can be used before it reaches the end of its lifespan. The cleaning quality of a cleaning tool may be determined based on its impact on cleaning quality. It is determined by the degree of cleaning of the wafer W when the cleaning process is performed with the cleaning tool, for example, It can also be information about particles present in the area, such as the surface distribution of particles and particle The second learning data 11B may include the total number of circles. The information is the same as in the first embodiment, and therefore the explanation will be omitted.

[0144] The learning data acquisition unit 400 refers to the cleaning test information 31 and, if necessary, By accepting the input operation of the user through the user terminal device 6, the second learning data 11B The cleaning test information 31 includes, for example, test result information such as cleaning tools and cleaning equipment used for the test. When repeated cleaning processes are performed using a cleaning test device, the cleaning tool reaches the end of its life. The remaining life information is set to "0" and the older the data, the larger the value is set. Cleaning quality information measured using measuring equipment such as a scanning electron microscope (SEM) is registered. Then, the learning data acquisition unit 400 acquires the following data from the cleaning test table 310 of the cleaning test information 31: By acquiring test result information when a cleaning test specified by the test ID is conducted, the remaining life of the product can be information and cleaning quality information.

[0145] The machine learning unit 401 incorporates a plurality of second learning data 11B into the second learning model 10B. The operation status information and cleaning tool status information (remaining life information) included in the second learning data 11B are and at least one of the cleaning quality information) to the second learning model 10B. By doing so, a trained second learning model 10B is generated.

[0146] FIG. 19 shows an example of the information processing device 5a functioning as the information processing device 5a according to the second embodiment. 20 is a block diagram showing an example of an information processing device 5a according to the second embodiment. FIG.

[0147] The information acquisition unit 500 acquires the substrate holder status information, the cleaning fluid supply information, and the like, in the same manner as in the first embodiment. Acquire operational status information including status information, substrate cleaning unit status information, and cleaning tool cleaning unit status information. do.

[0148] As described above, the state prediction unit 501 uses the operation state information acquired by the information acquisition unit 500. is input as input data to the second learning model 10B, the operation state information Cleaning tool status information (remaining life) indicating the status of the cleaning tool when the substrate processing apparatus 2 is operated in the operating state and at least one of life information and cleaning quality information.

[0149] The output processing unit 502 outputs the washing data generated by the state prediction unit 501 in the same manner as in the first embodiment. An output process for outputting cleaning tool status information (at least one of remaining life information and cleaning quality information) For example, the output processing unit 502 outputs the cleaning tool status information to the substrate processing apparatus 2 or a user. By transmitting the information to the terminal device 6, a display screen based on the cleaning tool status information is displayed on the substrate processing apparatus 2 or The cleaning tool status information may be displayed on the user terminal device 6, or may be sent to the database device 3. By transmitting the information, the cleaning tool status information may be registered in the production history information 30. The force processing unit 502 determines, for example, whether the remaining life of the cleaning tool indicated by the remaining life information is equal to or exceeds a predetermined reference number of times of advance notice or a predetermined number of times of advance notice. If the time is shorter than the standard time or if the cleaning quality indicated by the cleaning quality information falls below the specified standard quality, In such cases, the cleaning equipment replacement notice, the replacement procedure, the time required for the replacement work, and the price of the replacement parts shall be provided. Even if information for displaying the rank etc. is transmitted to the substrate processing apparatus 2 or the user terminal device 6, In addition, the output processing unit 502 may be configured so that the substrate processing apparatus 2 has a function of automatically replacing the cleaning tool. In this case, a command to automatically replace the cleaning tool may be sent to the substrate processing apparatus 2. The command to order replacement parts for the cleaning tool is sent to the inventory control device ( The information may be transmitted to a mobile terminal (not shown).

[0150] As described above, according to the information processing device 5a and the information processing method of this embodiment, the cleaning process In the process, the substrate holder status information, the cleaning fluid supply unit status information, the substrate cleaning unit status information, and The operating status information including the cleaning tool cleaning unit status information is input to the second learning model 10B. and the cleaning tool status information (at least remaining life information and cleaning quality information) for the operating status information. Since the above-mentioned condition (at least one of the conditions) can be predicted, the condition of the cleaning tool can be appropriately predicted according to the operating condition of the substrate processing apparatus 2. It can be measured.

[0151] (Other embodiments) The present invention is not limited to the above-described embodiments, and the scope of the present invention is not limited to the above-described embodiments. Various modifications can be made within the scope of the present invention. It is included in the idea.

[0152] In the above embodiment, the database device 3, the machine learning device 4, and the information processing device 5 are separate devices. However, the three devices are described as being composed of a single device. Alternatively, any two of the three devices may be configured as a single device. In addition, at least one of the machine learning device 4 and the information processing device 5 may be a substrate processing device. It may be incorporated in the control unit 26 of the device 2 or the user terminal device 6 .

[0153] In the above embodiment, the substrate processing apparatus 2 is described as including the units 21 to 25. However, the substrate processing apparatus 2 has a function of performing cleaning processing (roll spot cleaning) in the finishing unit 24. The cleaning unit is provided with at least one of the pen sponge cleaning units 24A, 24B and the pen sponge cleaning unit 24C, 24D. The other units may be omitted.

[0154] In the above embodiment, the learning model for realizing machine learning by the machine learning unit 401 is We have explained the case where a neural network is used, but other machine learning models can also be used. Other machine learning models include tree-type models such as decision trees and regression trees, Ensemble learning such as scalars, boosting, recurrent neural networks, convolutional neural networks Neural network types such as LSTM and deep learning (including hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, k-means, etc.) Multivariate analysis such as stochastic regression, principal component analysis, factor analysis, and logistic regression, and support vector -Machines, etc.

[0155] (Machine learning programs and information processing programs) The present invention is a program that causes the computer 900 to function as each unit of the machine learning device 4. The machine learning program and each step of the machine learning method are executed by the computer 900. It can also be provided in the form of a program for executing the algorithm (machine learning program). The present invention is directed to a computer 900 that functions as each unit of the information processing device 5. Each step of the program (information processing program) and the information processing method according to the above embodiment provided in the form of a program (information processing program) for causing the computer 900 to execute the It can also be offered.

[0156] (Inference device, inference method and inference program) The present invention relates to the information processing device 5 according to the above embodiment (information processing method or information processing program). ) as well as the inference device ( In this case, the inference device (inference method or inference program) may be provided. The logic method or inference program includes a memory and a processor, The processor may perform a series of operations. The information acquisition process acquires the operating status information (information acquisition step), and the information acquisition process acquires the operating status information. When the operating state information is acquired, the cleaning tool when the substrate processing apparatus operates in the operating state indicated by the operating state information is acquired. Inferring cleaning tool status information (condition information, remaining life information, or cleaning quality information) and an inference process (inference step) for performing the inference process.

[0157] By providing it in the form of an inference device (inference method or inference program), it is possible to implement an information processing device. This makes it easier to apply to various devices than when using an inference device (inference method or inference When the machine learning program infers cleaning tool status information, Inference performed by the state prediction unit using a trained learning model generated by a machine learning method It will be readily apparent to those skilled in the art that the method may be applied. [Explanation of symbols]

[0158] 1... substrate processing system, 2... substrate processing apparatus, 3... database device, 4, 4a...machine learning device, 5, 5a...information processing device, 6...user terminal device, 7...network, 10A...First learning model, 10B...Second learning model, 11A...first learning data, 11B...second learning data, 20...housing, 21...load / unload unit, 22... Polishing unit, 22A to 22D... Polishing section, 23... Substrate transport unit, 24...Finishing unit, 24A, 24B...Roll sponge cleaning unit, 24C, 24D...Pen sponge cleaning section, 24E, 24F...Drying section, 24G, 24H...Transportation unit, 25...Film thickness measurement unit, 26...Control unit, 30...Production history information, 31...Cleaning test information, 40...control unit, 41...communication unit, 42...learning data storage unit, 43...Trained model memory unit, 50...control unit, 51...communication unit, 52...trained model storage unit, 220...polishing table, 221...top ring, 222...polishing fluid supply nozzle, 223...Dresser, 224...Atomizer, 240...substrate cleaning unit, 241...substrate holding unit, 242...cleaning fluid supply unit, 243...cleaning tool cleaning unit, 244...environment sensor, 245...drying fluid supply unit, 260...control unit, 21...communication unit, 262...input unit, 263...output unit, 264...storage unit, 300...wafer history table, 301...cleaning history table, 310...cleaning test table, 400...learning data acquisition unit, 401...machine learning unit, 500: information acquisition unit, 501: state prediction unit, 502: output processing unit, 900...computer, 2200...Polishing pad, 2230...Dresser disc, 2400...Roll sponge, 2401...Pen sponge

Claims

1. a substrate holder for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; and rotatably supporting the cleaning tool and bringing the cleaning tool into contact with the substrate to clean the substrate. A substrate cleaning unit and a cleaning tool cleaning unit for cleaning the cleaning tool with a cleaning tool cleaning fluid. A substrate holding unit state indicating the state of the substrate holding unit as the operating state when the processing apparatus is operated. cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit; and cleaning tool cleaning unit status information indicating the state of the cleaning tool cleaning unit. an information acquisition unit that acquires operation status information including the The operating state information and the operating state indicated by the operating state information are used to determine whether the substrate processing apparatus is operating in the operating state indicated by the operating state information. The correlation between the cleaning tool status information indicating the status of the cleaning tool when it was made and the cleaning tool status information is learned by machine learning. inputting the operation state information acquired by the information acquisition unit into the learning model generated by the learning unit; and a state prediction unit that predicts the cleaning tool state information based on the operating state information. Information processing device.

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

3. The cleaning tool cleaning unit status information included in the operation status information is the number of rotations of the cleaning tool rotation mechanism; the rotation torque of the cleaning tool rotation mechanism; Position coordinates of the cleaning tool moving mechanism; the movement speed of the cleaning tool movement mechanism; the movement torque of the cleaning tool movement mechanism; a pressing load when the cleaning tool is brought into contact with the cleaning tool cleaning plate; the flow rate of the cleaning tool cleaning fluid; the pressure of the cleaning tool cleaning fluid; and at least one of the cleanliness of the cleaning tool cleaning fluid; The information processing device according to claim 2 .

4. The substrate holder includes: a substrate rotation mechanism that rotates the substrate around a third rotation axis that is perpendicular to the surface of the substrate to be cleaned; Department and a substrate holding mechanism for holding a side edge of the substrate, The substrate holder status information included in the operation status information is the number of holding points when the substrate holding mechanism holds the substrate; a holding pressure when the substrate holding mechanism holds the substrate; the rotation speed of the substrate rotation mechanism; The rotation torque of the substrate rotation mechanism, and at least one of the conditions of the substrate holding mechanism; The information processing device according to claim 1 .

5. The cleaning fluid supply unit status information included in the operation status information is a flow rate of the substrate cleaning fluid; the pressure of the substrate cleaning fluid; a dripping position of the substrate cleaning fluid; the temperature of the substrate cleaning fluid; and at least one of the concentrations of the substrate cleaning fluid; The information processing device according to claim 1 .

6. The operational status information is The cleaning tool further includes internal environment information indicating an environment of a space in which the substrate is cleaned by the cleaning tool, The internal environment information included in the operating state information is Temperature of the space the humidity of the space; the atmospheric pressure of said space; airflow in the space; the oxygen concentration in the space; and at least one of the sounds of the space, The information processing device according to claim 1 .

7. The cleaning tool status information is condition information indicating the condition of the cleaning tool, The condition information is The weight of the cleaning tool, the moisture content of the cleaning tool; The hardness of the cleaning tool, and at least one of the cleanliness of the cleaning tool; The information processing device according to claim 1 .

8. The cleaning tool status information is remaining life information indicating the remaining life of the cleaning tool; and and at least one piece of cleaning quality information indicating the cleaning quality of the cleaning tool. The information processing device according to claim 1 .

9. An inference device comprising a memory and a processor, The processor: a substrate holder for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; A cleaning tool is rotatably supported, and the cleaning tool is brought into contact with the substrate to clean the substrate. and a cleaning tool cleaning unit that cleans the cleaning tool with a cleaning tool cleaning fluid. The substrate holding part state indicating the state of the substrate holding part as the operating state when the substrate processing apparatus is operated. cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit; and cleaning tool cleaning unit status information indicating the state of the cleaning tool cleaning unit. an information acquisition process for acquiring operation status information including information on the operation status; When the operation status information is acquired in the information acquisition process, Cleaning tool status information indicating the status of the cleaning tool when the substrate processing apparatus is operated in an operating state and executing an inference process to infer the Reasoning device.

10. a substrate holder for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; and rotatably supporting the cleaning tool and bringing the cleaning tool into contact with the substrate to clean the substrate. A substrate cleaning unit and a cleaning tool cleaning unit for cleaning the cleaning tool with a cleaning tool cleaning fluid. A substrate holding unit state indicating the state of the substrate holding unit as the operating state when the processing apparatus is operated. cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit; and cleaning tool cleaning unit status information indicating the state of the cleaning tool cleaning unit. and operating state information including the operating state indicated by the operating state information, and cleaning tool status information indicating the status of the cleaning tool when the cleaning tool was made. a learning data storage unit for storing the learning data sets; By inputting a plurality of sets of the learning data into a learning model, the operating state information and the washing a machine learning unit that causes the learning model to learn correlations with cleaning tool state information; a learned model that stores the learned model in which the correlation is learned by the machine learning unit; and a data storage unit. Machine learning device.

11. a substrate holder for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; and rotatably supporting the cleaning tool and bringing the cleaning tool into contact with the substrate to clean the substrate. A substrate cleaning unit and a cleaning tool cleaning unit for cleaning the cleaning tool with a cleaning tool cleaning fluid. A substrate holding unit state indicating the state of the substrate holding unit as the operating state when the processing apparatus is operated. cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit; and cleaning tool cleaning unit status information indicating the state of the cleaning tool cleaning unit. an information acquisition step of acquiring operating status information including the The operating state information and the operating state indicated by the operating state information are used to determine whether the substrate processing apparatus is operating in the operating state indicated by the operating state information. The correlation between the cleaning tool status information indicating the status of the cleaning tool when it was made and the cleaning tool status information is learned by machine learning. The operating state information acquired in the information acquisition step is input to the learning model. and a state prediction step of predicting the cleaning tool state information based on the operating state information. Ru, Information processing methods.

12. An inference method executed by an inference device having a memory and a processor, The processor: a substrate holder for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; A cleaning tool is rotatably supported and the cleaning tool is brought into contact with the substrate to clean the substrate. and a cleaning tool cleaning unit that cleans the cleaning tool with a cleaning tool cleaning fluid. A substrate holding unit that indicates the state of the substrate holding unit as an operating state when the substrate processing apparatus is operated. status information, cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit, Substrate cleaning unit status information indicating a state of the cleaning tool cleaning unit, and a cleaning tool cleaning unit status indicating a state of the cleaning tool cleaning unit. an information acquisition step of acquiring operating status information including information; When the operation status information is acquired in the information acquisition step, Cleaning tool status information indicating the status of the cleaning tool when the substrate processing apparatus is operated in an operating state an inference step of inferring Reasoning method.

13. a substrate holder for holding a substrate; a cleaning fluid supply unit for supplying a substrate cleaning fluid to the substrate; and rotatably supporting the cleaning tool and bringing the cleaning tool into contact with the substrate to clean the substrate. A substrate cleaning unit and a cleaning tool cleaning unit for cleaning the cleaning tool with a cleaning tool cleaning fluid. A substrate holding unit state indicating the state of the substrate holding unit as the operating state when the processing apparatus is operated. cleaning fluid supply unit status information indicating the status of the cleaning fluid supply unit; and cleaning tool cleaning unit status information indicating the state of the cleaning tool cleaning unit. and operating state information including the operating state indicated by the operating state information, and cleaning tool status information indicating the status of the cleaning tool when the cleaning tool was made. a learning data storage step of storing a plurality of sets of learning data in a learning data storage unit; By inputting a plurality of sets of the learning data into a learning model, the operating state information and the washing a machine learning process for making the learning model learn correlations with cleaning tool state information; The learning model that has learned the correlation through the machine learning process is stored as a learned model. and a learned model storage step of storing the learned model in a memory unit. Machine learning methods.

Images