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

Abstract

The information processing apparatus (5) includes: an information acquisition unit (500) that acquires information on the top ring status, the grinding table status, and the grinding fluid supply nozzle status during chemical mechanical polishing of a substrate performed by a substrate processing apparatus having a grinding table rotatably supporting a grinding pad, a top ring pressing a substrate onto the grinding pad, and a grinding fluid supply nozzle supplying grinding fluid to the grinding pad; and a status prediction unit (501) that, by inputting the polishing conditions acquired by the information acquisition unit (500) into a learning model (10A) that has learned the correlation between the polishing conditions and the substrate status information displaying the status of the substrate undergoing chemical mechanical polishing under the polishing conditions, the substrate status information of the substrate undergoing chemical mechanical polishing under the polishing conditions.

Description

Technical Field

[0001] This invention relates to an information processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method. Prior Technology

[0002] A substrate processing apparatus for performing various processes on substrates such as semiconductor wafers is conventionally known to be a substrate processing apparatus for performing chemical mechanical polishing (CMP). Chemical mechanical polishing, for example, involves rotating a polishing table with a polishing pad while simultaneously supplying polishing fluid (slurry) onto the polishing pad from a polishing fluid supply nozzle. A polishing head, called a top ring, presses the substrate against the polishing pad to chemically and mechanically polish the substrate. At this time, pressure is applied to the substrate based on stress and friction; however, excessive pressure is a factor that reduces the production quality and yield of the substrate (for example, see Patent Document 1, paragraph).

[0003] -

[0004] ), Patent Document 2 (paragraph

[0026] ). [Previous Technical Documents] [Patent Literature]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2014-187110 [Patent Document 2] Japanese Patent Application Publication No. 2005-340431 Summary of the Invention

[0004] (The problem the invention aims to solve)

[0005] For example, by applying pressure to the substrate during chemical mechanical polishing (CMP), the substrate's condition during or after processing can be effectively monitored, or its condition can be predicted at any time before, during, or after processing, thus effectively managing substrate production quality and yield. However, it is impractical to directly install any detector on each substrate to monitor its condition. Furthermore, during CMP processing, the substrate's condition varies depending on the operation of the top ring, polishing table, and polishing fluid supply nozzles within the substrate processing apparatus. These operation states have complex and interactive effects on the substrate system. Therefore, accurately analyzing the impact of each operation state on the substrate's condition is difficult.

[0006] The purpose of this invention is to provide an information processing apparatus, inference apparatus, machine learning apparatus, information processing method, inference method, and machine learning method that can appropriately predict the state of a substrate during or after chemical mechanical polishing. (Technical means to solve the problem)

[0007] To achieve the above objectives, one aspect of the information processing apparatus of the present invention includes: The information acquisition unit acquires grinding processing conditions, including top ring status information (displaying the state of the top ring), grinding table status information (displaying the state of the grinding table), and grinding fluid supply nozzle status information (displaying the state of the grinding fluid supply nozzle), during the chemical mechanical polishing of the substrate performed by the substrate processing apparatus comprising a grinding table having a rotatable support for a grinding pad, a top ring pressing a substrate against the grinding pad, and a grinding fluid supply nozzle supplying grinding fluid to the grinding pad; and grinding processing conditions. The state prediction unit predicts the aforementioned substrate state information of the substrate to be subjected to the aforementioned chemical mechanical polishing treatment by inputting the aforementioned polishing treatment conditions obtained by the aforementioned information acquisition unit into a learning model that has learned the correlation between the aforementioned polishing treatment conditions and the substrate state information that shows the state of the substrate subjected to the aforementioned chemical mechanical polishing treatment by the aforementioned polishing treatment conditions through machine learning. (Compared to the effectiveness of previous technologies)

[0008] When using one aspect of the information processing apparatus of the present invention, since the substrate state information under the grinding conditions, including the top ring state information, grinding table state information, and grinding fluid supply nozzle state information, is input into the learning model, the substrate state information under the grinding conditions can be predicted. Therefore, the substrate state during or after the grinding process can be accurately predicted.

[0009] Other problems, components, and effects beyond those described above will become clear from the form in which the invention is implemented, as will be discussed later. Simple Explanation of the Diagram

[0010] Figure 1 is an overall configuration diagram of an example of a display substrate processing system 1. Figure 2 is a top view of an example of a substrate processing device 2. Figure 3 is a perspective view showing one example of the first to fourth grinding sections 22A to 22D. Figure 4 shows a cross-sectional view of one example of the top ring 221 in the series pattern. Figure 5 is a block diagram of an example of the display substrate processing apparatus 2. Figure 6 shows a hardware configuration diagram of an example of a computer 900. Figure 7 is a data structure diagram showing an example of production history information 30 managed by database device 3. Figure 8 is a data structure diagram showing an example of the grinding test information 31 managed by the database device 3. Figure 9 is a block diagram showing an example of the machine learning device 4 in the first embodiment. Figure 10 shows an example of the first learning model 10A and the first learning data 11A. Figure 11 is a flowchart showing an example of a machine learning method implemented by the machine learning device 4. Figure 12 is a block diagram showing an example of the information processing device 5 in the first embodiment. Figure 13 is a functional illustration of an example of the information processing device 5 in the first embodiment. Figure 14 is a flowchart showing an example of an information processing method implemented by the information processing device 5. Figure 15 is a block diagram showing an example of the second embodiment of the machine learning device 4a. Figure 16 shows an example of the second learning model 10B and the second learning data 11B. Figure 17 is a block diagram showing an example of an information processing device 5a functioning as a second embodiment of the information processing device 5a. Figure 18 is a functional illustration of an example of the information processing device 5a in the second embodiment. Figure 19 is a block diagram showing an example of the third embodiment of the machine learning device 4b. Figure 20 shows an example of the third learning model 10C and the third learning data 11C used to analyze grinding quality. Figure 21 is a block diagram showing an example of an information processing device 5b functioning as a third embodiment of the information processing device 5b. Figure 22 is a functional illustration of an example of the information processing device 5b in the third embodiment. Implementation

[0011] The following describes embodiments of the present invention with reference to the drawings. The necessary scope is shown in the following description for achieving the purpose of the present invention. This description mainly explains the necessary scope, while omissions are in accordance with prior art. (First implementation form)

[0012] Figure 1 is an overall configuration diagram of an example of the substrate processing system 1. The substrate processing system 1 of this embodiment functions as a system that manages a series of substrate processing processes, including chemical mechanical polishing (hereinafter referred to as "polishing process") to flatten the surface of a substrate (hereinafter referred to as "wafer") W such as a semiconductor wafer, and cleaning process to clean the wafer W after polishing process.

[0013] The substrate processing system 1 mainly comprises: a substrate processing device 2, a database device 3, a machine learning device 4, an information processing device 5, and a user terminal device 6. Each device 2-6 is configured, for example, as a general-purpose or special-purpose computer (refer to Figure 6 described later), and is connected to a wired or wireless network 7, capable of transmitting and receiving various types of data (a portion of the data transmission and reception is illustrated by dashed arrows in Figure 1). Furthermore, the number of devices 2-6 and the connection configuration of the network 7 are not limited to the example in Figure 1 and can be appropriately modified.

[0014] The substrate processing apparatus 2 is composed of a plurality of units and serves as an apparatus for performing a series of substrate processing on one or more wafers W, such as loading, polishing, cleaning, drying, film thickness measurement, and unloading. At this time, the substrate processing apparatus 2 refers to the apparatus setting information 265, which is composed of a plurality of apparatus parameters set in each unit, and the substrate processing scheme information 266, which determines the polishing processing conditions for polishing and the cleaning processing conditions for cleaning, and controls the operation of each unit.

[0015] The substrate processing apparatus 2 transmits various reports R to the database apparatus 3, user terminal apparatus 6, etc., according to the operation of each unit. The various reports R include, for example: process information of the wafer W that is identified as the target when substrate processing is performed, device status information that displays the status of each unit when each processing is performed, event information detected by the substrate processing apparatus 2, and operation information of the substrate processing apparatus 2 by users (operators, production managers, maintenance managers, etc.).

[0016] The database device 3 manages production history information 30 regarding the substrate processing of the wafer W used in this production; and grinding test information 31 regarding the grinding process test (hereinafter referred to as "grind test") of the virtual wafer used for testing. In addition, the database device 3 can also store device setting information 265 and substrate processing scheme information 266, which the substrate processing device 2 can also refer to.

[0017] When the substrate processing device 2 processes the wafer W used in this production, the database device 3 receives various reports R from the substrate processing device 2 at any time and records them in the production history information 30, and stores the reports R about substrate processing in the production history information 30.

[0018] The database device 3 receives various reports R (including at least device status information) from the substrate processing device 2 at any time during the polishing test of the virtual wafer used for testing, and records them in the polishing test information 31. It also records the polishing test results by comparing them, and stores the reports R and test results related to the polishing test in the polishing test information 31. The virtual wafer is a template simulating a wafer W. Virtual wafer detectors, such as pressure detectors or temperature detectors, are installed on the surface or inside the virtual wafer to measure the state of the wafer W during the polishing process. The measured values ​​of the virtual wafer detectors are recorded in the polishing test information 31 as test results. Furthermore, the virtual wafer detectors can be located at one or more locations on the substrate surface of the virtual wafer, and can also be planar. In addition, the polishing test can be performed by the substrate processing device 2 used in this production, or by a polishing test device (not shown) that can reproduce the same polishing process as the substrate processing device 2.

[0019] The machine learning device 4 operates as the main body of the learning stage of machine learning. For example, it obtains a portion of the grinding test information 31 from the database device 3 as first learning data 11A, and generates a first learning model 10A for use by the information processing device 5 through machine learning. The first learning model 10A, after learning is completed, is provided to the information processing device 5 via the network 7 and recording media.

[0020] Information processing device 5 operates as the main body of the inference stage of machine learning. Using the first learning model 10A generated by machine learning device 4, it predicts the state of wafer W when the substrate processing device 2 performs polishing processing on wafer W used in this production, and transmits the predicted substrate state information to database device 3 and user terminal device 6, etc. The timing of information processing device 5 predicting substrate state information can be after polishing processing (post-processing prediction), during polishing processing (real-time prediction), or before polishing processing (pre-processing prediction).

[0021] User terminal device 6 is a terminal device used by the user, and can be a fixed device or a portable device. User terminal device 6 accepts various input operations through the display screen of applications, web browsers, etc., and displays various information (e.g., notification events, substrate status information, production history information 30, grinding test information 31, etc.) through the display screen. (Substrate processing apparatus 2)

[0022] Figure 2 is a top view showing an example of a substrate processing apparatus 2. The substrate processing apparatus 2, which is roughly rectangular in plan view, comprises a loading / unloading unit 21, a polishing unit 22, a substrate conveying unit 23, a cleaning unit 24, a film thickness measurement unit 25, and a control unit 26. The loading / unloading unit 21 is separated from the polishing unit 22, the substrate conveying unit 23, and the cleaning unit 24 by a first partition wall 200A, and the substrate conveying unit 23 is separated from the cleaning unit 24 by a second partition wall 200B. (Loading / Unloading Unit)

[0023] The loading / unloading unit 21 includes: first to fourth front loading sections 210A to 210D for loading wafer cassettes (FOUP, etc.) that can hold multiple wafers W in the vertical direction; a transport robot 211 that can move up and down along the storage direction (vertical direction) of the wafers W stored in the wafer cassettes; and a horizontal moving mechanism 212 that moves the transport robot 211 along the arrangement direction (short side direction of the frame 20) of the first to fourth front loading sections 210A to 210D.

[0024] The transfer robot 211 is configured to access the wafer cassettes, substrate transfer unit 23 (specifically, the elevator 232 described later), cleaning unit 24 (specifically, the drying chamber 241 described later), and film thickness measurement unit 25 respectively loaded in the first to fourth front loading sections 210A-210D, and has upper and lower arms (not shown) for transferring wafers W between them. The lower arm is used for transferring wafers W before processing, and the upper arm is used for transferring wafers W after processing. When transferring wafers W between the substrate transfer unit 23 and the cleaning unit 24, the shutter (not shown) provided on the first partition wall 200A is opened and closed. (Grinding unit)

[0025] The polishing unit 22 has first to fourth polishing sections 22A to 22D that perform polishing (planarization) on the wafer W respectively. The first to fourth polishing sections 22A to 22D are arranged along the length of the frame 20.

[0026] Figure 3 is a perspective view showing an example of one of the first to fourth grinding sections 22A to 22D. The first to fourth grinding sections 22A to 22D have the same basic structure and function.

[0027] The first to fourth grinding sections 22A to 22D each include: a grinding table 220 on which a grinding pad 2200 with a grinding surface is mounted; a top ring (grinding head) 221 for holding the wafer W and for pressing the wafer W onto the grinding pad 2200 on the grinding table 220 for grinding; a grinding fluid supply nozzle 222 for supplying grinding fluid to the grinding pad 2200; a dressing device 223 for dressing the grinding surface of the grinding pad 2200; an atomizer 224 for spraying cleaning fluid onto the grinding pad 2200; and an environmental detector 225 for measuring the internal space status of the rack 20 for grinding.

[0028] The grinding table 220 includes: a rotary movement mechanism 220b supported by a grinding table shaft 220a and driven to rotate around its shaft; and a temperature control mechanism 220c for adjusting the surface temperature of the grinding pad 2200.

[0029] The top ring 221 includes: a rotary movement mechanism 221c supported by a top ring shaft 221a that can move in the vertical direction and drives the top ring 221 to rotate around its axis; an up-down movement mechanism 221d that moves the top ring 221 in the vertical direction; and a rocking movement mechanism 221e that forms the support shaft 221b as the center of rotation and causes the top ring 221 to rotate (rock).

[0030] The grinding fluid supply nozzle 222 includes: a rocking and moving mechanism 222b supported by a support shaft 222a, which forms the support shaft 222a as the center of rotation and causes the grinding fluid supply nozzle 222 to rotate; a flow regulating part 222c for regulating the flow rate of the grinding fluid; and a temperature regulating mechanism 222d for regulating the temperature of the grinding fluid. The grinding fluid system may contain grinding slurry (slurry) or pure water, or may contain a chemical solution, or may contain a dispersant added to the grinding slurry.

[0031] The dresser 223 includes: a rotary movement mechanism 223c supported by a dresser shaft 223a that can move in the vertical direction and drives the dresser 223 to rotate around its shaft; an up-down movement mechanism 223d that moves the dresser 223 in the vertical direction; and a rocking movement mechanism 223e that forms the support shaft 223b as the center of rotation and causes the dresser 223 to rotate.

[0032] The atomizer 224 includes: a rocking and moving mechanism 224b supported by a support shaft 224a, which forms the rotation center of the support shaft 224a and causes the atomizer 224 to rotate; and a flow regulating part 224c for regulating the flow rate of the cleaning fluid. The cleaning fluid system is a mixture of liquid (e.g., pure water) and gas (e.g., nitrogen) or liquid (e.g., pure water).

[0033] The environmental detector 225 consists of detectors disposed within the internal space of the rack 20, such as: a temperature detector 225a for measuring the temperature of the internal space; a humidity detector 225b for measuring the humidity of the internal space; and a pressure detector 225c for measuring the air pressure of the internal space. Additionally, the environmental detector 225 may also include a camera (image detector) capable of capturing images of the surface of the polishing pad 2200 during or before the polishing process.

[0034] Furthermore, Figure 3 omits the specific configurations of the rotary movement mechanisms 220b, 221c, 223c, the vertical movement mechanisms 221d, 223d, and the rocking movement mechanisms 221e, 222b, 223e, 224b. Instead, it is composed of appropriately combined modules for generating driving force, such as motors and air cylinders; driving force transmission mechanisms such as linear guides, ball screws, gears, belts, couplers, and bearings; and detectors such as linear detectors, encoder detectors, limit detectors, and torque detectors. Figure 3 also omits the specific configurations of the flow regulation units 222c and 224c. Instead, it is composed of appropriately combined modules for regulating fluid, such as pumps, valves, and regulators; and detectors such as flow detectors, pressure detectors, and liquid level detectors. Figure 3 omits the specific configuration of the temperature control mechanism sections 220c and 222d. However, it is composed of a module for temperature regulation (contact or non-contact) appropriately combined with a heater, heat exchanger, etc., and a detector such as a temperature detector and a current detector.

[0035] Figure 4 shows a cross-sectional view of one example of the top ring 221. The top ring 221 includes: a top ring body 2210 mounted on the top ring shaft 221a; a roughly disc-shaped carrier 2211 housed in the top ring body 2210; a diaphragm 2212 disposed on the underside of the carrier 2211 to press the wafer W against the polishing pad 2200; a roughly annular retaining ring 2213 disposed on the outer periphery of the carrier 2211 and the diaphragm 2212 to directly press the polishing pad 2200; and a retaining ring airbag 2214 disposed between the top ring body 2210 and the retaining ring 2213 to press the retaining ring 2213 against the polishing pad 2200.

[0036] The diaphragm 2212 is formed of an elastic membrane and has a plurality of concentric partition walls 2212e inside, forming first to fourth diaphragm pressure chambers 2212a to 2212d arranged concentrically from the center of the top ring body 2210 outwards. Furthermore, the diaphragm 2212 has a plurality of holes 2212f on its underside for adsorbing the wafer W, thus functioning to hold the substrate holding surface of the wafer W. The retaining ring airbag 2214 is formed of an elastic membrane and has a retaining ring pressure chamber 2214a inside. Additionally, the configuration of the top ring 221 can be appropriately modified; it can be equipped with a pressure chamber that presses down on the entire carrier 2211. The number and shape of the diaphragm pressure chambers in the diaphragm 2212 can also be appropriately modified, as can the number and arrangement of the adsorption holes 2212f. Alternatively, the diaphragm 2212 may not have adsorption holes 2212f.

[0037] The first to fourth diaphragm pressure chambers 2212a~2212d are respectively connected to the first to fourth flow paths 2216A~2216D, and the retaining ring pressure chamber 2214a is connected to the fifth flow path 2216E. The first to fifth flow paths 2216A~2216E are connected to the outside via a rotary joint 2215 located on the top ring shaft 221a, and branch into first branch flow paths 2217A~2217E and second branch flow paths 2218A~2218E respectively. Pressure detectors PA~PE are installed in the first to fifth flow paths 2216A~2216E respectively. The first branch flow paths 2217A~2217E are connected to the gas supply source GS of the pressurized fluid (air, nitrogen, etc.) via valves V1A~V1E, flow detectors FA~FE, and pressure regulators RA~RE. The second branching paths 2218A~2218E are connected to the vacuum source VS via valves V2A~V2E respectively, and can be connected to the atmosphere via valves V3A~V3E.

[0038] The wafer W is held under the top ring 221 and moved to the designated polishing position on the polishing table 220. The polishing surface of the polishing pad 2200, supplied with polishing fluid from the polishing fluid supply nozzle 222, is then polished by pressing it against the top ring 221. At this time, the top ring 221, through independent pressure regulators RA~RE, adjusts the pressing force of the pressure fluid supplied to the first to fourth diaphragm pressure chambers 2212a~2212d to press the wafer W against the polishing pad 2200, and adjusts the pressing force of the pressure fluid supplied to the retaining ring pressure chamber 2214a to press the retaining ring 2213 against the polishing pad 2200. The pressure of the pressure fluid supplied to the first to fourth diaphragm pressure chambers 2212a~2212d and the retaining ring pressure chamber 2214a is measured by pressure detectors PA~PE, and the flow rate of the pressurized gas is measured by flow detectors FA~FE. (Substrate transport unit)

[0039] As shown in FIG2, the substrate transport unit 23 includes: first and second linear conveyors 230A and 230B that can move horizontally along the arrangement direction of the first to fourth grinding sections 22A to 22D (the length direction of the frame 20); a swing conveyor 231 disposed between the first and second linear conveyors 230A and 230B; a lift 232 disposed on the side of the loading / unloading unit 21; and a temporary stage 233 for the wafer W disposed on the side of the cleaning unit 24.

[0040] The first linear conveyor 230A is configured adjacent to the first and second polishing sections 22A and 22B, and is a mechanism for conveying the wafer W between four conveying positions (numbered sequentially from the loading / unloading unit 21 to the fourth conveying positions TP1 to TP4). The second conveying position TP2 is the position where the wafer W is transferred to the first polishing section 22A, and the third conveying position TP3 is the position where the wafer W is transferred to the second polishing section 22B.

[0041] The second linear conveyor 230B is configured adjacent to the third and fourth polishing sections 22C and 22D, and is a mechanism for transporting the wafer W between three transport positions (numbered fifth to seventh transport positions TP5~TP7 sequentially from the loading / unloading unit 21 side). The sixth transport position TP6 is the position for transferring the wafer W to the third polishing section 22C, and the seventh transport position TP7 is the position for transferring the wafer W to the fourth polishing section 22D.

[0042] A swing conveyor 231 is configured adjacent to the fourth and fifth transport positions TP4 and TP5, and has an arm that can move between the fourth and fifth transport positions TP4 and TP5. The swing conveyor 231 is a mechanism for transferring wafer W between the first and second linear conveyors 230A and 230B, and for temporarily placing wafer W on a temporary stage 233. An elevator 232 is configured adjacent to the first transport position TP1, and is a mechanism for transferring wafer W between the elevator and the transport robot 211 of the loading / unloading unit 21. During wafer W transfer, a shutter (not shown) located on the first partition wall 200A is opened and closed. (Cleaning Unit)

[0043] As shown in FIG2, the cleaning unit 24 includes: first and second cleaning chambers 240A and 240B for cleaning wafer W using cleaning equipment; a drying chamber 241 for drying wafer W; and first and second transport chambers 242A and 242B for transporting wafer W. Each chamber of the cleaning unit 24 is arranged along the first and second linear conveyors 230A and 230B in a divided state, for example, in the following order: first cleaning chamber 240A, first transport chamber 242A, second cleaning chamber 240B, second transport chamber 242B, and drying chamber 241 (in the order away from loading / unloading unit 21). (Film thickness measurement unit)

[0044] The film thickness measurement unit 25 is a measuring instrument for measuring the film thickness of the wafer W before or after polishing, and is composed of, for example, an optical film thickness measuring instrument or an eddy current film thickness measuring instrument. The transfer of wafers W between each film thickness measurement module is carried out by a transfer robot 211. (Control unit)

[0045] Figure 5 is a block diagram of an example of the display substrate processing apparatus 2. The control unit 26 is electrically connected to each of the units 21 to 25 and functions as a control unit that oversees and controls each of the units 21 to 25. Hereinafter, the control system (module, detector, sequencer) of the polishing unit 22 will be used as an example for explanation. However, since the basic structure and function of the other units 21, 23 to 25 are also the same, the explanation will be omitted.

[0046] The grinding unit 22 includes: a plurality of modules 2271 to 227r respectively disposed in each sub-unit of the grinding unit 22 (e.g., grinding table 220, top ring 221, grinding fluid supply nozzle 222, dressing device 223, atomizer 224, etc.) and becoming the controlled objects; a plurality of detectors 2281 to 228s respectively disposed in the plurality of modules 2271 to 227r to detect and control the data (detection values) required for controlling each module 2271 to 227r; and a sequencer 229 that controls the operation of each module 2271 to 227r based on the detection values ​​of each detector 2281 to 228s.

[0047] The detectors 2281-228s of the grinding unit 22 include, for example: a detector for detecting the rotational speed of the grinding table 220; a detector for detecting the rotational torque of the grinding table 220; a detector for detecting the surface temperature of the grinding pad 2200; a detector for detecting the rotational speed of the top ring 221; a detector for detecting the rotational torque of the top ring 221; a detector for detecting the rocking position of the top ring 221; a detector for detecting the rocking torque of the top ring 221; a detector for detecting the height of the top ring 221; a detector for detecting the lifting torque of the top ring 221; and a detector for detecting the first to fourth diaphragms. Detectors for the pressure (positive and negative pressure) in pressure chambers 2212a-2212d and buckle pressure chamber 2214a; detectors for detecting the flow rate of pressure fluid supplied to the first to fourth diaphragm pressure chambers 2212a-2212d and buckle pressure chamber 2214a; detectors for detecting the flow rate of grinding fluid supplied from grinding fluid supply nozzle 222; detectors for detecting the temperature of grinding fluid; detectors for detecting the shaking position of grinding fluid supply nozzle 222, which can be changed to the dripping position of grinding fluid supply nozzle 222; and environmental detector 225, etc.

[0048] The control unit 26 includes a control unit 260, a communication unit 261, an input unit 262, an output unit 263, and a memory unit 264. The control unit 26 may be configured as, for example, a general-purpose or special-purpose computer (see Figure 6 described later).

[0049] The communication unit 261 is connected to the network 7 and functions as a communication interface for transmitting and receiving various data. The input unit 262 accepts various input operations, and the output unit 263 outputs various information through a display screen, signal tower lights, and buzzer sounds, thus functioning as a user interface.

[0050] The memory unit 264 stores various programs (operating system (OS), applications, web browsers, etc.) and data (device setting information 265, substrate processing scheme information 266, etc.) used when the substrate processing device 2 is in operation. The device setting information 265 and substrate processing scheme information 266 are data that can be edited by the user through the display screen.

[0051] The control unit 260 obtains the detection values ​​of a plurality of detectors 2181~218q, 2281~228s, 2381~238u, 2481~248w, 2581~258y (hereinafter referred to as the "detector group") via a plurality of sequencers 219, 229, 239, 249, 259 (hereinafter referred to as the "detector group"), and performs a series of substrate processing such as loading, grinding, cleaning, drying, film thickness measurement, and unloading by coordinating the operation of a plurality of modules 2171~217p, 2271~227r, 2371~237t, 2471~247v, 2571~257x (hereinafter referred to as the "module group"). (Hardware composition of each device)

[0052] Figure 6 is a hardware configuration diagram showing an example of a computer 900. The control unit 26 of the board processing device 2, the database device 3, the machine learning device 4, the information processing device 5, and the user terminal device 6 are respectively configured by a general-purpose or special-purpose computer 900.

[0053] As shown in Figure 6, the computer 900 mainly comprises: a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication I / F (interface) section 922, an external device I / F section 924, an I / O (input / output) device I / F section 926, and a media input / output section 928. Furthermore, the above-mentioned components may be appropriately omitted depending on the intended use of the computer 900.

[0054] The processor 912 consists of one or more arithmetic processing units (CPU (Central Processing Unit)), MPU (Micro-processing Unit)), DSP (Digital Signal Processor) and GPU (Graphics Processing Unit), and operates as the control unit overseeing the entire computer 900. The memory 914 stores various data and programs 930, and is composed of volatile memory (DRAM, SRAM, etc.) that performs the functions of main memory, and non-volatile memory (ROM), flash memory, etc.

[0055] Input device 916, for example, comprises a keyboard, mouse, numeric keypad, electronic pen, etc., and functions as an input unit. Output device 917, for example, comprises a voice (sound) output device, vibration device, etc., and functions as an output unit. Display device 918, for example, comprises a liquid crystal display, organic EL display, electronic paper, projector, etc., and functions as a display unit. Input device 916 and display device 918, such as a touch panel display, can also be integrated. Storage device 920, for example, comprises an HDD, SSD (Solid State Drive), etc., and functions as a memory unit. Storage device 920 stores various data required for the operation system and program 930 to execute.

[0056] The communication I / F unit 922 connects to networks 940, such as the Internet and enterprise networks (or network 7 in Figure 1), via wired or wireless means, and functions as a communication unit for transmitting and receiving data with other computers according to specified communication standards. The external device I / F unit 924 connects to external devices 950, such as cameras, printers, scanners, and readers / writers, via wired or wireless means, and functions as a communication unit for transmitting and receiving data with external devices 950 according to specified communication standards. The I / O device I / F unit 926 connects to I / O devices 960, such as various detectors and actuators, and functions as a communication unit for transmitting and receiving various signals and data, such as detector detection signals and actuator control signals, with I / O devices 960. The media input / output unit 928 is composed of a drive device such as a digital optical disc drive (DVD drive) or an optical disc drive (CD drive), and reads and writes data to media (permanent memory media) 970 such as DVDs and CDs.

[0057] In the computer 900 with the above-described configuration, the processor 912 calls the memory 914 to execute the program 930 stored in the storage device 920, and controls various parts of the computer 900 via the bus 910. Alternatively, the program 930 can also be stored in the memory 914 instead of the storage device 920. The program 930 can also be recorded on the media 970 as an installable or executable file and provided to the computer 900 via the media input / output unit 928. The program 930 can also be provided to the computer 900 via the communication I / F unit 922 and downloaded via the network 940. Furthermore, the computer 900 can also implement the various functions achieved by the processor 912 executing the program 930 using hardware such as an FPGA (FPGA, Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit).

[0058] Computer 900 can be any type of electronic device, such as a stationary computer or a portable computer. Computer 900 can also be a client computer, a server computer, or a cloud computer. Computer 900 can also be used with devices other than devices 2 to 6. (Production history information 30)

[0059] Figure 7 is a data structure diagram showing an example of the production history information 30 managed by the database device 3. The production history information 30 is a table that categorizes and records the reports R obtained during substrate processing of the wafers W used in this production. For example, it includes: a wafer history table 300 for each wafer W; and a grinding history table 301 for equipment status information during grinding processing. In addition to the above, the production history information 30 also includes: a cleaning history table for equipment status information during cleaning processing; an event history table for event information; and an operation history table for operation information, etc., but detailed descriptions are omitted.

[0060] The records in the wafer history table 300 include, for example, the wafer ID, box number, batch number, start time, end time, and cell ID for each process. Figure 7 illustrates the grinding and cleaning processes; however, other processes are also recorded in the same way.

[0061] The records in the grinding history form 301 include, for example, the registered wafer ID, top ring status information, grinding table status information, grinding fluid supply nozzle status information, and equipment environment information.

[0062] The top ring status information displays information about the status of the top ring 221 during the grinding process. The top ring status information may be, for example, the detection values ​​of each detector (or the instruction values ​​for each module) sampled at specified time intervals by the detector group (or module group) of the top ring 221.

[0063] The grinding station status information displays information about the status of the grinding station 220 during the grinding process. The grinding station status information may be, for example, the detection values ​​of each detector (or the command values ​​for each module) sampled at specified time intervals by the detector group (or module group) of the grinding station 220.

[0064] The grinding fluid supply nozzle status information displays information about the status of the grinding fluid supply nozzle 222 during the grinding process. The grinding fluid supply nozzle status information may be, for example, the detection values ​​(or command values ​​for each module) of each detector group (or module group) of the grinding fluid supply nozzle 222 sampled at specified time intervals.

[0065] The device internal environment information displays information about the internal space status of the substrate processing apparatus 2 formed by the rack 20. The internal space of the substrate processing apparatus 2 is the space where the polishing unit 22 is arranged, and the device internal environment information is, for example, the detection values ​​of each detector sampled by the environmental detector 225 at specified time intervals.

[0066] By referring to the polishing history table 301, the time series data of each detector (or the time series data of each module) can be extracted as the device status of the substrate processing device 2 when polishing the wafer W identified by the wafer ID. (Grinding Test Information 31)

[0067] Figure 8 is a data structure diagram showing an example of the polishing test information 31 managed by the database device 3. The polishing test information 31 includes a polishing test table 310 that categorizes and logs the reports R and test results obtained when performing polishing tests using a virtual wafer.

[0068] The records in Grinding Test Table 310 include, for example, the test ID, top ring status information, grinding table status information, grinding fluid supply nozzle status information, equipment internal environment information, and test result information. The top ring status information, grinding table status information, grinding fluid supply nozzle status information, and equipment internal environment information in Grinding Test Table 310 display the status of each part during the grinding test. Since its data structure is the same as that in Grinding History Table 301, detailed explanations are omitted.

[0069] The test result information displays the state of the virtual wafer during the grinding process in the grinding test. The test result information is generated by sampling the detection values ​​of the virtual wafer detector at specified time intervals using the virtual wafer detector. Figure 8 shows the test result information for a virtual wafer detector with three temperature detectors and three pressure detectors, specifically the detection values ​​T1~T3 and P1~P3 at various times t1, t2, ..., tm, ..., tn during the grinding process from start to finish. Alternatively, the test result information can be the detection values ​​of the virtual wafer detector, or it can be the image processing results obtained by image processing of images taken at specified time intervals using a camera mounted on an optical microscope or scanning electron microscope (SEM), and the experimental analysis results analyzed by the experimenter. In addition, the test results information can be collected from a single grinding test conducted continuously from the start of the grinding process to the end, or it can be collected by repeatedly conducting grinding tests from the start of the grinding process to the end of the specified time by gradually extending the specified time.

[0070] By referring to the polishing test table 310, in the polishing test identified by the test ID, the time series data of each detector (or the time series data of each module) showing the state of the polishing unit 22 when polishing the virtual wafer, and the time series data of the virtual wafer detector showing the state of the virtual wafer at that time can be extracted. (Machine learning device 4)

[0071] Figure 9 is a block diagram showing an example of the machine learning device 4 in the first embodiment. The machine learning device 4 includes: a control unit 40, a communication unit 41, a learning data memory unit 42, and a learning completed model memory unit 43.

[0072] The control unit 40 performs the functions of the learning data acquisition unit 400 and the machine learning unit 401. The communication unit 41 connects to external devices (e.g., board processing device 2, database device 3, information processing device 5, user terminal device 6, polishing test device (not shown)) via the network 7, and performs the function of a communication interface for transmitting and receiving various data.

[0073] The learning data acquisition unit 400 connects to an external device via the communication unit 41 and the network 7 to acquire first learning data 11A, which consists of polishing processing conditions as input data and substrate status information as output data. The first learning data 11A is used as teacher data (training data), verification data, and test data in teacher-led learning. Furthermore, the substrate status information is used as data for answer tags in teacher-led learning.

[0074] The learning data memory unit 42 is a database containing multiple arrays of the first learning data 11A acquired by the learning data acquisition unit 400. Furthermore, the specific structure of the database constituting the learning data memory unit 42 can be appropriately designed.

[0075] The machine learning unit 401 performs machine learning using a complex array of first learning data 11A stored in the learning data memory unit 42. That is, the machine learning unit 401 inputs the first learning data 11A into the first learning model 10A in a complex array, and generates a first learning model 10A that has completed learning by learning the correlation between the polishing conditions and substrate state information contained in the first learning data 11A.

[0076] The learning completion model memory unit 43 is a database that stores the first learning model 10A (specifically, the adjusted weighted parameter group) generated by the machine learning unit 401. The first learning model 10A stored in the learning completion model memory unit 43 is provided to a real system (e.g., information processing device 5) via a network 7 and recording media. Figure 9 shows the learning data memory unit 42 and the learning completion model memory unit 43 as separate memory units; however, they can also be configured as a single memory unit.

[0077] Furthermore, the number of first learning models 10A stored in the learning model memory unit 43 is not limited to one. For example, it can store mechanical learning methods, types of wafers W (size, thickness, film type, etc.), differences in the structure and material of the top ring 221, types of diaphragms 2212, types of retaining rings 2213, types of polishing pads 2200, types of polishing fluids, types of data included in polishing processing conditions, types of data included in substrate state information, etc. Multiple learning models with different conditions can also be stored. In this case, multiple types of learning data with data composition corresponding to multiple learning models with different conditions can be stored in the learning data memory unit 42.

[0078] Figure 10 shows 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 consists of polishing processing conditions and substrate state information.

[0079] The polishing processing conditions constituting the first learning data 11A include: top ring status information showing the status of the top ring 221 in the wafer W polished by the substrate processing apparatus 2; polishing table status information showing the status of the polishing table 220; and polishing fluid supply nozzle status information showing the status of the polishing fluid supply nozzle 222.

[0080] The grinding process conditions include at least one of the following top ring status information: the rotational speed of top ring 221, the rotational torque of top ring 221, the rocking position of top ring 221, the rocking torque of top ring 221, the height of top ring 221, the lifting torque of top ring 221, the pressure in diaphragm pressure chambers 2212a~2212d (diaphragm pressure), the flow rate of pressurized fluid supplied to diaphragm pressure chambers 2212a~2212d (diaphragm flow rate), the condition of diaphragm 2212, the pressure in retaining ring pressure chamber 2214a (retaining ring airbag pressure), the flow rate of pressurized fluid supplied to retaining ring pressure chamber 2214a (retaining ring airbag flow rate), and the condition of retaining ring 2213. The condition of diaphragm 2212 is expressed, for example, by surface properties, expansion and contraction, thickness, etc., and is set according to the usage status of diaphragm 2212 (usage time, whether it has been replaced), top ring status information, grinding table status information, etc. The condition of the retaining ring 2213 can be represented by factors such as surface properties, flatness, thickness, cross-sectional shape, cutting and contamination of the inner circumference, and is set according to the usage status of the retaining ring 2213 (usage time, whether it has been replaced), top ring status information, and grinding table status information. The condition of the diaphragm 2212 and the retaining ring 2213 may also change over time during the grinding process.

[0081] The grinding table status information included in the grinding process conditions includes at least one of the following: the rotational speed of the grinding table 220, the rotational torque of the grinding table 220, the condition of the grinding pad 2200, and the surface temperature of the grinding pad 2200. The condition of the grinding pad 2200 is expressed, for example, by surface properties, flatness, cleanliness, and wettability, and is set based on the usage of the grinding pad 2200 (usage time, whether it has been repaired, whether it has been replaced, and images of the surface of the grinding pad 2200), top ring status information, and grinding table status information. The condition of the grinding pad 2200 may also be something that changes over time during the grinding process.

[0082] The grinding fluid supply nozzle status information included in the grinding process conditions includes at least one of the following: the flow rate of the grinding fluid, the dripping position of the grinding fluid, and the temperature of the grinding fluid. Alternatively, in the case of multiple types of grinding fluids in the grinding flow system (e.g., grinding slurry, pure water, chemical solution, dispersant, etc.), it is sufficient to include at least one of each flow rate, dripping position, and temperature. For example, in the case of grinding slurry and pure water in the grinding flow system, it is sufficient to include at least one of the following: the flow rate of the grinding slurry, the dripping position of the grinding slurry, and the temperature of the grinding slurry; the flow rate of pure water, the dripping position of pure water, and the temperature of pure water.

[0083] In addition, the grinding conditions may further include information on the internal environment of the device that displays the spatial environment in which the grinding process is carried out. The internal environment information included in the grinding conditions includes at least one of the temperature, humidity, and air pressure of the internal space formed by the rack 20.

[0084] The substrate state information constituting the first learning data 11A displays information about the state of the wafer W undergoing polishing processing according to polishing processing conditions. In this embodiment, the substrate state information displays pressure information for at least one of the mechanical stress and thermal stress applied to the wafer W. The pressure information may, for example, display the instantaneous pressure value during the polishing processing period from start to finish (the time required to polish each wafer), or the cumulative pressure value during the target period from start to target time (any period below the polishing processing period), or the surface distribution of pressure applied to the substrate surface of the wafer W.

[0085] The learning data acquisition unit 400 obtains the first learning data 11A by referring to the grinding test information 31 and, when necessary, accepting input operations from the user through the user terminal device 6. For example, the learning data acquisition unit 400 obtains the top ring status information, grinding table status information, and grinding fluid supply nozzle status information (time series data of each detector of the top ring 221, grinding table 220, and grinding fluid supply nozzle 222) as grinding processing conditions by referring to the grinding test table 310 of the grinding test information 31 and the grinding test table 310.

[0086] Furthermore, this embodiment describes the acquisition of grinding processing conditions as time-series data of the detector group shown in FIG10. However, it can also be appropriately changed depending on the configuration of the grinding unit 22 (especially the top ring 221, the grinding table 220, and the grinding fluid supply nozzle 222). In addition, the grinding processing conditions can also use the command value of the module, the parameters converted from the detection value of the detector or the command value of the module, or the parameters calculated based on the detection values ​​of multiple detectors. Moreover, the grinding processing conditions can also be acquired as time-series data of the entire grinding processing period, as time-series data of a target period of a part of the grinding processing period, or as time data of a specific target time. As mentioned above, when changing the definition of the grinding processing conditions, it is only necessary to appropriately change the data configuration of the input data in the first learning model 10A and the first learning data 11A.

[0087] Furthermore, the learning data acquisition unit 400 obtains test result information (time series data of the virtual wafer detectors on the virtual wafer (Fig. 8)) when performing a polishing test with the same test ID by referring to the polishing test table 310 of the polishing test information 31, as substrate state information corresponding to the above-mentioned polishing processing conditions. At this time, each time series data of the pressure detector corresponds to the instantaneous value of mechanical stress, and each time series data of the temperature detector corresponds to the instantaneous value of thermal stress. In addition, if multiple virtual wafer detectors are distributed on the substrate surface of the virtual wafer, or if it is a virtual wafer detector that can measure surface shape, the learning data acquisition unit 400 obtains the measurement values ​​or surface shape measurement values ​​at multiple locations as instantaneous values ​​at the target time. In addition, the learning data acquisition unit 400 obtains the cumulative value of mechanical stress up to the target period by accumulating the time series data of pressure data included in the target period, and obtains the cumulative value of thermal stress up to the target period by accumulating the time series data of temperature data included in the target period.

[0088] Furthermore, this embodiment describes the substrate state information as the instantaneous and cumulative values ​​of mechanical stress and thermal stress shown in Figure 10, although it may include at least one of them. Additionally, mechanical stress and thermal stress can also be calculated by substituting the measurement values ​​of the virtual wafer detector into a specified calculation formula. Moreover, when the polishing processing conditions are obtained as time-series data for the entire polishing process or as time-series data for a specific period within a part of the polishing process, the substrate state information can also be obtained as time-series data for the entire polishing process or as time-series data for the specific period, or as time-series data for the polishing process end time or the specific time. Furthermore, when the polishing processing conditions are obtained as time-series data for a specific specific time, the substrate state information can also be obtained as time-series data for that specific time. As described above, when changing the definition of the substrate state information, it is only necessary to appropriately change the data composition of the output data in the first learning model 10A and the first learning data 11A.

[0089] The first learning model 10A, for example, employs a neural network-like structure and includes: an input layer 100, an intermediate layer 101, and an output layer 102. Synapses (not illustrated) connecting each neuron are laid between each layer, each synapse corresponding to a weight. The weighted parameter group, composed of the weights of each synapse, is adjusted through machine learning.

[0090] The input layer 100 has neurons corresponding to the number of grinding processing conditions as input data, and each value of the grinding processing conditions is input into each neuron. The output layer 102 has neurons corresponding to the number of substrate state information as output data, and the prediction result (inference result) of the substrate state information on the grinding processing conditions is output as output data. When the first learning model 10A is composed of a regression model, the substrate state information is output as a value normalized within a specified range (e.g., 0~1). Furthermore, when the first learning model 10A is composed of a classification model, the substrate state information is output as a score (reliability) for each level, as a value normalized within a specified range (e.g., 0~1). (Mechanical learning methods)

[0091] Figure 11 is a flowchart showing an example of a machine learning method implemented by the machine learning device 4.

[0092] First, in step S100, the learning data acquisition unit 400 acquires a desired amount of first learning data 11A from the grinding test information 31, etc., and stores the acquired first learning data 11A in the learning data memory unit 42 as preparation for starting machine learning. The amount of first learning data 11A prepared at this time can be set by considering the inference accuracy required by the final obtained first learning model 10A.

[0093] Next, in step S110, the machine learning unit 401 prepares a first learning model 10A before learning in order to start machine learning. At this time, the first learning model 10A before learning is composed of a neural network model as illustrated in FIG10, and the weights of each synapse are set to initial values.

[0094] Next, in step S120, the machine learning unit 401 randomly obtains a set of first learning data 11A from the complex array of first learning models 10A stored in the learning data memory unit 42.

[0095] Next, in step S130, the machine learning unit 401 inputs the polishing processing conditions (input data) contained in a set of first learning data 11A into the input layer 100 of the first learning model 10A before (or during) learning. As a result, substrate state information (output data) is output from the output layer 102 of the first learning model 10A as an inference result. However, this output data is generated using the first learning model 10A before (or during) learning. Therefore, the output data output as an inference result from the state before (or during) learning displays information different from the substrate state information (answer label) contained in the first learning data 11A.

[0096] Next, in step S140, the machine learning unit 401 compares the substrate state information (answer tags) included in the first set of learning data 11A obtained in step S120 with the substrate state information (output data) output from the output layer as a reasoning result in step S130, and performs machine learning by performing a process of adjusting the weights of each synapse (backpropagation). In this way, the machine learning unit 401 enables the first learning model 10A to learn the correlation between the polishing processing conditions and the substrate state information.

[0097] Secondly, in step S150, the machine learning unit 401 determines, for example, whether the specified learning termination condition is met based on the evaluation value of the error function between the substrate state information (answer tag) contained in the first learning data 11A and the substrate state information (output data) output as a result of inference; and the remaining quantity of the unlearned first learning data 11A stored in the learning data memory unit 42.

[0098] In step S150, if the machine learning unit 401 determines that the learning termination condition is not met and continues machine learning (No in step S150), it returns to step S120 and performs the processes of steps S120 to S140 multiple times on the first learning model 10A that is being learned, using the unlearned first learning data 11A. Alternatively, if in step S150 the machine learning unit 401 determines that the learning termination condition is met and ends machine learning (Yes in step S150), it proceeds to step S160.

[0099] Then, in step S160, the machine learning unit 401 stores the first learning model 10A (adjusted weighted parameter group) generated by adjusting the weights corresponding to each synapse in the learning completion model memory unit 43, and ends the series of machine learning methods shown in FIG11. In the machine learning method, step S100 is equivalent to the learning data memory process, steps S110 to S150 are equivalent to the machine learning process, and step S160 is equivalent to the learning completion model memory process.

[0100] As described above, when the machine learning device 4 and machine learning method of this embodiment are used, a first learning model 10A can be provided from the grinding processing conditions, including top ring state information, grinding table state information and grinding fluid supply nozzle state information, to predict (infer) the state of the wafer W, showing the substrate state information. (Information Processing Device 5)

[0101] Figure 12 is a block diagram showing an example of the information processing apparatus 5 in the first embodiment. Figure 13 is a functional diagram showing an example of the information processing apparatus 5 in the first embodiment. The information processing apparatus 5 includes: a control unit 50, a communication unit 51, and a learning completion model memory unit 52.

[0102] The control unit 50 performs the functions of the information acquisition unit 500, the status prediction unit 501, and the output processing unit 502. The communication unit 51 connects to external devices (e.g., the board processing device 2, the database device 3, the machine learning device 4, and the user terminal device 6) via the network 7, and performs the function of a communication interface for transmitting and receiving various types of data.

[0103] The information acquisition unit 500 connects to an external device via the communication unit 51 and the network 7 to obtain grinding processing conditions, including top ring status information, grinding table status information, and grinding fluid supply nozzle status information.

[0104] For example, in the case of "post-processing prediction" of substrate condition information for a wafer W that has already undergone polishing, the information acquisition unit 500 obtains the top ring condition information, polishing table condition information, and polishing fluid supply nozzle condition information during the polishing process of the wafer W by referring to the polishing history table 301 in the production history information 30 as polishing processing conditions. In the case of "real-time prediction processing" of substrate condition information for the wafer W during polishing, the information acquisition unit 500 obtains the top ring condition information, polishing table condition information, and polishing fluid supply nozzle condition information during the polishing process of the wafer W by receiving reports R on substrate condition information from the substrate processing apparatus 2 that performs the polishing process at any time. In the case of "pre-prediction processing" of substrate state information for wafer W before polishing, the information acquisition unit 500 receives substrate processing scheme information 266 from the predetermined substrate processing apparatus 2 for polishing, and obtains top ring state information, polishing table state information and polishing fluid supply nozzle state information as polishing conditions by simulating the apparatus state information when polishing unit 22 operates according to the substrate processing scheme information 266.

[0105] As described above, the state prediction unit 501 predicts the substrate state information (in this embodiment, stress information) of the wafer W that is being polished under the polishing conditions by inputting the polishing processing conditions obtained by the information acquisition unit 500 into the first learning model 10A.

[0106] The learning completion model memory unit 52 is a database of the first learning model 10A that has been learned and used by the state prediction unit 501. Furthermore, the number of first learning models 10A stored in the learning completion model memory unit 52 is not limited to one. For example, it can store the machine learning method, the type of wafer W (size, thickness, film type, etc.), the mechanism and material differences of the top ring 221, the type of diaphragm 2212, the type of retaining ring 2213, the type of polishing pad 2200, the type of polishing fluid, the types of data included in the polishing processing conditions, the types of data included in the substrate state information, etc. Multiple learning completion models with different conditions can also be stored and selectively used. In addition, the learning completion model memory unit 52 can also be replaced by the memory unit of an external computer (e.g., a server computer or a cloud computer). In this case, the state prediction unit 501 only needs to access the external computer.

[0107] The output processing unit 502 performs output processing for outputting the substrate status information generated by the status prediction unit 501. For example, the output processing unit 502 can also transmit the substrate status information to the user terminal device 6 and display a screen based on the substrate status information on the user terminal device 6, or it can transmit the substrate status information to the database device 3 and register the substrate status information in the production history information 30. (Information Processing Methods)

[0108] Figure 14 is a flowchart showing an example of the information processing method implemented by the information processing device 5. The following is an example of the operation when a user operates the user terminal device 6 to perform "post-processing" of substrate status information on a specific wafer W.

[0109] First, in step S200, when the user inputs the wafer ID of the wafer W to the user terminal device 6, the user terminal device 6 transmits the wafer ID to the information processing device 5.

[0110] Next, in step S210, the information acquisition unit 500 of the information processing device 5 receives the wafer ID transmitted in step S200. In step S211, the information acquisition unit 500 uses the wafer ID received in step S210 and refers to the grinding history table 301 of the production history information 30 to obtain the grinding conditions for grinding the wafer W identified by the wafer ID.

[0111] Secondly, in step S220, the state prediction unit 501 predicts the state of the wafer W by inputting the polishing conditions obtained in step S211 as input data into the first learning model 10A and generating substrate state information for the polishing conditions as output data.

[0112] Secondly, in step S230, the output processing unit 502 performs output processing for outputting the substrate status information generated in step S220, and transmits the substrate status information to the user terminal device 6. In addition to the user terminal device 6, the database device 3, or a device that replaces it, can also be used to transmit the substrate status information.

[0113] Secondly, in step S240, the user terminal device 6, in response to the transmission processing in step S200, receives the substrate status information transmitted in step S230 and displays a screen based on the substrate status information, allowing the user to confirm the status of the wafer W. In the above information processing method, steps S210 and S211 correspond to the information acquisition process, step S220 corresponds to the status prediction process, and step S230 corresponds to the output processing process.

[0114] As described above, when the information processing apparatus 5 and information processing method of this embodiment are used, since the grinding processing conditions including top ring state information, grinding table state information and grinding fluid supply nozzle state information are input into the first learning model 10A to predict the substrate state information (stress information) under the grinding processing conditions, the state of the wafer W during or after the grinding processing can be accurately predicted. (Second implementation form)

[0115] The second embodiment differs from the first embodiment in that the substrate state information displayed for the wafer W undergoing polishing is polishing quality information for the wafer W. Below, the differences between the second embodiment and the first embodiment will be mainly explained regarding the machine learning device 4a and the information processing device 5a.

[0116] Grinding quality information includes, for example: grinding rate, grinding profile, and remaining film information related to the degree of grinding on wafer W; and information on the degree of wafer W defects (scratches and corrosion) and the presence or absence of substrate defects, etc.

[0117] Figure 15 is a block diagram showing an example of the machine learning device 4a in the second embodiment. Figure 16 is an example diagram showing the second learning model 10B and the second learning data 11B. The second learning data 11B is used for machine learning of the second learning model 10B.

[0118] The substrate state information constituting the second learning data 11B displays polishing quality information of the wafer W. In this embodiment, the polishing quality information describes information regarding the degree of polishing and substrate defects; however, it may include at least one of these, or it may include other information displaying polishing quality. The polishing quality information may also display the polishing quality of the target time period during the polishing process from start to finish (the time required to polish each wafer), or it may display the surface distribution of polishing quality on the substrate surface of the wafer W. Furthermore, since the polishing conditions constituting the second learning data 11B are the same as in the first embodiment, their description is omitted.

[0119] The learning data acquisition unit 400 obtains second learning data 11B by referring to the polishing test information 31 and, when necessary, accepting input operations from the user via the user terminal device 6. Specifically, the learning data acquisition unit 400 obtains test result information (time series data of the pressure detector and the temperature detector of the virtual wafer) from the polishing test table 310 of the polishing test information 31 when polishing tests are performed using test IDs. For example, by calculating the polishing quality for each target time based on the time series data of the pressure detector (mainly reflecting mechanical effects) and the time series data of the temperature detector (mainly reflecting chemical effects), polishing quality information is obtained. In addition, the polishing test information 31 can also record the polishing quality measured by measuring instruments such as optical microscopes or scanning electron microscopes (SEM) for each target time as test result information. At this time, the learning data acquisition unit 400 can also further obtain the measurement results of the measuring instruments as polishing quality information.

[0120] The mechanical learning unit 401 inputs complex array second learning data 11B into the second learning model 10B, and generates a completed second learning model 10B by learning the correlation between grinding processing conditions and grinding quality information contained in the second learning data 11B.

[0121] Figure 17 is a block diagram showing an example of an information processing device 5a functioning as an information processing device 5a in the second embodiment. Figure 18 is a functional illustration diagram showing an example of an information processing device 5a in the second embodiment.

[0122] The information acquisition unit 500 acquires grinding processing conditions, including top ring status information, grinding table status information, and grinding fluid supply nozzle status information, in the same manner as in the first embodiment.

[0123] As described above, the state prediction unit 501 uses the polishing processing conditions obtained by the information acquisition unit 500 as input data to the second learning model 10B to predict the polishing quality information (in this embodiment, polishing degree information and substrate defect information) of the wafer W that is polished under the polishing processing conditions.

[0124] As described above, when the information processing apparatus 5a and information processing method of this embodiment are used, since the substrate state information (grinding quality information) of the grinding process is predicted by inputting the grinding process conditions, including top ring state information, grinding table state information and grinding fluid supply nozzle state information, into the second learning model 10B, the state of the wafer W during or after the grinding process can be predicted appropriately. (Third implementation form)

[0125] The third embodiment differs from the first embodiment in that the learning model consists of a learning model for analyzing stress and a learning model for analyzing grinding quality. The following will primarily explain the differences between the third embodiment and the first embodiment in terms of the mechanical learning device 4b and the information processing device 5b.

[0126] Figure 19 is a block diagram showing an example of the machine learning device 4b in the third embodiment. Figure 20 is a diagram showing an example of the third learning model 10C and the third learning data 11C used for analyzing grinding quality.

[0127] The learning model 10 consists of a first learning model 10A (Fig. 10) for stress analysis and a third learning model 10C (Fig. 20) for grinding quality analysis. The third learning data 11C used for machine learning by the third learning model 10C for grinding quality analysis, as shown in Fig. 20, consists of stress information and grinding quality information (in this embodiment, grinding degree information and substrate defect information). Since the first learning model 10A for stress analysis and the first learning data 11A are constructed in the same way as in the first embodiment (refer to Fig. 10), their description is omitted.

[0128] The learning data acquisition unit 400 obtains third learning data 11C, which consists of stress information and grinding quality information, by referring to the grinding test information 31 and, when necessary, accepting input operations from the user through the user terminal device 6.

[0129] The mechanical learning unit 401 inputs complex arrays of third learning data 11C into the third learning model 10C used for analyzing grinding quality, and uses the third learning model 10C used for analyzing grinding quality to learn the correlation between stress information and grinding quality information contained in the third learning data 11C, thereby generating a completed third learning model 10C for analyzing grinding quality.

[0130] Figure 21 is a block diagram showing an example of an information processing device 5b functioning as a third embodiment. Figure 22 is a functional illustration diagram showing an example of an information processing device 5b in the third embodiment.

[0131] The information acquisition unit 500 acquires grinding processing conditions, including top ring status information, grinding table status information, and grinding fluid supply nozzle status information, in the same manner as in the first embodiment.

[0132] As described above, the state prediction unit 501 predicts the stress information of the wafer W subjected to polishing under the polishing conditions by inputting the polishing conditions obtained by the information acquisition unit 500 into the first learning model 10A, and predicts the polishing quality information (in this embodiment, polishing degree information and substrate defect information) of the wafer W subjected to the stress displayed by the stress information by inputting the predicted stress information into the third learning model 10C.

[0133] As described above, when using the information processing apparatus 5b and information processing method of this embodiment, the grinding processing conditions, including top ring state information, grinding table state information, and grinding fluid supply nozzle state information, are input into the learning model 10 (first and third learning models 10A and 10C) to predict the substrate state information (grinding quality information) under the grinding processing conditions. Therefore, the wafer state during or after the grinding process can be accurately predicted. (Other implementation forms)

[0134] This invention is not limited to the above-described embodiments, and various modifications can be made to implement it without departing from the spirit of the invention. All of these modifications are included in the technical concept of this invention.

[0135] The above-described embodiments indicate that the database device 3, machine learning devices 4, 4a, 4b, and information processing devices 5, 5a, 5b are each composed of different devices. However, these three devices may also be composed of a single device, or any two of these three devices may be composed of a single device. Furthermore, at least one of the machine learning devices 4, 4a, 4b and the information processing devices 5, 5a, 5b may be inserted into the control unit 26 of the substrate processing device 2 or the user terminal device 6.

[0136] The above embodiment describes a substrate processing apparatus 2 having each of the units 21 to 25. However, the substrate processing apparatus 2 only needs to have at least the polishing unit 22, and other units may be omitted.

[0137] The above implementation describes the case where the machine learning model implemented by the machine learning unit 401 uses a neural network-like model. However, other machine learning models can also be used. Other machine learning models include: tree-type models such as decision trees and regression trees; integrated learning such as bagging and boosting; recurrent neural networks; stacked neural networks; neural network-like models such as LSTM (including deep learning); hierarchical clustering; non-hierarchical clustering; clustering types such as k-nearest neighbor and k-means; multivariate analysis such as principal component analysis, factor analysis, and logistic regression; and support vector machines.

[0138] Furthermore, the above-described embodiments illustrate the various information included in the polishing processing conditions in the input data of the first and second learning models 10A and 10B. It is also explained that the first and second learning models 10A and 10B can be prepared according to the type of wafer W. Correspondingly, the polishing processing conditions may further include information about the substrate before polishing, showing the substrate state (initial state) of the wafer W before polishing. The substrate information included in the polishing processing conditions includes at least one of the following: the shape (size, thickness, warpage, etc.) and weight of the substrate before polishing, and the condition of the substrate surface. The condition of the substrate surface may include, for example, information about the degree and presence of defects (missing parts) formed on the substrate surface; and information about the size, surface distribution, and number of microparticles attached to the substrate surface; any information that affects the polishing process is acceptable, but not limited to these. Information about the substrate before processing can be obtained, for example, from the operation information of the equipment in the previous process, or it can be measured by the film thickness measurement unit 25 and other measuring instruments (optical detectors, contact detectors, weight detectors, etc.) installed inside or outside the substrate processing apparatus 2. In addition, the information about the substrate before processing obtained or measured as described above can also be used for other substrates before processing in the same batch, or for other substrates before processing in another batch.

[0139] During the machine learning learning phase, the pre-processing substrate information is registered in the polishing test information 31 and obtained as part of the polishing processing conditions by the machine learning devices 4, 4a, and 4b. The machine learning devices 4, 4a, and 4b use the first and second learning data 11A and 11B, which are composed of the polishing processing conditions that further include the pre-processing substrate information and the substrate state information, to perform machine learning of the first and second learning models 10A and 10B.

[0140] In the inference stage of machine learning, the pre-processing substrate information is obtained by information processing devices 5, 5a, and 5b as part of the polishing processing conditions. By inputting the polishing processing conditions, which further include the pre-processing substrate information, into the first and second learning data 11A and 11B, the information processing devices 5, 5a, and 5b predict the substrate state information when the pre-processing substrate is polished under the polishing processing conditions. (Machine learning programs and information processing programs)

[0141] The machine learning devices 4, 4a, and 4b of the present invention are also provided as programs (machine learning programs) that enable the computer 900 to perform its functions, and programs (machine learning programs) that enable the computer 900 to execute the various steps of the machine learning method. Furthermore, the information processing devices 5, 5a, and 5b of the present invention are also provided as programs (information processing programs) that enable the computer 900 to perform its functions, and programs (information processing programs) that enable the computer 900 to execute the various steps of the information processing method described above. (Inference apparatus, inference method, and inference procedure)

[0142] This invention is not only applicable to the information processing apparatuses 5, 5a, and 5b (information processing methods or information processing programs) described in the above embodiments, but also to an inference apparatus (inference method or inference program) used for inferring substrate state information. In this case, the inference apparatus (inference method or inference program) includes: a memory and a processor, wherein the processor can execute a series of processes. This series of processes includes: an information acquisition process for obtaining polishing conditions (information acquisition step); obtaining polishing conditions through the information acquisition process; and an inference process (inference step) for inferring and displaying substrate state information (stress information or polishing quality information) of the substrate being polished under the polishing conditions. Furthermore, this series of processes includes: an information acquisition process for obtaining stress information (information acquisition step); obtaining stress information through the information acquisition process; and an inference process (inference step) for inferring and displaying polishing quality information of the substrate to which the stress information is applied.

[0143] By providing the inference device (inference method or inference program) in the form of an inference device, it can be easily applied to various devices compared to installing an information processing device. Those skilled in the art will naturally understand that when the inference device (inference method or inference program) infers the board state information, the learning model generated by the machine learning device and machine learning method described above can also be used to apply the inference method implemented by the state prediction unit. [Industrial Applicability]

[0144] This invention can be applied to information processing devices, inference devices, machine learning devices, information processing methods, inference methods, and machine learning methods.

[0145] 1: Substrate processing system 2: Substrate processing device 3: Database device 4, 4a, 4b: Machine learning device 5, 5a, 5b: Information processing device 6: User terminal device 7: Internet 10: Learning Model 10A: First Learning Model 10B: Second Learning Model 10C: Third Learning Model 11A: First Learning Materials 11B: Second Study Material 11C: Third Learning Material 20: Rack 21: Loading / Unloading Unit 22: Grinding Unit 22A~22D: First to Fourth Grinding Sections 23: Substrate transfer unit 24: Cleaning Unit 25: Film thickness measurement unit 26: Control Unit 30: Production Traceability Information 31: Grinding Test Information 40: Control Department 41:Ministry of Communications 42: Study Materials Memory Section 43: Learning to complete the model memory section 50: Control Department 51: Ministry of Communications 52: Learning to complete the model memory section 100: Input Layer 101: Intermediate Layer 102: Output Layer 200A: First partition wall 200B: Second partition wall 210A~210D: First to fourth front loading sections 211: Transport Robot 212: Horizontal Moving Mechanism 219,229,239,249,259: Sequencer 220: Grinding table 220a: Grinding table shaft 220b: Rotary moving mechanism section 220c: Temperature control mechanism 221: Top Ring 221a: Top ring shaft 221b: Rod 221c: Rotary Moving Mechanism 221d: Up and down moving mechanism 221e: Shaking and moving mechanism 222: Grinding fluid supply nozzle 222a: Support shaft 222b: Shaking and moving mechanism 222c: Flow regulation section 222d: Temperature Control Mechanism 223: Dresser 223a: Dresser shaft 223b: Support shaft 223c: Rotary moving mechanism 223d: Up and down moving mechanism 223e: Shaking and moving mechanism 224: Atomizer 224a: Support shaft 224b: Shaking and moving mechanism 224c: Flow regulation section 225: Environmental Detector 225a: Temperature detector 225b: Humidity detector 225c: Barometer 230A, 230B: First and second linear transmission machines 231: Swinging Conveyor 232: Elevator 233: Temporary Storage Table 240A, 240B: First and second cleaning chambers 241: Drying Chamber 242A, 242B: First and Second Transport Rooms 260: Control Department 261: Ministry of Communications 262: Input Section 263: Output Section 264: Memory Department 265: Device Setting Information 266: Information on substrate processing solutions 300: Wafer History 301: Grinding History 310: Grinding Test Table 400: Learning Materials Acquisition Department 401: Mechanical Engineering Department 500: Information Acquisition Department 501: State Prediction Department 502: Output Processing Unit 900: Computer 910: Busbar 912: Processor 914: Memory 916: Input device 917: Output device 918: Display device 920: Storage device 922: Communication I / F Department 924: External Equipment I / F Section 926:I / O device I / F section 928: Media Input / Output Department 930: Program 940: Internet 950: External devices 960:I / O device 970: Media 2200: Grinding pad 2210:Top ring body 2211: Carrier 2212: Diaphragm 2213: Buckle 2214: Buckle Airbag 2212a~2212d: First to fourth diaphragm pressure chambers 2212e: partition wall 2212f: Hole 2215: Rotary Joint 2216A~2216D: First to fourth flow paths 2217A~2217E: First branching path 2218A~2218E: Second branching path 2171~217p: Module 2271~227r: Module 2371~237t: Module 2471~247v: Module 2571~257x: Module 2181~218q: Detector 2281~228s: Detector 2381~238u: Detector 2481~248w: Detector 2581~258y: Detector W: substrate W: Wafer PA~PE: Pressure detector V1A~V1E: Valves FA~FE: Flow detectors RA~RE: Pressure Regulator GS: Gas Supply Source TP1~TP7: First to seventh transport positions

Claims

1. An information processing apparatus comprising: an information acquisition unit that acquires, during a chemical mechanical polishing process of a substrate performed by a substrate processing apparatus comprising a polishing table rotatably supporting a polishing pad, a top ring pressing a substrate against the polishing pad, and a polishing fluid supply nozzle supplying polishing fluid to the polishing pad; and a state prediction unit that predicts the aforementioned substrate state information for a substrate subjected to chemical mechanical polishing under the polishing conditions by inputting the aforementioned polishing conditions acquired by the information acquisition unit into a learning model that has learned the correlation between the aforementioned polishing conditions and the substrate state information showing the state of the substrate subjected to the aforementioned chemical mechanical polishing under the polishing conditions; wherein the top ring comprises: a top ring body that is moved by a rotational movement mechanism, a vertical movement mechanism, and a rocking movement mechanism; A diaphragm, which is housed in the aforementioned top ring body, presses the aforementioned substrate against the aforementioned polishing pad by pressure fluid supplied to the diaphragm pressure chamber; and a retaining ring, which is disposed on the outer periphery of the aforementioned diaphragm, and presses the aforementioned polishing pad by pressure fluid supplied to the retaining ring pressure chamber; the aforementioned polishing processing conditions include at least one of the following: the aforementioned top ring rotation speed, the aforementioned top ring rotation torque, the aforementioned top ring rocking position, the aforementioned top ring rocking torque, the aforementioned top ring height, the aforementioned top ring lifting torque, the aforementioned pressure in the aforementioned diaphragm pressure chamber, the aforementioned flow rate of the aforementioned pressure fluid supplied to the aforementioned diaphragm pressure chamber, the aforementioned diaphragm condition, the aforementioned pressure in the aforementioned retaining ring pressure chamber, the aforementioned flow rate of the aforementioned pressure fluid supplied to the aforementioned retaining ring pressure chamber, and the aforementioned retaining ring condition.

2. The information processing apparatus of claim 1, wherein the aforementioned grinding processing conditions include at least one of the following: the number of revolutions of the aforementioned grinding table, the rotational torque of the aforementioned grinding table, the surface temperature of the aforementioned grinding pad, and the condition of the aforementioned grinding pad.

3. The information processing apparatus of claim 1, wherein the aforementioned grinding processing conditions include the aforementioned grinding fluid supply nozzle status information including at least one of the following: the flow rate of the aforementioned grinding fluid, the dripping position of the aforementioned grinding fluid, and the temperature of the aforementioned grinding fluid.

4. The information processing apparatus of claim 1, wherein the aforementioned grinding conditions further include: apparatus internal environment information, which displays the environment of the space in which the aforementioned chemical mechanical grinding is performed, wherein the aforementioned grinding conditions include at least one of the aforementioned apparatus internal environment information: the temperature of the aforementioned space, the humidity of the aforementioned space, and the air pressure of the aforementioned space.

5. The information processing apparatus of claim 1, wherein the aforementioned polishing processing conditions further include pre-processing substrate information, which displays the state of the pre-processing substrate of the aforementioned substrate before the aforementioned chemical mechanical polishing processing is performed.

6. The information processing apparatus of claim 5, wherein the aforementioned polishing processing conditions include at least one of the following: the shape of the aforementioned substrate before processing, the weight of the aforementioned substrate before processing, and the condition of the substrate surface of the aforementioned substrate before processing.

7. The information processing apparatus of claim 1, wherein the aforementioned substrate state information displays stress information of stress applied to the aforementioned substrate, and the aforementioned stress information displays at least one of mechanical stress and thermal stress applied to the aforementioned substrate.

8. The information processing apparatus of claim 7, wherein the aforementioned stress information is displayed as an instantaneous value of the aforementioned stress before the object time included during the polishing process from the start of the aforementioned chemical mechanical polishing process to the end of the polishing process, or as a cumulative value of the aforementioned stress during the object time from the start of the aforementioned chemical mechanical polishing process to the aforementioned object time.

9. The information processing apparatus of claim 7 or 8, wherein the aforementioned stress information displays the surface distribution of the aforementioned stress applied to the substrate surface of the aforementioned substrate.

10. The information processing apparatus of claim 1, wherein the aforementioned substrate status information is polishing quality information that displays the polishing quality of the aforementioned substrate.

11. An information processing apparatus comprising: an information acquisition unit that acquires polishing conditions including, during a chemical mechanical polishing process of a substrate performed by a substrate processing apparatus comprising a polishing table rotatably supporting a polishing pad, a top ring pressing a substrate against the polishing pad, and a polishing fluid supply nozzle supplying polishing fluid to the polishing pad; and a state prediction unit that predicts the aforementioned substrate state information for a substrate subjected to chemical mechanical polishing under the polishing conditions by inputting the polishing conditions acquired by the information acquisition unit into a learning model that has learned the correlation between the polishing conditions and the substrate state information showing the state of the substrate subjected to the chemical mechanical polishing under the polishing conditions; wherein the learning model is configured as follows: The learning model for stress analysis learns the correlation between the aforementioned polishing conditions and stress information displayed on the substrate subjected to the aforementioned chemical mechanical polishing treatment under those conditions through machine learning; and the learning model for polishing quality analysis learns the correlation between the aforementioned stress information and polishing quality information displayed on the substrate subjected to the aforementioned stress. The aforementioned state prediction unit predicts the aforementioned stress information on the substrate subjected to the aforementioned chemical mechanical polishing treatment under those conditions by inputting the aforementioned polishing conditions obtained by the aforementioned information acquisition unit into the learning model for stress analysis, and predicts the aforementioned polishing quality information on the substrate subjected to the aforementioned stress by inputting the previously predicted stress information into the learning model for polishing quality analysis.

12. An inference device comprising: a memory and a processor, wherein the processor performs: an information acquisition process for acquiring polishing processing conditions, the polishing processing conditions including: top ring state information displaying the state of the top ring, polishing table state information displaying the state of the polishing table, and polishing fluid supply nozzle state information displaying the state of the polishing fluid supply nozzle during a chemical mechanical polishing process of the aforementioned substrate performed by a substrate processing apparatus comprising a polishing table having a polishing table rotatably supporting a polishing pad, a top ring pressing a substrate against the polishing pad, and a polishing fluid supply nozzle supplying polishing fluid to the polishing pad; and an inference process for inferring substrate state information, the substrate state information being the state of the aforementioned substrate before the chemical mechanical polishing process performed by the polishing processing conditions when the aforementioned information acquisition process acquires the aforementioned polishing processing conditions; wherein the top ring comprises: a top ring body, which is moved by a rotational movement mechanism, a vertical movement mechanism, and a rocking movement mechanism; A diaphragm, which is housed in the aforementioned top ring body, presses the aforementioned substrate against the aforementioned polishing pad by pressure fluid supplied to the diaphragm pressure chamber; and a retaining ring, which is disposed on the outer periphery of the aforementioned diaphragm, and presses the aforementioned polishing pad by pressure fluid supplied to the retaining ring pressure chamber; the aforementioned polishing processing conditions include at least one of the following: the aforementioned top ring rotation speed, the aforementioned top ring rotation torque, the aforementioned top ring rocking position, the aforementioned top ring rocking torque, the aforementioned top ring height, the aforementioned top ring lifting torque, the aforementioned pressure in the aforementioned diaphragm pressure chamber, the aforementioned flow rate of the aforementioned pressure fluid supplied to the aforementioned diaphragm pressure chamber, the aforementioned diaphragm condition, the aforementioned pressure in the aforementioned retaining ring pressure chamber, the aforementioned flow rate of the aforementioned pressure fluid supplied to the aforementioned retaining ring pressure chamber, and the aforementioned retaining ring condition.

13. A machine learning device comprising: a learning data memory unit, which stores a plurality of learning data, the learning data comprising: polishing processing conditions, which includes top ring state information displaying the state of the top ring, polishing table state information displaying the state of the polishing table, and polishing fluid supply nozzle state information displaying the state of the polishing fluid supply nozzle during a chemical mechanical polishing process of the substrate performed by a substrate processing apparatus having a polishing table having a polishing pad rotatably supporting a polishing pad, a top ring pressing a substrate against the polishing pad, and a polishing fluid supply nozzle supply nozzle supplying polishing fluid to the polishing pad; and substrate state information, which displays the state of the substrate before the chemical mechanical polishing process performed by the polishing processing conditions; a machine learning unit, which learns the correlation between the polishing processing conditions and the substrate state information by inputting a plurality of the aforementioned learning data into a learning model; and a learning completion model memory unit, which stores the aforementioned learning model in which the machine learning unit has learned the aforementioned correlation; wherein the top ring has: The top ring body is moved by a rotational movement mechanism, a vertical movement mechanism, and a rocking movement mechanism; a diaphragm is housed in the top ring body and presses the substrate against the polishing pad by pressure fluid supplied to the diaphragm pressure chamber; and a retaining ring is disposed on the outer periphery of the diaphragm and presses against the polishing pad by pressure fluid supplied to the retaining ring pressure chamber; the polishing processing conditions include at least one of the following: the number of rotations of the top ring, the rotational torque of the top ring, the rocking position of the top ring, the rocking torque of the top ring, the height of the top ring, the lifting torque of the top ring, the pressure in the diaphragm pressure chamber, the flow rate of the pressure fluid supplied to the diaphragm pressure chamber, the condition of the diaphragm, the pressure in the retaining ring pressure chamber, the flow rate of the pressure fluid supplied to the retaining ring pressure chamber, and the condition of the retaining ring.

Images