WO2024029236A1 - 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法 - Google Patents

情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法 Download PDF

Info

Publication number
WO2024029236A1
WO2024029236A1 PCT/JP2023/023932 JP2023023932W WO2024029236A1 WO 2024029236 A1 WO2024029236 A1 WO 2024029236A1 JP 2023023932 W JP2023023932 W JP 2023023932W WO 2024029236 A1 WO2024029236 A1 WO 2024029236A1
Authority
WO
WIPO (PCT)
Prior art keywords
polishing
information
reliability
end point
state information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2023/023932
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
隆一郎 三谷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ebara Corp
Original Assignee
Ebara Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ebara Corp filed Critical Ebara Corp
Priority to US18/998,420 priority Critical patent/US20260034636A1/en
Priority to CN202380055328.0A priority patent/CN119631164A/zh
Priority to KR1020257002803A priority patent/KR20250047726A/ko
Publication of WO2024029236A1 publication Critical patent/WO2024029236A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B37/00—Lapping machines or devices; Accessories
    • B24B37/005—Control means for lapping machines or devices
    • B24B37/013—Devices or means for detecting lapping completion
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B37/00—Lapping machines or devices; Accessories
    • B24B37/27—Work carriers
    • B24B37/30—Work carriers for single side lapping of plane surfaces
    • B24B37/32—Retaining rings
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
    • B24B49/12—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation involving optical means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
    • B24B49/16—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation taking regard of the load
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B53/00—Devices or means for dressing or conditioning abrasive surfaces
    • B24B53/017—Devices or means for dressing, cleaning or otherwise conditioning lapping tools
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B24—GRINDING; POLISHING
    • B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
    • B24B57/00—Devices for feeding, applying, grading or recovering grinding, polishing or lapping agents
    • B24B57/02—Devices for feeding, applying, grading or recovering grinding, polishing or lapping agents for feeding of fluid, sprayed, pulverised, or liquefied grinding, polishing or lapping agents
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Program-control systems
    • G05B19/02—Program-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H10—SEMICONDUCTOR DEVICES; ELECTRIC SOLID-STATE DEVICES NOT OTHERWISE PROVIDED FOR
    • H10P—GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
    • H10P52/00—Grinding, lapping or polishing of wafers, substrates or parts of devices
    • H—ELECTRICITY
    • H10—SEMICONDUCTOR DEVICES; ELECTRIC SOLID-STATE DEVICES NOT OTHERWISE PROVIDED FOR
    • H10P—GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
    • H10P72/00—Handling or holding of wafers, substrates or devices during manufacture or treatment thereof
    • H10P72/06—Apparatus for monitoring, sorting, marking, testing or measuring
    • H10P72/0606—Position monitoring, e.g. misposition detection or presence detection
    • H—ELECTRICITY
    • H10—SEMICONDUCTOR DEVICES; ELECTRIC SOLID-STATE DEVICES NOT OTHERWISE PROVIDED FOR
    • H10P—GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
    • H10P95/00—Generic processes or apparatus for manufacture or treatments not covered by the other groups of this subclass

Definitions

  • the present invention relates to an information processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method.
  • a substrate processing apparatus that performs various processes on substrates such as semiconductor wafers
  • CMP chemical mechanical polishing
  • a substrate processing apparatus for example, a polishing table having a polishing pad is rotated and a polishing liquid (slurry) is supplied to the polishing pad from a liquid supply nozzle, and a polishing head called a top ring presses a substrate against the polishing pad. Then, the substrate is chemically and mechanically polished. Then, in order to remove foreign matter such as polishing debris adhering to the polished substrate, a cleaning tool is brought into contact with the polished substrate while supplying substrate cleaning fluid, and the substrate is then dried. processing is completed, and the process moves on to the next substrate.
  • slurry polishing liquid
  • polishing apparatuses detect the end point of polishing by detecting changes in frictional force, changes in motor current, or changes in physical quantities of the wafer.
  • Patent Document 1 includes a learned model that machine-learns the waveform of measurement data from the start of polishing to the end of polishing that was output during past polishing from each of multiple types of end point detection sensors provided in one polishing unit. Then, the end point is detected by inputting the measurement data from the start of polishing up to the current point that is output from each of the multiple types of end point detection sensors during new polishing, and estimating whether or not the current point is the timing of the end point indicating the end of polishing.
  • a technique for improving the accuracy of is disclosed.
  • the present invention provides information that makes it possible to appropriately predict reliability information of a polishing end point detection function that indicates the reliability of an end point detection function that detects that chemical mechanical polishing processing has reached the end point.
  • the purpose of the present invention is to provide a processing device, an inference device, a machine learning device, an information processing method, an inference method, and a machine learning method.
  • an information processing device includes: Contains at least one of wear-out state information indicating the wear-out state of the constituent elements of the substrate processing apparatus in chemical mechanical polishing processing of the substrate performed by the substrate processing apparatus, and processing state information indicating the processing state during the polishing process.
  • an information acquisition unit that acquires reliability deterioration factor state information
  • Machine learning was used to learn the correlation between the reliability reduction factor state information and the reliability information of a polishing end point detection function that indicates the reliability of the end point detection function that detects that the chemical mechanical polishing process has reached the end point.
  • a state prediction unit that predicts reliability information of the polishing end point detection function with respect to the reliability reduction factor state information by inputting the reliability reduction factor state information acquired by the information acquisition unit into a learning model; equipped with
  • wear state information indicating the wear state of the constituent elements of the substrate processing apparatus in chemical mechanical polishing processing, and processing state information indicating the processing state during polishing processing;
  • the reliability deterioration factor status information including at least one of Reliability information of the polishing end point detection function, which indicates the reliability of the end point detection function that detects that the end point has been reached, can be appropriately predicted.
  • FIG. 1 is an overall configuration diagram showing an example of a substrate processing system 1.
  • FIG. FIG. 2 is a plan view showing an example of a substrate processing apparatus 2.
  • FIG. FIG. 3 is a perspective view showing an example of first to fourth polishing sections 22A to 22D. 3 is a cross-sectional view schematically showing an example of a top ring 221.
  • FIG. 1 is a block diagram showing an example of a substrate processing apparatus 2.
  • FIG. 9 is a hardware configuration diagram showing an example of a computer 900.
  • FIG. 3 is a data configuration diagram showing an example of production history information 30 managed by a database device 3.
  • FIG. 3 is a data configuration diagram showing an example of polishing test information 31 managed by the database device 3.
  • FIG. 2 is a block diagram showing an example of a machine learning device 4 according to the first embodiment. It is a diagram showing an example of a first learning model 10A and first learning data 11A.
  • 3 is a flowchart illustrating an example of a machine learning method by the machine learning device 4.
  • FIG. FIG. 2 is a block diagram showing an example of an information processing device 5 according to the first embodiment.
  • FIG. 2 is a functional explanatory diagram showing an example of the information processing device 5 according to the first embodiment.
  • 5 is a flowchart illustrating an example of an information processing method by the information processing device 5.
  • FIG. FIG. 7 is a schematic diagram for explaining an optical sensor 226 provided on a polishing table 220 according to a second embodiment.
  • FIG. 1 is an overall configuration diagram showing an example of a substrate processing system 1.
  • the substrate processing system 1 includes a chemical mechanical polishing process (hereinafter referred to as "polishing process”) for flattening the surface of a substrate W such as a semiconductor wafer (hereinafter referred to as "wafer”), It functions as a system that manages a series of substrate processing including cleaning processing for cleaning the wafer W and the like.
  • polishing process chemical mechanical polishing process for flattening the surface of a substrate W such as a semiconductor wafer (hereinafter referred to as "wafer")
  • the substrate processing system 1 includes 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 as its main components.
  • Each of the devices 2 to 6 is configured with, for example, a general-purpose or dedicated computer (see FIG. 6 described later), and is connected to a wired or wireless network 7 to collect various data (some data is shown in FIG. 1). (indicated by dotted line arrows) can be mutually transmitted and received. Note that the number of the devices 2 to 6 and the connection configuration of the network 7 are not limited to the example shown in FIG. 1, and may be changed as appropriate.
  • the substrate processing apparatus 2 is composed of a plurality of units, and performs a series of substrate processing on one or more wafers W, such as loading, polishing, cleaning, drying, film thickness measurement, and unloading. This is a device that performs each.
  • the substrate processing apparatus 2 includes apparatus setting information 265 consisting of a plurality of apparatus parameters set for each unit, and substrate recipe information 266 that defines polishing process status information for polishing processes, cleaning process conditions for cleaning processes, etc. Control the operation of each unit while referring to
  • the substrate processing device 2 transmits various reports R to the database device 3, user terminal device 6, etc. according to the operation of each unit.
  • Various reports R include, for example, process information that identifies the target wafer W when substrate processing is performed, equipment status information that indicates the status of each unit when each process is performed, and substrate processing apparatus 2.
  • the information includes event information detected by the system, operation information of users (operators, production managers, maintenance managers, etc.) on the substrate processing apparatus 2, and the like.
  • the database device 3 includes production history information 30 regarding the history of substrate processing performed on wafers W for main production, and a test of polishing processing on dummy wafers for testing (hereinafter referred to as "polishing test"). This is a device that manages polishing test information 31 regarding the history of polishing tests performed.
  • the database device 3 may also store device setting information 265 and substrate recipe information 266, and in that case, the substrate processing device 2 may refer to these information. good.
  • the database device 3 receives various reports R from the substrate processing device 2 at any time when the substrate processing device 2 performs substrate processing on wafers W for main production, and registers them in the production history information 30. , the production history information 30 stores reports R regarding substrate processing.
  • the database device 3 receives various reports R (including at least device status information) from the substrate processing device 2 at any time when the substrate processing device 2 performs a polishing test on a dummy wafer for testing, and stores polishing test information. 31 and register the test results of the polishing test in association with each other, the polishing test information 31 accumulates the report R and the test results regarding the polishing test.
  • reports R including at least device status information
  • the dummy wafer is a jig that simulates the wafer W.
  • a dummy wafer sensor such as a pressure sensor or a temperature sensor is provided on or inside the dummy wafer to measure the state of the wafer W when the polishing process is performed, and the measured values of the dummy wafer sensor are used as the test results. It is registered in the polishing test information 31.
  • the dummy wafer sensor may be provided at one or more locations on the substrate surface of the dummy wafer, or may be provided on the substrate surface of the dummy wafer.
  • the polishing test may be performed in the substrate processing apparatus 2 for main production, or may be performed in a polishing test apparatus (not shown) for testing that can reproduce the same polishing process as the substrate processing apparatus 2. good.
  • the machine learning device 4 operates as a subject of the learning phase of machine learning, and, for example, acquires a part of the polishing test information 31 from the database device 3 as the first learning data 11A, and uses it in the information processing device 5.
  • a first learning model 10A is generated by machine learning.
  • the trained first learning model 10A is provided to the information processing device 5 via the network 7, a recording medium, or the like.
  • the information processing device 5 operates as a subject in the inference phase of machine learning, and uses the first learning model 10A generated by the machine learning device 4 to perform polishing processing by the substrate processing device 2 on wafers W for main production.
  • the state of the wafer W is predicted when the polishing end point detection function is performed, and the reliability information of the polishing end point detection function, which is the predicted result, is transmitted to the database device 3, user terminal device 6, etc.
  • the timing at which the information processing device 5 predicts the reliability information of the polishing end point detection function may be after the polishing process is performed (post-event prediction process) or while the polishing process is being performed (real-time prediction process). Alternatively, it may be performed before the polishing process is performed (pre-prediction process).
  • the user terminal device 6 is a terminal device used by a user, and may be a stationary device or a portable device.
  • the user terminal device 6 receives various input operations via the display screen of an application program, a web browser, etc., and also receives various information (for example, notification of an event, reliability of the polishing end point detection function, etc.) via the display screen. information, production history information 30, polishing test information 31, etc.).
  • FIG. 2 is a plan view showing an example of the substrate processing apparatus 2.
  • the substrate processing apparatus 2 includes a load/unload unit 21, a polishing unit 22, a substrate transport unit 23, a cleaning unit 24, a film thickness measuring unit 25, inside a housing 20 that is approximately rectangular in plan view. and a control unit 26.
  • the load/unload unit 21, the polishing unit 22, the substrate transport unit 23, and the cleaning unit 24 are partitioned by a first partition wall 200A, and the substrate transport unit 23 and the cleaning unit 24 are partitioned by a second partition wall 200A. It is divided by a partition wall 200B.
  • the load/unload unit 21 includes first to fourth front load sections 210A to 210D on which wafer cassettes (FOUPs, etc.) capable of storing a large number of wafers W in the vertical direction are placed, and wafers stored in the wafer cassettes.
  • a transfer robot 211 that can move up and down along the storage direction (up and down direction) of the wafer W, and a transfer robot 211 that can move up and down along the direction in which the first to fourth front load sections 210A to 210D are lined up (the lateral direction of the housing 20).
  • a horizontal movement mechanism section 212 that moves the horizontal movement mechanism section 212 is provided.
  • the transfer robot 211 carries a wafer cassette mounted on each of the first to fourth front load sections 210A to 210D, a substrate transfer unit 23 (specifically, a lifter 232, which will be described later), and a cleaning unit 24 (specifically, It is configured to be accessible to a drying chamber 241) and a film thickness measurement unit 25 (to be described later), and includes upper and lower hands (not shown) for transferring the wafer W therebetween.
  • the lower hand is used when transferring the wafer W before processing, and the upper hand is used when transferring the wafer W after processing.
  • a shutter (not shown) provided on the first partition wall 200A is opened and closed.
  • the polishing unit 22 includes first to fourth polishing sections 22A to 22D that perform a polishing process (planarization) on the wafer W, respectively.
  • the first to fourth polishing parts 22A to 22D are arranged in parallel along the longitudinal direction of the housing 20.
  • FIG. 3 is a perspective view showing an example of the first to fourth polishing sections 22A to 22D.
  • the basic configuration and functions of the first to fourth polishing sections 22A to 22D are common.
  • Each of the first to fourth polishing units 22A to 22D includes a polishing table 220 to which a polishing pad 2200 having a polishing surface is attached, and a polishing table 220 that holds a wafer W and transfers the wafer W to the polishing pad 2200 on the polishing table 220.
  • an atomizer 224 that sprays cleaning fluid onto the polishing pad 2200
  • an environment sensor 225 that measures the state of the internal space of the housing 20 where polishing processing is performed.
  • the polishing table 220 is supported by a polishing table shaft 220a, and includes a rotary movement mechanism section 220b that rotates the polishing table 220 around its axis via a polishing table rotary connector 2201, and adjusts the surface temperature of the polishing pad 2200.
  • a polishing pad surface temperature control mechanism section 220c is provided.
  • the polishing pad surface temperature control mechanism section 220c has a radiation thermometer 220c1 above the polishing table 220 that measures the surface temperature of the polishing pad 2200 or the surface temperature of the grindstone.
  • the polishing table 220 of this embodiment includes a polishing table internal temperature control mechanism section 220d that controls the temperature of the polishing table 220 by supplying and discharging temperature-controlled water to the inside of the polishing table 220.
  • the polishing table internal temperature control mechanism section 220d has a temperature controlled water supply pipe 220d1 that supplies temperature controlled water to the inside of the polishing table 220, and a temperature controlled water discharge pipe 220d2 that discharges the temperature controlled water.
  • the polishing table internal temperature control mechanism section 220d has a temperature control water thermometer 220d3 for measuring the temperature of the supplied temperature control water in the temperature control water supply pipe 220d1, and a temperature control water thermometer 220d3 for measuring the temperature of the temperature control water being supplied to the temperature control water discharge pipe 220d2. It has a discharge temperature control water thermometer 220d4 that measures the temperature of the temperature control water.
  • the top ring 221 is supported by a top ring shaft 221a that is movable in the vertical direction, and includes a top ring rotation movement mechanism section 221c that rotates the top ring 221 around its axis and a top ring rotation movement mechanism section 221c that moves the top ring 221 in the vertical direction. It includes a top ring vertical movement mechanism section 221d and a top ring swing movement mechanism section 221e that swings (swings) the top ring 221 around the top ring swing support shaft 221b.
  • the top ring swing movement mechanism section 221e includes a top ring swing support shaft 221b, a top ring swing arm 221f that swingably connects the top ring shaft 221a to the top ring swing support shaft 221b, and a top ring swing support shaft 221b. It has a top ring swing shaft motor 221g that rotationally drives the swing support shaft 221b.
  • the top ring rocking movement mechanism section 221e detects the top ring rocking torque applied to the top ring rocking arm 221f at the connection part between the top ring rocking arm 221f and the top ring rocking shaft motor 221g. It has a sensor 221h. Specifically, the top ring swing torque sensor 221h may detect the torque applied to the top ring swing arm 221f from the current value of the top ring swing shaft motor 221g. The current value of the top ring swing shaft motor 221g is an amount that depends on the torque of the top ring swing arm 221f at the connection to the top ring swing shaft motor 221g.
  • the current value of the top ring swing shaft motor 221g is a current value supplied to the top ring swing shaft motor 221g, or a current command value generated within a driver (not shown). good. Note that the top ring swing torque may be detected using other methods.
  • an acceleration sensor 221j and/or an amplitude sensor may be attached to the top ring 221 to measure the vibration of the top ring 221 during polishing.
  • a noise measuring device 221k may be provided near the top ring 221 to measure noise during polishing.
  • the polishing fluid supply nozzle 222 is supported by a support shaft 222a, and includes a swing movement mechanism section 222b that pivots and moves the polishing fluid supply nozzle 222 around the support shaft 222a, and a polishing fluid flow rate that adjusts the flow rate of the polishing fluid. It includes an adjustment section 222c and a polishing fluid temperature adjustment mechanism section 222d that adjusts the temperature of the polishing fluid.
  • the polishing fluid is a polishing liquid (slurry) or pure water, and may also contain a chemical solution, or may be a polishing liquid with a dispersant added thereto.
  • the dresser 223 is supported by a dresser shaft 223a that is movable in the vertical direction, and includes a dresser rotation movement mechanism section 223c that rotates the dresser 223 around its axis, and a dresser vertical movement mechanism section that moves the dresser 223 in the vertical direction. 223d, and a dresser swing movement mechanism section 223e that swings and moves the dresser 223 around the dresser swing support shaft 223b.
  • the dresser swing movement mechanism section 223e includes a dresser swing support shaft 223b, a dresser swing arm 223f that swingably connects the dresser shaft 223a to the dresser swing support shaft 223b, and a dresser swing support shaft 223b.
  • the dresser swing shaft motor 223g is rotatably driven.
  • the dresser swing movement mechanism section 223e includes a dresser swing torque sensor 223h that detects the dresser swing torque applied to the dresser swing arm 223f at the connection part between the dresser swing arm 223f and the dresser swing shaft motor 223g.
  • the dresser swing torque sensor 223h may detect the torque applied to the dresser swing arm 223f from the current value of the dresser swing shaft motor 223g.
  • the current value of the dresser swing shaft motor 223g is an amount that depends on the torque of the dresser swing arm 223f at the connection to the dresser swing shaft motor 223g.
  • the current value of the dresser swing shaft motor 223g may be a current value supplied to the dresser swing shaft motor 223g, or a current command value generated within a driver (not shown). Note that the dresser swing torque may be detected by other methods.
  • the atomizer 224 is supported by a support shaft 224a, and includes an atomizer swing movement mechanism section 224b that rotates the atomizer 224 around the support shaft 224a, and a cleaning fluid flow rate adjustment section 224c that adjusts the flow rate of cleaning fluid.
  • the cleaning fluid is a mixed fluid of a liquid (eg, pure water) and a gas (eg, nitrogen gas) or a liquid (eg, pure water).
  • the environmental sensor 225 includes sensors arranged in the internal space of the housing 20, and includes, for example, a temperature sensor 225a that measures the temperature of the internal space, a humidity sensor 225b that measures the humidity of the internal space, and a sensor that measures the atmospheric pressure of the internal space. and an atmospheric pressure sensor 225c.
  • the environment sensor 225 may include a camera (image sensor) capable of photographing the surface of the polishing pad 2200 during the polishing process or before and after the polishing process.
  • each rotational movement mechanism section 220b, 221c, 223c, each vertical movement mechanism section 221d, 223d, and each swing movement mechanism section 221e, 222b, 223e, 224b are omitted.
  • modules for generating driving force such as motors and actuators, driving force transmission mechanisms such as linear guides, ball screws, gears, belts, couplings, and bearings, linear sensors, encoder sensors, limit sensors, and torque. It is configured by appropriately combining sensors such as sensors.
  • each flow rate adjustment unit 222c, 224c is omitted, but for example, a module for fluid adjustment such as a pump, a valve, a regulator, a flow rate sensor, a pressure sensor, a liquid level sensor, etc. It is configured by appropriately combining sensors such as the following.
  • specific configurations of the polishing table surface temperature control mechanism section 220c, polishing table internal temperature control mechanism section 220d, and polishing fluid temperature control mechanism section 222d are omitted, but for example, heaters, heat exchangers, etc. It is constructed by appropriately combining modules for temperature regulation (conduction type, radiation type, convection type), and sensors such as temperature sensors and current sensors.
  • FIG. 4 is a cross-sectional view schematically showing an example of the top ring 221.
  • the top ring 221 includes a top ring main body 2210 attached to a top ring shaft 221a, a substantially disc-shaped carrier 2211 housed in the top ring main body 2210, and a carrier 2211 disposed below the carrier 2211, and the top ring 221 is configured to move the wafer W onto a polishing pad.
  • a substantially annular retainer ring 2213 that is placed around the outer periphery of the carrier 2211 and the elastic membrane 2212 and directly presses the polishing pad 2200 , and the top ring body 2210 and the retainer ring 2213 .
  • a retaining ring airbag 2214 is provided as a retaining ring pressing mechanism that is disposed at and presses the retaining ring 2213 against the polishing pad 2200.
  • the retaining ring airbag 2214 is used as the retaining ring pressing mechanism, but the retaining ring pressing mechanism may be a fluid actuator using air, water, oil, etc., an electric actuator using a ball screw, etc., a spring or a bag. An elastic member including a shaped bag may be used.
  • the elastic membrane 2212 is formed of an elastic membrane, and has a plurality of concentric partition walls 2212e therein, so that first to second partition walls 2212e are arranged concentrically from the center of the top ring main body 2210 toward the outer circumference. It has fourth elastic membrane pressure chambers 2212a to 2212d. Further, the elastic film 2212 has a plurality of holes 2212f for adsorbing the wafer W on its lower surface, and functions as a substrate holding surface for holding the wafer W.
  • the retaining ring airbag 2214 is formed of an elastic membrane and has a retaining ring pressure chamber 2214a therein.
  • the configuration of the top ring 221 may be changed as appropriate, and it may be provided with a pressure chamber that presses the entire carrier 2211, and the number and shape of the elastic membrane pressure chambers that the elastic membrane 2212 has may be changed as appropriate.
  • the number and arrangement of the suction holes 2212f may be changed as appropriate.
  • the elastic membrane 2212 may not have the suction holes 2212f.
  • First to fourth flow paths 2216A to 2216D are connected to the first to fourth elastic membrane pressure chambers 2212a to 2212d, respectively, and a fifth flow path 2216E is connected to the retaining ring pressure chamber 2214a.
  • the first to fifth channels 2216A to 2216E communicate with the outside via a top ring rotary connector 2215 provided on the top ring shaft 221a, and are connected to first branch channels 2217A to 2217E and second branch channels 2217A to 2217E. It branches into paths 2218A to 2218E, respectively.
  • Pressure sensors PA to PE are installed in the first to fifth channels 2216A to 2216E, respectively.
  • the first branch channels 2217A to 2217E are connected to a gas supply source GS of pressure fluid (air, nitrogen, etc.) via valves V1A to V1E, flow rate sensors FA to FE, and pressure regulators RA to RE.
  • the second branch channels 2218A to 2218E are connected to the vacuum source VS via valves V2A to V2E, respectively, and are configured to be able to communicate with the atmosphere via valves V3A to V3E.
  • the wafer W is held by suction on the lower surface of the top ring 221 and moved to a predetermined polishing position on the polishing table 220, the wafer W is held against the polishing surface of the polishing pad 2200 to which polishing fluid is supplied from the polishing fluid supply nozzle 222. It is polished by being pressed by the top ring 221. At this time, the top ring 221 presses the wafer W against the polishing pad 2200 with the pressure fluid supplied to the first to fourth elastic membrane pressure chambers 2212a to 2212d by independently controlling the pressure regulators RA to RE.
  • the pressure is adjusted for each region of the wafer W, and the pressing force for pressing the retainer ring 2213 against the polishing pad 2200 is adjusted using the pressure fluid supplied to the retainer ring pressure chamber 2214a.
  • the pressure of the pressure fluid supplied to the first to fourth elastic membrane pressure chambers 2212a to 2212d and the retaining ring pressure chamber 2214a, respectively, is measured by the pressure sensors PA to PE, and the flow rate of the pressure gas is measured by the flow rate sensors FA to 2214a. Each is measured by FE.
  • the substrate transport unit 23 includes first and second linear transporters that are horizontally movable along the direction in which the first to fourth polishing sections 22A to 22D are lined up (the longitudinal direction of the housing 20).
  • a temporary holding table 233 for the wafer W is provided.
  • the first linear transporter 230A is arranged adjacent to the first and second polishing sections 22A and 22B, and has four transport positions (first to fourth transport positions in order from the load/unload unit 21 side). This is a mechanism for transporting the wafer W between TP1 and TP4).
  • the second transport position TP2 is a position where the wafer W is delivered to the first polishing section 22A
  • the third transport position TP3 is a position where the wafer W is delivered to the second polishing part 22B. be.
  • the second linear transporter 230B is arranged adjacent to the third and fourth polishing sections 22C and 22D, and has three transport positions (fifth to seventh transport positions in order from the load/unload unit 21 side). This is a mechanism for transporting the wafer W between TP5 and TP7).
  • the sixth transport position TP6 is a position where the wafer W is delivered to the third polishing section 22C
  • the seventh transport position TP7 is a position where the wafer W is delivered to the fourth polishing part 22D. be.
  • the swing transporter 231 is disposed adjacent to the fourth and fifth transport positions TP4 and TP5, and has a hand that is movable between the fourth and fifth transport positions TP4 and TP5.
  • the swing transporter 231 is a mechanism that transfers the wafer W between the first and second linear transporters 230A and 230B and temporarily places the wafer W on the temporary holding table 233.
  • the lifter 232 is a mechanism that is disposed adjacent to the first transfer position TP1 and transfers the wafer W to and from the transfer robot 211 of the load/unload unit 21.
  • a shutter (not shown) provided on the first partition wall 200A is opened and closed.
  • the cleaning unit 24 includes first and second cleaning chambers 240A and 240B for cleaning the wafer W using a cleaning tool, a drying chamber 241 for drying the wafer W, and a drying chamber 241 for transporting the wafer W. It includes first and second transfer chambers 242A and 242B. Each chamber of the cleaning unit 24 is divided into sections along the first and second linear transporters 230A and 230B, for example, a first cleaning chamber 240A, a first transfer chamber 242A, and a second conveyance chamber 242A.
  • the cleaning chamber 240B, the second transfer chamber 242B, and the drying chamber 241 are arranged in this order (in order of distance from the load/unload unit 21). Note that the number and arrangement of the cleaning chambers 240A, 240B, the drying chamber 241, and the transfer chambers 242A, 242B are not limited to the example shown in FIG. 2, and may be changed as appropriate.
  • the film thickness measuring unit 25 is a measuring device that measures the film thickness of the wafer W before or after the polishing process, and includes, for example, an optical film thickness measuring device, an eddy current type film thickness measuring device, or the like.
  • the transfer robot 211 transfers the wafer W to each film thickness measurement module.
  • FIG. 5 is a block diagram showing an example of the substrate processing apparatus 2. As shown in FIG. The control unit 26 is electrically connected to each unit 21-25 and controls each unit 21-25 in an integrated manner.
  • the control system (module, sensor, sequencer) of the polishing unit 22 will be explained as an example, but since the other units 21, 23 to 25 have the same basic configuration and functions, the explanation will be omitted.
  • the polishing unit 22 is arranged in each subunit (for example, polishing table 220, top ring 221, polishing fluid supply nozzle 222, dresser 223, atomizer 224, etc.) included in the polishing unit 22, and controls a plurality of modules to be controlled. 227 1 to 227 r , and a plurality of sensors 228 1 to 228 s that are respectively arranged in the plurality of modules 227 1 to 227 r and detect data (detected values) necessary for controlling each module 227 1 to 227 r . , and a sequencer 229 that controls the operation of each of the modules 227 1 to 227 r based on the detected values of each of the sensors 228 1 to 228 s .
  • each subunit for example, polishing table 220, top ring 221, polishing fluid supply nozzle 222, dresser 223, atomizer 224, etc.
  • the sensors 228 1 to 228 s of the polishing unit 22 include, for example, a sensor that detects the flow rate of polishing fluid, a sensor that detects the pressing force of the retainer ring pressing mechanism, a sensor that detects the rotational torque of the top ring 221, and a sensor that detects the rotational torque of the polishing table 220.
  • a sensor that detects the rotational torque of , a timer that measures the time until the end point is detected, an optical sensor that detects the end point, an environmental sensor 225, and the like are included.
  • the rotational torque measures the sliding resistance between the polishing table 220 and the top ring 221 or dresser 223 that are in contact with the polishing surface.
  • the control unit 26 includes a substrate processing control section 260, a communication section 261, an input section 262, an output section 263, and a storage section 264.
  • the control unit 26 is configured with, for example, a general-purpose or dedicated computer (see FIG. 6, which will be described later).
  • 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 functions as a user interface by outputting various information via a display screen, signal tower lighting, and buzzer sound.
  • the storage unit 264 stores various programs (operating system (OS), application programs, web browser, etc.) and data (device setting information 265, substrate recipe information 266, etc.) used in the operation of the substrate processing apparatus 2.
  • the device setting information 265 and the board recipe information 266 are data that can be edited by the user via the display screen.
  • the substrate processing control unit 260 controls a plurality of sensors 218 1 to 218 q , 228 1 to 228 s , and 238 1 to 238 via a plurality of sequencers 219 , 229 , 239 , 249 , and 259 (hereinafter referred to as "sequencer group").
  • sequencers 219 , 229 , 239 , 249 , and 259 hereinafter referred to as "sequencer group”
  • sensor group hereinafter referred to as " sensor group”
  • FIG. 6 is a hardware configuration diagram showing an example of the computer 900.
  • Each of the control unit 26, database device 3, machine learning device 4, information processing device 5, and user terminal device 6 of the substrate processing apparatus 2 is configured by a general-purpose or dedicated computer 900.
  • the computer 900 includes 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, and a communication I/F (interface) as its main components. 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 . Note that the above-mentioned components may be omitted as appropriate depending on the purpose for which the computer 900 is used.
  • the processor 912 includes one or more arithmetic processing units (CPU (Central Processing Unit), MPU (Micro-processing unit), DSP (digital signal processor), GPU (Graphics Processing Unit), NPU (Neural Processing Unit), etc.)
  • the computer 900 is configured as follows and controls the entire computer 900.
  • the memory 914 stores various data and programs 930, and includes, for example, a volatile memory (DRAM, SRAM, etc.) that functions as a main memory, a nonvolatile memory (ROM), a flash memory, etc.
  • the input device 916 includes, for example, a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit.
  • the output device 917 is configured with, for example, a sound (voice) output device, a vibration device, etc., and functions as an output section.
  • the display device 918 is configured with, for example, a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit.
  • Input device 916 and display device 918 may be configured integrally, such as a touch panel display.
  • the storage device 920 is configured with, for example, an HDD, an SSD (Solid State Drive), etc., and functions as a storage unit. The storage device 920 stores various data necessary for executing the operating system and programs 930.
  • the communication I/F section 922 is connected to a network 940 such as the Internet or an intranet (which may be the same as the network 7 in FIG. 1) by wire or wirelessly, and exchanges data with other computers according to a predetermined communication standard. It functions as a communication unit that sends and receives information.
  • the external device I/F section 924 is connected to an external device 950 such as a camera, printer, scanner, reader/writer, etc. by wire or wirelessly, and serves as a communication section that sends and receives data to and from the external device 950 according to a predetermined communication standard. Function.
  • the I/O device I/F unit 926 is connected to an I/O device 960 such as various sensors and actuators, and transmits, for example, a detection signal from a sensor, a control signal to an actuator, etc. with the I/O device 960. It functions as a communication unit that sends and receives various signals and data.
  • the media input/output unit 928 is configured with a drive device such as a DVD drive or a CD drive, and reads and writes data on a medium (non-temporary storage medium) 970 such as a DVD or a CD.
  • the processor 912 calls the program 930 stored in the storage device 920 to the memory 914 and executes it, and controls each part of the computer 900 via the bus 910.
  • the program 930 may be stored in the memory 914 instead of the storage device 920.
  • the program 930 may be recorded on the medium 970 in an installable file format or an executable file format, and provided to the computer 900 via the media input/output unit 928.
  • the program 930 may be provided to the computer 900 by being downloaded via the network 940 via the communication I/F unit 922.
  • the computer 900 may implement various functions achieved by the processor 912 executing the program 930 using hardware such as an FPGA or an ASIC.
  • the computer 900 is, for example, a stationary computer or a portable computer, and is any type of electronic device.
  • the computer 900 may be a client computer, a server computer, or a cloud computer.
  • the computer 900 may also be applied to devices other than the devices 2 to 6.
  • FIG. 7 is a data configuration diagram showing an example of production history information 30 managed by the database device 3.
  • the production history information 30 includes, for example, a wafer history table 300 for each wafer W, as a table in which reports R acquired when substrate processing is performed on wafers W for main production are classified and registered; A polishing history table 301 regarding device status information in polishing processing is provided.
  • the production history information 30 includes a cleaning history table regarding device status information in cleaning processing, an event history table regarding event information, an operation history table regarding operation information, etc., but detailed description thereof will be omitted.
  • each record of the wafer history table 300 for example, a wafer ID, cassette number, slot number, start time and end time of each process, used unit ID, etc. are registered. Note that although FIG. 7 shows a polishing process and a cleaning process, other processes are also registered in the same way.
  • wafer ID For example, wafer ID, wear state information, processing state information, etc. are registered in each record of the polishing history table 301.
  • the wear state information is information indicating the wear state of each component of the substrate processing apparatus 2 that can be obtained before polishing.
  • the wear status information includes, for example, information indicating the condition of the polishing pad 2200, information indicating the condition of the top ring rotary connector 2215, information indicating the condition of the polishing table rotary connector 2201, information indicating the condition of the dresser 223, and information indicating the condition of the substrate processing control unit. This information indicates the condition of H.260.
  • the information indicating each condition includes at least the usage time of each component and the number of wafers processed.
  • the processing state information is information indicating the processing state of the substrate processing apparatus 2 that can be obtained during the polishing process.
  • the processing state information is provided by, for example, a sensor group such as a polishing fluid flow rate sensor of the substrate processing apparatus 2, a pressing force sensor of the retainer ring pressing mechanism, a rotational torque sensor of the top ring 221, or a rotational torque sensor of the polishing table 220. These are detection values of each sensor sampled at predetermined time intervals.
  • the processing state information is, for example, a statistical value of the time until end point detection for each wafer W, and a statistical value of sensor time series data for each wafer W.
  • time-series data of each sensor can be extracted as the device state of the substrate processing apparatus 2 when the polishing process was performed on the wafer W specified by the wafer ID.
  • FIG. 8 is a data configuration diagram showing an example of the polishing test information 31 managed by the database device 3. As shown in FIG.
  • the polishing test information 31 includes a polishing test table 310 in which reports R and test results obtained when a polishing test is performed are classified and registered.
  • a test ID, wear state information, processing state information, test result information, etc. are registered in each record of the polishing test table 310.
  • the wear state information and processing state information of the polishing test table 310 are information indicating the state of each part in the polishing test, and the data structure is the same as that of the polishing history table 301, so detailed explanation will be omitted. .
  • the test result information is information indicating the state of the test polishing device when the polishing process was performed in the polishing test.
  • the test result information may be a measurement value measured by a polishing device measuring device provided in a polishing device for testing.
  • the test result information shown in FIG. 8 includes the number of wafers processed 1, 2, . . . , m, . . . , n and usage times t1, t2, .
  • the reliability of end point detection at each time tm1, tm2, ..., ...tmm, ..., tmn included in the m-th polishing processing period, signs of reliability deterioration, and types of components that cause reliability deterioration are also shown.
  • types of processes TR1 to TR4 that cause a decrease in reliability respectively.
  • time series data of each sensor indicating the state of the polishing unit 22 when the polishing process is performed and the end point detection function at that time can be obtained.
  • reliability can be extracted.
  • the signs of a decline in the reliability of the end point detection function can be determined by using data from the first target period of the polishing process, which is before the time tmm when the reliability of the end point detection function has decreased.
  • data of the second target period including the time point tmm at which the reliability of the end point detection function decreases may be used.
  • FIG. 9 is a block diagram showing an example of the machine learning device 4 according to the first embodiment.
  • the machine learning device 4 includes a machine learning control section 40, a communication section 41, a learning data storage section 42, and a learned model storage section 43.
  • the machine learning control unit 40 functions as a learning data acquisition unit 400 and a machine learning unit 401.
  • the communication unit 41 is connected to external devices (for example, the substrate processing device 2, the database device 3, the information processing device 5, the user terminal device 6, the polishing test device (not shown), etc.) via the network 7, and is connected to various external devices. Functions as a communication interface for sending and receiving data.
  • the learning data acquisition unit 400 is connected to an external device via the communication unit 41 and the network 7, and receives reliability deterioration factor state information as input data and reliability information of the polishing end point detection function as output data.
  • First learning data 11A configured as a set is acquired.
  • the first learning data 11A is data used as teacher data (training data), verification data, and test data in supervised learning.
  • the reliability information of the polishing end point detection function is data used as a correct answer label in supervised learning.
  • the learning data storage unit 42 is a database that stores a plurality of sets of first learning data 11A acquired by the learning data acquisition unit 400. Note that the specific configuration of the database that constitutes the learning data storage section 42 may be designed as appropriate.
  • the machine learning unit 401 performs machine learning using the plurality of sets of first learning data 11A stored in the learning data storage unit 42. That is, the machine learning unit 401 inputs a plurality of sets of first learning data 11A to the first learning model 10A, and compares the reliability deterioration factor state information included in the first learning data 11A with the polishing end point detection function. By causing the first learning model 10A to learn the correlation with the reliability information, a trained first learning model 10A is generated.
  • the trained model storage unit 43 is a database that stores the trained first learning model 10A (specifically, the adjusted weight parameter group) generated by the machine learning unit 401.
  • the trained first learning model 10A stored in the trained model storage unit 43 is provided to the actual system (for example, the information processing device 5) via the network 7, a recording medium, or the like. Note that although the learning data storage section 42 and the learned model storage section 43 are shown as separate storage sections in FIG. 9, they may be configured as a single storage section.
  • the number of first learning models 10A stored in the learned model storage unit 43 is not limited to one, and may be changed depending on, for example, the machine learning method, the mechanism or material of the top ring 221, or the type of the elastic membrane 2212. , the type of retainer ring 2213, the type of polishing pad 2200, the type of polishing fluid, the type of data included in the reliability deterioration factor state information, the type of data included in the reliability information of the polishing end point detection function, etc.
  • a plurality of learning models with different conditions may be stored.
  • the learning data storage unit 42 may store a plurality of types of learning data each having a data structure corresponding to a plurality of learning models with different conditions.
  • FIG. 10 is a diagram showing an example of the first learning model 10A and the first learning data 11A.
  • the first learning data 11A used for machine learning of the first learning model 10A is composed of reliability deterioration factor state information and reliability information of the polishing end point detection function.
  • the reliability deterioration factor state information constituting the first learning data 11A includes wear state information indicating the wear state of the components of the substrate processing apparatus 2, and processing state information of the substrate processing apparatus 2 that can be acquired during polishing. Contains the polishing status information shown.
  • the wear state information included in the reliability deterioration factor state information is information indicating the wear state of the constituent elements of the substrate processing apparatus 2.
  • the wear state information includes, for example, at least one of the condition of the polishing pad 2200, the condition of the top ring rotary connector 2215, the condition of the polishing table rotary connector 2201, the condition of the dresser 223, and the condition of the substrate processing control unit 260.
  • the condition of the polishing pad 2200 includes at least the usage time of the polishing pad 2200 and the number of wafers processed by the polishing pad 2200.
  • the conditions of the polishing pad 2200 include, for example, the cumulative number of rotations of the polishing table 220, the rotation speed of the polishing table 220, the rotational torque of the polishing table 220, the presence or absence of dressing, the presence or absence of replacement, an image of the surface, surface shape, and flatness. , cleanliness, humidity, etc.
  • the condition of polishing pad 2200 may change over time during the polishing process.
  • the condition of the top ring rotary connector 2215 includes at least the usage time of the top ring 221 and the number of wafers processed by the top ring 221. Further, the condition of the top ring rotary connector 2215 may be set based on, for example, the cumulative number of rotations of the top ring 221, the rotation speed of the top ring 221, the rotation torque of the top ring 221, and the like. The condition of the top ring 221 may change over time during the polishing process, for example.
  • the condition of the polishing table rotary connector 2201 includes at least the usage time of the polishing table 220 and the number of wafers processed by the polishing table 220. Further, the condition of the polishing table rotary connector 2201 may be set based on, for example, the cumulative number of rotations of the polishing table 220, the rotation speed of the polishing table 220, the rotation torque of the polishing table 220, and the like. For example, the condition of the polishing table 220 may change over time during the polishing process.
  • the condition of the dresser 223 includes at least the usage time of the dresser 223 and the number of wafers processed by the polishing table 220.
  • the condition of the dresser 223 includes, for example, the cumulative number of rotations of the dresser 223, the rotation speed of the dresser 223, the rotation torque of the dresser 223, the presence or absence of dressing, the presence or absence of replacement, an image of the surface, surface shape, flatness, and cleanliness. It may also be set based on the temperature, humidity, etc. For example, the condition of the dresser 223 may change over time during the polishing process.
  • the condition of the substrate processing control section 260 includes at least the usage time of the substrate processing control section 260 and the number of wafers processed by the substrate processing control section 260.
  • the conditions of the substrate processing control unit 260 may change over time during the polishing process, for example.
  • the processing state information included in the reliability deterioration factor state information is information indicating the processing state of the substrate processing apparatus 2 that can be obtained during the polishing process.
  • the processing state information includes, for example, the flow rate of the polishing fluid, the pressing force of the retainer ring pressing mechanism, the rotational torque of the top ring 221, the rotational torque of the polishing table 220, the swinging torque of the top ring 221, the vibration of the top ring 221, and the dresser 223. oscillating torque during polishing, noise during polishing, temperature of the polishing surface, temperature control water temperature of polishing table 220, statistical values of time until end point detection for each wafer, and statistical values of sensor time series data for each wafer. Contains at least one.
  • the flow rate of the polishing fluid may be the flow rate of the polishing fluid supplied from the polishing fluid supply nozzle 222.
  • the pressing force of the retaining ring pressing mechanism may be the pressure within the retaining ring pressure chamber 2214a of the retaining ring airbag 2214, the flow rate of the pressure fluid supplied to the retaining ring pressure chamber 2214a, or the like.
  • the rotational torque of the top ring 221 may be determined from the motor current that drives the top ring 221 or the like.
  • the rotational torque of the polishing table 220 may be determined from the motor current that drives the polishing table 220 or the like.
  • the swing torque of the top ring 221 may be the top ring swing torque applied to the top ring swing arm 221f, which is detected by the top ring swing torque sensor 221h.
  • the vibration of the top ring 221 may be the vibration of the top ring 221 during polishing, which is measured by the acceleration sensor 221j attached to the top ring 221.
  • the swinging torque of the dresser 223 may be, for example, the dresser swinging torque applied to the dresser swinging arm 223f detected by the dresser swinging torque sensor 223h.
  • the noise during polishing may be the noise during polishing measured by the noise measuring device 221k provided near the top ring 221.
  • the temperature of the polishing surface may be the surface temperature of the polishing pad 2200 or the surface temperature of the grindstone measured by the radiation thermometer 220c1 installed above the polishing table 220.
  • the temperature of the temperature controlled water of the polishing table 220 may be the temperature of the supplied temperature controlled water measured by the supplied temperature controlled water thermometer 220d3.
  • the statistical value of the time until end point detection for each wafer may be obtained from the measured time until end point detection for each wafer.
  • the time required to detect the end point of each measured wafer may be divided into predetermined ranges and calculated from the number of data for each range.
  • Statistical values of sensor time series data for each wafer may be obtained from time series data measured by sensors such as the flow rate, pressing force, rotational torque, etc. of the constituent elements.
  • the time required to detect the end point of the measured time series data may be divided into predetermined ranges, and the number of data for each range may be determined.
  • the statistical values obtained in this way may be used as they are, after processing such as noise reduction so that they can be easily captured by a measuring instrument, or by using the results of statistical processing. In any case, it is sufficient if the dispersion of the results can be determined.
  • the top ring status information included in the polishing process status information includes the pressure in the retaining ring pressure chamber 2214a (retaining ring airbag pressure), It includes the flow rate of pressure fluid (retaining ring airbag flow rate) supplied to the retaining ring pressure chamber 2214a.
  • the pressing force of the retaining ring pressing mechanism in the machining state information included in the reliability reduction factor status information is determined by the amount of elements that adjust the pressing force of the retaining ring pressing mechanism. good.
  • the pressing force of the electric actuator may be the amount of current that adjusts the pressing force of the electric actuator.
  • the pressing force of the retaining ring pressing mechanism may be a vertical position that adjusts the pressing force of the elastic member and the pressing force of the elastic member.
  • the reliability information of the polishing end point detection function that constitutes the first learning data 11A indicates the reliability of the polishing end point detection function of the wafer W that has been subjected to the polishing process in the state shown in the reliability deterioration factor state information. It is information.
  • the reliability information of the polishing end point detection function includes information on the current reliability of end point detection, information on a sign of reliability deterioration, information on the type of component that causes reliability deterioration, and reliability deterioration. This is information on the type of process that is a factor.
  • the learning data acquisition unit 400 acquires the first learning data 11A by referring to the polishing test information 31 and accepting user input operations via the user terminal device 6 as necessary. For example, by referring to the polishing test table 310 of the polishing test information 31, the learning data acquisition unit 400 determines the wear state of the components of the substrate processing apparatus 2 when the polishing test specified by the test ID is performed.
  • the consumption state information shown in FIG. 1 and the processing state information showing the processing state of the substrate processing apparatus 2 that can be obtained during the polishing process are acquired as reliability deterioration factor state information.
  • reliability deterioration factor state information is acquired as time series data of a sensor group, but it may be changed as appropriate depending on the configuration of the polishing unit 22 (in particular, the top ring 221 and the polishing table 220). May be changed.
  • a command value to the module may be used, a parameter converted from a sensor detection value or a command value to the module may be used, or detection values of multiple sensors may be used. Parameters calculated based on may also be used.
  • the reliability deterioration factor state information may be acquired as time series data for the entire polishing process period, or as time series data for a target period that is a part of the polishing process period, or for example, It may also be acquired as point-in-time data at a specific target point, such as the point in time when the reliability of the end point detection function decreases.
  • the data structure of the input data in the first learning model 10A and the first learning data 11A may be changed as appropriate.
  • the learning data acquisition unit 400 acquires the test result information when the polishing test specified by the same test ID is performed. Obtained as reliability information of the polishing end point detection function corresponding to the deterioration factor status information.
  • the reliability information of the polishing end point detection function includes reliability information of the current end point detection, information on the sign of reliability deterioration, and the type of component that causes the reliability deterioration, as shown in FIG. A case will be explained in which the information is process type information that causes a decrease in reliability.
  • the current end point detection reliability information is information about what percentage the current end point detection reliability is.
  • the reliability may be classified on a scale of 0 to 100%. For example, if the reliability of the current endpoint detection is 100%, the current endpoint detection is reliable, and if the reliability of the current endpoint detection is 0%, the current endpoint detection is unreliable. It can be determined that there is.
  • the predictor information of reliability decline is information about the time until the end point detection reliability is reduced or the end point is not detected, or the number of sheets to be processed. For example, if there is a high possibility that the reliability of end point detection will decrease in the polishing process several hours or several sheets from now, some kind of treatment can be performed on the substrate processing apparatus 2 before that.
  • the type information of the component that causes a decrease in reliability is information about the type of component that causes a decrease in the reliability of end point detection, among the components prepared in advance. For example, if the top ring is a factor that reduces the reliability of end point detection, some kind of treatment can be taken for the top ring.
  • the information on the type of process that causes a decrease in reliability is information on the type of process that causes a decrease in the reliability of end point detection among the previously prepared processes. For example, if the factor that reduces the reliability of end point detection is the film formation process, some measures can be taken to improve the film strength, film thickness, variation, etc. in the film formation process.
  • the first learning model 10A employs, for example, a neural network structure, and includes an input layer 100, an intermediate layer 101, and an output layer 102. Synapses (not shown) connecting each neuron are placed between each layer, and each synapse is associated with a weight. A weight parameter group consisting of the weight of each synapse is adjusted by machine learning.
  • the input layer 100 has a number of neurons corresponding to the reliability reduction factor state information as input data, and each value of the reliability reduction factor state information is input to each neuron.
  • the output layer 102 has a number of neurons corresponding to the reliability information of the polishing end point detection function as output data, and the prediction result (inference result) of the reliability information of the polishing end point detection function with respect to the reliability deterioration factor state information is , is output as output data.
  • the reliability information of the polishing end point detection function is output as a numerical value normalized to a predetermined range (for example, 0 to 1).
  • the reliability information of the polishing end point detection function is set within a predetermined range (for example, 0 to 1) as a score (accuracy) for each class. Each is output as a normalized value.
  • Inference results corresponding to numerical values are set in advance in the "predetermined range (0 to 1)".
  • the "predetermined range (0 to 1)” that is the inference result is divided into multiple ranges, and the current end point detection reliability ( 0 to 100%) may be set.
  • the "predetermined range (0 to 1)" which is the inference result is divided into multiple ranges, and the predictive time until reliability deterioration is set for each divided range. That's fine.
  • a predetermined threshold is set between the "predetermined range (0 to 1)" that is the inference result of each component, and the output value is the threshold value. If it is less than or equal to the threshold, the component may be set as "not a factor in reducing reliability", and if it exceeds a threshold value, it may be set as "being a factor in reducing reliability”. Note that each component may be prepared in advance and a respective threshold value may be set for each component.
  • a predetermined threshold value is set between the "predetermined range (0 to 1)" that is the inference result of each process, and the output value is the threshold value. If the process is less than or equal to the threshold value, the process may be set as "not a factor in reducing reliability," and if it exceeds a threshold value, it may be set as "a factor in reducing reliability.” Note that each process may be prepared in advance and a respective threshold value may be set for each process.
  • FIG. 11 is a flowchart illustrating an example of a machine learning method by the machine learning device 4.
  • step S100 the learning data acquisition unit 400 acquires a desired number of first learning data 11A from the polishing test information 31 etc. as advance preparation for starting machine learning, and the acquired first learning data 11A. 1 learning data 11A is stored in the learning data storage section 42.
  • the number of first learning data 11A prepared here may be set in consideration of the inference accuracy required for the first learning model 10A finally obtained.
  • step S110 the machine learning unit 401 prepares the first learning model 10A before learning in order to start machine learning.
  • the first learning model 10A before learning prepared here is configured by the neural network model illustrated in FIG. 10, and the weight of each synapse is set to an initial value.
  • step S120 the machine learning unit 401 randomly selects one set of first learning data 11A from the plurality of sets of first learning data 11A stored in the learning data storage unit 42. get.
  • the machine learning unit 401 converts the polishing process state information (input data) included in the set of first learning data 11A into the prepared first learning data before learning (or during learning). It is input to the input layer 100 of the learning model 10A.
  • the reliability information (output data) of the polishing end point detection function is output as an inference result from the output layer 102 of the first learning model 10A, but the output data is different from the first learning model before learning (or during learning). It is generated by the learning model 10A of . Therefore, in the state before learning (or during learning), the output data output as the inference result contains information different from the reliability information (correct label) of the polishing end point detection function included in the first learning data 11A. show.
  • step S140 the machine learning unit 401 outputs the reliability information (correct label) of the polishing end point detection function included in the set of first learning data 11A acquired in step S120 and the output in step S130.
  • Machine learning is performed by comparing the reliability information (output data) of the polishing end point detection function output as the inference result from the layer and adjusting the weight of each synapse (backpropagation).
  • the machine learning unit 401 causes the first learning model 10A to learn the correlation between the reliability reduction factor state information and the reliability information of the polishing end point detection function.
  • step S150 the machine learning unit 401 determines whether or not a predetermined learning end condition is satisfied using, for example, the reliability information (correct label) of the polishing end point detection function included in the first learning data 11A. and the reliability information (output data) of the polishing end point detection function output as the inference result, and the evaluation value of the error function based on the reliability information (output data) of the polishing end point detection function output as the inference result, and the unlearned first learning data stored in the learning data storage unit 42. The determination is made based on the remaining number of 11A.
  • step S150 if the machine learning unit 401 determines that the learning end condition is not satisfied and machine learning is to be continued (No in step S150), the process returns to step S120 and the first learning model 10A that is currently learning is On the other hand, the steps S120 to S140 are performed multiple times using the unlearned first learning data 11A. On the other hand, in step S150, if the machine learning unit 401 determines that the learning termination condition is satisfied and the machine learning is to be terminated (Yes in step S150), the process proceeds to step S160.
  • step S160 the machine learning unit 401 stores the learned first learning model 10A (adjusted weight parameter group) generated by adjusting the weight associated with each synapse in the learned model memory. 43, and the series of machine learning methods shown in FIG. 11 is completed.
  • step S100 corresponds to a learning data storage step
  • steps S110 to S150 correspond to a machine learning step
  • step S160 corresponds to a learned model storage step.
  • the polishing end point detection function indicates the state of the wafer W from the reliability deterioration factor state information including the wear state information and the processing state information. It is possible to provide a first learning model 10A that can predict (infer) reliability information of.
  • FIG. 12 is a block diagram showing an example of the information processing device 5 according to the first embodiment.
  • FIG. 13 is a functional explanatory diagram showing an example of the information processing device 5 according to the first embodiment.
  • the information processing device 5 includes an information processing control section 50, a communication section 51, and a learned model storage section 52.
  • the information processing control unit 50 functions as an information acquisition unit 500, a state prediction unit 501, and an output processing unit 502.
  • the communication unit 51 is connected to external devices (for example, the substrate processing device 2, the database device 3, the machine learning device 4, the user terminal device 6, etc.) via the network 7, and serves as a communication interface for transmitting and receiving various data. Function.
  • the information acquisition section 500 is connected to an external device via the communication section 51 and the network 7, and acquires reliability deterioration factor state information including wear state information and processing state information.
  • the information acquisition unit 500 When performing "real-time prediction processing" of the reliability information of the polishing end point detection function for a wafer W in the middle of polishing, the information acquisition unit 500 By receiving the report R regarding reliability deterioration factor state information from the device 2 at any time, the wear state information and processing state information during the polishing process on the wafer W are converted into reliability deterioration factor state information. obtained from time to time.
  • the state prediction unit 501 inputs the reliability reduction factor state information acquired by the information acquisition unit 500 as input data to the first learning model 10A, thereby determining the reliability reduction factor state information indicated in the reliability reduction factor state information. Reliability information of a polishing end point detection function for a wafer W undergoing polishing processing is predicted.
  • the trained model storage unit 52 is a database that stores the trained first learning model 10A used by the state prediction unit 501.
  • the number of first learning models 10A stored in the learned model storage unit 52 is not limited to one, and may vary depending on, for example, the machine learning method, the mechanism or material of the top ring 221, or the type of elastic membrane 2212. , the type of retainer ring 2213, the type of polishing pad 2200, the type of polishing fluid, the type of data included in the reliability deterioration factor state information, the type of data included in the reliability information of the polishing end point detection function, etc.
  • a plurality of trained models with different states may be stored and selectively available.
  • the learned model storage unit 52 may be replaced by a storage unit of an external computer (for example, a server type computer or a cloud type computer), and in that case, the state prediction unit 501 will be able to access the external computer.
  • an external computer for example, a server type computer or a cloud type computer
  • the output processing unit 502 performs output processing to output the reliability information of the polishing end point detection function generated by the state prediction unit 501. For example, the output processing unit 502 transmits the reliability information of the polishing end point detection function to the user terminal device 6, so that a display screen based on the reliability information of the polishing end point detection function is displayed on the user terminal device 6. Alternatively, by transmitting the reliability information of the polishing end point detection function to the database device 3, the reliability information of the polishing end point detection function may be registered in the production history information 30.
  • FIG. 14 is a flowchart illustrating an example of an information processing method by the information processing device 5. Below, an example of operation will be described in which the user operates the user terminal device 6 to perform "prediction processing" on reliability information of the polishing end point detection function for a specific wafer W.
  • step S200 when the user performs an input operation on the user terminal device 6 to input a wafer ID that specifies a wafer W to be predicted, the user terminal device 6 inputs the wafer ID to the information processing device 5. Send to.
  • step S210 the information acquisition unit 500 of the information processing device 5 receives the wafer ID transmitted in step S200.
  • step S211 the information acquisition unit 500 uses the wafer ID received in step S210 to refer to the polishing history table 301 of the production history information 30, so that the wafer W specified by the wafer ID is polished. Obtain reliability deterioration factor status information when the process is performed.
  • step S220 the state prediction unit 501 inputs the reliability reduction factor state information acquired in step S211 as input data to the first learning model 10A, thereby Reliability information of the polishing end point detection function is generated as output data, and the state of the wafer W is predicted.
  • step S230 the output processing unit 502 outputs the reliability information of the polishing end point detection function to the user terminal device as output processing for outputting the reliability information of the polishing end point detection function generated in step S220. Send to 6.
  • the destination of the reliability information of the polishing end point detection function may be the database device 3 in addition to or instead of the user terminal device 6.
  • step S240 when the user terminal device 6 receives the reliability information of the polishing end point detection function transmitted in step S230 as a response to the transmission process of step S200, the user terminal device 6 receives the reliability information of the polishing end point detection function.
  • steps S210 and S211 correspond to an information acquisition step
  • step S220 corresponds to a state prediction step
  • step S230 corresponds to an output processing step.
  • reliability reduction factor information in the polishing process is inputted to the first learning model 10A. Since the reliability information of the polishing end point detection function is predicted based on the state information, the reliability information of the polishing end point detection function, which indicates the reliability of the end point detection function that detects that the chemical mechanical polishing process has reached the end point, can be appropriately predicted. can do.
  • the second embodiment differs from the first embodiment in that an optical sensor is used as a polishing end point detection function.
  • an optical sensor is used as a polishing end point detection function.
  • a machine learning device 4a and an information processing device 5a according to the second embodiment will be described, focusing on the differences from the first embodiment.
  • FIG. 15 is a schematic diagram for explaining the optical sensor 226 provided on the polishing table 220 according to the second embodiment.
  • an optical sensor 226 that detects the state of the film on the wafer W is embedded inside the polishing table 220.
  • the optical sensor 226 irradiates the wafer W with light and detects the state (film thickness, etc.) of the film on the wafer W based on the intensity (reflection intensity or reflectance) of the reflected light from the wafer W.
  • a light transmitting portion 2200a is attached to the polishing pad 2200 to transmit light from the optical sensor 226.
  • the light transmitting portion 2200a is made of a material with high transmittance, such as quartz glass, a glass material, or pure water (with a transparent fluid supply portion and flow path not shown).
  • the light transmitting portion 2200a may be configured by providing a through hole in the polishing pad 2200, and flowing a transparent fluid such as pure water from below from the transparent fluid supply portion while the through hole is blocked by the wafer W. .
  • the transparent portion 2200a is arranged at a position passing through the center of the wafer W held by the top ring 221.
  • the optical sensor 226B includes a light source 226a, a light emitting optical fiber 226b serving as a light emitting section that irradiates the surface to be polished of the wafer W with light from the light source 226a, and a light emitting optical fiber 226b that emits light reflected from the surface to be polished.
  • a light-receiving optical fiber 226c serving as a light-receiving section for receiving light, a spectroscope for dispersing the light received by the light-receiving optical fiber 226c, and a plurality of light-receiving elements for accumulating the light separated by the spectrometer as electrical information are installed inside.
  • a spectrometer unit 226d an operation control section 226e that controls the timing of turning on and off the light source 226a and the start of reading of the light receiving element in the spectrometer unit 226d, and a power source 226f that supplies power to the operation control section 226e. It is equipped with Note that power is supplied to the light source 226a and the spectrometer unit 226d via the operation control section 226e.
  • the light emitting end of the light emitting optical fiber 226b and the light receiving end of the light receiving optical fiber 226c are configured to be substantially perpendicular to the polished surface of the wafer W.
  • a 128-element photodiode array can be used as the light-receiving element in the spectrometer unit 226d.
  • the spectrometer unit 226d is connected to the operation control section 226e. Information from the light receiving element in the spectrometer unit 226d is sent to the operation control section 226e, and spectrum data of reflected light is generated based on this information. That is, the operation control unit 226e reads electrical information accumulated in the light receiving element and generates spectrum data of reflected light. This spectral data indicates the intensity of reflected light resolved according to wavelength, and varies depending on the film thickness.
  • the operation control section 226e is connected to the optical sensor control section 226g. In this way, the spectrum data generated by the operation control section 226e is transmitted to the optical sensor control section 226g.
  • the optical sensor control unit 226g calculates a characteristic value associated with the film thickness of the wafer W based on the spectrum data received from the operation control unit 226e, and uses this as a monitoring signal to detect the end point. Note that the optical sensor control section 226g may be included in the substrate processing control section 260.
  • FIG. 16 is a block diagram showing an example of a machine learning device 4a according to the second embodiment.
  • FIG. 17 is a diagram showing an example of the second learning model 10B and the second learning data 11B.
  • the second learning data 11B is used for machine learning of the second learning model 10B.
  • the reliability deterioration factor state information constituting the second learning data 11B includes the condition of the optical sensor 226 and the condition of the transparent liquid supply section as consumption state information, and the condition of the optical sensor 226 as processing state information. Light reflection intensity information and transparent liquid flow rate information are added. Note that other reliability deterioration factor state information constituting the second learning data 11B is the same as that in the first embodiment, and therefore a description thereof will be omitted.
  • the condition of the optical sensor 226 includes at least the usage time of the optical sensor 226 and the number of wafers processed by the optical sensor 226.
  • the condition of the optical sensor 226 may be set based on, for example, the usage time of the light source 226a such as a lamp of the optical sensor 226, the temperature of the optical sensor 226, and the like.
  • the condition of the optical sensor 226 may change over time during the polishing process.
  • the conditions of the pure water transparent liquid supply section include at least the usage time of the pure water supply section and the number of wafers processed by the polishing unit 22.
  • the condition of the transparent liquid supply section may be set based on, for example, the cumulative supply flow rate of the transparent liquid supply section.
  • the condition of the transparent liquid supply section may change over time during the polishing process.
  • the light reflection intensity information of the optical sensor 226 may be the intensity of the reflected light emitted by the optical sensor 226 and reflected by the wafer W.
  • the transparent liquid information may be the flow rate of transparent liquid such as pure water supplied from the transparent liquid supply section.
  • the learning data acquisition unit 400 acquires the second learning data 11B by referring to the polishing test information 31 and accepting user input operations via the user terminal device 6 as necessary. For example, by referring to the polishing test table 310 of the polishing test information 31, the learning data acquisition unit 400 obtains wear state information and processing state information (each time series data of each sensor that each component has) is acquired as reliability deterioration factor status information.
  • FIG. 18 is a block diagram showing an example of an information processing device 5a that functions as the information processing device 5a according to the second embodiment.
  • FIG. 19 is a functional explanatory diagram showing an example of the information processing device 5a according to the second embodiment.
  • the information acquisition unit 500 acquires reliability deterioration factor state information including wear state information and processing state information.
  • the information acquisition unit 500 When performing "post-prediction processing" of the reliability information of the polishing end point detection function for the wafer W after the polishing process has already been performed, the information acquisition unit 500 refers to the polishing history table 301 of the production history information 30. Therefore, wear state information and processing state information when the polishing process is performed on the wafer W may be acquired as reliability deterioration factor state information.
  • the state prediction unit 501 inputs the reliability reduction factor state information acquired by the information acquisition unit 500 as input data to the second learning model 10B, thereby determining the reliability reduction factor state information indicated in the reliability reduction factor state information. Reliability information of a polishing end point detection function for a wafer W undergoing polishing processing is predicted.
  • the reliability deterioration factor state information including the wear state information and the machining state information in the polishing process is used in the second learning model 10B. Since the reliability of the polishing end point detection function with respect to the reliability deterioration factor status information is predicted by inputting the above information, it is possible to appropriately predict the reliability of the polishing end point detection function of the wafer W in the polishing process.
  • the optical sensor 226 is used to detect the polishing end point of the wafer W, but other polishing end point detection functions may be used.
  • an eddy current sensor may be used as another example of the polishing end point detection function.
  • the eddy current sensor has an excitation coil, and when magnetic lines of force generated from the excitation coil connected to a high-frequency AC power source pass through a conductive film, an eddy current is generated on the surface of the wafer W.
  • the magnitude of this eddy current changes depending on the resistance of the metal film, that is, the thickness of the metal film.
  • lines of magnetic force are generated from the eddy current in a direction opposite to the lines of magnetic force generated from the exciting coil.
  • the change in the thickness of the metal film can be measured by the detection coil measuring the intensity of the magnetic lines of force generated in the opposite direction.
  • the eddy current sensor is installed below the polishing table 220 shown in FIG. 3, and generates lines of magnetic force in the direction penetrating the polishing table 220.
  • the eddy current sensor rotates together with the polishing table 220 and passes below the wafer W held by the top ring 221. At this time, if a conductive film exists on the surface of the wafer W, the magnetic lines of force pass through the conductive film, so that the thickness of the conductive film can be measured.
  • the metal film on the surface of the wafer W decreases, and the resistance value of the metal film increases accordingly. Then, the eddy current generated by the magnetic lines of force generated from the coil of the eddy current sensor decreases, and the strength of the magnetic lines of force generated from the eddy current also decreases. Eddy current sensors convert changes in magnetic lines of force generated by this eddy current into voltages corresponding to changes in film thickness using circuits and software within the sensor.
  • the eddy current sensor measures and stores the detected voltage for the wafer W after polishing in advance, and compares the stored voltage value with the voltage value while the wafer W is being polished. It is preferable to detect the polishing end point by doing this.
  • the analog processing portion may be replaced with digital processing. By using digital processing, eddy current sensors have improved performance and stability.
  • the condition of the eddy current sensor may be used as wear state information, and the magnetic force line strength information of the eddy current sensor may be used as processing state information.
  • the condition of the eddy current sensor includes at least the usage time of the eddy current sensor and the number of wafers processed by the eddy current sensor.
  • the condition of the eddy current sensor may be set based on, for example, the usage time of the excitation coil.
  • the condition of the eddy current sensor may change over time, for example, during a polishing process.
  • the magnetic force line strength information of the eddy current type sensor may be the magnetic force line strength generated in the opposite direction detected by the eddy current type sensor.
  • a rotational torque method may be used as another example of the polishing end point detection function.
  • the rotational torque method is, for example, the rotational torque of a polishing table rotation motor included in the rotational movement mechanism section 220b that rotationally drives the polishing table 220, or the top ring rotation that is included in the topring rotational movement mechanism section 221c that rotationally drives the top ring 221. What is necessary is to detect at least one of the rotational torque of the motor.
  • the polishing resistance rapidly decreases, making it possible to detect when the polishing of the wafer W has ended.
  • polishing end point of the wafer W may be detected by using an optical sensor, an eddy current sensor, a torque method, or a combination of all of them.
  • the database device 3, machine learning device 4, and information processing device 5 are described as being configured as separate devices, but these three devices may be configured as a single device. However, any two of these three devices may be configured as a single device. Further, at least one of the machine learning device 4 and the information processing device 5 may be incorporated in the control unit 26 of the substrate processing device 2 or the user terminal device 6.
  • the substrate processing apparatus 2 has been described as including each of the units 21 to 25, but the substrate processing apparatus 2 only needs to include at least the polishing unit 22, and the other units may be omitted. good.
  • machine learning models include tree types such as decision trees and regression trees, ensemble learning such as bagging and boosting, and neural network types (including deep learning) such as recurrent neural networks, convolutional neural networks, and LSTM. ), hierarchical clustering, non-hierarchical clustering, clustering types such as k-nearest neighbor method and k-means method, multivariate analysis such as principal component analysis, factor analysis, and logistic regression, support vector machine, etc.
  • the test result information is information indicating the state when the polishing process is performed in the polishing test using the dummy wafer in the test equipment, but the test result information is information indicating the state when the polishing process is performed in the polishing test using the dummy wafer in the test equipment.
  • the information may be continuously acquired as information indicating the state when the actual wafer polishing process is performed using the polishing unit 22.
  • the continuously acquired test result information is continuously learned by the machine learning device 4.
  • test result information may be continuously acquired by a person in the polishing unit 22 where no sensor is installed, by determining whether the reliability of the polishing end point detection function has decreased and by labeling the data.
  • the information continuously acquired using the actual polishing unit 22 may be uploaded to the cloud, and after machine learning is performed in the cloud, the learned model may be deployed to the substrate processing apparatus 2. Further, the processing method may be learned within the substrate processing apparatus 2 without being uploaded to the cloud.
  • the present invention is provided in the form of a program (machine learning program) that causes the computer 900 to function as each part of the machine learning device 4, and a program (machine learning program) that causes the computer 900 to execute each step included in the machine learning method. You can also. Further, the present invention provides a program (information processing program) for causing the computer 900 to function as each unit included in the information processing device 5, and a program for causing the computer 900 to execute each step included in the information processing method according to the above embodiment. It can also be provided in the form of (information processing program).
  • the present invention is applicable not only to aspects of the information processing device 5 (information processing method or information processing program) according to the above embodiments, but also to an inference device (inference method) used for inferring reliability information of a polishing end point detection function. or an inference program).
  • the inference device may include a memory and a processor, of which the processor may execute a series of processes.
  • the series of processes includes an information acquisition process (information acquisition step) that acquires reliability deterioration factor state information, and, when reliability deterioration factor state information is acquired in the information acquisition process, polishing using the reliability deterioration factor state information.
  • the method includes an inference process (inference step) for inferring reliability information of a polishing end point detection function indicating the reliability of the polishing end point detection function of the processed substrate.
  • an inference device inference method or inference program
  • it can be applied to various devices more easily than in the case of implementing an information processing device.
  • the inference device inference method or inference program
  • it uses the trained learning model generated by the machine learning device and machine learning method according to the above embodiment to perform state prediction. It will be understood by those skilled in the art that the inference techniques implemented by the Department may also be applied.
  • 1...Substrate processing system 2...Substrate processing device, 3...Database device, 4, 4a... Machine learning device, 5, 5a... Information processing device, 6... User terminal device, 7... Network, 10... learning model, 10A... first learning model, 10B... second learning model, 11A...first learning data, 11B...second learning data, 20...housing, 21...load/unload unit, 22... Polishing unit, 22A to 22D... Polishing section, 23... Substrate transport unit, 24...Cleaning unit, 25...Film thickness measurement unit, 26...Control unit, 30... Production history information, 31... Polishing test information, 40...Machine learning control unit, 41...Communication unit, 42...Learning data storage unit, 43...Learned model storage unit, 50...
  • Information processing control unit 51... Communication unit, 52... Learned model storage unit, 220... Polishing table, 221... Top ring, 222... Polishing fluid supply nozzle, 223...Dresser, 224...Atomizer, 225...Environmental sensor 260...Substrate processing control section, 21...Communication section, 262...Input section, 263...Output section, 264...Storage section, 300... Wafer history table, 301... Polishing history table, 310... Polishing test table, 400...Learning data acquisition unit, 401...Machine learning unit, 500...information acquisition unit, 501...state prediction unit, 502...output processing unit, 900... Computer 2200... Polishing pad, 2210... Top ring body, 2211...
  • Carrier 2212...Elastic membrane, 2212a to 2212d...Elastic membrane pressure chamber, 2213...retainer ring, 2214... Retainer ring airbag (retainer ring pressing mechanism), 2214a...retaining ring pressure chamber, 226...Optical sensor

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Automation & Control Theory (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Finish Polishing, Edge Sharpening, And Grinding By Specific Grinding Devices (AREA)
  • Mechanical Treatment Of Semiconductor (AREA)
  • Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
  • General Factory Administration (AREA)
  • Cleaning Or Drying Semiconductors (AREA)
PCT/JP2023/023932 2022-08-01 2023-06-28 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法 Ceased WO2024029236A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US18/998,420 US20260034636A1 (en) 2022-08-01 2023-06-28 Information processing device, inference device, machine learning device, information processing method, inference method, and machine learning method
CN202380055328.0A CN119631164A (zh) 2022-08-01 2023-06-28 信息处理装置、推论装置、机器学习装置、信息处理方法、推论方法、及机器学习方法
KR1020257002803A KR20250047726A (ko) 2022-08-01 2023-06-28 정보 처리 장치, 추론 장치, 기계 학습 장치, 정보 처리 방법, 추론 방법 및 기계 학습 방법

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2022122766A JP2024019962A (ja) 2022-08-01 2022-08-01 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
JP2022-122766 2022-08-01

Publications (1)

Publication Number Publication Date
WO2024029236A1 true WO2024029236A1 (ja) 2024-02-08

Family

ID=89848872

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/023932 Ceased WO2024029236A1 (ja) 2022-08-01 2023-06-28 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法

Country Status (6)

Country Link
US (1) US20260034636A1 (https=)
JP (1) JP2024019962A (https=)
KR (1) KR20250047726A (https=)
CN (1) CN119631164A (https=)
TW (1) TW202406675A (https=)
WO (1) WO2024029236A1 (https=)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2025170830A (ja) * 2024-05-08 2025-11-20 株式会社荏原製作所 基板研磨装置および膜厚算出方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013176828A (ja) * 2012-02-29 2013-09-09 Ebara Corp 研磨終点検出装置の遠隔監視システム
WO2020235581A1 (ja) * 2019-05-22 2020-11-26 株式会社荏原製作所 基板処理システム

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021028099A (ja) 2019-08-09 2021-02-25 株式会社荏原製作所 終点検知装置、終点検知方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2013176828A (ja) * 2012-02-29 2013-09-09 Ebara Corp 研磨終点検出装置の遠隔監視システム
WO2020235581A1 (ja) * 2019-05-22 2020-11-26 株式会社荏原製作所 基板処理システム

Also Published As

Publication number Publication date
JP2024019962A (ja) 2024-02-14
TW202406675A (zh) 2024-02-16
CN119631164A (zh) 2025-03-14
US20260034636A1 (en) 2026-02-05
KR20250047726A (ko) 2025-04-04

Similar Documents

Publication Publication Date Title
US20250217670A1 (en) Information processing apparatus, inference apparatus, machine-learning apparatus, information processing method, inference method, and machine-learning method
WO2024029236A1 (ja) 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
JP2023116396A (ja) 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
US20250050461A1 (en) Information processing apparatus, inference apparatus, machine-learning apparatus, information processing method, inference method, and machine-learning method
WO2023189165A1 (ja) 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
US20250173611A1 (en) Information processing apparatus, inference apparatus, machine-learning apparatus, information processing method, inference method, and machine-learning method
WO2023149162A1 (ja) 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
US20240399527A1 (en) Information processing apparatus, inference apparatus, machine-learning apparatus, information processing method, inference method, and machine-learning method
CN118434534A (zh) 信息处理装置、推论装置、机器学习装置、信息处理方法、推论方法及机器学习方法
WO2023153208A1 (ja) 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
KR20250038752A (ko) 정보 처리 장치, 기계 학습 장치, 정보 처리 방법 및 기계 학습 방법
JP7753124B2 (ja) 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
US20250303514A1 (en) Information processing device, substrate polishing device, inference device, machine learning device, information processing method, inference method, and machine learning method
JP2023090667A (ja) 情報処理装置、推論装置、機械学習装置、情報処理方法、推論方法、及び、機械学習方法
CN118660786A (zh) 信息处理装置、推论装置、机器学习装置、信息处理方法、推论方法及机器学习方法
WO2024053221A1 (ja) 情報処理装置、機械学習装置、情報処理方法、及び、機械学習方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23849795

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202380055328.0

Country of ref document: CN

WWE Wipo information: entry into national phase

Ref document number: 18998420

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 11202500578R

Country of ref document: SG

WWP Wipo information: published in national office

Ref document number: 11202500578R

Country of ref document: SG

NENP Non-entry into the national phase

Ref country code: DE

WWP Wipo information: published in national office

Ref document number: 202380055328.0

Country of ref document: CN

WWP Wipo information: published in national office

Ref document number: 1020257002803

Country of ref document: KR

122 Ep: pct application non-entry in european phase

Ref document number: 23849795

Country of ref document: EP

Kind code of ref document: A1

WWP Wipo information: published in national office

Ref document number: 18998420

Country of ref document: US