Learning apparatus, information processing apparatus, substrate processing apparatus, substrate processing system, learning method, and processing condition determination method

Abstract

The learning apparatus according to the present invention includes: an experimental data acquisition unit configured to acquire a first processing amount indicating a difference in film thickness before and after processing a film formed on a substrate by driving a substrate processing apparatus under a processing condition including a variation condition indicating a relative position of a nozzle that varies with respect to the substrate as time elapses; a conversion unit that converts, among the variation condition and the processing condition, other conditions other than the variation condition into processing state data indicating a state of processing for concentrically dividing each of a plurality of divided regions on the upper surface of the substrate; and a predictor generation unit that generates a learning model that estimates a second processing amount by performing machine learning on learning data including the processing state data and the first processing amount corresponding to the processing condition.

Description

Technical Field

[0001] The present invention relates to a learning device, an information processing device, a substrate processing device, a substrate processing system, a learning method and a processing condition determination method, and relates to a learning device that generates a learning model that simulates processing according to the processing conditions of a substrate processing device, an information processing device that uses the learning model to determine the processing conditions, a substrate processing device having the information processing device, a substrate processing system having the learning device and the information processing device, a learning method executed by the learning device, and a processing condition determination method executed by the information processing device. Background Art

[0002] There is a cleaning process in the semiconductor manufacturing process. In the cleaning process, the film thickness of the film formed on the substrate is adjusted by etching treatment in which a chemical solution is applied to the substrate. In this film thickness adjustment, it is important to perform the etching treatment in a manner that the surface of the substrate becomes uniform or to flatten the surface of the substrate by etching treatment. In the case of spraying the etching liquid from the nozzle to a part of the substrate, it is necessary to move the nozzle in the radial direction relative to the substrate. However, the etching treatment is a complex process in which the amount of processing of the film to be processed varies depending on the action of moving the nozzle. In addition, the amount of processing of the film to be processed by the etching treatment is determined after the substrate is processed. Therefore, the operation of setting the action of moving the nozzle requires trial and error by the technician. It takes a lot of cost and time to determine the optimal action of the nozzle.

[0003] Patent Document 1 describes a device that uses a learned model that performs machine learning using learning data in which the "input" is the processing amount (etching amount) and the "output" is the scanning speed information, and determines the scanning speed information according to the processing amount set as a target. According to this technology, one scanning speed information is determined according to the processing amount set as a target.

[0004] Patent Document 1: Japanese Patent Application Publication No. 2021-108367 Summary of the invention

[0005] Problem that the invention aims to solve

[0006] On the other hand, it is desirable to make the action of moving the nozzle more complex. The action of moving the nozzle is time series data representing a position that changes over time. If the action of moving the nozzle becomes complex, the sampling interval becomes shorter, and therefore, the dimension of the time series data increases. Usually, when the dimension of the learning data increases, the amount of data required for machine learning increases exponentially. Therefore, since the dimension of the learning data increases, it is difficult to optimize the learning model obtained by machine learning. In addition, etching processing is a complex process, and therefore, the action of the nozzle suitable for the target processing amount is not limited to one, and there may be multiple cases.

[0007] One of the objects of the present invention is to provide a learning device, a learning method, and a substrate processing system suitable for machine learning of conditions that change over time for processing a substrate.

[0008] In addition, another object of the present invention is to provide an information processing device, a substrate processing device, a substrate processing system, and a processing condition determination method that can present a plurality of processing conditions for a processing result of a complex process for processing a substrate.

[0009] Means used to solve problems

[0010] A learning device according to one embodiment of the present invention comprises: an experimental data acquisition unit for acquiring a first processing amount indicating a difference in film thickness before and after the processing of a film formed on a substrate after a substrate processing device is driven to move a nozzle for supplying a processing liquid to a substrate on which a film is formed and to supply the processing liquid to the substrate under processing conditions including a variable condition indicating a relative position of the nozzle relative to the substrate that varies with time to process the film formed on the substrate; a conversion unit for converting the variable condition and other conditions other than the variable condition in the processing condition into processing state data indicating a state of processing of each of a plurality of divided areas on an upper surface of the substrate divided by concentric circles; and a model generation unit for generating a learning model, the learning model performing machine learning on learning data including the processing state data and the first processing amount corresponding to the processing conditions, and inferring a second processing amount indicating a difference in film thickness before and after the processing of the film formed on the substrate before the film is processed by the substrate processing device.

[0011] An information processing device according to another embodiment of the present invention manages a substrate processing device, wherein the substrate processing device processes a film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under a processing condition including a variable condition indicating a relative position of a nozzle that changes with time relative to the substrate; the information processing device includes: a conversion unit that converts the variable condition and other conditions other than the variable condition in the processing condition into processing state data indicating a state of processing of each of a plurality of divided areas on an upper surface of the substrate divided by concentric circles; and a processing condition determination unit that determines a processing condition for driving the substrate processing device using a learning model for a second processing amount that infers a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing device. The learning model is an inference model for machine learning of learning data including processing state data and a first processing amount, wherein the processing state data is processing state data obtained by performing the same conversion as the conversion unit on the variable condition included in the processing condition for processing a film formed on a substrate by the substrate processing device, and the first processing amount is a first processing amount showing the difference in film thickness before and after the film is formed on the substrate after the film is processed by the substrate processing device; the processing condition determination unit assigns the learning model the processing state data obtained by converting the temporary variable condition by the conversion unit, and when the second processing amount inferred by the learning model satisfies the permissible condition, determines the processing condition including the temporary variable condition as the processing condition for driving the substrate processing device.

[0012] A substrate processing system according to another embodiment of the present invention manages a substrate processing device for processing a substrate, wherein the substrate processing device has a learning device and an information processing device; the substrate processing device processes a film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under a processing condition including a variable condition indicating a relative position of a nozzle relative to the substrate that varies with time; the learning device has: an experimental data acquisition unit for acquiring a first processing amount indicating a difference in film thickness before and after the film is processed after the substrate processing device is driven under the processing condition to process the film formed on the substrate; a first conversion unit for converting the variable condition and other conditions other than the variable condition in the processing condition into processing status data indicating a processing status of each of a plurality of divided areas on the upper surface of the substrate divided by concentric circles; and a model generation unit for generating a learning model. A model, which performs machine learning on learning data including processing state data after variable conditions are converted by a first conversion unit and a first processing amount corresponding to the processing conditions, and estimates a second processing amount showing the difference in film thickness before and after the film is processed, for a film formed on a substrate before the film is processed by a substrate processing device; an information processing device comprises: a second conversion unit that is the same as the first conversion unit; and a processing condition determination unit, which determines the processing conditions for driving the substrate processing device using the learning model generated by the learning device; the processing condition determination unit assigns the conversion result after the temporary variable conditions are converted by the second conversion unit to the learning model, and when the second processing amount estimated by the learning model satisfies the permissible condition, determines the processing conditions including the temporary variable conditions as the processing conditions for driving the substrate processing device.

[0013] A learning method according to another embodiment of the present invention causes a computer to perform the following processing: after a substrate processing device that moves a nozzle that supplies a processing liquid to a substrate on which a film is formed and supplies the processing liquid to the substrate is driven with a processing condition including a variable condition indicating a relative position of the nozzle relative to the substrate that changes with the passage of time to process a film formed on a substrate, a first processing amount indicating a difference in film thickness before and after the film is processed is obtained; the variable condition and other conditions other than the variable condition in the processing condition are converted into processing state data indicating a state of processing of each of a plurality of divided areas on the upper surface of the substrate divided by concentric circles; and a learning model is generated that performs machine learning on learning data including the processing state data and the first processing amount corresponding to the processing condition, and infers a second processing amount indicating a difference in film thickness before and after the film is processed for a film formed on the substrate before the film is processed by the substrate processing device.

[0014] A processing condition determination method according to another embodiment of the present invention is executed by a computer managing a substrate processing apparatus, wherein the substrate processing apparatus processes a film formed on a substrate by supplying a processing liquid to the substrate on which the film is formed under a processing condition including a variable condition indicating a relative position of a nozzle that changes with time relative to the substrate; the processing condition determination method includes the following processing: converting the variable condition and other conditions other than the variable condition in the processing condition into processing state data indicating a state of processing of each of a plurality of divided areas on an upper surface of the substrate divided by concentric circles; and determining a learning model for driving the substrate processing apparatus using a second processing amount that infers a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing apparatus. Processing conditions; the learning model is an inference model that performs machine learning on learning data including processing state data and a first processing amount, wherein the processing state data is processing state data in which a variable condition included in a processing condition for a substrate processing device to process a film formed on a substrate is converted in the same manner as a conversion process, and the first processing amount is a first processing amount that shows the difference in film thickness before and after the film is formed on the substrate after the film is processed by the substrate processing device; in the process of determining the processing conditions, the processing state data obtained by converting the temporary variable condition through the conversion process is assigned to the learning model, and when the second processing amount estimated by the learning model satisfies the permissible condition, the processing condition including the temporary variable condition is determined as the processing condition for driving the substrate processing device.

[0015] Effects of the Invention

[0016] The present invention can provide a learning device, a learning method, and a substrate processing system suitable for machine learning of conditions that change over time for processing a substrate.

[0017] In addition, the present invention can provide an information processing device, a substrate processing device, a substrate processing system, and a processing condition determination method that can present a plurality of processing conditions for a processing result of a complex process for processing a substrate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A diagram for explaining a configuration of a substrate processing system according to an embodiment of the present invention.

[0019] Figure 2 This is a diagram showing an example of the structure of an information processing device.

[0020] Figure 3 This is a diagram showing an example of the configuration of a learning device.

[0021] Figure 4This is a diagram showing an example of the functional structure of a substrate processing system according to one embodiment of the present invention.

[0022] Figure 5 A diagram for explaining changes in the relative position of the nozzle with respect to the substrate.

[0023] Figure 6 This is a diagram showing an example of the operation mode of the nozzle.

[0024] Figure 7 This is a diagram showing an example of film thickness characteristics.

[0025] Figure 8 A diagram for explaining segmented regions.

[0026] Fig. 9 This is a diagram showing an example of a change in substrate temperature predicted over time in a divided region.

[0027] Fig.10 is a diagram illustrating the predictor.

[0028] Fig.11 This is a flowchart showing an example of the flow of the predictor generation process.

[0029] Fig.12 This is a flowchart showing an example of the flow of the processing condition determination process.

[0030] Fig.13 This is a flowchart showing an example of the flow of the processing status data generation process.

[0031] Fig.14 This is a diagram showing an example of a change in the film thickness of the etching solution on the substrate in the divided regions as predicted time passes.

[0032] Fig.15 This is a flowchart showing an example of the flow of the additional learning process. DETAILED DESCRIPTION

[0033] Hereinafter, a substrate processing system according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the following description, a substrate refers to a semiconductor substrate (semiconductor wafer), a substrate for a FPD (Flat Panel Display) such as a liquid crystal display device or an organic EL (ElectroLuminescence) display device, a substrate for an optical disk, a substrate for a magnetic disk, a substrate for an optical magneto-optical disk, a substrate for a photomask, a ceramic substrate, or a substrate for a solar cell.

[0034] 1. Overall structure of substrate processing system

[0035] Figure 1A diagram for explaining a configuration of a substrate processing system according to an embodiment of the present invention. Figure 1 The substrate processing system 1 includes an information processing apparatus 100, a learning apparatus 200, and a substrate processing apparatus 300. The learning apparatus 200 is, for example, a server, and the information processing apparatus 100 is, for example, a personal computer.

[0036] The learning device 200 and the information processing device 100 are used to manage the substrate processing apparatus 300. In addition, the substrate processing apparatus 300 managed by the learning device 200 and the information processing device 100 is not limited to one, and a plurality of substrate processing apparatuses 300 may be managed.

[0037] In the substrate processing system 1 of the present embodiment, the information processing device 100, the learning device 200 and the substrate processing device 300 are connected to each other through a wired or wireless communication line or communication line network. The information processing device 100, the learning device 200 and the substrate processing device 300 are respectively connected to the network and can send and receive data to each other. The network uses, for example, a local area network (LAN: Local Area Network) or a wide area network (WAN: Wide Area Network). In addition, the network can also be the Internet. In addition, the information processing device 100 and the substrate processing device 300 can also be connected by a dedicated communication line network. The connection method of the network can be a wired connection or a wireless connection.

[0038] In addition, the learning device 200 does not necessarily need to be connected to the substrate processing device 300 and the information processing device 100 by a communication line or a communication line network. In this case, the data generated by the substrate processing device 300 can be delivered to the learning device 200 via a storage medium. In addition, the data generated by the learning device 200 can also be delivered to the information processing device 100 via a storage medium.

[0039] The substrate processing apparatus 300 is provided with a display device, a sound output device, and an operation unit (not shown). The substrate processing apparatus 300 is operated according to a predetermined processing condition (process) of the substrate processing apparatus 300 .

[0040] 2. Overview of substrate processing equipment

[0041] The substrate processing device 300 has a control device 10 and a plurality of substrate processing units WU. The control device 10 controls the plurality of substrate processing units WU. The plurality of substrate processing units WU processes the substrate by supplying a constant flow of processing liquid to the substrate W on which a film is formed. In the present embodiment, the diameter of the substrate W to be processed is 300 mm, but the present invention is not limited thereto. The processing liquid includes an etching liquid, and the substrate processing unit WU performs an etching process. The etching liquid is a chemical liquid. For example, the etching liquid is a mixture of hydrofluoric acid (HF) and nitric acid (HNO3 ) mixture), hydrofluoric acid, buffered hydrofluoric acid (BHF), ammonium fluoride, HFEG (a mixture of hydrofluoric acid and ethylene glycol), or phosphoric acid (H 3 PO 4 ).

[0042] The substrate processing unit WU includes a rotary chuck SC, a rotary motor SM, a nozzle 311, and a nozzle moving mechanism 301. The rotary chuck SC holds the substrate W horizontally. The substrate W is held by the rotary chuck SC in such a manner that the first rotation axis AX1 of the rotary motor SM is consistent with the center of the substrate W. The rotary motor SM has a first rotation axis AX1. The first rotation axis AX1 extends in the up-down direction. The rotary chuck SC is mounted on the upper end of the first rotation axis AX1 of the rotary motor SM. When the rotary motor SM rotates, the rotary chuck SC rotates around the first rotation axis AX1. The rotary motor SM is a stepping motor. The substrate W held by the rotary chuck SC rotates around the first rotation axis AX1. Therefore, the rotation speed of the substrate W is the same as the rotation speed of the stepping motor. In addition, in the case of providing an encoder that generates a rotation speed signal indicating the rotation speed of the rotary motor, the rotation speed of the substrate W can also be obtained from the rotation speed signal generated by the encoder. In this case, the rotary motor SM can use a motor other than a stepping motor.

[0043] The nozzle 311 supplies the etching liquid to the substrate W. The nozzle 311 supplies the etching liquid from an etching liquid supply unit (not shown) and ejects the etching liquid toward the substrate W that is rotating.

[0044] The nozzle moving mechanism 301 moves the nozzle 311 in a substantially horizontal direction. Specifically, the nozzle moving mechanism 301 includes a nozzle motor 303 having a second rotation axis AX2, and a nozzle arm 305. The nozzle motor 303 is configured in a manner that the second rotation axis AX2 is along a substantially vertical direction. The nozzle arm 305 has a long side shape extending in a straight line. One end of the nozzle arm 305 is mounted on the upper end of the second rotation axis AX2 in a manner that the long side direction of the nozzle arm 305 is in a direction different from the second rotation axis AX2. At the other end of the nozzle arm 305, the nozzle 311 is mounted in a manner that its nozzle is facing downward.

[0045] When the nozzle motor 303 is operated, the nozzle arm 305 rotates in a horizontal plane around the second rotation axis AX2. Therefore, the nozzle 311 mounted on the other end of the nozzle arm 305 moves (rotates) in a horizontal direction around the second rotation axis AX2. The nozzle 311 sprays the etching liquid toward the substrate W while moving in the horizontal direction. The nozzle motor 303 is, for example, a stepping motor.

[0046] The controller 10 includes a CPU (Central Processing Unit) and a memory. The CPU executes a program stored in the memory to control the entire substrate processing apparatus 300. The controller 10 controls the rotary motor SM and the nozzle motor 303.

[0047] The learning device 200 inputs experimental data from the substrate processing apparatus 300 , performs machine learning on the learning model using the experimental data, and outputs the learned learning model to the information processing apparatus 100 .

[0048] The information processing apparatus 100 uses the learned learning model to determine the processing conditions for processing a substrate to be processed by the substrate processing apparatus 300. The information processing apparatus 100 outputs the determined processing conditions to the substrate processing apparatus 300.

[0049] Figure 2 2 is a diagram showing an example of the configuration of an information processing device. Figure 2 The information processing device 100 is composed of a CPU 101, a RAM (Random Access Memory) 102, a ROM (Read Only Memory) 103, a storage device 104, an operation unit 105, a display device 106, and an input / output I / F (Interface) 107. The CPU 101, the RAM 102, the ROM 103, the storage device 104, the operation unit 105, the display device 106, and the input / output I / F 107 are connected to a bus 108.

[0050] RAM 102 is used as a work area of ​​CPU 101. System programs are stored in ROM 103. Storage device 104 includes a storage medium such as a hard disk or a semiconductor memory, and stores programs. Programs can be stored in ROM 103 or other external storage devices.

[0051] The CD-ROM (Compact Disk-Read Only Memory) 109 can be loaded and unloaded relative to the storage device 104. The storage medium for storing the program executed by the CPU 101 is not limited to the CD-ROM 109, and may also be a medium such as an optical disk (MO (Magnetic Optical Disc) / MD (Mini Disc) / DVD (Digital Versatile Disc)), an IC card, an optical card, a shielded ROM, an EPROM (Erasable Programmable ROM) or other semiconductor memory. Furthermore, the program stored in the storage device 104 may be downloaded to the RAM 102 and executed by the CPU 101 in such a manner that the CPU 101 downloads the program from a computer connected to the network and stores it in the storage device 104, or the computer connected to the network writes the program to the storage device 104. The program mentioned here includes not only a program that can be directly executed by the CPU 101, but also a source program, a compressed program, an encrypted program, etc.

[0052] The operation unit 105 is an input device such as a keyboard, a mouse or a touch panel. The user can give a predetermined instruction to the information processing device 100 by operating the operation unit 105. The display device 106 is a display device such as a liquid crystal display device, which displays a GUI (Graphical User Interface) for receiving user instructions. The input / output I / F 107 is connected to a network.

[0053] Figure 3 2 is a diagram showing an example of the configuration of a learning device. Figure 3 The learning device 200 is composed of a CPU 201 , a RAM 202 , a ROM 203 , a storage device 204 , an operation unit 205 , a display device 206 , and an input / output I / F 207 . The CPU 201 , the RAM 202 , the ROM 203 , the storage device 204 , the operation unit 205 , the display device 206 , and the input / output I / F 207 are connected to a bus 208 .

[0054] RAM 202 is used as a work area of ​​CPU 201. ROM 203 stores a system program. Storage device 204 includes a storage medium such as a hard disk or a semiconductor memory, and stores a program. The program can be stored in ROM 203 or other external storage devices. CD-ROM 209 can be loaded and unloaded with respect to storage device 204.

[0055] The operation unit 205 is an input device such as a keyboard, a mouse, or a touch panel. The input / output I / F 207 is connected to a network.

[0056] 3. Functional composition of substrate processing system

[0057] Figure 4 A diagram showing an example of the functional configuration of a substrate processing system according to one embodiment of the present invention. Figure 4 The control device 10 of the substrate processing device 300 controls the substrate processing unit WU and processes the substrate W according to the processing conditions. The processing conditions are conditions for processing the substrate W during a predetermined processing time. The processing time is the time determined for processing the substrate. In the present embodiment, the processing time is the time during which the nozzle 311 sprays the etching liquid onto the substrate W.

[0058] In this embodiment, the processing conditions include the temperature of the etching solution, the concentration of the etching solution, the flow rate of the etching solution, the rotation speed of the substrate W, and the relative position of the nozzle 311 and the substrate W. The processing conditions include variable conditions that change with the passage of time. In this embodiment, the variable condition is the relative position of the nozzle 311 and the substrate W. The relative position is shown by the rotation angle of the nozzle motor 303. The processing conditions include fixed conditions that do not change with the passage of time. In this embodiment, the fixed conditions are the temperature of the etching solution, the concentration of the etching solution, the flow rate of the etching solution, and the rotation speed of the substrate W.

[0059] The learning device 200 causes the learning model to learn the learning data, and generates an inference model that estimates the etching profile from the processing conditions. Hereinafter, the inference model generated by the learning device 200 is referred to as a predictor.

[0060] The learning device 200 includes an experimental data acquisition unit 261, a first conversion unit 263, a predictor generation unit 265, and a predictor transmission unit 267. The CPU 201 of the learning device 200 executes a learning program stored in the RAM 202, so that the functions of the learning device 200 are realized by the CPU 201.

[0061] The experimental data acquisition unit 261 acquires experimental data from the substrate processing apparatus 300. The experimental data includes processing conditions used when the substrate processing apparatus 300 actually processes the substrate W, and film thickness characteristics of a film formed on the substrate W before and after processing. The film thickness characteristics are represented by the film thickness of each of a plurality of different positions of the film formed on the substrate W in the radial direction of the substrate W.

[0062] The changing condition includes the relative position of the nozzle 311 with respect to the substrate W which changes with the passage of time. The substrate W rotates around the first rotation axis AX1, and the nozzle 311 rotates around the second rotation axis AX2. Therefore, the change in the relative position of the nozzle 311 and the substrate W is represented by the change in the position of the nozzle 311. The position of the nozzle 311 is determined by the rotation angle of the nozzle motor 303. In addition, the range of the angle of rotation of the nozzle motor 303 is limited to a specified range. Moreover, the processing time is a predetermined period. In the present embodiment, the processing time is 60 seconds.

[0063] Figure 5 2 is a diagram for explaining the change in the relative position of the nozzle with respect to the substrate. Figure 5 , showing the change in the relative position of the nozzle 311 with respect to the substrate W held by the rotary chuck SC. The nozzle 311 moves in the upper area of ​​the substrate W held by the rotary chuck SC. Since the nozzle 311 rotates around the second rotation axis AX2, the trajectory of the movement of the nozzle 311 is an arc. The trajectory of the movement of the nozzle 311 passes through the substrate center OP, which represents the center of the substrate W held by the rotary chuck SC. Therefore, the nozzle 311 moves between the substrate center OP and the peripheral portion in the radial direction of the substrate W. Here, one end of the trajectory of the movement of the nozzle 311 is shown by an action end EP1 that is closer to the inner side than the peripheral portion of the substrate W, and the other end is shown by an action end EP2 that is closer to the inner side than the peripheral portion of the substrate W. The scanning of the nozzle 311 moving from the action end EP1 to the substrate center OP is shown by arrow a1, the scanning of the nozzle 311 moving from the substrate center OP to the action end EP2 is shown by arrow a2, the scanning of the nozzle 311 moving from the action end EP2 to the substrate center OP is shown by arrow a3, and the scanning of the nozzle 311 moving from the substrate center OP to the action end EP1 is shown by arrow a4.

[0064] Figure 6 is a diagram showing an example of the operation mode of the nozzle. Figure 6In the figure, the relative position of the nozzle 311 relative to the substrate W is shown on the vertical axis, and the elapsed time (seconds) is shown on the horizontal axis. In the present embodiment, the scanning period from the start of the nozzle action of moving the nozzle 311 relative to the substrate W to the end is equal to the processing time. As described above, since the processing time is set to 60 seconds, the action pattern of the nozzle shows the relative position during the period of 0 to 60 seconds. The relative position of the nozzle sets the substrate center OP to zero, the range from the substrate center OP to the action end EP1 is shown as a negative value, and the range from the substrate center OP to the action end EP2 is shown as a positive value. Since the diameter of the substrate W is 300 mm, the distance from the substrate center OP to the action ends EP1 and EP2 is set to less than ±150 mm. Here, the distance from the substrate center OP to the action end EP1 is set to -147 mm, and the distance from the substrate center OP to the action end EP2 is set to +147 mm. The relative position of nozzle 311 when nozzle 311 is located at the center OP of the substrate is shown as 0, the relative position of nozzle 311 when nozzle 311 is located at the action end EP1 is shown as -147 mm, and the relative position of nozzle 311 when nozzle 311 is located at the action end EP2 is shown as 147 mm.

[0065] Figure 6 The nozzle motion pattern shown in FIG. 1 is shown as scanning back and forth five times between the motion end EP1 and the motion end EP2. In the nozzle motion pattern, relative to the first reciprocating scan, Figure 5 Parts of relative positions corresponding to scans indicated by arrows a1 to a4 are denoted by the same reference numerals.

[0066] Figure 7 This is a diagram showing an example of film thickness characteristics. Figure 7 , the horizontal axis shows the position of the substrate in the radial direction, and the vertical axis shows the film thickness. The origin of the horizontal axis represents the center of the substrate. The film thickness of the film formed on the substrate W before being processed by the substrate processing apparatus 300 is shown by a solid line. The substrate processing apparatus 300 performs a process of applying an etching solution according to the processing conditions, thereby adjusting the film thickness of the film formed on the substrate W. The film thickness of the film formed on the substrate W after being processed by the substrate processing apparatus 300 is shown by a dotted line.

[0067] The difference between the film thickness of the film formed on the substrate W before being processed by the substrate processing apparatus 300 and the film thickness of the film formed on the substrate W after being processed by the substrate processing apparatus 300 is the processing amount (etching amount). The processing amount indicates the thickness of the film reduced by the processing of applying the etching liquid by the substrate processing apparatus 300. The radial distribution of the processing amount is called an etching profile. The etching profile includes the processing amount of each of a plurality of positions in the radial direction of the substrate W.

[0068] In addition, it is desired that the film thickness formed by the substrate processing apparatus 300 is uniform over the entire surface of the substrate W. Therefore, a target film thickness is determined for the processing performed by the substrate processing apparatus 300. The target film thickness is shown by a single dotted line. The deviation characteristic is the difference between the film thickness formed on the substrate W after being processed by the substrate processing apparatus 300 and the target film thickness. The deviation characteristic includes the difference between each of a plurality of positions in the radial direction of the substrate W.

[0069] Back to Figure 4 The first conversion unit 263 converts the variable conditions, the rotation speed of the substrate W, the temperature of the etching liquid, and the flow rate of the etching liquid included in the processing conditions of the experimental data input from the experimental data acquisition unit 261 into processing state data showing the processing state of the substrate. Here, the variable conditions are the relative position of the nozzle with respect to the substrate W that changes with the passage of time during the processing time. The first conversion unit 263 outputs the processing state data to the predictor generation unit 265.

[0070] Here, the processing status data is described. Generally, the amount of film removed from the substrate W varies depending on the state of processing of the substrate W. For example, the amount of film removed from the substrate W varies depending on the temperature of the substrate W. When the temperature of the substrate W is high, the amount of film removed from the substrate W becomes larger. On the other hand, when the temperature of the substrate W is low, the amount of film removed from the substrate W becomes smaller. The temperature of the substrate W varies depending on the temperature of the etching liquid supplied to the substrate W. The temperature of the portion of the substrate W to which the etching liquid is supplied becomes the same as or close to the temperature of the etching liquid, and the temperature of the portion of the substrate W to which the etching liquid is not supplied becomes lower than the temperature of the etching liquid.

[0071] The processing state data shows the processing state of each of the plurality of divided regions of the upper surface of the substrate W divided by concentric circles with the substrate center OP as the center. The processing state is the temperature of the substrate. The first conversion unit 263 generates compressed data indicating the temperature of the substrate W in each of the plurality of divided regions using the variable condition, the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution.

[0072] Figure 8 is a diagram for explaining the segmentation area. Figure 8, showing 15 divided areas b1 to b15 on the top of the substrate W divided by a plurality of concentric circles with the substrate center OP as the center. The divided area b15 is a circle, and the divided areas b1 to b14 are rings. The radial length of the substrate W in each of the plurality of divided areas b1 to b14 is the same. The radial length of the substrate in each of the divided areas b1 to b14 is the difference between the radius of the outer circumference and the radius of the inner circumference. The radius of the divided area b15 is the same as the radial length of the substrate W in each of the plurality of divided areas b1 to b14. Here, the radius of the divided area b15 is 10 mm, and the difference between the radius of the outer circumference and the inner circumference of each of the divided areas b1 to b14 is 10 mm. The radial length of the substrate in each of the divided areas b1 to b15 is preferably greater than the inner diameter of the nozzle 311.

[0073] The nozzle 311 rotates about the second rotation axis AX2 via the nozzle arm 305, so the rotation center is different from the substrate center OP. The movement range of the nozzle 311 is a trajectory drawn from the operating end EP1 through the substrate center OP to the operating end EP2, and is an arc.

[0074] The moving range of the nozzle 311 is the trajectory of the nozzle 311 during the processing period (scanning period) in which the nozzle 311 processes the substrate. The moving range is divided into 29 moving sections d1 to d29 by the divided areas b1 to b15. The moving sections d1 to d29 are sections that cross the divided areas b1 to b15 in the trajectory of the nozzle 311 during the period of moving between the action end EP1 and the action end EP2. For example, the moving sections d1 to d14 are the trajectories that cross the divided areas b1 to b14 during the period of moving between the action end EP1 and the center OP of the substrate. The moving section d15 is the trajectory that crosses the divided area b15 during the period of moving between the action end EP1 and the action end EP2. In addition, the moving sections d16 to d29 are the sections that cross the divided areas b1 to b14 in the trajectory of the nozzle 311 during the period of moving between the center OP of the substrate and the action end EP2. In this way, the moving range of the nozzle 311 is divided into a plurality of moving intervals d1 to d29 in which the nozzle 311 respectively crosses a plurality of divided areas b1 to b15. In addition, the number of divided areas b1 to b15 is not limited to 15, and can be set to any value. In this case, the number of divided moving ranges, in other words, the number of moving intervals is different.

[0075] Here, refer to Figure 6 , shows the portion corresponding to the segmented area b15 in the operation mode of the nozzle 311. The segmented area b15 is in the range of -10 mm to +10 mm relative to the nozzle 311. Figure 6 In FIG. 1 , a period during which the nozzle 311 traverses the divided region b1 (hereinafter referred to as a residence period) is shown as T1 to T10. Fig. 9 FIG. 1 is a diagram showing an example of a change in substrate temperature in a divided region as time passes. Fig. 9 , the temperature of the substrate W that changes with the passage of time for the divided area b15 is shown. Fig. 9 In the graph of FIG. 1 , the vertical axis shows the temperature of the substrate W, and the horizontal axis shows time (seconds). Here, the temperature of the etching solution supplied to the substrate W is T L .exist Fig. 9 The dialog box diagram shows an enlarged diagram of a portion of the substrate temperature that changes over time. In the graph shown in the dialog box, the scale of the horizontal axis is enlarged. During the processing of the substrate W, the etching liquid is supplied from the nozzle 311 while the substrate W is rotating. At the time t0 when the nozzle 311 starts to supply the etching liquid to the substrate W, the nozzle 311 is located at the action end EP1, and therefore, the nozzle 311 does not exist in the divided area b15. Therefore, the etching liquid is not supplied to the divided area b15. At this stage, the temperature of the substrate W in the divided area b15 becomes a predetermined temperature Tw. The predetermined temperature is a temperature that depends on the ambient temperature. The temperature of the divided area b15 changes at a constant temperature Tw.

[0076] After time t1 when the nozzle 311 approaches the divided area b15, the temperature of the divided area b15 of the substrate W rises due to the temperature of the etching liquid supplied from the nozzle 311. The temperature change in the divided area b15 of the substrate W after time t1 can be expressed by equation (1). The coefficient α of equation (1) is 1 It is shown by formula (2).

[0077] [Mathematical formula 1]

[0078] f 1 (t) = α 1 ×t+T W …(1)

[0079]

[0080] In formula (1), t represents time, T W is a specified temperature that depends on the ambient temperature. In formula (2), C u1 ~C u4 is a constant. L is the temperature of the etching liquid supplied from the nozzle 311. D is the flow rate of the etching liquid supplied from the nozzle 311. R is the rotation speed of the substrate W. In this way, the change in temperature in the divided area b15 of the substrate W is represented by a function of the elapsed time t taking into account the rotation speed of the substrate W, the temperature of the etching liquid, the flow rate of the etching liquid, and the like.

[0081] Next, at time t2 when the nozzle 311 stays in the divided region b15, the temperature of the divided region b15 of the substrate W is maintained at the temperature T of the etching liquid. L After time t3 when the nozzle 311 stays in the segmented area b15 during the retention period T1, the nozzle 311 leaves the segmented area b15. Since the nozzle 311 leaves the segmented area b15, the etching liquid is not supplied from the nozzle 311 to the segmented area b15, and therefore the temperature of the substrate W in the segmented area b15 decreases. The change in the temperature of the substrate W in the segmented area b15 after time t3 can be expressed by equation (3). The coefficient β of equation (3) is 1 It is represented by the following formula (4).

[0082] [Mathematical formula 2]

[0083] f 2 (t)=(T L -T W )×exp(-β 1 ×t)+T W …(3)

[0084]

[0085] In formula (3), T L is the temperature of the etching solution supplied from the nozzle 311. W is a specified temperature that depends on the ambient temperature. In formula (4), C d1 is a constant. D is the flow rate of the etching liquid supplied from the nozzle 311. R is the rotation speed of the substrate W. Thus, the change in temperature in the divided area b15 of the substrate W is represented by a function that takes into account the rotation speed of the substrate W, the temperature of the etching liquid, and the flow rate of the etching liquid.

[0086] Time t3 and time t4 are determined by Figure 6 The operation mode of the nozzle 311 shown is determined. The time t2 is determined based on the temperature at the time t1 using the formula (1).

[0087] Back to Figure 4, the first conversion unit 263 predicts the temperature change of the substrate W during the process of supplying the etching liquid to the substrate W for each of the plurality of divided areas b1 to b15 of the substrate W. The first conversion unit 263 determines the average value AV1 representing the value of the temperature changed during the process as the temperature of the divided area of ​​the substrate W for each of the plurality of divided areas b1 to b15 of the substrate W. The first conversion unit 263 determines the temperature determined in each of the plurality of divided areas b1 to b15 of the substrate W as the process status data. Here, since the upper surface of the substrate W is divided into 15 divided areas b1 to b15, the number of process status data is 15. The larger the radial length of the substrate of each of the divided areas b1 to b15, the smaller the number of process status data. The radial length of the substrate of each of the divided areas b1 to b15 is greater than the inner diameter of the nozzle 311, and therefore the maximum value of the number of process status data is determined by the inner diameter of the nozzle 311.

[0088] Back to Figure 4 The predictor generation unit 265 inputs the processing state data after the conversion of the change condition from the first conversion unit 263, and inputs the experimental data from the experimental data acquisition unit 261. The predictor generation unit 265 generates the predictor by making the neural network perform supervised learning. In addition, the neural network may also be a convolutional neural network.

[0089] Specifically, the learning data includes input data and correct answer data. The input data includes processing state data after the variable conditions are converted by the first conversion unit 263, and fixed conditions other than the variable conditions of the processing conditions included in the experimental data. The correct answer data includes an etching profile. The etching profile is the difference between the film thickness characteristics of the film before processing included in the experimental data and the film thickness characteristics of the film after processing included in the experimental data. The etching profile included in the correct answer data is an example of the first processing amount. The predictor generation unit 265 inputs the input data to the neural network and determines the parameters of the neural network in a manner that the output of the neural network is equal to the correct answer data. The predictor generation unit 265 generates a neural network incorporating the parameters set in the learned neural network as a predictor. The predictor is an inference program incorporating the parameters set in the learned neural network. The predictor generation unit 265 sends the predictor to the information processing device 100.

[0090] Fig.10 is a diagram illustrating the predictor. Fig.10, the predictor includes an input layer, an intermediate layer and an output layer, and each layer includes a plurality of nodes represented by 0. In addition, although one intermediate layer is shown in the figure, the number of intermediate layers can be more than this. In addition, although five nodes are shown in the input layer, four nodes are shown in the intermediate layer, and three nodes are shown in the output layer, the number of nodes is not limited to this. The output of the node of the upper level is connected to the input of the node of the lower level. The parameters include coefficients for weighting the output of the node of the upper level. In addition, the number of intermediate layers is greater than 1, and its number is not limited.

[0091] When the processing state data and the fixed conditions converted into the variable conditions are input to the predictor, an etching profile is output. The etching profile output by the predictor is an example of the second processing amount. The etching profile is represented by the difference E[n] of the film thickness before and after the processing of each of the plurality of radial positions P[n] (n is an integer greater than 1) of the substrate W. In addition, although the number of output nodes of the predictor is shown as 3 in the figure, the number of output nodes is actually n.

[0092] The processing state data that the predictor generator 265 causes the predictor machine to learn includes the temperature of the substrate W associated with the position on the substrate W. The temperature of the substrate W contributes to the processing of the substrate W, and therefore a predictor with high prediction accuracy can be generated.

[0093] Back to Figure 4 The information processing device 100 includes a processing condition determination unit 151, a predictor receiving unit 155, a second conversion unit 157, a prediction unit 159, an evaluation unit 161, and a processing condition sending unit 163. The CPU 101 of the information processing device 100 executes a processing condition determination program stored in the RAM 102, so that the CPU 101 realizes the functions of the information processing device 100.

[0094] The predictor receiving unit 155 receives the predictor transmitted from the learning device 200 , and outputs the received predictor to the predicting unit 159 .

[0095] The processing condition determination unit 151 determines the processing condition for the substrate W to be processed by the substrate processing apparatus 300. The processing condition determination unit 151 outputs the processing condition to the second conversion unit 157, and outputs the fixed condition included in the processing condition to the prediction unit 159. The processing condition determination unit 151 selects one from a plurality of variable conditions prepared in advance using an experimental planning method, a paired test method, or a Bayesian estimation, and determines the processing condition including the selected variable condition and the fixed condition as the processing condition for the prediction unit 159 to estimate. The plurality of variable conditions prepared in advance are preferably the plurality of variable conditions generated by the learning device 200 for generating a compressor.

[0096] The second conversion unit 157 has the same function as the first conversion unit 263 of the learning device 200. The second conversion unit 157 generates processing state data based on the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution among the variable conditions and fixed conditions included in the processing conditions input from the processing condition determination unit 151. The second conversion unit 157 outputs the generated processing state data to the prediction unit 159.

[0097] The prediction unit 159 uses a predictor to estimate an etching profile based on the processing state data and fixed conditions. Specifically, the prediction unit 159 inputs the processing state data input from the second conversion unit 157 and the fixed conditions input from the processing condition determination unit 151 to the predictor, and outputs the etching profile output by the predictor to the evaluation unit 161.

[0098] The evaluation unit 161 evaluates the etching profile input from the prediction unit 159, and outputs the evaluation result to the processing condition determination unit 151. In detail, the evaluation unit 161 obtains the film thickness characteristics before processing of the predetermined substrate W as the processing object of the substrate processing device 300. The evaluation unit 161 calculates the film thickness characteristics predicted after the etching process based on the etching profile input from the prediction unit 159 and the film thickness characteristics of the substrate W before processing, and compares it with the target film thickness characteristics. If the result of the comparison meets the evaluation criterion, the processing conditions determined by the processing condition determination unit 151 are output to the processing condition sending unit 163. For example, the evaluation unit 161 calculates the deviation characteristic and determines whether the deviation characteristic meets the evaluation criterion. The deviation characteristic is the difference between the film thickness characteristics of the substrate W after the etching process and the target film thickness characteristics. The evaluation criterion can be determined arbitrarily. For example, the evaluation criterion can be that the maximum value of the difference in the deviation characteristic is below the threshold, or that the average of the difference is below the threshold.

[0099] The processing condition transmitting unit 163 transmits the processing condition determined by the processing condition determining unit 151 to the substrate processing apparatus 300. The substrate processing apparatus 300 processes the substrate W according to the processing condition.

[0100] If the evaluation result does not satisfy the evaluation criterion, the evaluation unit 161 outputs the evaluation result to the processing condition determination unit 151. The evaluation result includes the film thickness characteristics predicted after the etching process or the difference between the film thickness characteristics predicted after the etching process and the target film thickness characteristics.

[0101] The processing condition determination unit 151 determines a new processing condition for the prediction unit 159 to estimate based on the evaluation result input from the evaluation unit 161. The processing condition determination unit 151 selects one of a plurality of variable conditions prepared in advance using an experimental planning method, a paired testing method, or a Bayesian estimation, and determines a processing condition including the selected variable condition and a fixed condition as a new processing condition for the prediction unit 159 to estimate.

[0102] The processing condition determination unit 151 can use Bayesian estimation to explore the processing conditions. When a plurality of evaluation results are output by the evaluation unit 161, there are a plurality of sets of processing conditions and evaluation results. Based on the tendency of the etching profiles of each of the plurality of sets, the processing conditions that make the film thickness uniform or the processing conditions that minimize the difference between the predicted film thickness characteristics after the etching process and the target film thickness characteristics are explored.

[0103] Specifically, the processing condition determination unit 151 explores the processing conditions in a manner that minimizes the objective function. The objective function is a function that represents the uniformity of the film thickness of the film or a function that represents the consistency between the film thickness characteristics of the film and the target film thickness characteristics. For example, the objective function is a function that represents the difference between the film thickness characteristics predicted after the etching process and the target film thickness characteristics in terms of parameters. The parameters here are the processing state data generated by the second conversion unit 157 based on the corresponding variable conditions. The corresponding variable conditions are the variable conditions that form the basis for generating the processing state data used by the prediction unit 159 to infer the etching profile. The processing condition determination unit 151 selects the variable conditions corresponding to the parameters determined by the exploration, i.e., the processing state data, from a plurality of variable conditions, and determines new processing conditions including the selected variable conditions and fixed conditions.

[0104] Fig.11 2 is a flowchart showing an example of the flow of the predictor generation process. The predictor generation process is a process performed by the CPU 201 included in the learning device 200 by executing a predictor generation program stored in the RAM 202. The predictor generation program is a part of the learning program.

[0105] Reference Fig.11 , the CPU 201 of the learning device 200 obtains experimental data. The CPU 201 controls the input / output I / F 107 to obtain experimental data from the substrate processing device 300 (step S01). The experimental data can also be obtained by using the storage device 104 to read the experimental data stored in a storage medium such as CD-ROM 209. The experimental data obtained here are plural. The experimental data include processing conditions and film thickness characteristics of the film formed on the substrate W before and after processing. The film thickness characteristics are represented by the film thickness of each of the different plural positions of the film formed on the substrate W in the radial direction of the substrate W.

[0106] In the next step S02, the experimental data to be processed is selected, and the process proceeds to step S03. In step S03, the processing status data is generated, and the process proceeds to step S04. The details of the processing status data generation process will be described later, and the processing is based on the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution among the variable conditions and fixed conditions included in the experimental data.

[0107] In step S04, the processing state data, the fixed conditions included in the experimental data, and the etching profile are set as learning data. The etching profile is the difference between the film thickness characteristics of the film before processing included in the experimental data and the film thickness characteristics of the film after processing included in the experimental data. The learning data includes input data and correct answer data. The processing state data converted in step S03 and the fixed conditions included in the experimental data are set as input data. The etching profile is set as the correct answer data.

[0108] In the next step S05, CPU 201 causes the predictor to perform machine learning, and the process proceeds to step S06. Input data is input to the neural network, i.e., the predictor, and parameters are determined in such a way that the output of the predictor is equal to the correct answer data. Thus, the parameters of the predictor are adjusted. The predictor is a neural network having parameters determined by machine learning using learning data. In addition, the neural network may also be a convolutional neural network.

[0109] In step S06, it is determined whether the adjustment is completed. Learning data for evaluating the predictor is prepared in advance, and the performance of the predictor is evaluated with the learning data for evaluation. When the evaluation result satisfies the predetermined evaluation criterion, it is determined that the adjustment is completed. If the evaluation result does not meet the evaluation criterion (No in step S06), the process returns to step S02, but if the evaluation result meets the evaluation criterion (Yes in step S06), the process proceeds to step S07.

[0110] When the processing returns to step S02, in step S02, experimental data that has not been selected as the processing object is selected from the experimental data obtained in step S01. In the loop of steps S02 to S06, CPU201 uses a plurality of learning data to make the predictor machine learn. Thus, the parameters of the neural network, i.e., the predictor, are adjusted to appropriate values. In step S08, the predictor is sent and the processing ends. CPU201 controls the input / output I / F107 and sends the predictor to the information processing device 100.

[0111] Fig.12 1 is a flowchart showing an example of the flow of the processing condition determination process. The processing condition determination process is a process executed by the CPU 101 included in the information processing device 100 by the CPU 101 executing the processing condition determination program stored in the RAM 102 .

[0112] Reference Fig.12 , the CPU 101 of the information processing device 100 selects one from the plurality of change conditions prepared in advance (step S11), and the process proceeds to step S12. The plurality of change conditions are the plurality of change conditions generated by the learning device 200 to generate a compressor. One is selected from the plurality of change conditions prepared in advance using an experimental planning method, a paired test method, or a Bayesian estimation method.

[0113] In step S12, processing status data generation processing is executed, and the process proceeds to step S13.

[0114] In step S13, a predictor is used to estimate the etching profile based on the processing state data and fixed conditions, and the process proceeds to step S14. The processing state data and fixed conditions generated in step S12 are input to the predictor, and the etching profile output by the predictor is obtained. In step S14, the film thickness characteristics after processing are compared with the target film thickness characteristics. Based on the film thickness characteristics before processing of the substrate W that is the processing object of the substrate processing device 300 and the etching profile estimated in step S13, the film thickness characteristics after processing the substrate W are calculated. Then, the film thickness characteristics after processing are compared with the target film thickness characteristics. Here, the difference between the film thickness characteristics after processing the substrate W and the target film thickness characteristics is calculated.

[0115] In step S15, it is determined whether the comparison result satisfies the evaluation criteria. If the comparison result satisfies the evaluation criteria (yes in step S15), the process proceeds to step S16, otherwise the process returns to step S11. For example, when the maximum value of the difference is below the threshold, it is determined that the evaluation criteria are satisfied. In addition, when the average of the difference is below the threshold, it is determined that the evaluation criteria are satisfied.

[0116] In step S16, the processing conditions including the variable conditions selected immediately before step S11 are set in the candidates of the processing conditions for driving the substrate processing apparatus 300, and the process proceeds to step S17. In step S17, it is determined whether an end instruction of the search is received. If the end instruction is received by the user operating the information processing apparatus 100, the process proceeds to step S18, otherwise the process returns to step S11. In addition, it is also possible to change to an end instruction input by the user to determine whether a predetermined number of processing conditions are set as candidates.

[0117] In step S18, one of the processing conditions set as candidates is determined, and the process proceeds to step S19. Alternatively, a user operating the information processing device 100 may select one of the processing conditions set as candidates. Therefore, the user's range of selection becomes larger. In addition, a variable condition with the simplest nozzle movement may be automatically selected from the variable conditions included in the plurality of processing conditions. The variable condition with the simplest nozzle movement can be set, for example, as a variable condition with the least number of speed change points. Thus, a plurality of variable conditions can be prompted for the processing result of the complex nozzle movement of processing the substrate W. If a variable condition that is easy to control the nozzle is selected from the plurality of variable conditions, the control of the substrate processing device 300 becomes easier.

[0118] In step S19, the processing conditions including the variable conditions determined in step S18 are sent to the substrate processing apparatus 300, and the processing ends. The CPU 101 controls the input / output I / F 107 to send the processing conditions to the substrate processing apparatus 300. When receiving the processing conditions from the information processing apparatus 100, the substrate processing apparatus 300 processes the substrate W according to the processing conditions.

[0119] Fig.13 is a flowchart showing an example of the process of processing status data generation processing. Fig.10 Step S03 or Fig.11 The processing is performed in step S12. In step S21, time series data is obtained. The time series data is the relative position of the nozzle relative to the substrate W that changes with the passage of time. In step S22, the number of divisions K (K is an integer greater than 2) for setting a plurality of division areas on the upper surface of the substrate W is obtained. In this embodiment, the number of divisions K is preset. In addition, the number of divisions K can also be input by the user through the operation unit, etc. In addition, in Figure 8 In the example, the number of divisions K is 15.

[0120] In step S23, the variable n is set to 1. In step S24, an average value AV1 representing the average temperature change of the substrate W in the divided area b(n) is calculated. The divided area b(n) represents the nth divided area among the divided areas b1 to b15. When the average value AV1 in the divided area b(n) is calculated, 1 is added to the variable n in step S25. At this time, in step S26, it is determined whether the variable n is greater than the number of divisions K. When the variable n is less than the number of divisions K, the process returns to step S24. When the variable n is greater than the number of divisions K, in step S27, the calculated temperature of the substrate W of the nozzle 311 of each of the divided areas b(1) to b(K) is determined as the processing status data. By repeating steps S24 to S26, the temperature of the substrate W of each of the next divided areas b(1) to b(K) is calculated.

[0121] 4. Specific examples

[0122] In this embodiment, the variable condition is time series data sampled with a processing time of 60 seconds and a sampling interval of 0.01 seconds for the nozzle action. The variable condition consists of 6001 values. Therefore, the variable condition can express complex nozzle actions. On the contrary, the dimension of the variable condition is large, so when machine learning is performed on the time series data of the variable condition, overfitting sometimes occurs.

[0123] The predictor generation unit 265 in the present embodiment generates a predictor by performing machine learning on the processing status data, and therefore can explicitly add the known relationship between the variable conditions and the fixed conditions to the learning model.

[0124] The first conversion unit 263 in this embodiment converts the rotation speed of the substrate W, the temperature of the etching liquid, and the flow rate of the etching liquid in the variable conditions and the fixed conditions into processing state data. The processing state data is the average value of the temperature change of the substrate W in each of the plurality of divided areas b1 to b15 divided by the moving range of the nozzle 311 by the number of divisions 15, and is composed of 15 values. The inventors have found through experiments that even when the processing state data is used for prediction instead of the variable conditions composed of 6001 values ​​representing the complex nozzle movement, the etching profile predicted by the predictor can obtain the desired result.

[0125] Therefore, the amount of data input to the predictor can be reduced, so the configuration of the predictor can be simplified, and the neural network can be easily learned. In addition, the parameters of the neural network can be adjusted to appropriate values, thereby improving the accuracy of the predictor.

[0126] In addition, the variable condition with a dimension of 6001 is converted into the processing state data with a dimension of 15. Therefore, among the plurality of variable conditions, there may be a plurality of variable conditions with equal processing state data. In this case, the etching profiles predicted by the predictor based on the plurality of variable conditions with the same processing state data are the same. In this embodiment, when the processing condition determination unit 151 explores the processing conditions, the processing conditions corresponding to the etching profiles different from each other are explored, and thus the processing conditions corresponding to the plurality of different etching profiles are selected. Therefore, the processing condition determination unit 151 can effectively explore and predict the processing conditions that become the target etching profile from the plurality of processing conditions.

[0127] In addition, although the example of setting the sampling interval to 0.01 seconds has been described, the sampling interval is not limited to this. The sampling interval may be longer or shorter than this. For example, the sampling interval may be set to 0.1 seconds or 0.005 seconds.

[0128] 5. Other Implementation Methods

[0129] (1) In the above-described embodiment, although the average value AV1 of the temperature change relative to each of the plurality of divided regions is converted into processing status data, the present invention is not limited thereto. By supplying the etching liquid to the substrate W, the amount of film removal on the substrate W is changed according to the thickness of the etching liquid film formed on the substrate W. For example, when the thickness of the etching liquid film is large, the amount of film removal on the substrate W becomes large. On the other hand, when the thickness of the etching liquid film is small, the amount of film removal on the substrate W becomes small. Therefore, the thickness of the etching liquid film relative to each of the plurality of divided regions may also be used as processing status data.

[0130] Fig.14 1 is a diagram showing an example of the change in the film thickness of the etching solution on the substrate as the time elapses predicted in the divided area. Fig.14 , the change in film thickness of the etching solution on the substrate W over time for the divided area b15 is shown. Fig.14 In the graph of , the vertical axis shows the film thickness of the etching liquid on the substrate W, and the horizontal axis shows time (seconds). Here, the etching liquid is supplied to the substrate W without the substrate W rotating, so that the film thickness of the etching liquid to be formed on the substrate W is FT. Fig.14 The dialog box diagram of shows a partially enlarged diagram of the substrate temperature changing over time. In the graph shown in the dialog box, the scale of the horizontal axis is enlarged.

[0131] During the processing of the substrate W, the etching liquid is supplied from the nozzle 311 while the substrate W is rotating. At time t0 when the nozzle 311 starts supplying the etching liquid to the substrate W, the nozzle 311 is located at the operation end EP1, and therefore, the nozzle 311 does not exist in the divided area b15. Therefore, the etching liquid is not supplied to the divided area b15. At this stage, the film thickness of the etching liquid on the substrate W in the divided area b15 is zero.

[0132] After time t1 when the nozzle 311 approaches the segmented area b15, the etching liquid supplied from the nozzle 311 causes the film thickness of the etching liquid in the segmented area b15 of the substrate W to increase. The change in the film thickness of the etching liquid in the segmented area b15 of the substrate W after time t1 can be expressed by equation (5). The coefficient α of equation (5) is 2 It is represented by the following formula (6).

[0133] [Mathematical formula 3]

[0134] g 1 (t) = α 2 ×t…(5)

[0135]

[0136] In formula (6), C U1 ~CU3 is a constant related to the increase of the liquid film in the divided area b15 of the substrate W. D in formula (6) is the flow rate of the etching liquid supplied from the nozzle 311. R in formula (6) is the rotation speed of the substrate W. In this way, the change (increase) of the film thickness of the etching liquid in the divided area b15 can be expressed by a function of the elapsed time t taking into account the rotation speed of the substrate W and the flow rate of the etching liquid.

[0137] Next, at time t2 when the nozzle 311 is retained in the divided area b15, the liquid film of the etching liquid in the divided area b15 of the substrate W is maintained at the film thickness FT. After time t3 when the retention period T1 has passed, the nozzle 311 leaves the divided area b15. The nozzle 311 leaves the divided area b15 without supplying the etching liquid to the divided area b15 from the nozzle 311. In addition, due to the centrifugal force of the rotating substrate W, the film thickness of the etching liquid on the substrate W in the divided area b15 decreases. The change in the film thickness of the etching liquid on the substrate W in the divided area b15 of the substrate W after time t3 can be expressed by formula (7). The coefficient β of formula (7) 2 It is shown by formula (8).

[0138] [Formula 4]

[0139] g 2 (t) = Film max ×exp(-β 2 ×t)…(7)

[0140]

[0141] Film in formula (7) max Indicates the maximum thickness of the etching solution film. max is the film thickness FT. In formula (8), C D1 is a constant related to the decrease in the film thickness of the etching solution in the divided area b15 of the substrate W. D in formula (8) is the flow rate of the etching solution supplied from the nozzle 311. R in formula (8) is the rotation speed of the substrate W. In this way, the change (decrease) in the film thickness of the etching solution in the divided area b15 can be expressed by a function of the elapsed time t taking into account the rotation speed of the substrate W, the temperature of the etching solution, the flow rate of the etching solution, etc.

[0142] Figure 4The first conversion unit 263 predicts the change in the film thickness of the etching liquid on the substrate W during the process of supplying the etching liquid to the substrate W for each of the plurality of divided areas b1 to b15 of the substrate W. The first conversion unit 263 determines, for each of the plurality of divided areas b1 to b15 of the substrate W, an average value AV2 of the values ​​representing the film thickness of the etching liquid on the substrate W that changes during the process as the film thickness of the etching liquid in the divided area of ​​the substrate W. The first conversion unit 263 determines the film thickness of the etching liquid determined in each of the plurality of divided areas b1 to b15 of the substrate W as the process status data.

[0143] Alternatively, the first conversion unit 263 may determine the average value AV1 of the temperature change of each of the plurality of divided regions b1 to b15 and the average value AV2 of the film thickness change of the etching solution as the processing state data. In this case, the variable condition with a dimension of 6001 can be converted into processing state data with a dimension of 30.

[0144] Furthermore, the predictor generator 265 causes the predictor machine to learn processing state data including the film thickness of the etching solution associated with the position on the substrate W. The film thickness of the etching solution contributes to the processing of the substrate W, and therefore a learning model with high prediction accuracy can be generated.

[0145] (2) In the above embodiment, the learning device 200 generates a predictor based on learning data. The learning device 200 may also add a learning predictor. After generating the predictor, the learning device 200 obtains the film thickness characteristics and processing conditions of the film before and after the substrate W processed by the substrate processing device 300. Then, the learning device 200 generates learning data based on the film thickness characteristics and processing conditions of the film before and after the processing, and adds a learning predictor by machine learning the predictor. By additional learning, the parameters are adjusted without changing the structure of the neural network constituting the predictor.

[0146] Since the predictor is machine-learned using information obtained from the results of the substrate processing apparatus 300 actually processing the substrate W, the accuracy of the predictor can be improved. In addition, the amount of learning data for generating the predictor can be reduced as much as possible.

[0147] Fig.15 2 is a flowchart showing an example of the flow of the additional learning process. The additional learning process is a process performed by the CPU 201 of the learning device 200 by executing the additional learning program stored in the RAM 202. The additional learning program is a part of the learning program.

[0148] Reference Fig.15, the CPU 201 of the learning device 200 obtains the production data (step S31), and the process enters step S32. The production data includes the processing conditions when the substrate processing device 300 processes the substrate W after the predictor is generated, and the film thickness characteristics of the film before and after the processing. The CPU 201 controls the input and output I / F 107 to obtain the production data from the substrate processing device 300. The production data can also be obtained by reading the experimental data stored in the storage medium such as CD-ROM 209 by the storage device 104.

[0149] In step S32, execute Fig.13 The processing state data generation process shown in the figure proceeds to step S33. In step S33, the processing state data, the fixed conditions included in the processing conditions of the production data, and the etching profile are set as learning data. The etching profile is the difference between the film thickness characteristics of the film before the processing included in the production data and the film thickness characteristics of the film after the processing included in the production data. The processing state data generated by the first conversion unit 263 and the fixed conditions included in the processing conditions are set as input data. The etching profile is set as correct solution data.

[0150] In the next step S34, the CPU 201 adds a learning predictor, and the process proceeds to step S35. The input data is input to the predictor, which is a neural network, and the parameters are determined so that the output of the predictor is equal to the correct answer data. In this way, the parameters of the predictor are further adjusted.

[0151] In step S35, it is determined whether the adjustment is completed. The performance of the predictor is evaluated with the learning data for evaluation. When the evaluation result satisfies the predetermined additional learning evaluation criterion, the adjustment is determined to be completed. The additional learning evaluation criterion is a higher criterion than the evaluation criterion used when the predictor is generated. If the evaluation result does not satisfy the additional learning evaluation criterion (No in step S35), the process returns to step S31, but if the evaluation result satisfies the additional learning evaluation criterion (Yes in step S35), the process ends.

[0152] (3) The learning device 200 may generate a distillation model for learning a new learning model using the distillation data including the processing conditions determined by the information processing device 100 and the etching profile estimated by the predictor based on the processing conditions. Therefore, it is easy to prepare data for learning the new learning model.

[0153] (4) In this embodiment, in the learning data for generating the predictor, the input data includes the processing state data and the fixed conditions. The present invention is not limited to this. The input data may include only the processing state data after the variable conditions and the fixed conditions such as the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution are converted, and may not include the fixed conditions.

[0154] (5) In this embodiment, the relative position between the nozzle 311 and the substrate W is shown as an example of a variable condition, but the present invention is not limited to this. In the case where at least one of the temperature of the etching solution, the concentration of the etching solution, the flow rate of the etching solution, and the rotation speed of the substrate W changes with the passage of time, these may be used as the variable condition. In addition, the variable condition is not limited to one type, and a plurality of types may be combined.

[0155] (6) Although the information processing apparatus 100 and the learning apparatus 200 are provided as separate bodies from the substrate processing apparatus 300, the present invention is not limited thereto. The information processing apparatus 100 may be incorporated into the substrate processing apparatus 300. Furthermore, the information processing apparatus 100 and the learning apparatus 200 may also be incorporated into the substrate processing apparatus 300. In addition, although the information processing apparatus 100 and the learning apparatus 200 are provided as separate bodies, they may also be provided as an integrated body.

[0156] 6. Effects of implementation methods

[0157] The learning device 200 in this embodiment drives the substrate processing device 300 under the processing conditions including the variable conditions to process the film formed on the substrate, obtains the processing amount representing the difference in film thickness before and after the processing of the film, and generates a predictor, which is a learning model that causes the neural network machine to learn the learning data to infer the etching profile, and the learning data includes the processing state data after the variable conditions and the fixed conditions of the rotation speed of the substrate W, the temperature of the etching liquid, and the flow rate of the etching liquid are converted by the first conversion unit 263 as input data, and includes the etching profile corresponding to the processing conditions as correct answer data. As the learning data, since the processing state data converted in a manner to reduce the dimension of the variable conditions that change with the passage of time are included as input data, the dimension of the learning data can be reduced. Therefore, a learning device suitable for machine learning to learn the conditions that change with the passage of time in order to process the substrate W can be generated. In addition, the predictor generation unit 265 causes the predictor machine to learn the processing state data including the temperature of the substrate W associated with the position on the substrate W. The temperature of the substrate W contributes to the processing of the substrate W, and therefore, a learning model with high prediction accuracy can be generated.

[0158] Furthermore, the learning apparatus 200 converts the average value AV1 indicating the average temperature change of each of the plurality of movement sections into which the movement range of the nozzle 311 of the substrate processing apparatus 300 is divided into processing status data, thereby facilitating conversion from the variation condition to the processing status data.

[0159] In addition, the processing conditions include variable conditions and fixed conditions that do not change with the passage of time. Therefore, it is possible to cope with processing different from the fixed conditions, and it is not necessary to generate a plurality of learning models with different fixed conditions.

[0160] In addition, after the learning device 200 generates the predictor, after the substrate processing device 300 processes the film formed on the substrate W according to the processing conditions, the processing amount indicating the difference in film thickness before and after the processing of the film is obtained, and the learning model is trained using the additional learning data including the processing state data obtained by converting the temporary variable conditions by the first conversion unit 263 and the obtained processing amount. Therefore, since the learning model is additionally learned, the performance of the learning model can be improved.

[0161] In addition, the learning device 200 assigns the processing state data after the temporary change condition is converted by the first conversion unit 263 to the learning model, and generates a new learning model using the distillation data including the conversion result and the processing amount estimated by the learning model when the processing amount estimated by the learning model satisfies the permissible condition. Therefore, it is easy to prepare data for learning the new learning model.

[0162] In addition, the substrate processing apparatus 300 includes a nozzle 311 for supplying an etching liquid to a substrate W, and a nozzle moving mechanism 301 for changing the relative position of the nozzle and the substrate W, and the change condition is the relative position of the nozzle 311 and the substrate W changed by the nozzle moving mechanism 301. The relative position of the nozzle 311 and the substrate W is changed, and a learning model is generated for estimating the processing amount of a film processed by supplying the etching liquid to the substrate W from the nozzle 311. Therefore, a learning model for estimating the processing amount in the etching process can be generated.

[0163] In addition, the information processing device 100 assigns the conversion result after the temporary variable condition is converted by the compressor generated by the learning device 200 to the learning model generated by the learning device 200, and when the etching profile estimated by the learning model satisfies the permissible condition, the processing condition including the temporary variable condition is determined as the processing condition for driving the substrate processing device 300. Therefore, the etching profile is estimated based on the processing condition, so it is not necessary to conduct experiments, etc. to find out the influence of the action of the nozzle that moves in a complex manner on the processing result of the etching process. In addition, a plurality of temporary variable conditions are determined for the processing amount that satisfies the permissible condition, so a plurality of variable conditions corresponding to the plurality of etching profiles that satisfy the permissible condition can be determined. Therefore, a plurality of variable conditions can be prompted for the processing result of the complex process of processing the substrate. If a processing condition that makes it easy to control the nozzle action is selected from the plurality of variable conditions, the control of the substrate processing device 300 becomes easy.

[0164] In addition, the information processing device 100 determines a plurality of processing conditions for the processing amount that satisfies the allowable conditions, and thus, it is possible to determine a plurality of processing conditions corresponding to a plurality of etching profiles that satisfy the allowable conditions. Furthermore, the fixed conditions include the temperature of the etching liquid. Therefore, it is possible to prompt a plurality of etching liquid temperatures for the processing result of a complex process for processing a substrate. In addition, it is possible to select the temperature of the etching liquid that is easy to apply to the etching process from among the plurality of etching liquid temperatures. Furthermore, since it is possible to select the temperature of the etching liquid that is easy to apply, it is easy to adjust the temperature of the etching liquid used for the etching process. Furthermore, the fixed conditions include the rotation speed of the substrate W and the flow rate of the etching liquid. Therefore, for the processing result of the complex process for processing a substrate, similarly to the temperature of the etching liquid, it is possible to prompt a plurality of candidates for each of the rotation speed of the substrate W and the flow rate of the etching liquid, thereby facilitating their selection.

[0165] 7. Correspondence between the components of the technical solution and the parts of the implementation method

[0166] The substrate W is an example of a substrate, the etching liquid is an example of a processing liquid, the substrate processing device 300 is an example of a substrate processing device, the experimental data acquisition unit 261 is an example of an experimental data acquisition unit, the first conversion unit 263 is an example of a conversion unit and a first conversion unit, the predictor is an example of a learning model, and the predictor generation unit 265 is an example of a model generation unit. In addition, the information processing device 100 is an example of an information processing device, the second conversion unit 157 is an example of a second conversion unit, the nozzle 311 is an example of a nozzle that supplies the processing liquid to the substrate, the nozzle moving mechanism 301 is an example of a moving unit, and the prediction unit 159, the evaluation unit 161 and the processing condition determination unit 151 are examples of a processing condition determination unit.

[0167] 8. Summary of implementation methods

[0168] (Item 1) A learning device, wherein:

[0169] have:

[0170] an experimental data acquisition unit that acquires a first processing amount indicating a difference in film thickness before and after processing of the film, after driving a substrate processing device that moves a nozzle that supplies a processing liquid to a substrate on which a film is formed and supplies the processing liquid to the substrate under processing conditions including a change condition indicating a relative position of the nozzle relative to the substrate that changes with time to process the film formed on the substrate;

[0171] a conversion unit that converts the change condition and other conditions of the processing conditions other than the change condition into processing status data indicating a status of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; and

[0172] A model generation unit generates a learning model that performs machine learning on learning data including the processing status data and the first processing amount corresponding to the processing conditions, and infers a second processing amount that shows the difference in film thickness before and after the film is processed, with respect to the film formed on the substrate before the film is processed by the substrate processing device.

[0173] According to the learning device described in the first item, the learning data includes processing state data and processing volume converted from the change condition representing the relative position of the nozzle relative to the substrate that changes over time and other conditions other than the change condition. Therefore, the dimension of the learning data can be reduced. In addition, the known relationship between the multiple parameters included in the processing condition can be explicitly added to the learning model. As a result, a learning device suitable for machine learning of conditions that change over time for processing a substrate can be provided.

[0174] (Item 2) The learning device as described in Item 1, wherein:

[0175] The processing state is the temperature of the substrate;

[0176] The conversion unit determines the temperature of the substrate as the state of the process in each of the plurality of divided regions based on the variation condition, the temperature of the process liquid, the flow rate of the process liquid ejected from the nozzle, and the rotation speed of the substrate.

[0177] According to the learning device described in item 2, the processing state data includes the temperature of the substrate associated with the position on the substrate. The temperature of the substrate contributes to the processing of the substrate, and therefore a learning model with high prediction accuracy can be generated.

[0178] (Item 3) A learning device as described in Item 1 or Item 2, wherein:

[0179] The state of the treatment is a thickness of a liquid film formed on the substrate by supplying the treatment liquid from the nozzle;

[0180] The conversion section determines a thickness of a liquid film formed on the substrate as a state of the processing in each of the plurality of divided regions based on the variation condition, a flow rate of the processing liquid ejected from the nozzle, and a rotation speed of the substrate.

[0181] According to the learning device described in item 3, the processing state data includes a film of the processing liquid associated with a position on the substrate. The thickness of the film of the processing liquid contributes to processing of the substrate, and therefore a highly accurate learning model can be generated.

[0182] (Item 4) A learning device as described in Item 2 or Item 3, wherein:

[0183] The model generation unit performs machine learning on learning data including the processing status data, replacing the change condition.

[0184] According to the learning device described in item 4, the dimension of machine learning performed by the model generation unit can be reduced, so over-learning in the model generation unit can be suppressed.

[0185] (Item 5) A learning device as described in Item 1, wherein:

[0186] The length of each of the plurality of divided regions in the radial direction of the substrate is equal to or greater than the inner diameter of the nozzle.

[0187] According to the learning device described in item 5, since the radial length of the divided region in the substrate is set to be equal to or larger than the inner diameter of the nozzle, the amount of processing status data can be reduced.

[0188] (Item 6) An information processing device for managing a substrate processing device, wherein:

[0189] The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under processing conditions including a change condition indicating that a relative position of a nozzle changes with time relative to the substrate;

[0190] The information processing device comprises:

[0191] a conversion unit that converts the change condition and other conditions of the processing conditions other than the change condition into processing status data indicating a status of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; and

[0192] a processing condition determination unit that determines a processing condition for driving the substrate processing apparatus using a learning model for estimating a second processing amount indicating a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing apparatus;

[0193] The learning model is an inference model for performing machine learning on learning data including processing state data and a first processing amount, wherein the processing state data is processing state data in which the variable condition included in the processing condition for the substrate processing apparatus to process the film formed on the substrate is converted in the same manner as the conversion unit, and the first processing amount is a first processing amount indicating a difference in film thickness before and after the film formed on the substrate after the substrate processing apparatus processes the film;

[0194] The processing condition determination unit assigns processing status data after the temporary variable conditions are converted by the conversion unit to the learning model, and when the second processing amount estimated by the learning model satisfies the permissible conditions, the processing conditions including the temporary variable conditions are determined as the processing conditions for driving the substrate processing device.

[0195] According to the information processing device described in item 6, the processing state data converted from the temporary change condition that changes with the passage of time is given to the learning model, and when the processing amount estimated by the learning model satisfies the allowable condition, the processing condition including the temporary change condition is determined as the processing condition for driving the substrate processing device. Therefore, it is possible to determine a plurality of temporary change conditions for the processing amount that satisfies the allowable condition. As a result, it is possible to provide an information processing device that can indicate a plurality of processing conditions for the processing result of a complex process for processing a substrate.

[0196] (Item 7) A substrate processing device having the information processing device described in Item 6.

[0197] According to the substrate processing apparatus described in Item 7, it is possible to provide a substrate processing apparatus capable of presenting a plurality of processing conditions for processing results of a complex process for processing a substrate.

[0198] (Item 8) A substrate processing system that manages a substrate processing device for processing a substrate, wherein:

[0199] Having a learning device and an information processing device;

[0200] The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under processing conditions including a change condition indicating that a relative position of a nozzle with respect to the substrate changes with the passage of time;

[0201] The learning device comprises:

[0202] an experimental data acquisition unit that acquires a first processing amount indicating a difference in film thickness before and after the film is processed after the substrate processing device is driven under the processing conditions to process the film formed on the substrate;

[0203] a first conversion unit that converts the variation condition and other conditions of the processing conditions other than the variation condition into processing status data indicating a status of processing of each of a plurality of divided regions that divide the upper surface of the substrate into concentric circles; and

[0204] a model generating unit generating a learning model that performs machine learning on learning data including the processing state data after the variable condition is converted by the first converting unit and the first processing amount corresponding to the processing condition, and estimates a second processing amount indicating a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing device;

[0205] The information processing device comprises:

[0206] a second conversion unit identical to the first conversion unit; and

[0207] a processing condition determination unit that determines a processing condition for driving the substrate processing device using the learning model generated by the learning device;

[0208] The processing condition determination unit assigns a conversion result of the temporary variable condition converted by the second conversion unit to the learning model, and when the second processing amount estimated by the learning model satisfies the allowable condition, the processing condition including the temporary variable condition is determined as the processing condition for driving the substrate processing device.

[0209] According to the substrate processing system described in Item 8, it is possible to provide a substrate processing system that can present a plurality of processing conditions for processing results of a complex process for processing a substrate.

[0210] (Item 9) A learning method that causes a computer to perform the following processing:

[0211] After a substrate processing apparatus that moves a nozzle that supplies a processing liquid to a substrate on which a film is formed and supplies the processing liquid to the substrate is driven under processing conditions including a change condition indicating that a relative position of the nozzle changes with time relative to the substrate to process the film formed on the substrate, a first processing amount indicating a difference in film thickness before and after the processing of the film is acquired;

[0212] converting the variation condition and other conditions of the processing conditions other than the variation condition into processing status data indicating the status of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; and

[0213] A learning model is generated that performs machine learning on learning data including the processing status data and the first processing amount corresponding to the processing conditions, and estimates a second processing amount showing the difference in film thickness before and after the film is processed, with respect to the film formed on the substrate before the film is processed by the substrate processing device.

[0214] According to the learning method described in item 9, the learning data includes processing state data and processing amount converted from the change condition indicating the relative position of the nozzle relative to the substrate that changes over time and other conditions other than the change condition. Therefore, the dimension of the learning data can be reduced. In addition, the known relationship between the plurality of parameters included in the processing condition can be explicitly added to the learning model. As a result, a learning method suitable for machine learning of conditions that change over time for processing a board can be provided.

[0215] (Item 10) A method for determining processing conditions, executed by a computer managing a substrate processing apparatus, wherein:

[0216] The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under processing conditions including a change condition indicating that a relative position of a nozzle with respect to the substrate changes with time.

[0217] The processing condition determination method includes the following processing:

[0218] converting the variation condition and other conditions of the processing conditions other than the variation condition into processing status data indicating the status of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; and

[0219] determining a processing condition for driving the substrate processing apparatus using a learning model for estimating a second processing amount indicating a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing apparatus;

[0220] The learning model is an inference model that performs machine learning on learning data including processing state data and a first processing amount, wherein the processing state data is processing state data in which the variable condition included in the processing condition for the substrate processing apparatus to process the film formed on the substrate is converted in the same manner as the conversion process, and the first processing amount is a first processing amount indicating a difference in film thickness before and after the film formed on the substrate after the film is processed by the substrate processing apparatus;

[0221] In the process of determining the processing conditions, the learning model is assigned processing status data after the temporary variable conditions are converted through the conversion process, and when the second processing amount estimated by the learning model satisfies the allowable conditions, the processing conditions including the temporary variable conditions are determined as the processing conditions for driving the substrate processing device.

[0222] According to the processing condition determination method described in item 10, the processing state data converted from the temporary variable conditions that change with the passage of time is assigned to the learning model, and when the processing volume estimated by the learning model satisfies the permissible conditions, the processing conditions including the temporary variable conditions are determined as the processing conditions for driving the substrate processing device. Therefore, a plurality of temporary variable conditions can be determined for the processing volume that satisfies the permissible conditions. As a result, a processing condition determination method that can indicate a plurality of processing conditions for the processing results of a complex process for processing a substrate can be provided.

Claims

1. A learning device, wherein: have: an experimental data acquisition unit that acquires a first processing amount indicating a difference in film thickness before and after processing of the film, after driving a substrate processing device that moves a nozzle that supplies a processing liquid to a substrate on which a film is formed and supplies the processing liquid to the substrate under processing conditions including a change condition indicating a relative position of the nozzle relative to the substrate that changes with time to process the film formed on the substrate; a conversion unit that converts the change condition and other conditions of the processing conditions other than the change condition into processing state data indicating a state of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; as well as A model generation unit generates a learning model that performs machine learning on learning data including the processing status data and the first processing amount corresponding to the processing conditions, and infers a second processing amount that shows the difference in film thickness before and after the film is processed, with respect to the film formed on the substrate before the film is processed by the substrate processing device.

2. The learning device according to claim 1, wherein: The processing state is the temperature of the substrate; The conversion unit determines the temperature of the substrate as the state of the process in each of the plurality of divided regions based on the variation condition, the temperature of the process liquid, the flow rate of the process liquid ejected from the nozzle, and the rotation speed of the substrate.

3. The learning device according to claim 1 or 2, wherein: The state of the treatment is a thickness of a liquid film formed on the substrate by supplying the treatment liquid from the nozzle; The conversion section determines a thickness of a liquid film formed on the substrate as a state of the processing in each of the plurality of divided regions based on the variation condition, a flow rate of the processing liquid ejected from the nozzle, and a rotation speed of the substrate.

4. The learning device according to claim 2, wherein: The model generation unit performs machine learning on learning data including the processing status data, replacing the change condition.

5. The learning device according to claim 1, wherein: The length of each of the plurality of divided regions in the radial direction of the substrate is equal to or greater than the inner diameter of the nozzle.

6. An information processing device for managing a substrate processing device, wherein: The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under processing conditions including a change condition indicating that a relative position of a nozzle changes with time relative to the substrate; The information processing device comprises: a conversion unit that converts the change condition and other conditions of the processing conditions other than the change condition into processing status data indicating a status of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; and a processing condition determination unit that determines a processing condition for driving the substrate processing apparatus using a learning model for estimating a second processing amount indicating a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing apparatus; The learning model is an inference model for performing machine learning on learning data including processing state data and a first processing amount, wherein the processing state data is processing state data in which the variable condition included in the processing condition for the substrate processing apparatus to process the film formed on the substrate is converted in the same manner as the conversion unit, and the first processing amount is a first processing amount indicating a difference in film thickness before and after the film formed on the substrate after the substrate processing apparatus processes the film; The processing condition determination unit assigns processing status data after the temporary variable conditions are converted by the conversion unit to the learning model, and when the second processing amount estimated by the learning model satisfies the permissible conditions, the processing conditions including the temporary variable conditions are determined as the processing conditions for driving the substrate processing device.

7. A substrate processing apparatus comprising the information processing apparatus according to claim 6.

8. A substrate processing system, managing a substrate processing device for processing a substrate, wherein: Having a learning device and an information processing device; The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under processing conditions including a change condition indicating that a relative position of a nozzle with respect to the substrate changes with the passage of time; The learning device comprises: an experimental data acquisition unit that acquires a first processing amount indicating a difference in film thickness before and after the film is processed after the substrate processing device is driven under the processing conditions to process the film formed on the substrate; a first conversion unit that converts the change condition and other conditions of the processing conditions other than the change condition into processing state data indicating a state of processing of each of a plurality of divided regions that divide the upper surface of the substrate into concentric circles; as well as a model generating unit generating a learning model that performs machine learning on learning data including the processing state data after the variable condition is converted by the first converting unit and the first processing amount corresponding to the processing condition, and estimates a second processing amount indicating a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing device; The information processing device comprises: a second conversion unit identical to the first conversion unit; and a processing condition determination unit that determines a processing condition for driving the substrate processing device using the learning model generated by the learning device; The processing condition determination unit assigns a conversion result of the temporary variable condition converted by the second conversion unit to the learning model, and when the second processing amount estimated by the learning model satisfies the allowable condition, the processing condition including the temporary variable condition is determined as the processing condition for driving the substrate processing device.

9. A learning method, causing a computer to perform the following processing: After a substrate processing apparatus that moves a nozzle that supplies a processing liquid to a substrate on which a film is formed and supplies the processing liquid to the substrate is driven under processing conditions including a change condition indicating that a relative position of the nozzle changes with time relative to the substrate to process the film formed on the substrate, a first processing amount indicating a difference in film thickness before and after the processing of the film is acquired; converting the change condition and other conditions of the processing conditions other than the change condition into processing status data indicating the status of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; as well as A learning model is generated that performs machine learning on learning data including the processing status data and the first processing amount corresponding to the processing conditions, and estimates a second processing amount showing the difference in film thickness before and after the film is processed, with respect to the film formed on the substrate before the film is processed by the substrate processing device.

10. A method for determining processing conditions, executed by a computer managing a substrate processing apparatus, wherein: The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film is formed under processing conditions including a change condition indicating that a relative position of a nozzle with respect to the substrate changes with time. The processing condition determination method includes the following processing: converting the change condition and other conditions of the processing conditions other than the change condition into processing status data indicating the status of processing of each of a plurality of divided regions dividing the upper surface of the substrate by concentric circles; as well as determining a processing condition for driving the substrate processing apparatus using a learning model for estimating a second processing amount indicating a difference in film thickness before and after the film is processed for the film formed on the substrate before the film is processed by the substrate processing apparatus; The learning model is an inference model that performs machine learning on learning data including processing state data and a first processing amount, wherein the processing state data is processing state data in which the variable condition included in the processing condition for the substrate processing apparatus to process the film formed on the substrate is converted in the same manner as the conversion process, and the first processing amount is a first processing amount indicating a difference in film thickness before and after the film formed on the substrate after the film is processed by the substrate processing apparatus; In the process of determining the processing conditions, the learning model is assigned processing status data after the temporary variable conditions are converted through the conversion process, and when the second processing amount estimated by the learning model satisfies the allowable conditions, the processing conditions including the temporary variable conditions are determined as the processing conditions for driving the substrate processing device.

Images