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

Abstract

To perform machine learning of a condition which is changed in accordance with the lapse of time for processing a substrate.SOLUTION: A learning device comprises: an examination data acquisition part 261 that acquires a first processing amount indicating a difference in film thickness between before and after a processing of a film after the processing of the film formed on a substrate by driving a substrate processing apparatus under a processing condition including a fluctuation condition indicating a relative position of a nozzle fluctuated with respect to the substrate in accordance with the lapse of time; a conversion part that converts the fluctuation condition and the other condition other than the fluctuation condition of the processing condition into processing state data indicating a processing state in each of a plurality of division regions obtained by dividing an upper surface of the substrate in a concentric circle; and a prediction device generation part 265 that generates a learning model for estimating a second processing amount by performing machine learning of the learning data containing the processing state data and the first processing amount corresponded to the processing condition.SELECTED DRAWING: Figure 4

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 for simulating processing according to processing conditions by a substrate processing device, an information processing device that determines processing conditions using the learning model, a substrate processing device including the information processing device, a substrate processing system including 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] In a semiconductor manufacturing process, there is a cleaning process. In the cleaning process, the film thickness of the film formed on the substrate is adjusted by an etching process of applying a chemical solution to the substrate. In this film thickness adjustment, it is important to perform the etching process so that the surface of the substrate becomes uniform, or to flatten the surface of the substrate by the etching process. When discharging the etching solution from the nozzle to a part of the substrate, it is necessary to move the nozzle in the radial direction with respect to the substrate. However, the etching process is a complex process in which the amount of film processed changes depending on the difference in the operation of moving the nozzle. Also, the amount of film processed by the etching process is determined after processing the substrate. Therefore, the work of setting the operation of moving the nozzle requires trial and error by a technician. It takes a great deal of cost and time to determine the optimal operation of the nozzle.

[0003] Japanese Patent Application Laid-Open No. 2021-108367 describes a device that determines scan speed information from a target processing amount using a learned model obtained by machine learning with learning data having "input" as the processing amount (etching amount) and "output" as the scan speed information. According to this technique, one scan speed information is determined from the target processing amount.

Prior Art Documents

Patent Documents

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-108367 [Overview of the project] [Problems that the invention aims to solve]

[0005] On the other hand, it is desirable to make the nozzle movement more complex. The nozzle movement represents time-series data indicating the position that changes over time. Making the nozzle movement more complex shortens the sampling interval, thus increasing the dimensionality of the time-series data. In general, as the dimensionality of the training data increases, the amount of data required for machine learning increases exponentially. Therefore, as the dimensionality of the training data increases, it becomes difficult to optimize the learning model obtained by machine learning. Also, since etching is a complex process, there may not be just one nozzle movement suitable for the target processing volume, but rather multiple such movements may exist.

[0006] One of the objectives of the present invention is to provide a learning device, a learning method, and a substrate processing system suitable for machine learning the conditions that change over time when processing a substrate.

[0007] Another object of the present invention is to provide an information processing device, a substrate processing device, a substrate processing system, and a method for determining processing conditions that can present multiple processing conditions for the processing results of a complex process for processing a substrate. [Means for solving the problem]

[0008] A learning device according to one aspect of the present invention includes: an experimental data acquisition unit that acquires a first processing amount indicating the difference in film thickness before and after processing a film formed on a substrate by moving a nozzle that supplies a processing liquid to a substrate on which a film has been formed, and driving the substrate processing device that supplies the processing liquid to the substrate with processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates with respect to the substrate over time; a conversion unit that converts the fluctuation condition and other processing conditions other than the fluctuation condition into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles; and a model generation unit that uses machine learning on learning data including the processing state data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing a film formed on a substrate before it is processed by the substrate processing device.

[0009] An information processing apparatus according to another aspect of the present invention is an information processing apparatus for 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 with processing conditions that include a fluctuation condition indicating the relative position of a nozzle that fluctuates with respect to the substrate over time, and converts the fluctuation condition and other processing conditions other than the fluctuation condition into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, and uses a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing for a film formed on the substrate before it is processed by the substrate processing apparatus, The system includes a processing condition determination unit that determines processing conditions for driving the processing device, and the learning model is an inference model that has learned by machine learning from learning data which includes processing state data that has been transformed in the same way as the transformation unit, and a first processing amount that indicates the difference in film thickness before and after processing of the film formed on the substrate processed by the substrate processing device, and the processing condition determination unit provides the processing state data, which has been transformed by the transformation unit into provisional fluctuation conditions, to the learning model, and determines the processing conditions including the provisional fluctuation conditions as the processing conditions for driving the substrate processing device if the second processing amount estimated by the learning model satisfies the acceptable conditions.

[0010] A substrate processing system according to yet another aspect of the present invention is a substrate processing system for managing a substrate processing apparatus, comprising a learning device and an information processing device, wherein the substrate processing apparatus processes a film formed on a substrate by supplying a processing liquid to the substrate with processing conditions including a variable condition indicating the relative position of a nozzle that fluctuates with respect to the substrate over time, and the learning device includes an experimental data acquisition unit that acquires a first processing amount indicating the difference in film thickness before and after processing the film after driving the substrate processing apparatus with processing conditions, and a first conversion unit that converts the variable condition and other processing conditions other than the variable condition into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, and the first conversion unit The information processing device includes a model generation unit that uses machine learning to generate a learning model that estimates a second processing amount, which indicates the difference in film thickness before and after processing of a film formed on a substrate before it is processed by a substrate processing device, by using learning data including processing state data in which the fluctuating conditions have been transformed and a first processing amount corresponding to the processing conditions. The information processing device also includes a second transformation unit, which is the same as the first transformation unit, and a processing condition determination unit that uses the learning model generated by the learning device to determine processing conditions for driving the substrate processing device. The processing condition determination unit provides the transformation result in which the provisional fluctuating conditions have been transformed by the second transformation unit to the learning model, and determines the processing conditions including the provisional fluctuating conditions as the processing conditions for driving the substrate processing device if the second processing amount estimated by the learning model satisfies the acceptable conditions.

[0011] A learning method according to yet another aspect of the present invention involves having a computer perform the following steps: moving a nozzle that supplies a processing liquid to a substrate on which a film has been formed, and driving a substrate processing apparatus that supplies the processing liquid to the substrate with processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, to process the film formed on the substrate, and then obtaining a first processing amount indicating the difference in film thickness before and after processing the film; converting the fluctuation condition and other processing conditions other than the fluctuation condition into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles; and using machine learning on learning data including the processing state data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing the film for a film formed on a substrate before it is processed by the substrate processing apparatus.

[0012] A method for determining processing conditions according to yet another aspect of the present invention is a method for determining processing conditions executed by a computer that manages 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 has been formed, using processing conditions that include a variable condition indicating the relative position of a nozzle that changes with respect to the substrate over time, and converts the variable condition and other processing conditions other than the variable condition into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, and a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing for the film formed on the substrate before processing by the substrate processing apparatus. The process includes determining processing conditions for driving the substrate processing apparatus, and the learning model is an inference model that has learned by machine learning training data including processing state data that has been transformed in the same way as the transformation process, and a first processing amount that shows the difference in film thickness before and after processing of the film formed on the substrate processed by the substrate processing apparatus, and the process for determining the processing conditions is to provide the learning model with processing state data into which the provisional fluctuation conditions have been transformed by the transformation process, and if the second processing amount estimated by the learning model satisfies the acceptable conditions, the processing conditions including the provisional fluctuation conditions are determined as the processing conditions for driving the substrate processing apparatus. [Effects of the Invention]

[0013] We can provide a learning device, a learning method, and a substrate processing system suitable for machine learning to process substrate conditions that change over time.

[0014] Furthermore, it is possible to provide an information processing device, a substrate processing device, a substrate processing system, and a method for determining processing conditions that can present multiple processing conditions for the processing results of a complex process for processing substrates. [Brief explanation of the drawing]

[0015] [Figure 1] This is a diagram illustrating the configuration of a substrate processing system according to one embodiment of the present invention. [Figure 2] This figure shows an example of the configuration of an information processing device. [Figure 3] This figure shows an example of the configuration of a learning device. [Figure 4] This figure shows an example of the functional configuration of a substrate processing system in one embodiment of the present invention. [Figure 5] This diagram illustrates the change in the relative position of the nozzle with respect to the substrate. [Figure 6] This figure shows an example of a nozzle operation pattern. [Figure 7] This figure shows an example of film thickness characteristics. [Figure 8] This is a diagram to explain the divided regions. [Figure 9] This figure shows an example of the substrate temperature change over time in a divided region. [Figure 10] This is a diagram explaining the predictor. [Figure 11] This is a flowchart illustrating an example of the predictor generation process. [Figure 12] This flowchart shows an example of the process flow for determining processing conditions. [Figure 13] This flowchart shows an example of the process for generating processing status data. [Figure 14] It is a diagram showing an example of the change in the film thickness of the etching solution on the substrate that changes with the passage of time predicted in the divided region. [Figure 15] It is a flowchart showing an example of the flow of additional learning processing.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, a substrate processing system according to an embodiment of the present invention will be described in detail with reference to the drawings. In the following description, the substrate refers to a semiconductor substrate (semiconductor wafer), a substrate for an FPD (Flat Panel Display) such as a liquid crystal display device or an organic EL (Electro Luminescence) display device, a substrate for an optical disk, a substrate for a magnetic disk, a substrate for a magneto-optical disk, a substrate for a photomask, a ceramic substrate, or a substrate for a solar cell, etc.

[0017] 1. Overall Configuration of the Substrate Processing System FIG. 1 is a diagram for explaining the configuration of a substrate processing system according to an embodiment of the present invention. The substrate processing system 1 in FIG. 1 includes an information processing device 100, a learning device 200, and a substrate processing device 300. The learning device 200 is, for example, a server, and the information processing device 100 is, for example, a personal computer.

[0018] The learning device 200 and the information processing device 100 are used to manage the substrate processing device 300. Note that the substrate processing device 300 managed by the learning device 200 and the information processing device 100 is not limited to one, and a plurality of substrate processing devices 300 may be managed.

[0019] In the substrate processing system 1 according to this embodiment, the information processing device 100, the learning device 200, and the substrate processing device 300 are connected to each other by wired or wireless communication lines or a communication network. The information processing device 100, the learning device 200, and the substrate processing device 300 are each connected to a network and are capable of sending and receiving data to and from each other. The network may be, for example, a local area network (LAN) or a wide area network (WAN). Alternatively, the network may be the internet. Furthermore, the information processing device 100 and the substrate processing device 300 may be connected by a dedicated communication network. The network connection may be wired or wireless.

[0020] Furthermore, 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 communication network. In this case, data generated by the substrate processing device 300 may be passed to the learning device 200 via a recording medium. Alternatively, data generated by the learning device 200 may be passed to the information processing device 100 via a recording medium.

[0021] The substrate processing apparatus 300 is equipped with a display device, an audio output device, and an operating unit (not shown). The substrate processing apparatus 300 is operated according to predetermined processing conditions (processing recipe) of the substrate processing apparatus 300.

[0022] 2. Overview of substrate processing equipment The substrate processing apparatus 300 comprises 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 process the substrate by supplying a constant flow rate of processing liquid to the substrate W on which a film has been formed. In this embodiment, the substrate W to be processed has a diameter of 300 mm, but the present invention is not limited thereto. The processing liquid includes an etching solution, and the substrate processing units WU perform the etching process. The etching solution is a chemical solution. Examples of etching solutions include hydrofluoric acid (a mixture of hydrofluoric acid (HF) and nitric acid (HNO3)), hydrofluoric acid, buffered hydrofluoric acid (BHF), ammonium fluoride, HFEG (a mixture of hydrofluoric acid and ethylene glycol), or phosphoric acid (H3PO4).

[0023] The substrate processing unit WU comprises a spin chuck SC, a spin motor SM, a nozzle 311, and a nozzle moving mechanism 301. The spin chuck SC holds the substrate W horizontally. The substrate W is held in the spin chuck SC such that the center of the substrate W coincides with the first rotation axis AX1 of the spin motor SM. The spin motor SM has a first rotation axis AX1. The first rotation axis AX1 extends in the vertical direction. The spin chuck SC is attached to the upper end of the first rotation axis AX1 of the spin motor SM. When the spin motor SM rotates, the spin chuck SC rotates around the first rotation axis AX1. The spin motor SM is a stepping motor. The substrate W held in the spin 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. If an encoder that generates a rotation speed signal indicating the rotation speed of the spin motor is provided, the rotation speed of the substrate W may be obtained from the rotation speed signal generated by the encoder. In this case, the spin motor SM can use a motor other than a stepping motor.

[0024] The nozzle 311 supplies etching solution to the substrate W. The nozzle 311 receives etching solution from an etching solution supply unit (not shown) and discharges the etching solution toward the rotating substrate W.

[0025] 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 positioned so that the second rotation axis AX2 is aligned substantially vertically. The nozzle arm 305 has a linear longitudinal shape. One end of the nozzle arm 305 is attached to the upper end of the second rotation axis AX2 such that the longitudinal direction of the nozzle arm 305 is different from that of the second rotation axis AX2. The nozzle 311 is attached to the other end of the nozzle arm 305 so that its discharge port faces downward.

[0026] When the nozzle motor 303 operates, the nozzle arm 305 rotates in the horizontal plane about the second rotation axis AX2. As a result, the nozzle 311 attached to the other end of the nozzle arm 305 moves horizontally (rotates) about the second rotation axis AX2. The nozzle 311 discharges etching solution toward the substrate W while moving horizontally. The nozzle motor 303 is, for example, a stepping motor.

[0027] The control device 10 includes a CPU (Central Processing Unit) and memory, and the CPU controls the entire substrate processing device 300 by executing a program stored in the memory. The control device 10 controls the spin motor SM and the nozzle motor 303.

[0028] The learning device 200 receives experimental data from the substrate processing device 300, uses the experimental data to train a learning model, and outputs the trained learning model to the information processing device 100.

[0029] The information processing device 100 uses a pre-trained model to determine the processing conditions for the substrate that the substrate processing device 300 is scheduled to process. The information processing device 100 outputs the determined processing conditions to the substrate processing device 300.

[0030] Figure 2 shows an example of the configuration of an information processing device. Referring to Figure 2, the information processing device 100 consists of a CPU 101, RAM (random access memory) 102, ROM (read-only memory) 103, storage device 104, operation unit 105, display device 106, and input / output interface 107. The CPU 101, RAM 102, ROM 103, storage device 104, operation unit 105, display device 106, and input / output interface 107 are connected to a bus 108.

[0031] RAM 102 is used as the working area for CPU 101. ROM 103 stores the system program. Storage device 104 includes a storage medium such as a hard disk or semiconductor memory and stores the program. The program may also be stored in ROM 103 or other external storage devices.

[0032] A CD-ROM 109 is removable from the storage device 104. The recording medium for storing the program executed by the CPU 101 is not limited to the CD-ROM 109, but may also be an optical disc (MO (Magnetic Optical Disc) / MD (Mini Disc) / DVD (Digital Versatile Disc)), an IC card, an optical card, a mask ROM, an EPROM (Erasable Programmable ROM), or other semiconductor memory. Furthermore, the CPU 101 may download a program from a computer connected to the network and store it in the storage device 104, or a computer connected to the network may write a program to the storage device 104, load the program stored in the storage device 104 into the RAM 102, and execute it on the CPU 101. The program referred to here includes not only programs that can be directly executed by the CPU 101, but also source programs, compressed programs, encrypted programs, etc.

[0033] The operation unit 105 is an input device such as a keyboard, mouse, or touch panel. The user can give predetermined instructions 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, and displays a GUI (Graphical User Interface) or the like to receive instructions from the user. The input / output I / F 107 is connected to a network.

[0034] Figure 3 shows an example of the configuration of a learning device. Referring to Figure 3, the learning device 200 consists of a CPU 201, RAM 202, ROM 203, storage device 204, operation unit 205, display device 206, and input / output I / F 207. The CPU 201, RAM 202, ROM 203, storage device 204, operation unit 205, display device 206, and input / output I / F 207 are connected to a bus 208.

[0035] RAM202 is used as the working area for CPU201. ROM203 stores the system program. Storing device204 includes a storage medium such as a hard disk or semiconductor memory and stores the program. The program may also be stored in ROM203 or other external storage devices. A CD-ROM209 is removable from storage device204.

[0036] The control unit 205 is an input device such as a keyboard, mouse, or touch panel. The input / output interface 207 is connected to a network.

[0037] 3. Functional configuration of the substrate processing system Figure 4 shows an example of the functional configuration of a substrate processing system in one embodiment of the present invention. Referring to Figure 4, the control device 10 of the substrate processing apparatus 300 controls the substrate processing unit WU to process the substrate W according to processing conditions. The processing conditions are the conditions for processing the substrate W during a predetermined processing time. The processing time is the time determined for processing the substrate. In this embodiment, the processing time is the time while the nozzle 311 is discharging the etching solution onto the substrate W.

[0038] 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 between the nozzle 311 and the substrate W. The processing conditions also include variable conditions that change over time. In this embodiment, the variable condition is the relative position between the nozzle 311 and the substrate W. The relative position is indicated by the rotation angle of the nozzle motor 303. The processing conditions also include fixed conditions that do not change over 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.

[0039] The learning device 200 trains a learning model with training data and generates an inference model that predicts the etching profile from the processing conditions. Hereinafter, the inference model generated by the learning device 200 will be referred to as the predictor.

[0040] 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 functions of the learning device 200 are realized by the CPU 201 of the learning device 200, which executes a learning program stored in the RAM 202.

[0041] The experimental data acquisition unit 261 acquires experimental data from the substrate processing apparatus 300. The experimental data includes the processing conditions used when the substrate processing apparatus 300 actually processes the substrate W, and the film thickness characteristics of the film formed on the substrate W before and after processing. The film thickness characteristics are indicated by the film thickness at multiple different positions in the radial direction of the substrate W.

[0042] The variable conditions include the relative position of the nozzle 311 with respect to the substrate W, which changes over 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 between the nozzle 311 and the substrate W is indicated 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. Furthermore, the range of the rotation angle of the nozzle motor 303 is limited to a predetermined range. In addition, the processing time is a predetermined period. In this embodiment, the processing time is 60 seconds.

[0043] Figure 5 illustrates the change in the relative position of the nozzle with respect to the substrate. Referring to Figure 5, the change in the relative position of the nozzle 311 with respect to the substrate W held in the spin chuck SC is shown. The nozzle 311 moves in the region above the substrate W held in the spin chuck SC. Since the nozzle 311 rotates around the second rotation axis AX2, the trajectory of the nozzle 311 is an arc. The trajectory of the nozzle 311 passes through the substrate center OP, which indicates the center of the substrate W held in the spin chuck SC. Therefore, the nozzle 311 moves radially across the substrate W from the substrate center OP to the periphery. Here, the trajectory of the nozzle 311 is shown with one end in the operating end EP1 inside the periphery of the substrate W, and the other end in the operating end EP2 inside the periphery of the substrate W. The scan in which the nozzle 311 moves from the operating end EP1 to the substrate center OP is indicated by arrow a1, the scan in which the nozzle 311 moves from the substrate center OP to the operating end EP2 is indicated by arrow a2, the scan in which the nozzle 311 moves from the operating end EP2 to the substrate center OP is indicated by arrow a3, and the scan in which the nozzle 311 moves from the substrate center OP to the operating end EP1 is indicated by arrow a4.

[0044] Figure 6 shows an example of a nozzle operation pattern. In Figure 6, the vertical axis shows the relative position of the nozzle 311 with respect to the substrate W, and the horizontal axis shows the elapsed time (seconds). In this embodiment, the scanning period from the start to the end of the nozzle operation, which moves the nozzle 311 relative to the substrate W, is equal to the processing time. As described above, the processing time is set to 60 seconds, so the nozzle operation pattern shows the relative position for the period from 0 to 60 seconds. The relative position of the nozzle is set with the substrate center OP as zero, the range from the substrate center OP to the operating end EP1 is shown as a negative value, and the range from the substrate center OP to the operating end EP2 is shown as a positive value. Since the substrate W has a diameter of 300 mm, the distance from the substrate center OP to the operating ends EP1 and EP2 is set to ±150 mm or less. Here, the distance from the substrate center OP to the operating end EP1 is set to -147 mm, and the distance from the substrate center OP to the operating end EP2 is set to +147 mm. The relative position of the nozzle 311 when it is located at the center OP of the substrate is indicated by 0, the relative position of the nozzle 311 when it is located at the operating end EP1 is indicated by -147 mm, and the relative position of the nozzle 311 when it is located at the operating end EP2 is indicated by 147 mm.

[0045] The nozzle operation pattern shown in Figure 6 is represented as a scan that makes five reciprocating motions between the operating end EP1 and the operating end EP2. In the nozzle operation pattern, the same reference numerals are used to indicate the relative positions corresponding to the scans shown by arrows a1 to a4 in Figure 5 for the first reciprocating scan.

[0046] Figure 7 shows an example of film thickness characteristics. Referring to Figure 7, the horizontal axis shows the radial position of the substrate, and the vertical axis shows the film thickness. The origin of the horizontal axis indicates the center of the substrate. The film thickness formed on the substrate W before processing by the substrate processing apparatus 300 is shown by the solid line. The film thickness formed on the substrate W is adjusted by applying the etching solution according to the processing conditions performed by the substrate processing apparatus 300. The film thickness formed on the substrate W after processing by the substrate processing apparatus 300 is shown by the dotted line.

[0047] The difference between the film thickness formed on the substrate W before processing by the substrate processing apparatus 300 and the film thickness formed on the substrate W after processing by the substrate processing apparatus 300 is the processing amount (etching amount). The processing amount indicates the thickness of the film reduced by the process of applying the etching solution by the substrate processing apparatus 300. The radial distribution of the processing amount is called the etching profile. The etching profile includes the processing amount at each of several locations in the radial direction of the substrate W.

[0048] Furthermore, it is desirable that the film thickness formed by the substrate processing apparatus 300 be uniform across the entire surface of the substrate W. For this reason, a target film thickness is defined for the processing performed by the substrate processing apparatus 300. The target film thickness is indicated by a dashed line. The deviation characteristic is the difference between the film thickness formed on the substrate W after processing by the substrate processing apparatus 300 and the target film thickness. The deviation characteristic includes the difference at each of several locations in the radial direction of the substrate W.

[0049] Returning to Figure 4, the first conversion unit 263 converts the variable conditions included in the processing conditions of the experimental data input from the experimental data acquisition unit 261, along with the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution, into processing state data indicating the processing state of the substrate. Here, the variable condition is the relative position of the nozzle with respect to the substrate W, which changes over time during the processing period. The first conversion unit 263 outputs the processing state data to the predictor generation unit 265.

[0050] Here, we will explain the processing state data. Generally, the amount of film removed from the substrate W changes depending on the processing state of the substrate W. For example, the amount of film removed from the substrate W changes 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 is large. On the other hand, when the temperature of the substrate W is low, the amount of film removed from the substrate W is small. The temperature of the substrate W changes depending on the temperature of the etching solution supplied to the substrate W. The temperature of the part of the substrate W to which the etching solution is supplied will be the same as or close to the temperature of the etching solution, and the temperature of the part of the substrate W to which the etching solution is not supplied will be lower than the temperature of the etching solution.

[0051] The processing status data indicates the processing status in each of the multiple divided regions obtained by dividing the upper surface of the substrate W into concentric circles centered on the substrate center OP. The processing status is the temperature of the substrate. The first conversion unit 263 generates compressed data indicating the temperature of the substrate W for each of the multiple divided regions using the fluctuating conditions, the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution.

[0052] Figure 8 is a diagram illustrating the divided regions. Referring to Figure 8, the upper surface of the substrate W is divided into 15 divided regions b1 to b15 by multiple concentric circles centered on the substrate center OP. Divided region b15 is a circle, and divided regions b1 to b14 are annular. The radial length of each of the divided regions b1 to b14 of the substrate W is the same. The radial length of each of the divided regions b1 to b14 of the substrate is the difference between the radius of the outer circumference and the radius of the inner circumference. The radius of divided region b15 is the same as the radial length of each of the divided regions b1 to b14 of the substrate W. Here, the radius of divided region b15 is 10 mm, and the difference between the radii of the outer circumference and the inner circumference of each of the divided regions b1 to b14 is 10 mm. Preferably, the radial length of each of the divided regions b1 to b15 of the substrate is greater than or equal to the inner diameter of the nozzle 311.

[0053] Since the nozzle 311 rotates around the second rotation axis AX2 via the nozzle arm 305, its center of rotation is different from the substrate center OP. The range of movement of the nozzle 311 is the trajectory it traces from the operating end EP1 through the substrate center OP to the operating end EP2, and is an arc.

[0054] The range of movement 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 range of movement is divided into 29 movement segments d1 to d29 by the division regions b1 to b15. Movement segments d1 to d29 are segments of the trajectory of the nozzle 311 as it moves between the operating end EP1 and the operating end EP2, crossing each of the division regions b1 to b15. For example, movement segments d1 to d14 are the trajectories of the nozzle 311 as it moves between the operating end EP1 and the substrate center OP, crossing division regions b1 to b14. Movement segment d15 is the trajectory of the nozzle 311 as it moves between the operating end EP1 and the operating end EP2, crossing division region b15. Movement segments d16 to d29 are segments of the trajectory of the nozzle 311 as it moves between the substrate center OP and the operating end EP2, crossing each of the division regions b1 to b14. Thus, the range of movement of the nozzle 311 is divided into multiple movement intervals d1 to d29, each of which the nozzle 311 traverses multiple divisional regions b1 to b15. Note that the number of divisional regions b1 to b15 is not limited to 15, but can be set to any value. In this case, the number of divisions in the range of movement, in other words, the number of movement intervals, will differ.

[0055] Here, referring to Figure 6, the portion of the nozzle 311's operating pattern corresponding to the divided region b15 is shown. The divided region b15 is in the range of -10 mm to +10 mm relative to the nozzle 311. In Figure 6, the period during which the nozzle 311 crosses the divided region b1 (hereinafter referred to as the residence period) is shown as T1 to T10. Figure 9 is a diagram showing an example of the substrate temperature change over time in the divided region. In Figure 9, the temperature of the substrate W changes over time relative to the divided region b15. In the graph of Figure 9, 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 assumed to be TL. The blowout diagram in Figure 9 shows a magnified view of a part of the substrate temperature that changes over time. In the graph shown in the blowout, the scale of the horizontal axis is magnified. During the processing of the substrate W, the etching solution is supplied from the nozzle 311 while the substrate W is rotating. At point t0, when the nozzle 311 begins supplying etching solution to the substrate W, the nozzle 311 is located at the operating end EP1, and therefore the nozzle 311 is not present in the divided region b15. For this reason, etching solution is not supplied to the divided region b15. At this stage, the temperature of the substrate W in the divided region b15 becomes a predetermined temperature Tw. This predetermined temperature is dependent on the ambient temperature. The temperature of the divided region b15 remains constant at a constant temperature Tw.

[0056] From time t1 onward, when the nozzle 311 is in close proximity to the divided region b15, the temperature of the divided region b15 of the substrate W rises due to the temperature of the etching solution supplied from the nozzle 311. The change in temperature of the divided region b15 of the substrate W from time t1 onward can be expressed by equation (1). The coefficient α1 in equation (1) is given by equation (2).

[0057]

number

[0058] In equation (1), t represents time, and TW is a predetermined temperature that depends on the ambient temperature. In equation (2), Cu1 to Cu4 are constants. TL is the temperature of the etching solution supplied from the nozzle 311. D is the flow rate of the etching solution supplied from the nozzle 311. R is the rotation speed of the substrate W. Thus, the temperature change in the divided region b15 of the substrate W is expressed as a function of elapsed time t, taking into account the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution.

[0059] Next, at time t2, when the nozzle 311 remains in the divided region b15, the temperature of the substrate W in the divided region b15 is maintained at the etching solution temperature TL. After time t3, when the stay period T1 of the nozzle 311 in the divided region b15 has elapsed, the nozzle 311 moves away from the divided region b15. As the nozzle 311 moves away from the divided region b15, etching solution is no longer supplied to the divided region b15 from the nozzle 311, and the temperature of the substrate W in the divided region b15 decreases. The change in temperature of the substrate W in the divided region b15 after time t3 can be expressed by equation (3). The coefficient β1 in equation (3) is given by the following equation (4).

[0060]

number

[0061] In equation (3), TL is the temperature of the etching solution supplied from the nozzle 311. TW is a predetermined temperature that depends on the ambient temperature. In equation (4), Cd1 is a constant. D is the flow rate of the etching solution supplied from the nozzle 311. R is the rotation speed of the substrate W. Thus, the temperature change in the divided region b15 of the substrate W is expressed as a function that takes into account the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution.

[0062] Time t3 and time t4 are determined from the operating pattern of the nozzle 311 shown in Figure 6. Time t2 is determined using equation (1) based on the temperature at time t1.

[0063] Returning to Figure 4, the first conversion unit 263 predicts the temperature change of the substrate W during the processing period in which etching solution is supplied to the substrate W for each of the multiple divided regions b1 to b15 of the substrate W. For each of the multiple divided regions b1 to b15 of the substrate W, the first conversion unit 263 determines the average value AV1, which represents the average value of the temperature change during the processing period, as the temperature of that divided region of the substrate W. The first conversion unit 263 determines the temperature determined for each of the multiple divided regions b1 to b15 of the substrate W as processing state data. Here, the top surface of the substrate W is divided into 15 divided regions b1 to b15, so the number of processing state data is 15. The larger the radial length of each divided region b1 to b15 of the substrate, the smaller the number of processing state data. Since the radial length of each divided region b1 to b15 of the substrate is greater than or equal to the inner diameter of the nozzle 311, the maximum number of processing state data is determined by the inner diameter of the nozzle 311.

[0064] Returning to Figure 4, the predictor generation unit 265 receives processing state data obtained by transforming the variation conditions from the first transformation unit 263, and experimental data from the experimental data acquisition unit 261. The predictor generation unit 265 generates a predictor by having a neural network perform supervised learning. Note that the neural network may be a convolutional neural network.

[0065] Specifically, the training data includes input data and ground truth data. The input data includes processing state data whose variable conditions have been transformed by the first transformation unit 263, and fixed conditions other than the variable conditions of the processing conditions included in the experimental data. The ground truth 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. This etching profile included in the ground truth data is an example of the first processing amount. The predictor generation unit 265 inputs the input data into the neural network and determines the parameters of the neural network so that the output of the neural network is equal to the ground truth data. The predictor generation unit 265 generates a neural network as a predictor by incorporating the parameters set in the trained neural network. The predictor is an inference program that incorporates the parameters set in the trained neural network. The predictor generation unit 265 transmits the predictor to the information processing device 100.

[0066] Figure 10 illustrates a predictor. Referring to Figure 10, the predictor includes an input layer, a hidden layer, and an output layer, with each layer containing multiple nodes indicated by circles. Although the figure shows one hidden layer, the number of hidden layers may be greater. Also, while the figure shows five nodes in the input layer, four in the hidden layer, and three in the output layer, the number of nodes is not limited to these. The outputs of higher-level nodes are connected to the inputs of lower-level nodes. Parameters include coefficients that weight the outputs of higher-level nodes. The number of hidden layers is one or more, and is not limited to that number.

[0067] When the predictor receives processing state data converted from variable conditions and fixed conditions, an etching profile is output. The etching profile output by this predictor is an example of a second processing amount. The etching profile is represented by the difference in film thickness E[n] before and after processing at multiple radial positions P[n] (n is an integer of 1 or more) on the substrate W. Although the figure shows three output nodes for the predictor, the actual number of output nodes is n.

[0068] The processing state data that the predictor generation unit 265 uses to train the predictor includes the temperature of the substrate W, which is associated with the position on the substrate W. Since the temperature of the substrate W contributes to the processing of the substrate W, it becomes possible to generate a predictor with high prediction accuracy.

[0069] Returning 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 transmission unit 163. The functions of the information processing device 100 are realized by the CPU 101 of the information processing device 100, which executes a processing condition determination program stored in the RAM 102.

[0070] The predictor receiver 155 receives the predictor transmitted from the learning device 200 and outputs the received predictor to the prediction unit 159.

[0071] The processing condition determination unit 151 determines the processing conditions for the substrate W to be processed by the substrate processing apparatus 300. The processing condition determination unit 151 outputs the processing conditions to the second conversion unit 157 and outputs the fixed conditions included in the processing conditions to the prediction unit 159. The processing condition determination unit 151 selects one of a plurality of pre-prepared variable conditions using experimental design, pairwise method, or Bayesian estimation, and determines the processing conditions including the selected variable condition and the fixed condition as processing conditions for the prediction unit 159 to predict. Preferably, the plurality of pre-prepared variable conditions are the plurality of variable conditions generated by the learning device 200 to generate the compressor.

[0072] The second conversion unit 157 has the same function as the first conversion unit 263 of the learning device 200 described above. The second conversion unit 157 generates processing state data from the variable conditions and fixed conditions included in the processing conditions input from the processing condition determination unit 151, namely the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution. The second conversion unit 157 outputs the generated processing state data to the prediction unit 159.

[0073] The prediction unit 159 uses a predictor to estimate the etching profile from 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.

[0074] 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. Specifically, the evaluation unit 161 acquires the film thickness characteristics of the substrate W that the substrate processing apparatus 300 is scheduled to process before processing. The evaluation unit 161 calculates the predicted film thickness characteristics after etching from 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 comparison result satisfies the evaluation criteria, the processing conditions determined by the processing condition determination unit 151 are output to the processing condition transmission unit 163. For example, the evaluation unit 161 calculates the deviation characteristics and determines whether the deviation characteristics satisfy the evaluation criteria. The deviation characteristics are the difference between the film thickness characteristics of the substrate W after etching and the target film thickness characteristics. The evaluation criteria can be arbitrarily determined. For example, the evaluation criteria may be that the maximum difference in the deviation characteristics is less than or equal to a threshold, or that the average difference is less than or equal to a threshold.

[0075] The processing condition transmission unit 163 transmits the processing conditions determined by the processing condition determination unit 151 to the substrate processing device 300. The substrate processing device 300 processes the substrate W according to the processing conditions.

[0076] If the evaluation result does not meet the evaluation criteria, 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.

[0077] The processing condition determination unit 151 determines new processing conditions for the prediction unit 159 to predict, in response to the evaluation results input from the evaluation unit 161. The processing condition determination unit 151 selects one of several pre-prepared variable conditions using experimental design, pairwise method, or Bayesian estimation, and determines the processing conditions, which include the selected variable condition and fixed conditions, as new processing conditions for the prediction unit 159 to predict.

[0078] The processing condition determination unit 151 may use Bayesian estimation to search for processing conditions. When the evaluation unit 161 outputs multiple evaluation results, there will be multiple pairs of processing conditions and evaluation results. From the trends of the etching profiles in each of the multiple pairs, the system searches for processing conditions that result in a uniform film thickness or processing conditions that minimize the difference between the film thickness characteristics predicted after etching and the target film thickness characteristics.

[0079] Specifically, the processing condition determination unit 151 searches for processing conditions that minimize the objective function. The objective function is a function that indicates the uniformity of the film thickness or a function that indicates the agreement between the film thickness characteristics and the target film thickness characteristics. For example, the objective function is a function in which the difference between the film thickness characteristics predicted after etching and the target film thickness characteristics is expressed as a parameter. The parameter here is 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 were used by the prediction unit 159 to generate the processing state data used to estimate the etching profile. The processing condition determination unit 151 selects a variable condition from among a plurality of variable conditions that corresponds to the processing state data, which is the parameter determined by the search, and determines a new processing condition that includes the selected variable condition and a fixed condition.

[0080] Figure 11 is a flowchart showing an example of the predictor generation process. The predictor generation process is performed by the CPU 201 of the learning device 200, which executes the predictor generation program stored in the RAM 202. The predictor generation program is part of the learning program.

[0081] Referring to Figure 11, the CPU 201 of the learning device 200 acquires experimental data. The CPU 201 controls the input / output I / F 107 to acquire experimental data from the substrate processing device 300 (step S01). The experimental data may also be acquired by reading experimental data recorded on a recording medium such as a CD-ROM 209 with the storage device 104. Multiple experimental data sets are acquired here. The experimental data includes processing conditions and the film thickness characteristics of the film formed on the substrate W before and after processing. The film thickness characteristics are shown as the film thickness at multiple different positions in the radial direction of the substrate W.

[0082] In the next step, S02, experimental data to be processed is selected, and the process proceeds to step S03. In step S03, 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, but it is a process that generates processing status data based on the variable conditions included in the experimental data and the fixed conditions, namely the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution.

[0083] In step S04, the processing state data, the fixed conditions included in the experimental data, and the etching profile are set as training data. The etching profile is the difference between the film thickness characteristics of the film before processing and the film thickness characteristics of the film after processing included in the experimental data. The training data includes input data and ground truth data. In step S03, the processed state data converted and the fixed conditions included in the experimental data are set as input data. The etching profile is set as ground truth data.

[0084] In the next step, S05, the CPU 201 trains the predictor using machine learning and proceeds to step S06. The input data is fed into the predictor, which is a neural network, and the parameters are determined so that the predictor's output is equal to the correct data. This adjusts the predictor's parameters. The predictor is a neural network with parameters determined by machine learning using training data. The neural network may also be a convolutional neural network.

[0085] In step S06, it is determined whether the adjustment is complete. Training data to be used to evaluate the predictor is prepared in advance, and the performance of the predictor is evaluated using the evaluation training data. If the evaluation result meets the predetermined evaluation criteria, it is determined that the adjustment is complete. If the evaluation result does not meet the evaluation criteria (NO in step S06), the process returns to step S02, but if the evaluation result meets the evaluation criteria (YES in step S06), the process proceeds to step S07.

[0086] If the process returns to step S02, in step S02, experimental data that was not selected for processing from the experimental data acquired in step S01 is selected. In the loop from step S02 to step S06, the CPU 201 trains the predictor using multiple training data sets. This adjusts the parameters of the predictor, which is a neural network, to appropriate values. In step S08, the predictor is sent and the process ends. The CPU 201 controls the input / output interface 107 and sends the predictor to the information processing device 100.

[0087] Figure 12 is a flowchart showing an example of the processing condition determination process. The processing condition determination process is a process executed by the CPU 101 of the information processing device 100 when the CPU 101 executes a processing condition determination program stored in the RAM 102.

[0088] Referring to Figure 12, the CPU 101 of the information processing device 100 selects one of several pre-prepared variable conditions (step S11) and proceeds to step S12. The multiple variable conditions are those generated by the learning device 200 to generate the compressor. One of the pre-prepared variable conditions is selected using experimental design, pairwise method, or Bayesian estimation, etc.

[0089] In step S12, the processing status data generation process is executed, and the process proceeds to step S13.

[0090] In step S13, the etching profile is estimated from the processing state data and fixed conditions using a predictor, 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. The film thickness characteristics after processing the substrate W are calculated from the film thickness characteristics of the substrate W to be processed by the substrate processing apparatus 300 before processing and the etching profile estimated in step S13. 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.

[0091] In step S15, it is determined whether the comparison result meets the evaluation criteria. If the comparison result meets the evaluation criteria (YES in step S15), the process proceeds to step S16; otherwise, the process returns to step S11. For example, the evaluation criteria are met if the maximum difference is less than or equal to the threshold. Also, the evaluation criteria are met if the average difference is less than or equal to the threshold.

[0092] In step S16, a processing condition including the variable condition selected immediately before in step S11 is set as a candidate for the processing condition to drive the substrate processing device 300, and the process proceeds to step S17. In step S17, it is determined whether or not a search termination instruction has been received. If a termination instruction is received by the user operating the information processing device 100, the process proceeds to step S18; otherwise, the process returns to step S11. Alternatively, instead of a termination instruction entered by the user, it may be determined whether or not a predetermined number of processing conditions have been set as candidates.

[0093] In step S18, one processing condition is selected from the one or more processing conditions set as candidates, and the process proceeds to step S19. Alternatively, one processing condition may be selected by the user operating the information processing device 100 from the one or more processing conditions set as candidates. This expands the range of selection for the user. Furthermore, the variation condition that results in the simplest nozzle operation may be automatically selected from among the variation conditions included in the multiple processing conditions. The variation condition that results in the simplest nozzle operation can be, for example, the variation condition with the fewest number of speed change points. This makes it possible to present multiple variation conditions for the processing results of complex nozzle operations that process the substrate W. By selecting a variation condition that makes nozzle control easy from among the multiple variation conditions, the control of the substrate processing device 300 becomes easier.

[0094] In step S19, the processing conditions, including the variable conditions determined in step S18, are transmitted to the substrate processing device 300, and the processing ends. The CPU 101 controls the input / output I / F 107 to transmit the processing conditions to the substrate processing device 300. When the substrate processing device 300 receives the processing conditions from the information processing device 100, it processes the substrate W according to those processing conditions.

[0095] Figure 13 is a flowchart showing an example of the processing status data generation process. The processing status data generation process is performed in step S03 in Figure 10 or step S12 in Figure 11. In step S21, time-series data is acquired. The time-series data is the relative position of the nozzle to the substrate W, which changes over time. In step S22, the number of divisions K (K is an integer of 2 or more) for setting multiple division regions on the upper surface of the substrate W is acquired. In this embodiment, the number of divisions K is set in advance. The number of divisions K may also be input by the user through an operation unit or the like. In the example in Figure 8, the number of divisions K is 15.

[0096] In step S23, the variable n is set to 1. In step S24, the average value AV1, which represents the average temperature change of the substrate W in the divided region b(n), is calculated. The divided region b(n) is the nth divided region out of divided regions b1 to b15. Once the average value AV1 in divided region b(n) is calculated, in step S25, 1 is added to the variable n. At this time, in step S26, it is determined whether the variable n is greater than the number of divisions K. If the variable n is less than or equal to the number of divisions K, the process returns to step S24. If the variable n is greater than the number of divisions K, in step S27, the temperature of the substrate W of the nozzle 311 in each of the calculated divided regions b(1) to b(K) is determined as processing state data. Steps S24 to S26 are repeated to calculate the temperature of the substrate W in each of the next divided regions b(1) to b(K).

[0097] 4. Specific Examples In this embodiment, the variable conditions are time-series data sampled with a nozzle operation processing time of 60 seconds and a sampling interval of 0.01 seconds. The variable conditions consist of 6001 values. Therefore, the variable conditions can represent complex nozzle operations. On the other hand, because the variable conditions have a large number of dimensions, overfitting may occur when machine learning is performed on the time-series data of the variable conditions.

[0098] In this embodiment, the predictor generation unit 265 generates a predictor by machine learning the processing state data, so it is possible to explicitly incorporate known relationships between variable conditions and fixed conditions into the learning model.

[0099] In this embodiment, the first conversion unit 263 converts the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution, which are among the variable and fixed conditions, into processing state data. The processing state data consists of 15 values, which are the average values ​​of the temperature change of the substrate W in each of the multiple divided regions b1 to b15 obtained by dividing the movement range of the nozzle 311 into 15 divisions. The inventors have experimentally discovered that even when predicting using processing state data instead of variable conditions consisting of 6001 values ​​that represent complex nozzle operation, the desired result can be obtained as the etching profile predicted by the predictor.

[0100] Therefore, the amount of data input to the predictor can be reduced, simplifying the predictor's configuration and making it easier to train the neural network. Furthermore, the neural network's parameters can be adjusted to appropriate values, improving the predictor's accuracy.

[0101] Furthermore, since the 6001-dimensional variation conditions are converted into 15-dimensional processing state data, there may be multiple variation conditions that have the same processing state data. In this case, the etching profiles predicted by the predictor from each of the multiple variation conditions with the same processing state data will be the same. In this embodiment, when the processing condition determination unit 151 searches for processing conditions, it searches for processing conditions that correspond to different etching profiles, so that processing conditions corresponding to multiple different etching profiles are selected. For this reason, the processing condition determination unit 151 can efficiently search for processing conditions from among multiple processing conditions that predict the target etching profile.

[0102] Although an example using a sampling interval of 0.01 seconds was explained, the sampling interval is not limited to this. A longer or shorter sampling interval may be used. For example, the sampling interval may be 0.1 seconds or 0.005 seconds.

[0103] 5. Other Embodiments (1) In the above-described embodiment, the average value AV1 of the temperature change for each of the multiple divided regions is converted as processing state data, but the present invention is not limited thereto. When an etching solution is supplied to the substrate W, the amount of film removed from the substrate W changes according to the thickness of the film formed by the etching solution on the substrate W. For example, when the thickness of the film by the etching solution is large, the amount of film removed from the substrate W is large. On the other hand, when the thickness of the film by the etching solution is small, the amount of film removed from the substrate W is small. For this reason, the thickness of the etching solution film for each of the multiple divided regions may be used as processing state data.

[0104] Figure 14 shows an example of the change in etching film thickness on a substrate over time in a divided region. In Figure 14, the change in etching film thickness on substrate W over time is shown for the divided region b15. In the graph of Figure 14, the vertical axis shows the etching film thickness on substrate W, and the horizontal axis shows time (seconds). Here, it is assumed that FT is the etching film thickness that should be formed on substrate W when the etching solution is supplied to substrate W without the substrate W being rotated. The callout diagram in Figure 14 shows a magnified view of a part of the substrate temperature that changes over time. In the graph shown in the callout, the scale of the horizontal axis is magnified.

[0105] During the processing of the substrate W, etching solution is supplied from the nozzle 311 while the substrate W is rotating. At time t0, when the nozzle 311 begins supplying etching solution to the substrate W, the nozzle 311 is located at the operating end EP1, so the nozzle 311 is not in the divided region b15. Therefore, etching solution is not supplied to the divided region b15. At this stage, the thickness of the etching solution film on the substrate W in the divided region b15 is zero.

[0106] From time t1 onward, when the nozzle 311 approaches the divided region b15, the thickness of the etching solution in the divided region b15 of the substrate W increases due to the etching solution supplied from the nozzle 311. The change in the thickness of the etching solution in the divided region b15 of the substrate W from time t1 onward can be expressed by equation (5). The coefficient α2 in equation (5) is given by the following equation (6).

[0107]

number

[0108] In equation (6), CU1 to CU3 are constants related to the increase in the liquid film in the divided region b15 of the substrate W. D in equation (6) is the flow rate of the etching solution supplied from the nozzle 311. R in equation (6) is the rotation speed of the substrate W. Thus, the change (increase) in the film thickness of the etching solution in the divided region b15 can be expressed as a function of elapsed time t, taking into account the rotation speed of the substrate W and the flow rate of the etching solution.

[0109] Next, at time t2, when the nozzle 311 remains in the divided region b15, the etching solution film in the divided region b15 of the substrate W is maintained at film thickness FT. After time t3, when the residence period T1 has elapsed, the nozzle 311 moves away from the divided region b15. As the nozzle 311 moves away from the divided region b15, the etching solution is no longer supplied to the divided region b15 from the nozzle 311. In addition, the centrifugal force of the rotating substrate W causes the film thickness of the etching solution on the substrate W in the divided region b15 to decrease. The change in the film thickness of the etching solution on the substrate W in the divided region b15 of the substrate W after time t3 can be expressed by equation (7). The coefficient β2 in equation (7) is given by equation (8).

[0110]

number

[0111] In equation (7), Filmmax represents the maximum thickness of the etching solution film. In this example, Filmmax is the film thickness FT. In equation (8), CD1 is a constant related to the decrease in the etching solution film thickness in the divided region b15 of the substrate W. In equation (8), D is the flow rate of the etching solution supplied from the nozzle 311. In equation (8), R is the rotation speed of the substrate W. Thus, the change (decrease) in the etching solution film thickness in the divided region b15 can be expressed as a function of elapsed time t, taking into account the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution.

[0112] The first conversion unit 263 in Figure 4 predicts the change in the film thickness of the etching solution on the substrate W during the processing period in which the etching solution is supplied to the substrate W, for each of the multiple divided regions b1 to b15 of the substrate W. The first conversion unit 263 determines the film thickness of the etching solution in each of the multiple divided regions b1 to b15 of the substrate W as the average value AV2, which represents the average value of the film thickness of the etching solution on the substrate W that changes during the processing period. The first conversion unit 263 determines the film thickness of the etching solution determined for each of the multiple divided regions b1 to b15 of the substrate W as processing state data.

[0113] Furthermore, the first conversion unit 263 may determine the average value AV1 of the temperature change for each of the multiple divided regions b1 to b15 and the average value AV2 of the film thickness change of the etching solution as processing state data. In this case, it becomes possible to convert the 6001-dimensional fluctuation conditions into processing state data with 30 dimensions.

[0114] Furthermore, the processing state data that the predictor generation unit 265 uses to train the predictor includes the film thickness of the etching solution associated with its position on the substrate W. Since the film thickness of the etching solution contributes to the processing of the substrate W, it becomes possible to generate a learning model with high prediction accuracy.

[0115] (2) In the embodiment described above, the learning device 200 generates a predictor based on the training data. The learning device 200 may also perform additional training on the predictor. After the predictor is generated, the learning device 200 obtains the film thickness characteristics and processing conditions of the substrate W processed by the substrate processing device 300 before and after processing. The learning device 200 then generates training data from the film thickness characteristics and processing conditions before and after processing, and performs additional training on the predictor by having it learn machine learning. The configuration of the neural network constituting the predictor is not changed by the additional training, but the parameters are adjusted.

[0116] The information obtained from the actual processing of the substrate W by the substrate processing device 300 is used to train the predictor through machine learning, thereby improving the accuracy of the predictor. Furthermore, the amount of training data used to generate the predictor can be minimized.

[0117] Figure 15 is a flowchart showing an example of the flow of the additional learning process. The additional learning process is a process executed by the CPU 201 of the learning device 200, which executes the additional learning program stored in the RAM 202. The additional learning program is part of the learning program.

[0118] Referring to Figure 15, the CPU 201 of the learning device 200 acquires production data (step S31) and proceeds to 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 processing. The CPU 201 controls the input / output I / F 107 to acquire production data from the substrate processing device 300. The production data may also be acquired by reading experimental data recorded on a recording medium such as a CD-ROM 209 with the storage device 104.

[0119] In step S32, the processing state data generation process shown in Figure 13 is executed, and the process 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 training data. The etching profile is the difference between the film thickness characteristics of the film before processing included in the production data and the film thickness characteristics of the film after processing included in the production data. The processing state data and the fixed conditions included in the processing conditions by the first conversion unit 263 are set as input data. The etching profile is set as the correct data.

[0120] In the next step, S34, the CPU 201 further trains the predictor and proceeds to step S35. The input data is fed into the predictor, which is a neural network, and the parameters are determined so that the predictor's output is equal to the correct data. This further adjusts the predictor's parameters.

[0121] In step S35, it is determined whether the adjustment is complete. The performance of the predictor is evaluated using the training data for evaluation. The adjustment is determined to be complete if the evaluation result meets the predetermined additional training evaluation criteria. The additional training evaluation criteria are higher than the evaluation criteria used when the predictor was generated. If the evaluation result does not meet the additional training evaluation criteria (NO in step S35), the process returns to step S31, but if the evaluation result meets the additional training evaluation criteria (YES in step S35), the process ends.

[0122] (3) The learning device 200 may generate a distillation model that has been trained on a new learning model using distillation data including processing conditions determined by the information processing device 100 and etching profiles predicted by a predictor from those processing conditions. This makes it easier to prepare data for training the new learning model.

[0123] (4) In this embodiment, the training data used to generate the predictor includes processing state data and fixed conditions. The present invention is not limited thereto. The input data may include only processing state data obtained by converting the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution from among the variable conditions and fixed conditions, and may not include fixed conditions.

[0124] (5) In this embodiment, the relative position between the nozzle 311 and the substrate W was shown as an example of a variable condition, but the present invention is not limited thereto. If at least one of the etching solution temperature, etching solution concentration, etching solution flow rate, and substrate W rotation speed fluctuates over time, these may be considered variable conditions. Furthermore, the variable conditions are not limited to one type, but may include multiple types.

[0125] (6) Although the present invention has been described using the example of the information processing device 100 and the learning device 200 being separate from the substrate processing device 300, the present invention is not limited thereto. The information processing device 100 may be incorporated into the substrate processing device 300. Furthermore, the information processing device 100 and the learning device 200 may be incorporated into the substrate processing device 300. Also, although the information processing device 100 and the learning device 200 were described as separate devices, they may be configured as a single integrated device.

[0126] Effects in the embodiment of 6. In this embodiment, the learning device 200 drives the substrate processing apparatus 300 with processing conditions including variable conditions to process a film formed on a substrate. After processing, it obtains a processing amount indicating the difference in film thickness before and after processing. The first conversion unit 263 converts processing state data, which includes the rotation speed of the substrate W, the temperature of the etching solution, and the flow rate of the etching solution among the variable and fixed conditions, as input data. This learning data, which also includes etching profiles corresponding to the processing conditions as ground truth data, is then used to train a neural network to generate a predictor, which is a learning model that estimates etching profiles. Since the learning data includes processing state data converted so that the number of dimensions of the variable conditions that change over time is reduced, the number of dimensions of the learning data can be reduced. Therefore, a learning device suitable for machine learning conditions that change over time in order to process the substrate W can be generated. Furthermore, the processing state data that the predictor generation unit 265 uses to train the predictor includes the temperature of the substrate W associated with its position on the substrate W. Since the temperature of the substrate W contributes to the processing of the substrate W, it becomes possible to generate a learning model with high prediction accuracy.

[0127] Furthermore, the learning device 200 converts the average value AV1, which represents the average of the temperature changes in each of the multiple movement sections obtained by dividing the movement range of the nozzle 311 of the substrate processing device 300, into processing state data, making it possible to easily convert from fluctuating conditions to processing state data.

[0128] Furthermore, the processing conditions include variable conditions and fixed conditions that do not change over time. Therefore, it can handle processing with different fixed conditions, and there is no need to generate multiple learning models with different fixed conditions.

[0129] Furthermore, after generating a predictor, the learning device 200 acquires a processing amount indicating the difference in film thickness before and after processing the film, after the substrate processing device 300 has processed the film formed on the substrate W according to the processing conditions. The first conversion unit 263 then uses the processing state data, which has been converted with provisional fluctuation conditions, and the acquired processing amount to train the learning model using additional learning data. As a result, the learning model is further trained, which improves the performance of the learning model.

[0130] Furthermore, the learning device 200 provides the learning model with processing state data transformed by the first transformation unit 263, and if the processing amount estimated by the learning model satisfies the acceptable conditions, it generates a new learning model using distillation data that includes the transformation result and the processing amount estimated by the learning model. This makes it easier to prepare data for training the new learning model.

[0131] Furthermore, the substrate processing apparatus 300 includes a nozzle 311 for supplying etching solution to the substrate W, and a nozzle movement mechanism 301 for changing the relative position between the nozzle and the substrate W. The variable condition is the relative position between the nozzle 311 and the substrate W, which is changed by the nozzle movement mechanism 301. By changing the relative position between the nozzle 311 and the substrate W and supplying etching solution from the nozzle 311 to the substrate W, a learning model is generated that estimates the amount of film processed. Therefore, a learning model that estimates the amount of processing in the etching process can be generated.

[0132] Furthermore, the information processing device 100 provides the conversion result, obtained by the compressor generated by the learning device 200, to the learning model generated by the learning device 200. If the etching profile predicted by the learning model satisfies the acceptable conditions, the processing conditions including the provisional variation conditions are determined as the processing conditions for driving the substrate processing device 300. Therefore, since the etching profile is predicted from the processing conditions, there is no need to determine, through experiments or other means, the influence of the operation of the complex nozzle on the processing result of the etching process. In addition, since multiple provisional variation conditions are determined for a processing amount that satisfies the acceptable conditions, multiple variation conditions corresponding to multiple etching profiles that satisfy the acceptable conditions can be determined. Thus, multiple variation conditions can be presented for the processing results of a complex process that processes substrates. By selecting processing conditions that are easy to control the operation of the nozzle from among the multiple variation conditions, the control of the substrate processing device 300 becomes easier.

[0133] Furthermore, the information processing device 100 determines multiple processing conditions for a processing volume that satisfies the acceptable conditions, so it can determine multiple processing conditions corresponding to multiple etching profiles that satisfy the acceptable conditions. The fixed conditions include the temperature of the etching solution. Therefore, multiple etching solution temperatures can be presented for the processing results of a complex process that processes the substrate. In addition, an etching solution temperature that is easy to apply to the etching process can be selected from among the multiple etching solution temperatures. And because an easily applicable etching solution temperature can be selected, temperature control of the etching solution used in the etching process becomes easier. The fixed conditions also include the rotation speed of the substrate W and the flow rate of the etching solution. Therefore, similar to the etching solution temperature, multiple candidates can be presented for the rotation speed of the substrate W and the flow rate of the etching solution for the processing results of a complex process that processes the substrate, and their selection becomes easier.

[0134] 7. Correspondence between each component of the claim and each part of the embodiment Substrate W is an example of a substrate, etching solution is an example of a processing solution, substrate processing apparatus 300 is an example of a substrate processing apparatus, experimental data acquisition unit 261 is an example of an experimental data acquisition unit, first conversion unit 263 is an example of a conversion unit and first conversion unit, predictor is an example of a learning model, and predictor generation unit 265 is an example of a model generation unit. Furthermore, information processing apparatus 100 is an example of an information processing apparatus, second conversion unit 157 is an example of a second conversion unit, nozzle 311 is an example of a nozzle that supplies processing solution to the substrate, nozzle moving mechanism 301 is an example of a moving unit, and prediction unit 159, evaluation unit 161, and processing condition determination unit 151 are examples of processing condition determination units.

[0135] 8. Summary of Embodiments (1) An experimental data acquisition unit that, after processing the film formed on the substrate by moving a nozzle that supplies a processing liquid to the substrate on which a film has been formed and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, acquires a first processing amount indicating the difference in film thickness before and after processing the film, A conversion unit converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, A learning device comprising: a model generation unit that performs machine learning on learning data including the processing state data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing device.

[0136] According to the learning device described in paragraph 1, the learning data includes processing state data and processing amount converted from fluctuation conditions indicating the relative position of the nozzle relative to the substrate that changes over time, as well as other conditions other than the fluctuation conditions. Therefore, the number of dimensions of the learning data can be reduced. In addition, known relationships between multiple parameters included in the processing conditions can be explicitly incorporated into the learning model. As a result, a learning device suitable for machine learning the conditions that change over time for processing a substrate can be provided.

[0137] (Clause 2) The state of the process is the temperature of the substrate, The learning device according to paragraph 1, wherein the conversion unit determines the temperature of the substrate as the processing state in each of the plurality of divided regions based on the fluctuating conditions, the temperature of the processing liquid, the flow rate of the processing liquid discharged from the nozzle, and the rotation speed of the substrate.

[0138] According to the learning device described in Section 2, the processing state data includes the temperature of the substrate associated with its position on the substrate. Since the substrate temperature contributes to the processing of the substrate, it becomes possible to generate a learning model with high predictive accuracy.

[0139] (Clause 3) The state of the processing is the thickness of the liquid film formed on the substrate by the supply of processing liquid from the nozzle, The learning device according to the first or second paragraph, wherein the conversion unit determines the thickness of the liquid film formed on the substrate as the processing state in each of the plurality of divided regions, based on the variable conditions, the flow rate of the processing liquid discharged from the nozzle, and the rotation speed of the substrate.

[0140] According to the learning device described in Section 3, the processing state data includes a liquid film of the processing solution associated with its position on the substrate. Since the thickness of the liquid film of the processing solution contributes to the processing on the substrate, it becomes possible to generate a highly accurate learning model.

[0141] (Clause 4) The learning device according to Clause 2 or 3, wherein the model generation unit performs machine learning on training data including the processing state data instead of the variable conditions.

[0142] According to the learning device described in Section 4, the number of dimensions that the model generation unit performs machine learning on can be reduced, thereby making it possible to suppress overfitting in the model generation unit.

[0143] (Clause 5) The learning apparatus according to Clause 1, wherein the radial length of each of the plurality of divided regions of the substrate is greater than or equal to the inner diameter of the nozzle.

[0144] According to the learning device described in Section 5, the radial length of the substrate in the divided region is set to be greater than or equal to the inner diameter of the nozzle, making it possible to reduce the number of data points in the processing state data.

[0145] (Clause 6) Information processing device for managing substrate 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 has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. A conversion unit converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus, The learning model is an inference model that uses machine learning to acquire learning data that includes processing state data obtained by performing the same transformation as the conversion unit on the variable conditions included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus, and a first processing amount indicating the difference in film thickness before and after processing the film formed on the substrate processed by the substrate processing apparatus. The processing condition determination unit provides the processing state data, which has been transformed by the transformation unit, to the learning model, and determines the processing conditions, including the provisional variation conditions, as processing conditions for driving the substrate processing device when the second processing amount estimated by the learning model satisfies the acceptable conditions.

[0146] According to the information processing device described in Section 6, processing state data obtained by transforming provisional fluctuation conditions that change over time is provided to a learning model, and when the processing amount estimated by the learning model satisfies the acceptable conditions, the processing conditions including the provisional fluctuation conditions are determined as the processing conditions for driving the substrate processing device. Therefore, multiple provisional fluctuation conditions can be determined for a processing amount that satisfies the acceptable conditions. As a result, it is possible to provide an information processing device that can present multiple processing conditions for the processing results of a complex process that processes a substrate.

[0147] (Item 7) A substrate processing apparatus equipped with the information processing apparatus described in Item 6.

[0148] The substrate processing apparatus described in Section 7 provides a substrate processing apparatus that can offer multiple processing conditions for the processing results of a complex process for processing a substrate.

[0149] (Clause 8) A substrate processing system for managing a substrate processing apparatus for processing substrates, Equipped with 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 has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. The learning device includes an experimental data acquisition unit that, after driving the substrate processing apparatus under the processing conditions to process the film formed on the substrate, acquires a first processing amount indicating the difference in film thickness before and after processing the film, A first conversion unit converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, The apparatus comprises: a model generation unit that performs machine learning on learning data including processing state data obtained by the first conversion unit from which the variable conditions have been converted and the first processing amount corresponding to the processing conditions, and generates a learning model that estimates a second processing amount that indicates the difference in film thickness before and after processing of the film formed on a substrate before the film is processed by the substrate processing apparatus, The information processing device includes a second conversion unit, which is the same as the first conversion unit, The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing device using the learning model generated by the learning device, A substrate processing system in which the processing condition determination unit provides the conversion result obtained by the second conversion unit from the provisional fluctuation conditions to the learning model, and determines the processing conditions including the provisional fluctuation conditions as processing conditions for driving the substrate processing apparatus when the second processing amount estimated by the learning model satisfies the allowable conditions.

[0150] The substrate processing system described in Section 8 provides a substrate processing system that can offer multiple processing conditions for the processing results of a complex process for processing a substrate.

[0151] (Clause 9) After processing the film formed on the substrate by moving a nozzle that supplies a processing liquid to the substrate on which a film has been formed and driving the substrate processing apparatus that supplies the processing liquid to the substrate with processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, a process is performed to obtain a first processing amount indicating the difference in film thickness before and after processing the film; and a process is performed to convert the fluctuation condition and other processing conditions other than the fluctuation condition into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, A learning method that causes a computer to perform the following steps: machine learning training on learning data including the processing state data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus.

[0152] According to the learning method described in Section 9, the training data includes processing state data and processing amount converted from fluctuation conditions indicating the relative position of the nozzle relative to the substrate that changes over time, as well as other conditions other than the fluctuation conditions. Therefore, the dimensionality of the training data can be reduced. In addition, known relationships between multiple parameters included in the processing conditions can be explicitly incorporated into the learning model. As a result, a learning method suitable for machine learning the conditions that change over time for processing a substrate can be provided.

[0153] (Clause 10) A method for determining processing conditions, which is performed by a computer that manages a substrate processing apparatus, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. A process that converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data that indicates the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, The process includes determining processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before processing the film by the substrate processing apparatus, The learning model is an inference model that uses machine learning to acquire learning data that includes processing state data obtained by performing the same transformation as the transformation process, and a first processing amount that indicates the difference in film thickness before and after processing of the film formed on the substrate by the substrate processing apparatus, wherein the variable conditions included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus are processed. A method for determining the processing conditions, wherein the processing condition for determining the processing conditions is to provide the learning model with processing state data obtained by the conversion process from which the provisional fluctuation conditions have been converted, and if the second processing amount estimated by the learning model satisfies the allowable conditions, the processing conditions including the provisional fluctuation conditions are determined as the processing conditions for driving the substrate processing apparatus.

[0154] According to the processing condition determination method described in Section 10, processing state data obtained by transforming provisional fluctuation conditions that change over time is provided to a learning model, and if the processing amount estimated by the learning model satisfies the acceptable conditions, the processing conditions including the provisional fluctuation conditions are determined as the processing conditions for driving the substrate processing apparatus. Therefore, multiple provisional fluctuation conditions can be determined for a processing amount that satisfies the acceptable conditions. As a result, a processing condition determination method can be provided that can present multiple processing conditions for the processing results of a complex process that processes substrates. [Explanation of symbols]

[0155] 1...Substrate processing system, 10...Control device, 100...Information processing device, 151...Processing condition determination unit, 155...Predictor receiving unit, 157...Second conversion unit, 159...Prediction unit, 161...Evaluation unit, 163...Processing condition transmission unit, 200...Learning device, 261...Experimental data acquisition unit, 263...First conversion unit, 265...Predictor generation unit, 267...Predictor transmission unit, 300...Substrate processing device, 301...Nozzle movement mechanism, 303...Nozzle motor, 305...Nozzle arm, 311...Nozzle, AV1...Average value, AX1...First rotation axis, AX2...Second rotation axis, EP1...Operating end, EP2...Operating end, FT...Film thickness, OP...Substrate center, SC...Spin chuck, SM...Spin motor, W...Substrate, WU...Substrate processing unit, b1~b15...Divided region, d1~d29...Movement section

Claims

1. An experimental data acquisition unit acquires a first processing amount that indicates the difference in film thickness before and after processing the film formed on the substrate, by moving a nozzle that supplies processing liquid to the substrate and driving the substrate processing apparatus that supplies processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, and A conversion unit converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, A learning device comprising: a model generation unit that performs machine learning on learning data including the processing state data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing device.

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

3. The state of the process is the thickness of the liquid film formed on the substrate by the supply of the processing liquid from the nozzle. The learning device according to claim 1 or 2, wherein the conversion unit determines the thickness of the liquid film formed on the substrate as the processing state in each of the plurality of divided regions, based on the variable conditions, the flow rate of the processing liquid discharged from the nozzle, and the rotation speed of the substrate.

4. The learning device according to claim 2, wherein the model generation unit performs machine learning on training data including the processing state data instead of the variable conditions.

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

6. An information processing device for managing a substrate 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 has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. A conversion unit converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus, The learning model is an inference model that uses machine learning to acquire learning data that includes processing state data obtained by performing the same transformation as the conversion unit on the variable conditions included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus, and a first processing amount indicating the difference in film thickness before and after processing the film formed on the substrate processed by the substrate processing apparatus. The processing condition determination unit provides the processing state data, which has been transformed by the transformation unit, to the learning model, and determines the processing conditions, including the provisional variation conditions, as processing conditions for driving the substrate processing device when the second processing amount estimated by the learning model satisfies the acceptable conditions.

7. A substrate processing apparatus comprising the information processing apparatus described in claim 6.

8. A substrate processing system for managing a substrate processing apparatus that processes substrates, Equipped with 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 has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. The learning device includes an experimental data acquisition unit that, after driving the substrate processing apparatus under the processing conditions to process the film formed on the substrate, acquires a first processing amount indicating the difference in film thickness before and after processing the film, A first conversion unit converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data indicating the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, The system includes a model generation unit that performs machine learning on learning data including processing state data obtained by the first conversion unit from which the variable conditions have been converted and the first processing amount corresponding to the processing conditions, to generate a learning model that estimates a second processing amount that indicates the difference in film thickness before and after processing of the film formed on a substrate before the film is processed by the substrate processing apparatus, The information processing device includes a second conversion unit, which is the same as the first conversion unit, The system includes a processing condition determination unit that determines processing conditions for driving the substrate processing device using the learning model generated by the learning device, A substrate processing system in which the processing condition determination unit provides the conversion result obtained by the second conversion unit from the provisional fluctuation conditions to the learning model, and determines the processing conditions including the provisional fluctuation conditions as processing conditions for driving the substrate processing apparatus when the second processing amount estimated by the learning model satisfies the allowable conditions.

9. A process to obtain a first processing amount indicating the difference in film thickness before and after processing the film formed on the substrate, by moving a nozzle that supplies a processing liquid to the substrate and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, and then moving a nozzle that supplies a processing liquid to the substrate on which the film has been formed, and driving the substrate processing apparatus that supplies the processing liquid to the substrate under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time, A process that converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data that indicates the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, A learning method that causes a computer to perform the following steps: machine learning training on learning data including the processing state data and the first processing amount corresponding to the processing conditions to generate a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before the film is processed by the substrate processing apparatus.

10. A method for determining processing conditions, which is executed by a computer that manages a substrate processing apparatus, The substrate processing apparatus processes the film formed on the substrate by supplying a processing liquid to the substrate on which the film has been formed, under processing conditions that include a fluctuation condition indicating the relative position of the nozzle with respect to the substrate which fluctuates over time. A process that converts the aforementioned variable conditions and other processing conditions other than the aforementioned variable conditions into processing state data that indicates the processing state in each of a plurality of divided regions obtained by dividing the upper surface of the substrate into concentric circles, The process includes determining processing conditions for driving the substrate processing apparatus, using a learning model that estimates a second processing amount indicating the difference in film thickness before and after processing of the film formed on the substrate before processing the film by the substrate processing apparatus, The learning model is an inference model that uses machine learning to acquire learning data that includes processing state data obtained by performing the same transformation as the transformation process, and a first processing amount that indicates the difference in film thickness before and after processing of the film formed on the substrate by the substrate processing apparatus, wherein the variable conditions included in the processing conditions for processing the film formed on the substrate by the substrate processing apparatus are processed. A method for determining the processing conditions, wherein the processing condition for determining the processing conditions is to provide the learning model with processing state data obtained by the conversion process from which the provisional fluctuation conditions have been converted, and if the second processing amount estimated by the learning model satisfies the allowable conditions, the processing conditions including the provisional fluctuation conditions are determined as the processing conditions for driving the substrate processing apparatus.

Images