JP7796791B2 - Parameter optimization device, parameter optimization method, and computer program - Google Patents

Description

The subject matter disclosed in this specification relates to a parameter optimization device, a parameter optimization method, and a computer program.

In the manufacturing process of flat panel displays, a device called a coater is used. A coater is a substrate processing device that uses a pump to eject processing liquid from a slit nozzle, coating the entire substrate as it is being transported. With the recent trend toward higher product quality, coaters are required to apply processing liquid so that the film thickness of the processing liquid is uniform across the entire substrate. For example, in Patent Document 1, the parameters for controlling the pump are adjusted and optimized by repeatedly measuring the ejection characteristics when the processing liquid is ejected.

Japanese Patent Application Laid-Open No. 2020-040046 International Publication No. 2019/244474

K. Swersky et al., "Multi-Task Bayesian Optimization," [online], [Retrieved June 1, 2018], NIPS, 2013, Internet <https://papers.nips.cc/paper/5086-multi-task-bayesian-optimization.pdf>

However, in the case of Patent Document 1, the control process and measurement of ejection characteristics are repeated multiple times, which could result in a long period of time required to optimize the control parameters.

The object of the present invention is to provide technology that enables efficient optimization of control parameters.

To solve the above problem, a first aspect of the present invention is a parameter optimization device that optimizes control parameters for controlling a coating device that discharges a processing liquid onto a substrate to form a coating film. The parameter optimization device includes: a parameter determination unit that determines the next control parameter to be evaluated using multiple pieces of film thickness information, each of which is associated with a specific control parameter; a film thickness information acquisition unit that acquires film thickness information based on measurement results of the film thickness of a coating film formed by controlling the coating device using the control parameters determined by the parameter determination unit; a film thickness information estimation unit that estimates film thickness information corresponding to the control parameter determined by the parameter determination unit using an estimation model that inputs control parameters and process information and outputs film thickness information; and a loop control unit that controls the parameter determination unit, the film thickness information acquisition unit, and the film thickness information estimation unit so that a first process including processing by the parameter determination unit and processing by the film thickness information acquisition unit and a second process including processing by the parameter determination unit and processing by the film thickness information acquisition unit are alternately executed.

A second aspect is a parameter optimization device according to the first aspect, further comprising a learning unit that learns the estimation model using film thickness information acquired by the film thickness information acquisition unit.

A third aspect is a parameter optimization device according to the first or second aspect, wherein the second process is a process in which the process of the parameter determination unit and the process of the film thickness information estimation unit are repeated multiple times, and the loop control unit executes the first process when the number of times film thickness information is estimated by the film thickness information estimation unit in the second process reaches a predetermined number.

A fourth aspect is a parameter optimization device according to the first or second aspect, in which the parameter determination unit calculates an evaluation value from the film thickness information and determines the next control parameter to be evaluated based on the evaluation value.

A fifth aspect is the parameter optimization device of the fourth aspect, in which the parameter determination unit determines the next control parameter to be evaluated using a multitask Bayesian optimization algorithm.

A sixth aspect is a parameter optimization method for optimizing parameters for controlling a coating device that discharges a processing liquid onto a substrate to form a coating film, the method including: a) a parameter determination process for determining the next control parameter to be evaluated using multiple pieces of film thickness information, each of which is associated with a specific parameter; b) a film thickness information acquisition process for acquiring film thickness information based on measurement results of a coating film formed by controlling the coating device using the control parameters determined in the parameter determination process; and c) a film thickness information estimation process for estimating film thickness information corresponding to the control parameters determined in the parameter determination process using an estimation model that inputs control parameters and process information and outputs film thickness information, and the first process including the parameter determination process and the film thickness information acquisition process and the second process including the parameter determination process and the film thickness information estimation process are alternately performed.

A seventh aspect is a computer program executable by a computer, causing the computer to execute the parameter optimization method of the sixth aspect.

According to the first to seventh aspects, the search for control parameters via an estimation model and the search for control parameters based on the time-consuming film thickness measurement results are alternated, allowing for efficient optimization of control parameters while reducing film thickness measurements. Furthermore, by including process information in the input to the estimation model, film thickness information obtained in different processes can be used as training data. Therefore, inputting process information can improve the output accuracy of the estimation model. This allows for accurate optimization of control parameters.

The parameter optimization device of the second aspect can improve the accuracy of the estimation model by performing learning using film thickness information of the coating film measured during optimization.

The parameter optimization device of the third aspect can further shorten the parameter optimization time.

The parameter optimization device of the fifth aspect makes it possible to perform Bayesian optimization searches more efficiently even if there is a difference between the distribution of evaluation values of film thickness information based on measurement results and the distribution of evaluation values of film thickness information via an estimation model.

1 is a diagram schematically illustrating an overall configuration of a coating apparatus according to an embodiment. 2 is a diagram showing a configuration of a treatment liquid supply mechanism included in the coating apparatus shown in FIG. 1; FIG. FIG. 2 is a block diagram showing the configuration of a control unit. FIG. 2 is a diagram showing the configuration of a control unit together with the flow of data. FIG. 10 is a diagram illustrating an example of a flow of a control parameter optimization process performed by a control unit.

Embodiments of the present invention will now be described with reference to the accompanying drawings. Note that the components described in these embodiments are merely examples and are not intended to limit the scope of the present invention. For ease of understanding, the dimensions and number of parts may be exaggerated or simplified as necessary in the drawings.

1. Embodiment
1 is a diagram schematically illustrating the overall configuration of a coating apparatus 1 according to an embodiment. The coating apparatus 1 is a substrate processing apparatus that forms a coating film on a substrate S by discharging a processing liquid onto an upper surface Sf of the substrate S. As will be described later, the coating apparatus 1 functions as a parameter optimization apparatus that optimizes parameters for controlling the discharge of the processing liquid.

Substrate S is, for example, a glass substrate for a liquid crystal display device. Substrate S may also be a semiconductor wafer, a glass substrate for a photomask, a glass substrate for a plasma display, a glass or ceramic substrate for a magnetic or optical disk, a glass substrate for an organic EL display, a glass or silicon substrate for a solar cell, or any other substrate to be processed for electronic devices such as a flexible substrate or a printed circuit board. Coating device 1 is, for example, a slit coater.

In Figure 1, an XYZ coordinate system is defined to explain the relative positions of the elements of the coating device 1. The transport direction of the substrate S is the "X direction." The direction in which the substrate S advances in the X direction (toward downstream in the transport direction) is the +X direction, and the opposite direction (toward upstream in the transport direction) is the -X direction. The direction perpendicular to the X direction is the Y direction, and the direction perpendicular to the X and Y directions is the Z direction. In the following description, the Z direction is the vertical direction, and the X and Y directions are the horizontal directions. In the Z direction, the +Z direction is the upward direction, and the -Z direction is the downward direction. Note that these directions are not intended to limit the placement of the coating device.

The coating device 1 comprises, in order in the +X direction, an input conveyor 100, an input transfer unit 2, a floating stage unit 3, an output transfer unit 4, and an output conveyor 110. The input conveyor 100, the input transfer unit 2, the floating stage unit 3, the output transfer unit 4, and the output conveyor 110 form a transport path along which the substrate S passes. The coating device 1 also comprises a substrate transport unit 5, a coating mechanism 7, a treatment liquid supply mechanism 8, and a control unit 9.

The substrate S is transported to the input conveyor 100 from a device upstream of the coating device 1. The input conveyor 100 comprises a roller conveyor 101 and a rotation drive mechanism 102. The rotation drive mechanism 102 rotates each roller of the roller conveyor 101. As each roller of the roller conveyor 101 rotates, the substrate S is transported downstream (+X direction) in a horizontal position. A "horizontal position" refers to a state in which the main surface (the surface with the largest area) of the substrate S is parallel to the horizontal plane (XY plane).

The input transfer section 2 is equipped with a roller conveyor 21 and a rotation/lift drive mechanism 22. The rotation/lift drive mechanism 22 rotates each roller of the roller conveyor 21 and raises and lowers the roller conveyor 21. As the roller conveyor 21 rotates, the substrate S is transported downstream (+X direction) in a horizontal position. Additionally, as the roller conveyor 21 is raised and lowered, the position of the substrate S in the Z direction is changed. The substrate S is transferred from the input conveyor 100 to the floating stage section 3 via the input transfer section 2.

As shown in FIG. 1, the levitation stage unit 3 is generally flat. The levitation stage unit 3 is divided into three sections along the X direction. The levitation stage unit 3 comprises, in order along the +X direction, an entrance levitation stage 31, a coating stage 32, and an exit levitation stage 33. The top surfaces of the entrance levitation stage 31, the coating stage 32, and the exit levitation stage 33 are all flush with each other. The levitation stage unit 3 further comprises a lift pin drive mechanism 34, a levitation control mechanism 35, and an elevation drive mechanism 36. The lift pin drive mechanism 34 raises and lowers the multiple lift pins arranged on the entrance levitation stage 31. The levitation control mechanism 35 supplies compressed air to the entrance levitation stage 31, the coating stage 32, and the exit levitation stage 33 to lift the substrate S. The elevation drive mechanism 36 raises and lowers the exit levitation stage 33.

A large number of nozzles that spray compressed air supplied from the levitation control mechanism 35 are arranged in a matrix on the upper surface of the entrance levitation stage 31 and the upper surface of the exit levitation stage 33. When compressed air is sprayed from each nozzle, the substrate S is levitated upward relative to the levitation stage unit 3. As a result, the lower surface Sb of the substrate S is separated from the upper surface of the levitation stage unit 3, and the substrate S is supported in a horizontal position. When the substrate S is levitated, the distance (levitation amount) between the lower surface Sb of the substrate S and the upper surface of the levitation stage unit 3 is, for example, 10 μm or more and 500 μm or less.

The upper surface of the coating stage 32 is provided with jet holes that eject compressed air supplied from the levitation control mechanism 35 and suction holes that suck in gas. The jet holes and suction holes are arranged alternately in the X and Y directions. The levitation control mechanism 35 controls the amount of compressed air ejected from the jet holes and the amount of air sucked in from the suction holes. This precisely controls the amount of levitation of the substrate S relative to the coating stage 32 so that the position in the Z direction of the upper surface Sf of the substrate S passing above the coating stage 32 is a specified value. The amount of levitation of the substrate S relative to the coating stage 32 is calculated by the control unit 9 based on the detection results of sensor 61 or sensor 62, described below. The amount of levitation of the substrate S relative to the coating stage 32 is preferably adjustable with high precision by airflow control.

The substrate S carried into the floating stage section 3 is imparted with a driving force in the +X direction by the roller conveyor 21 and transported onto the entrance floating stage 31. The entrance floating stage 31, coating stage 32, and exit floating stage 33 support the substrate S in a floating state. For example, the configuration described in Patent No. 5346643 can be used as the floating stage section 3.

The substrate transport unit 5 is disposed below the floating stage unit 3. The substrate transport unit 5 comprises a chuck mechanism 51 and a suction/travel control mechanism 52. The chuck mechanism 51 comprises a suction pad (not shown) attached to a suction member. The chuck mechanism 51 supports the substrate S from below by bringing the suction pad into contact with the peripheral edge of the lower surface Sb of the substrate S. The suction/travel control mechanism 52 applies negative pressure to the suction pad, thereby suctioning the substrate S to the suction pad. The suction/travel control mechanism 52 also causes the substrate transport unit 5 to travel back and forth in the X direction.

The chuck mechanism 51 holds the substrate S with the lower surface Sb of the substrate S positioned higher than the upper surface of the floating stage unit 3. With the peripheral edge of the substrate S held by the chuck mechanism 51, the buoyancy applied by the floating stage unit 3 maintains the substrate S in a horizontal position.

As shown in FIG. 1, the coating device 1 is equipped with a sensor 61 for measuring plate thickness. The sensor 61 is located near the roller conveyor 21. The sensor 61 detects the position in the Z direction of the upper surface Sf of the substrate S held by the chuck mechanism 51. Furthermore, by positioning a chuck (not shown) that is not holding the substrate S directly below the sensor 61, the sensor 61 can detect the position in the vertical direction Z of the suction surface, which is the upper surface of the suction member.

The chuck mechanism 51 moves in the +X direction while holding the substrate S that has been loaded into the floating stage section 3. This transports the substrate S from above the entrance floating stage 31, past above the coating stage 32, and to above the exit floating stage 33. The substrate S is then moved from the exit floating stage 33 to the output transfer section 4.

The output transfer unit 4 moves the substrate S from a position above the exit floating stage 33 to the output conveyor 110. The output transfer unit 4 includes a roller conveyor 41 and a rotation/lifting drive mechanism 42. The rotation/lifting drive mechanism 42 drives the roller conveyor 41 to rotate and raises and lowers the roller conveyor 41 in the Z direction. As each roller of the roller conveyor 41 rotates, the substrate S moves in the +X direction. Additionally, as the roller conveyor 41 rises and falls, the substrate S is displaced in the Z direction.

The output conveyor 110 includes a roller conveyor 111 and a rotation drive mechanism 112. The output conveyor 110 transports the substrate S in the +X direction by rotating each roller of the roller conveyor 111, and discharges the substrate S outside the coating device 1. The input conveyor 100 and output conveyor 110 are part of the coating device 1. However, the input conveyor 100 and output conveyor 110 may be incorporated into a device separate from the coating device 1.

The coating mechanism 7 coats the upper surface Sf of the substrate S with a processing liquid. The coating mechanism 7 is disposed above the transport path of the substrate S. The coating mechanism 7 has a nozzle 71. The nozzle 71 is a slit nozzle with a slit-shaped outlet on its underside. The nozzle 71 is connected to a positioning mechanism (not shown). The positioning mechanism moves the nozzle 71 between a coating position above the coating stage 32 (the position indicated by the solid line in Figure 1) and a maintenance position, which will be described later. The processing liquid supply mechanism 8 is connected to the nozzle 71. The processing liquid supply mechanism 8 supplies the processing liquid to the nozzle 71, causing the processing liquid to be ejected from an outlet disposed on the underside of the nozzle 71.

Figure 2 shows the configuration of the treatment liquid supply mechanism 8 included in the coating apparatus 1 shown in Figure 1. The treatment liquid supply mechanism 8 includes a pump 81, piping 82, a treatment liquid replenishment unit 83, piping 84, an on-off valve 85, a pressure sensor 86, and a drive unit 87. The pump 81 is a supply source for supplying the treatment liquid to the nozzle 71 and supplies the treatment liquid by changing its volume. The pump 81 may be, for example, a bellows-type pump as described in Japanese Patent Application Laid-Open No. 10-61558. As shown in Figure 2, the pump 81 has a flexible tube 811 that is elastically expandable and contractible in the radial direction. One end of the flexible tube 811 is connected to the treatment liquid replenishment unit 83 via piping 82. The other end of the flexible tube 811 is connected to the nozzle 71 via piping 84.

The pump 81 has a bellows 812 that is elastically deformable in the axial direction. The bellows 812 has a small bellows section 813, a large bellows section 814, a pump chamber 815, and an actuation disk section 816. The pump chamber 815 is disposed between the flexible tube 811 and the bellows 812. An incompressible medium is sealed in the pump chamber 815. The actuation disk section 816 is connected to the drive section 87.

The processing liquid replenishment unit 83 has a storage tank 831 that stores processing liquid. The storage tank 831 is connected to the pump 81 via piping 82. An on-off valve 833 is inserted in the piping 82. The on-off valve 833 opens and closes in response to commands from the control unit 9. When the on-off valve 833 is opened, processing liquid can be replenished from the storage tank 831 to the flexible tube 811 of the pump 81. When the on-off valve 833 is closed, the replenishment of processing liquid from the storage tank 831 to the flexible tube 811 of the pump 81 is restricted.

The pipe 84 is connected to the output side of the pump 81. The on-off valve 85 is provided on the pipe 84. The on-off valve 85 opens and closes the pipe 84 in response to commands from the control unit 9. The opening and closing of the on-off valve 85 switches between sending and stopping the treatment liquid to the nozzle 71. The pressure sensor 86 is provided on the pipe 84. The pressure sensor 86 detects the pressure (discharge pressure) applied to the treatment liquid sent to the nozzle 71, and outputs a signal indicating the detected pressure value to the control unit 9.

As shown in Figures 1 and 2, a sensor 62 is disposed on the nozzle 71 to which the processing liquid is supplied from the processing liquid supply mechanism 8. The sensor 62 detects the height of the substrate S in the Z direction in a non-contact manner. The sensor 62 is electrically connected to the control unit 9. Based on the detection results of the sensor 62, the control unit 9 measures the distance (separation distance) between the floating substrate S and the upper surface of the coating stage 32. The control unit 9 then adjusts the coating position of the nozzle 71 using the positioning mechanism based on the measured separation distance. Note that the sensor 62 can be, for example, an optical sensor or an ultrasonic sensor.

The substrate S carried out from the output conveyor 110 is dried in a drying device or the like to form a coating film. Then, as shown in FIG. 1, the substrate S on which the coating film has been formed is transported to a film thickness measuring device AP1, as needed, where the thickness of the coating film is measured. The film thickness measuring device AP1 can be, for example, a spectroscopic ellipsometer or an X-ray reflectance measuring device.

The coating mechanism 7 is equipped with a nozzle cleaning standby unit 72. The nozzle cleaning standby unit 72 performs predetermined maintenance on the nozzle 71 positioned at the maintenance position. The nozzle cleaning standby unit 72 has a roller 721, a cleaning section 722, and a roller butt 723. The nozzle cleaning standby unit 72 cleans the nozzle 71 and forms a liquid pool, thereby preparing the nozzle 71's outlet for coating processing.

Figure 3 is a block diagram showing the configuration of the control unit 9. The control unit 9 controls the operation of each component within the coating device 1. A computer can be used as the control unit 9. The control unit 9 includes a processor 91 and a memory 93. The processor has, for example, a CPU (Central Processing Unit). The memory 93 has a transient storage device such as RAM (Random Access Memory). Note that the memory 93 may also have a non-transient storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). The memory 93 is connected to the processor 91 via a bus wiring.

The control unit 9 has a display device 95 that displays various information and an input device 97 that accepts user command input. The display device 95 and input device 97 are connected to the processor 91 via a wiring bus. The display device 95 is, for example, a liquid crystal display. The input device 97 has, for example, a mouse or keyboard. Note that the display device 95 may also function as an input device by having a touch panel.

Memory 93 stores a computer program 931. The computer program 931 is provided to the control unit 9 via a recording medium M. In other words, the computer program 931 is recorded on the recording medium M so that it can be read by the control unit 9, which is a computer. The recording medium M is specifically a USB (Universal Serial Bus) memory, an optical disk such as a DVD (Digital Versatile Disc), a magnetic disk, etc.

By executing the computer program 931, the processor 91 functions as an ejection control unit 910, a parameter determination unit 913, a film thickness information acquisition unit 914, a film thickness information estimation unit 915, a learning unit 916, and a loop control unit 918.

Figure 4 is a diagram showing the configuration of the control unit 9 along with the data flow. The discharge control unit 910 controls the operation (supply operation) of the pump 81 that supplies the processing liquid to the nozzle 71 based on preset control parameters. In the coating apparatus 1, in order to coat the processing liquid discharged from the nozzle 71 on the upper surface Sf of the substrate S with a uniform film thickness, control parameters closely related to the discharge pressure waveform are optimized in advance before production (or mass production) of the substrate S begins so that the discharge pressure waveform has an ideal shape.

The control parameters are set values for pump control, such as various parameters that define the movement of the actuation disk portion 816 (e.g., acceleration time, steady-state speed, time to maintain steady-state speed, deceleration time, etc.). The control parameters are optimized by the parameter determination unit 913, film thickness information acquisition unit 914, film thickness information estimation unit 915, learning unit 916, and loop control unit 918. In other words, the parameter determination unit 913, film thickness information acquisition unit 914, film thickness information estimation unit 915, learning unit 916, and loop control unit 918 constitute a parameter optimization device that optimizes the control parameters.

The parameter determination unit 913 determines the next control parameter to be evaluated using multiple pieces of acquired film thickness information, each of which is associated with a specific control parameter. As shown in FIG. 4, the acquired film thickness information used by the parameter determination unit 913 is stored in database DB1 in association with specific control parameters. Database DB1 is a function realized by memory 93. Film thickness information is information related to the film thickness of the coating film formed on the substrate S, and is the film thickness distribution in one direction (film thickness profile). Note that film thickness information is not limited to film thickness distribution. For example, indices representing the uniformity of the film thickness (such as the mean value and variance) can also be used as film thickness information.

The film thickness information acquisition unit 914 acquires film thickness information TH1, which is the measurement result of the coating film formed on the substrate S, by controlling the coating apparatus 1 using the control parameter P1 determined by the parameter determination unit 913. Specifically, the discharge control unit 910 performs a discharge process based on the control parameter P1 to form a coating film on the substrate S, and then the thickness of the formed coating film is measured by the film thickness measuring device AP1. The film thickness information acquisition unit 914 acquires film thickness information TH1 using the measured film thickness. The film thickness information acquisition unit 914 stores the acquired film thickness information TH1 in database DB1 in association with the control parameter P1 (i.e., the corresponding control parameter P1), which is the control condition when the film thickness information TH1 was obtained.

The film thickness information estimation unit 915 uses estimation model Y to estimate film thickness information TH2 corresponding to the control parameter P2 determined by the parameter determination unit 913. Estimation model Y is a trained model that receives control parameters and process information as inputs and outputs film thickness information. The process information is information related to the process conditions for forming the coating film and is different from the control parameters. Examples of process information that can be used include the model name of the coating apparatus, the size and type of substrate (surface material, etc.) on which the coating film is formed, and information about the processing liquid (physical property information, etc.). Note that the process information used as input may be one type of information or multiple types of information. The film thickness information estimation unit 915 stores the estimated film thickness information TH2 in database DB1 in association with the corresponding control parameter P2.

The parameter determination unit 913 determines the next control parameter to be evaluated using the film thickness information TH1 stored in database DB1 by the film thickness information acquisition unit 914, or the film thickness information TH2 stored in database DB1 by the film thickness information estimation unit 915.

The learning unit 916 learns an estimation model Y through machine learning using training data in which the acquired control parameters and process information are input and film thickness information is output. For example, by using a recurrent neural network (RNN) as the estimation model Y, it becomes possible to estimate the film thickness distribution, which is one-dimensional data, as film thickness information. Furthermore, if the film thickness information is used as an index of uniformity, for example, random forest regression can be used as the estimation model Y.

As shown in FIG. 4, the training data (learning data set) used by the learning unit 916 for machine learning is stored in database DB2. Database DB2 is a function realized by memory 93. In database DB2, film thickness information is stored in association with the corresponding control parameters and corresponding process information. The film thickness information acquisition unit 914 stores the acquired film thickness information TH1 in database DB2 in association with the corresponding control parameters and process information. Also, as shown in FIG. 4, database DB2 also stores film thickness information provided from database DB3, which is separate from the coating apparatus 1, via a network (not shown) or the like.

The loop control unit 918 controls the parameter determination unit 913, film thickness information acquisition unit 914, and film thickness information estimation unit 915 so that the first process and the second process are executed alternately. Here, the first process is a process that includes a process of determining control parameters by the parameter determination unit 913 and a process of acquiring film thickness information by the film thickness information acquisition unit 914. The second process is a process that includes a process of determining control parameters by the parameter determination unit 913 and a process of estimating film thickness information by the film thickness information estimation unit 915. As will be described later, the loop control unit 918 controls the second process so that the process by the parameter determination unit 913 and the process by the film thickness information estimation unit 915 are repeated multiple times. Details of this will be explained with reference to Figure 5.

<Parameter optimization process>
Fig. 5 is a diagram showing an example of the flow of parameter optimization processing by the control unit 9. In the flow of Fig. 5, the parameter determination step S10 corresponds to the control parameter determination processing by the parameter determination unit 913. The estimation step S3 corresponds to the film thickness information estimation processing by the film thickness information estimation unit 915, and the acquisition step S5 corresponds to the film thickness information estimation processing by the film thickness information acquisition unit 914. In other words, the first processing corresponds to the parameter determination step S10 and the acquisition step S5, and the second processing corresponds to the parameter determination step S10 and the estimation step S3.

5, an estimation upper limit number of times N _est is set in advance. The estimation upper limit number of times N _est is the number of times the estimation step S3 should be repeated in one execution of the second process. The loop control unit 918 uses the estimation execution number C _est as a variable to count the number of times the estimation step S3 has been executed.

5, a search upper limit number N _all is set in advance. The search upper limit number N _all is the number of times that control parameters should be searched for in one optimization process (i.e., the number of times that the parameter determination unit 913 determines control parameters). The loop control unit 918 uses the search execution number C _ser as a variable to count the number of times a search has been executed.

When the optimization process begins, the parameter determination unit 913 first determines the initial control parameters (initial parameter determination step S1). The initial control parameters can be values that have already been used in the coating device. Alternatively, the initial control parameters may be values that have been determined randomly.

Next, the loop control unit 918 determines whether the number of estimation executions C _est has reached the upper estimation limit number N _est (determination step S2). If it is determined in the determination step S2 that the number of estimation executions C _est has not reached the upper estimation limit number N _est , the loop control unit 918 causes the film thickness information estimation unit 915 to execute an estimation process. That is, the film thickness information estimation unit 915 estimates film thickness information by inputting the control parameters determined in the initial parameter determination step S1 (or the parameter determination step S10 described later) into the estimation model Y (estimation step S3). Furthermore, the loop control unit 918 adds 1 to the number of estimation executions C _est (increment step S4). Upon completion of the increment step S4, the control unit 9 proceeds to the evaluation value calculation step S9.

If it is determined in the determination step S2 that the estimated number of executions C _est has reached the estimated upper limit number of executions N _est , the film thickness information acquisition unit 914 executes an acquisition process (acquisition step S5). Specifically, the discharge control unit 910 controls the pump 81 using the control parameters P1 determined in the initial parameter determination step S1 (or the parameter determination step S10 described later), thereby forming a coating film on the substrate S. Then, the film thickness of the coating film is measured by the film thickness measuring device AP1. The film thickness information acquisition unit 914 acquires film thickness information, which is the measurement result of the film thickness. After the acquisition step S5, the loop control unit 918 sets the estimated number of executions C _est to 0 (reset step S6).

After the reset step S6, the loop control unit 918 determines whether to update the estimation model Y (determination step S7). The estimation model Y may be updated, for example, when the number of pieces of film thickness information TH1 acquired in the acquisition step S5 that have not been used to re-learn the estimation model Y reaches a predetermined number. If it is determined in the determination step S7 that the estimation model Y should be updated, the loop control unit 918 causes the learning unit 916 to update the estimation model Y (model update step S8). That is, the estimation model Y is re-learned using the additional film thickness information added to the database DB1 in the acquisition step S5. After the model update step S8 is completed, the control unit 9 proceeds to the evaluation value calculation step S9. If it is determined in the determination step S7 that the estimation model Y should not be updated, the control unit 9 skips the model update step S8 and proceeds to the evaluation value calculation step S9.

In the evaluation value calculation step S9, the parameter determination unit 913 calculates an evaluation value for the film thickness information TH2 estimated in the estimation step S3 or the film thickness information TH1 obtained in the acquisition step S5. For example, an index representing the magnitude of variation in the film thickness distribution may be used as an evaluation value for achieving a uniform film thickness. In this case, the error from a predetermined target film thickness or the variation in the error may be used as the evaluation value.

The parameter determination unit 913 then determines the control parameters to be evaluated next based on the evaluation value obtained in the evaluation value calculation step S9 (parameter determination step S10). Specifically, techniques such as reinforcement learning (RL), Bayesian optimization, or particle swarm optimization can be used. These techniques make it possible to update the control parameters for each trial so that the evaluation value is optimized.

Also, as a parameter search method, multitask Bayesian optimization described in Non-Patent Document 1 or Patent Document 2 (WO 2019/244474) may be used. The film thickness information TH1 acquired in the acquisition process S5 may be affected by noise components generated by actual measurement. For this reason, there is a possibility that a difference in the distribution of evaluation values may occur between the film thickness information TH2 estimated in the estimation process S3 and the film thickness information TH1 acquired in the acquisition process S5. Therefore, by using multitask Bayesian optimization with one as the target observation data and the other as the reference observation data, it is possible to perform a Bayesian optimization search more efficiently, even if there is a difference in the distribution of evaluation values between the two.

After the parameter determination step S10, the loop control unit 918 increments the search execution count C _ser by 1 (increment step S11). Then, the loop control unit 918 determines whether the search execution count C _ser has reached the search upper limit count N _all (determination step S12). If it is determined in the determination step S12 that the search execution count C _ser has not reached the search upper limit count N _all , the control unit 9 returns to the determination step S2 and continues the process. On the other hand, if it is determined in the determination step S12 that the search execution count C _ser has reached the search upper limit count N _all , the control unit 9 ends the process. The optimized control parameters are stored in the memory 93 and are used in subsequent coating processes in the coating apparatus 1.

As described above, the control unit 9 of this embodiment alternates between searching for control parameters via the estimation model Y and searching for control parameters based on film thickness measurements, which takes time. This reduces the number of times a coating film is formed and the film thickness is measured, thereby shortening the time required to adjust the control parameters. Furthermore, since the number of times a coating film is formed can be reduced, consumption of the substrate S and processing liquid can be reduced, thereby easing the environmental burden. Furthermore, by including process information in the input of the estimation model, film thickness information obtained in different processes can be used as training data. Therefore, inputting process information can improve the output accuracy of the estimation model. Therefore, control parameters can be searched accurately, allowing for efficient optimization.

In addition, by re-learning estimation model Y using film thickness information measured during optimization of control parameters, the output accuracy of estimation model Y can be improved along with optimization.

In the second process, the parameter determination unit 914 determines the next control parameter and the film thickness information estimation unit 915 estimates the film thickness information TH2 multiple times until the maximum number of estimations N _est is reached, thereby further reducing the time required for parameter optimization.

2. Modified Examples
Although the embodiments have been described above, the present invention is not limited to the above and various modifications are possible.

5, the parameter determination step S10 and the estimation step S3 are repeated an estimated upper limit number of times N _est in the second process, whereas the parameter determination step S10 and the acquisition step S5 are executed only once in the first process. However, the loop control unit 918 may also perform control so that the parameter determination step S10 and the acquisition step S5 are executed twice or more times in the first process.

The film thickness information obtained in the estimation step S3 and the acquisition step S5 may be the same as the evaluation value obtained in the evaluation value calculation step S9. In this case, the estimation model Y may be trained so that it outputs an evaluation value from the control parameters. The film thickness information acquisition unit 914 may also calculate the evaluation value from the film thickness distribution.

5, in the determination step S12, generation of the control parameters is repeated until the number of search executions C _ser reaches the upper search limit number N _all . Alternatively, the loop control unit 918 may perform control so that generation of the control parameters is repeated until the evaluation value calculated in the evaluation value calculation step S9 exceeds a predetermined reference value.

In addition, in the above embodiment, the parameter optimization device is realized by the control unit 9 provided in the coating device 1, but it may also be configured as a device separate from the coating device 1.

Although this invention has been described in detail, the above description is illustrative in all respects and does not limit the invention. It is understood that countless variations not illustrated can be envisioned without departing from the scope of this invention. The configurations described in the above embodiments and variations can be combined or omitted as appropriate, as long as they are not mutually inconsistent.

1: Coating device 9: Control unit (parameter optimization device)
913: Parameter determination unit 914: Film thickness information acquisition unit 915: Film thickness information estimation unit 916: Learning unit 918: Loop control unit 931: Computer program Y: Estimation model

Claims (7)

A parameter optimization device for optimizing control parameters for controlling a coating device that discharges a treatment liquid onto a substrate to form a coating film, the parameter optimization device comprising:
a parameter determination unit that determines a control parameter to be next evaluated using a plurality of pieces of film thickness information, each of which is associated with a specific control parameter;
a film thickness information acquiring unit that acquires film thickness information based on a measurement result of a film thickness of a coating film formed by controlling a coating device using the control parameters determined by the parameter determining unit;
a film thickness information estimation unit that estimates film thickness information corresponding to the control parameters determined by the parameter determination unit using an estimation model that receives control parameters and process information as inputs and outputs film thickness information;
a loop control unit that controls the parameter determination unit, the film thickness information acquisition unit, and the film thickness information estimation unit so that a first process including a process by the parameter determination unit and a process by the film thickness information acquisition unit, and a second process including a process by the parameter determination unit and a process by the film thickness information estimation unit are alternately executed;
A parameter optimization device comprising: 2. The parameter optimization device according to claim 1,
a learning unit that learns the estimation model using the film thickness information acquired by the film thickness information acquisition unit;
The parameter optimization device further comprises: 3. The parameter optimization device according to claim 1 or 2,
the second process is a process of repeating the process of the parameter determination unit and the process of the film thickness information estimation unit a plurality of times;
The parameter optimization device, wherein the loop control unit executes the first process when the number of times that the film thickness information has been estimated by the film thickness information estimation unit reaches a predetermined number in the second process. 3. The parameter optimization device according to claim 1 or 2,
The parameter determination unit calculates an evaluation value from the film thickness information, and determines a control parameter to be evaluated next based on the evaluation value. 5. The parameter optimization device according to claim 4,
The parameter determination unit determines the control parameter to be next evaluated using a multitask Bayesian optimization algorithm. A parameter optimization method for optimizing parameters for controlling a coating apparatus that discharges a treatment liquid onto a substrate to form a coating film, comprising:
a) a parameter determination step of determining a control parameter to be next evaluated using a plurality of pieces of film thickness information, each of which is associated with a specific parameter;
b) a film thickness information acquisition step of acquiring film thickness information based on measurement results of a coating film formed by controlling a coating device using the control parameters determined in the parameter determination step;
c) a film thickness information estimation step of estimating film thickness information corresponding to the control parameters determined in the parameter determination step using an estimation model that receives control parameters and process information as inputs and outputs film thickness information;
wherein a first process including the parameter determination step and the film thickness information acquisition step and a second process including the parameter determination step and the film thickness information estimation step are alternately performed. A computer-executable computer program,
A computer program that causes a computer to execute the parameter optimization method according to claim 6.