TW202345257A - Parameter optimization method, program, recording medium and substrate processing apparatus - Google Patents

Abstract

The present invention addresses the problem of providing a technique capable of appropriately and efficiently implementing parameter optimization in an apparatus that discharges a processing liquid. A coating device (1) is provided with: a discharge control unit (910) for controlling the discharge of a coating liquid from a nozzle (71) on the basis of a plurality of parameters including a first parameter and a second parameter; a discharge characteristic measurement unit (911) that measures discharge characteristics when the nozzle (71) discharges the coating liquid; a first optimization unit (915) that optimizes the first parameter by global search on the basis of the discharge characteristics; and a second optimization unit (917) that optimizes the second parameter by a local search on the basis of the discharge characteristics. The first parameters include parameters V1-V4, T1-T9 corresponding to a rising period during which the discharge speed of the coating liquid from the nozzle 71 is increased to a stable discharge speed. The second parameter includes a parameter V5 corresponding to a stable discharge period in which the discharge speed is maintained at a stable discharge speed.

Description

Parameter optimization method, program, recording medium and substrate processing device

The subject matter disclosed in this specification relates to a parameter optimization method, program, recording medium and substrate processing device.

As shown in Patent Document 1, when a processing liquid discharged from a nozzle is applied to a substrate, the discharge pressure given to the processing liquid greatly affects the thickness of the processing liquid applied to the substrate. Therefore, in Patent Document 1, optimization of parameters related to discharge pressure is sought.

Specifically, the optimization method of Patent Document 1 includes: a simulated discharge step, which discharges the processing liquid outside the substrate; a discharge characteristic measurement step, which measures the discharge characteristics of the processing liquid in the simulated discharge step; and a state quantity derivation step. , which derives the state quantity that deviates from the target characteristic of the measured discharge characteristics; and the learning step, which performs machine learning on changes in the state quantity accompanying changes in parameters, thereby constructing a learning model. In addition, while the state quantity exceeds the predetermined allowable range, after changing the parameters based on the learning model, the simulated discharge step, the discharge characteristic measurement step, the state quantity derivation step, and the learning step are repeatedly executed. When the state quantity is within the allowable range, the last changed parameter is set to the parameter when the processing liquid is discharged in the processing liquid supply step. [Prior technical literature] [Patent Document]

[Patent Document 1] Japanese Patent Application Publication No. 2020-040046

(The problem that the invention wants to solve)

According to the optimization method of Patent Document 1, the parameter adjustment operation can be automated by utilizing machine learning, so the labor of technicians can be reduced. However, the learning of machine learning models generally requires a large amount of learning materials or repeated trials many times. Therefore, compared with the situation where the parameter optimization operation is simply automated and the parameter adjustment operation is performed by technicians with knowledge and experience, there is the time required for optimization or the processing liquid accompanying the simulated discharge. There is a risk of increased consumption.

An object of the present invention is to provide a technology that can appropriately and efficiently implement parameter optimization in a device that discharges a treatment liquid. (Technical means to solve problems)

In order to solve the above problem, a first aspect is a parameter optimization method that optimizes parameters for controlling the discharge of the processing liquid discharged from a nozzle in a substrate processing apparatus that supplies the processing liquid discharged from a nozzle; The parameter optimization method includes: a) a first optimization step, which optimizes the first parameter through a large area search; and b) a second optimization step, which optimizes the first parameter through a local search. Second parameter optimization; the first parameter includes a parameter corresponding to a rising period in which the discharge speed of the treatment liquid from the nozzle is increased to a constant discharge speed, and the second parameter includes a parameter related to maintaining the discharge speed at the constant speed. Parameters corresponding to the constant discharge period of the discharge speed.

The second aspect is the parameter optimization method of the first aspect, wherein the aforementioned step b) is performed after the aforementioned step a).

A third aspect is a parameter optimization method of the first aspect, wherein the first optimization step includes a step of optimizing the first parameter through Bayesian optimization.

A fourth aspect is a parameter optimization method according to any one of the first to third aspects, wherein the parameter is a control amount that controls an operation of a pump that supplies the processing liquid to the nozzle.

A fifth aspect is a parameter optimization method according to any one of the first aspect to the fourth aspect, wherein the aforementioned step a) includes: deriving based on the characteristic amount of the discharge characteristics when the treatment liquid is discharged from the aforementioned nozzle. Cost value, and the step of optimizing the first parameter mentioned above.

The sixth aspect is a parameter optimization method of any one of the first to fifth aspects, wherein the aforementioned step b) includes: based on the discharging speed at the beginning of the aforementioned steady discharging period, and the aforementioned steady discharging The ratio of the discharge speed at the end of the period is the step of optimizing the aforementioned second parameter.

The seventh aspect is a program for causing the computer to optimize parameters for controlling the discharge of the treatment liquid from the nozzle; the program causes the computer to execute: a) the first optimization step, by Optimize the first parameter by a large area search; and b) a second optimization step, which optimizes the second parameter by a local search; the aforementioned first parameter includes the aforementioned treatment liquid from the aforementioned nozzle The second parameters include parameters corresponding to the steady discharge period during which the discharge speed is maintained at the steady discharge speed.

The eighth aspect is a computer-readable recording medium that records the program of the seventh aspect.

A ninth aspect is a substrate processing apparatus that supplies a processing liquid discharged from a nozzle to a substrate, and includes a discharge control unit that controls based on a plurality of parameters including a first parameter and a second parameter. Discharge of the processing liquid from the nozzle; a discharge characteristic measurement unit that measures the discharge characteristics when the nozzle discharges the processing liquid; and a first optimization unit that performs a large-area search based on the discharge characteristics. The aforementioned first parameter optimization; and a second optimization unit, which optimizes the aforementioned second parameter through local search based on the aforementioned discharge characteristics; the aforementioned first parameter includes the aforementioned treatment liquid from the aforementioned nozzle The second parameter includes a parameter corresponding to a steady discharge period during which the discharge speed is maintained at the steady discharge speed. (Compare the effectiveness of previous technologies)

According to the parameter optimization method of the first to sixth aspects, the local search is used to optimize the parameters corresponding to the steady discharge speed, which is easier to optimize. Therefore, it is better to use the large-area search to optimize all parameters. In the case of parameter optimization, the amount of calculation can be reduced. Therefore, parameters corresponding to the discharge of the treatment liquid can be appropriately and efficiently optimized.

According to the parameter optimization method of the second aspect, the second parameter can be optimized based on the optimized first parameter.

According to the parameter optimization method of the third aspect, the first parameter can be optimized through Bayesian optimization.

According to the parameter optimization method of the fifth aspect, the first parameter can be optimized based on the cost value.

According to the parameter optimization method of the sixth aspect, the second parameter can be optimized based on the ratio of the discharge speed at the beginning and end of the steady discharge period, so that the discharge speed during the steady discharge period can be maintained at the steady discharge The speed method optimizes the second parameter.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. In addition, the components described in this embodiment are only examples, and the scope of the present invention is not intended to be limited to these components. In the drawings, in order to facilitate understanding, the size or number of each part may be exaggerated or simplified as necessary.

FIG. 1 is a diagram schematically showing the overall structure of the coating device 1 according to the embodiment. The coating device 1 is a substrate processing device that applies a coating liquid to the upper surface Sf of the substrate S. For example, the substrate S is a glass substrate for a liquid crystal display device. In addition, the 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 disk or an optical disk, a glass substrate for an organic EL, a glass substrate or a silicon substrate for a solar cell, or others. Flexible substrates, printed circuit boards, etc. are used in various processing substrates for electronic equipment. The coating device 1 is, for example, a slit coater.

In FIG. 1 , an XYZ coordinate system is defined in order to explain the arrangement relationship of each element of the coating device 1 . The conveyance direction of the substrate S is the "X direction". In the X direction, the direction in which the substrate S travels (the downstream side in the conveyance direction) is the +X direction, and the opposite direction (the upstream side in the conveyance direction) is the -X direction. In addition, the direction orthogonal to the X direction is the Y direction, and the direction orthogonal to the X direction and the Y direction is the Z direction. In the following description, the Z direction is regarded as the vertical direction, and the X direction and the Y direction are regarded as the horizontal direction. In the Z direction, the +Z direction is regarded as the upward direction, and the -Z direction is regarded as the downward direction.

The coating device 1 includes an input conveyor 100, an input transfer part 2, a floating platform part 3, an output transfer part 4, and an output conveyor 110 in order in the +X direction. The input conveyor 100, the input transfer unit 2, the floating platform unit 3, the output transfer unit 4, and the output conveyor 110 form a transfer path through which the substrate S passes. In addition, the coating device 1 further includes a substrate transport unit 5 , a coating mechanism 7 , a coating liquid supply mechanism 8 , and a control unit 9 .

The substrate S is conveyed to the input conveyor 100 from the upstream side. The input conveyor 100 includes a roller conveyor 101 and a rotation drive mechanism 102 . The rotation drive mechanism 102 rotates each roller of the roller conveyor 101 . By the rotation of each roller of the roller conveyor 101, the substrate S is conveyed downstream (+X direction) in a horizontal posture. "Horizontal posture" refers to the 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 unit 2 includes a roller conveyor 21 and a rotation and lifting drive mechanism 22 . The rotation/lifting drive mechanism 22 rotates each roller of the roller conveyor 21 and raises and lowers the roller conveyor 21 . By the rotation of the roller conveyor 21, the substrate S is conveyed downstream (+X direction) in a horizontal attitude. Furthermore, the position of the substrate S in the Z direction is changed by the lifting and lowering of the roller conveyor 21 . The substrate S is transferred from the input conveyor 100 to the floating platform part 3 via the input transfer part 2 .

As shown in FIG. 1 , the floating platform portion 3 has a substantially flat plate shape. The floating platform portion 3 is divided into three parts along the X direction. The floating platform part 3 includes an entrance floating platform 31, a coating platform 32, and an exit floating platform 33 in order in the +X direction. The upper surface of the inlet floating platform 31, the upper surface of the coating platform 32, and the upper surface of the outlet floating platform 33 are on the same plane. The floating platform part 3 further includes a lifting pin driving mechanism 34 , a floating control mechanism 35 , and a lifting driving mechanism 36 . The lifting pin driving mechanism 34 raises and lowers several lifting pins arranged on the entrance floating platform 31 . The floating control mechanism 35 supplies compressed air for floating the substrate S to the inlet floating platform 31 , the coating platform 32 , and the outlet floating platform 33 . The lifting drive mechanism 36 raises and lowers the outlet floating platform 33 .

On the upper surface of the inlet floating platform 31 and the upper surface of the outlet floating platform 33, a plurality of ejection holes for ejecting the compressed air supplied from the floating control mechanism 35 are arranged in a matrix. When the compressed air is ejected from each ejection hole, the substrate S floats upward with respect to the floating platform portion 3 . Then, the lower surface Sb of the substrate S is supported in a horizontal posture while being separated from the upper surface of the floating platform portion 3 . In the state where the substrate S is floated, the distance (lifting amount) between the lower surface Sb of the substrate S and the upper surface of the floating platform portion 3 is, for example, 10 μm or more and 500 μm or less.

On the upper surface of the coating platform 32, ejection holes for ejecting compressed air supplied from the floating control mechanism 35 and suction holes for sucking gas are alternately arranged in the X direction and the Y direction. The floating control mechanism 35 controls the ejection amount of compressed air from the ejection hole and the suction amount of air from the suction hole. Thereby, the floating amount of the substrate S with respect to the coating platform 32 is precisely controlled so that the position of the upper surface Sf of the substrate S passing above the coating platform 32 in the Z direction becomes a predetermined value. In addition, the floating amount of the substrate S relative to the coating platform 32 is calculated by the control unit 9 based on the detection result of the sensor 61 or the sensor 62 described later. In addition, it is preferable that the floating amount of the substrate S relative to the coating platform 32 can be adjusted with high accuracy by controlling the air flow.

The substrate S carried into the floating platform part 3 is given a propulsive force in the +X direction from the roller conveyor 21, and is conveyed to the entrance floating platform 31. The inlet floating platform 31, the coating platform 32, and the outlet floating platform 33 support the substrate S in a floating state. As the floating platform portion 3, for example, the structure described in Japanese Patent No. 5346643 can be adopted.

The substrate transfer unit 5 is arranged below the floating platform unit 3 . The substrate transfer unit 5 includes a chuck mechanism 51 and an adsorption/transfer control mechanism 52 . The chuck mechanism 51 includes an adsorption pad (not shown) provided on the adsorption member. The chuck mechanism 51 supports the substrate S from the lower side by bringing the suction pad into contact with the peripheral edge portion of the lower surface Sb of the substrate S. The adsorption/movement control mechanism 52 adsorbs the substrate S to the adsorption pad by applying negative pressure to the adsorption pad. Furthermore, the adsorption/transfer control mechanism 52 reciprocates the substrate transport unit 5 in the X direction.

The chuck mechanism 51 holds the substrate S in a state where the lower surface Sb of the substrate S is located at a higher position than the upper surface of the floating platform portion 3 . The substrate S maintains its horizontal posture by the buoyancy force imparted from the floating platform portion 3 while the peripheral portion is held by the chuck mechanism 51 .

As shown in FIG. 1 , the coating device 1 is provided with a sensor 61 for plate thickness measurement. The sensor 61 is arranged near the roller conveyor 21 . The sensor 61 detects the position of the upper surface Sf of the substrate S held by the chuck mechanism 51 in the Z direction. In addition, since the chuck (not shown) that does not hold the substrate S is located directly below the sensor 61, the sensor 61 can detect the position of the upper surface of the adsorption member, that is, the adsorption surface, in the vertical direction Z.

The chuck mechanism 51 moves in the +X direction while holding the substrate S loaded into the floating platform portion 3 . Thereby, the substrate S is conveyed from above the entrance floating platform 31 to above the exit floating platform 33 via the upper side of the coating platform 32 . Then, the substrate S moves from the outlet floating platform 33 to the output transfer unit 4 .

The output transfer unit 4 moves the substrate S from a position above the outlet floating platform 33 toward 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. Furthermore, as the roller conveyor 41 moves up and down, 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 conveys the substrate S in the +X direction by the rotation of each roller of the roller conveyor 111, and moves the substrate S out of the coating device 1. In addition, the input conveyor 100 and the output conveyor 110 are part of the coating device 1 . However, the input conveyor 100 and the output conveyor 110 may be installed in a device different from the coating device 1 .

The coating mechanism 7 applies the coating liquid on the upper surface Sf of the substrate S. The coating mechanism 7 is arranged above the conveyance path of the substrate S. The coating mechanism 7 has a nozzle 71 . The nozzle 71 is a slit nozzle having a slit-shaped discharge port on the lower surface. The nozzle 71 is connected to a positioning mechanism (not shown). The positioning mechanism moves the nozzle 71 between the coating position above the coating platform 32 (the position indicated by the solid line in FIG. 1 ) and the maintenance position described below. The coating liquid supply mechanism 8 is connected to the nozzle 71 . The coating liquid supply mechanism 8 supplies the coating liquid to the nozzle 71 and discharges the coating liquid from the discharge port arranged on the lower surface of the nozzle 71 .

FIG. 2 is a diagram showing the structure of the coating liquid supply mechanism 8 . The coating liquid supply mechanism 8 includes a pump 81 , a pipe 82 , a coating liquid replenishing unit 83 , a pipe 84 , an on-off valve 85 , a pressure gauge 86 , and a drive unit 87 . The pump 81 is a supply source for supplying the coating liquid to the nozzle 71, and supplies the coating liquid by volume change. The pump 81 may be a bellows type pump described in Japanese Patent Application Laid-Open No. 10-61558, for example. As shown in FIG. 2 , the pump 81 has a flexible tube 811 that can elastically expand and contract in the radial direction. One end of the flexible tube 811 is connected to the coating liquid replenishing unit 83 via a pipe 82 . The other end of the flexible tube 811 is connected to the nozzle 71 via the pipe 84 .

The pump 81 has a bellows 812 that is elastically deformable in the axial direction. The bellows 812 has a small bellows part 813, a large bellows part 814, a pump chamber 815, and an actuator plate part 816. The pump chamber 815 is arranged between the flexible tube 811 and the bellows 812 . A non-compressible medium is enclosed in the pump chamber 815 . The operating plate part 816 is connected to the driving part 87 .

The coating liquid replenishing unit 83 has a storage tank 831 for storing coating liquid. The storage tank 831 is connected to the pump 81 via the pipe 82 . An on-off valve 833 is inserted into the pipe 82 . The opening and closing valve 833 opens and closes based on the command from the control unit 9 . When the on-off valve 833 is opened, the coating liquid can be supplied from the storage tank 831 to the flexible tube 811 of the pump 81 . Furthermore, when the on-off valve 833 is closed, replenishment of the coating 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 inserted into the pipe 84 . The on-off valve 85 opens and closes based on the command from the control unit 9 . The on-off valve 85 switches between feeding and stopping the coating liquid to the nozzle 71 by opening and closing. The pressure gauge 86 is arranged in the pipe 84 . The pressure gauge 86 detects the pressure (discharge pressure) of the coating liquid sent to the nozzle 71 and outputs a signal indicating the detected pressure value to the control unit 9 .

FIG. 3 is a line diagram showing the movement pattern of the actuating disk portion 816 of the pump 81 shown in FIG. 2 . In FIG. 3 , the horizontal axis represents time, and the vertical axis represents the moving speed of the actuating disk portion 816 . The driving part 87 displaces the actuating disk part 816 in the axial direction in the movement pattern shown in FIG. 3 (a pattern showing changes in the speed of the actuating disk part 816 with respect to the passage of time) in accordance with instructions from the control unit 9 . Through the displacement of the actuating disk portion 816, the volume inside the bellows 812 changes. Thereby, the flexible tube 13 expands and contracts in the radial direction to perform a pump operation, and the coating liquid supplied from the coating liquid supply unit 83 is supplied to the nozzle 71 . Since the movement pattern of the actuating disk portion 816 is closely related to the discharge characteristics of the coating liquid discharged from the nozzle 71, the discharge characteristics (pressure waveform showing the time change of the discharge pressure) as shown in FIG. 4 can be obtained according to the movement pattern.

Figure 4 is a graph showing discharge characteristics. FIG. 4(a) is a graph showing ideal discharge characteristics, that is, target characteristics. Figure 4(b) is an example of the discharge characteristics actually measured. In FIG. 4 , the horizontal axis represents time, and the vertical axis represents pressure value (or discharge speed).

In this embodiment, by adjusting various parameters (acceleration time, constant speed, constant speed time, deceleration time, etc.) that regulate the movement of the actuating disk portion 816 , the coating liquid ejected from the nozzle 71 is appropriately ejected. Optimization processing in which the characteristics (specifically, the time change of the discharge speed (discharge pressure)) are consistent with or approximate the desired target characteristics (the graph shown in FIG. 4(a) ). This point will be discussed in detail below.

As shown in FIGS. 1 and 2 , a sensor 62 is disposed in the nozzle 71 that supplies the coating liquid from the coating 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 . The control unit 9 measures the distance (separation distance) between the floating substrate S and the upper surface of the coating platform 32 based on the detection result of the sensor 62 . Furthermore, the control unit 9 adjusts the coating position of the nozzle 71 through the positioning mechanism based on the measured separation distance. In addition, as the sensor 62, an optical sensor or an ultrasonic sensor can be applied.

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 arranged at the maintenance position. The nozzle cleaning standby unit 72 has a roller 721, a cleaning part 722, and a roller tank 723. The nozzle cleaning standby unit 72 adjusts the discharge port of the nozzle 71 to a state suitable for coating processing by cleaning the nozzle 71 and forming liquid accumulation. In addition, in the coating device 1 , in order to evaluate the discharge pressure applied to the coating liquid, a simulated discharge of the coating liquid from the nozzle 71 is performed with the nozzle 71 disposed in the maintenance position.

FIG. 5 is a block diagram showing an example of the structure of the control unit 9. The control unit 9 controls the operation of each element of the coating device 1 . The control unit 9 is a computer and includes a computing unit 91 , a storage unit 93 , and a user interface 95 . The computing unit 91 is a processor composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like. The storage unit 93 is composed of disposable storage devices such as RAM (Random Access Memory) and non-disposable storage devices such as HDD (Hard Disk Drive) and SSD (Solid State Drive). consists of auxiliary storage devices.

The user interface 95 has a display that displays information to the user and an input device that accepts the user's input operations. As the control unit 9, a desktop, laptop or tablet computer can be used, for example.

The storage unit 93 stores the program 931. The program 931 is provided by the recording medium M. That is, the recording medium M records the program 931 in a readable manner by the control unit 9 which is a computer. The recording medium M is, for example, a USB (Universal Serial Bus) memory, a DVD (Digital Versatile Disc) and other optical disks, magnetic disks, etc.

By executing the program 931, the calculation unit 91 functions as the discharge control unit 910, the discharge characteristic measurement unit 911, the cost value derivation unit 913, the first optimization unit 915, and the second optimization unit 917.

The discharge control unit 910 controls the operation (feeding operation) of the pump 81 that supplies the coating liquid to the nozzle 71 based on preset parameters.

The discharge characteristic measuring unit 911 measures the discharge characteristics. Specifically, the discharge characteristic measuring unit 911 measures the pressure waveform based on the discharge pressure (the pressure value of the coating liquid) output from the pressure gauge 86 during simulated discharge. That is, the discharge characteristic measurement unit 911 periodically obtains the discharge pressure measured by the pressure gauge 86 at a predetermined sampling cycle. Thereby, the discharge pressure given to the coating liquid is acquired while the coating liquid is discharged from the nozzle 71, and is stored in the storage unit 93 as discharge pressure measurement data. The discharge pressure measurement data is data showing the time and the discharge pressure measured at that time.

The cost value derivation unit 913 derives a cost value from the discharge characteristics (pressure waveform) measured by the discharge characteristics measurement unit 911 based on a predetermined cost function. The cost value is used when the first optimization unit 915 performs optimization calculations. The first optimization unit 915 optimizes parameters using a large area search method. In this example, the optimization performed by the large area search is Bayesian optimization. In addition, the large area search method is not limited to Bayesian optimization, and genetic algorithms can also be used. The second optimization unit 917 optimizes the parameters using the local search method. Optimization by local search will be described below.

In the coating device 1, in order to apply the coating liquid discharged from the nozzle 71 to the upper surface Sf of the substrate S with a uniform film thickness, the discharge speed, that is, the discharge characteristics of the coating liquid when it is discharged from the nozzle 71 is adjusted. important. For example, by discharging the coating liquid from the nozzle 71 with the target characteristics as shown in FIG. 4(a) , the uniformity of the film thickness can be improved. Therefore, in order to bring the discharge characteristics close to the target characteristics, it is important to optimize parameters closely related to the discharge characteristics. In this embodiment, as shown in FIG. 3 , the following 16 set values for pump control that regulate the movement of the actuating plate portion 816 are used as parameters to be optimized. ・Steady speed V1 ・Acceleration time T1: The time to accelerate from the stop state to the constant speed V1 ・Steady speed time T2: the time to maintain constant speed V1 ・Steady speed V2 ・Acceleration time T3: the time to decelerate from the constant speed V1 to the constant speed V2 ・Steady speed time T4: the time to maintain constant speed V2 ・Constant speed V3 ・Acceleration time T5: The time to accelerate from the constant speed V2 to the constant speed V3 ・Steady speed time T6: the time to continue the steady speed V3 ・Constant speed V4 ・Acceleration time T7: The time to decelerate from the constant speed V3 to the constant speed V4 ・Steady speed time T8: The time to continue the steady speed V4 ・Constant speed V5 ・Acceleration time T9: The time to accelerate from the constant speed V4 to the constant speed V5 ・Steady speed time T10: the time to maintain constant speed V5 ・Deceleration time T11: The time to decelerate from the constant speed V5 to the stop state

The above parameters correspond to control quantities for controlling the operation (feeding operation) of the pump 81 that supplies the coating liquid to the nozzle 71 . In addition, the type and number of parameters are not particularly limited, and can be set arbitrarily as long as they are control variables for controlling the feeding operation of the pump 81 .

For example, the above parameters can be adjusted to change the formula according to the type of coating treatment. In addition, there are also cases where parameters are adjusted based on the user's input instructions through the input device. For V5 among the above 16 parameters, most can be adjusted by slightly changing the value of the constant speed V4 as the center. Therefore, V5 is relatively easy to optimize. On the other hand, for parameters other than V5 (V1 to V4, T1 to T11), since it is necessary to grasp the discharge characteristics and make adjustments through repeated tests for each coating liquid, optimization is relatively difficult. high.

Therefore, in this embodiment, the optimization of the parameters other than V5 (the first parameter) is based on Bayesian optimization that can search widely and in a large area. On the other hand, the optimization of V5 (second parameter) applies the local search method described below after the above-mentioned adjustment of Bayesian optimization.

FIG. 6 is a flowchart showing parameter optimization processing performed in the coating device 1 . When the parameter optimization process starts, first, the nozzle moving step S1 is performed. In the nozzle moving step S1, the nozzle 71 is moved to the above-mentioned maintenance position. In the coating device 1, simulated discharge can be executed by the nozzle movement step S1.

After the nozzle moving step S1 is completed, the first optimization step S2 is performed. In the first optimization step S2, the first optimization unit 915 optimizes parameters other than V5 (V1 to V4, T1 to T11). In addition, in the first optimization step S2, the parameter V5 is fixed at a predetermined value. Then, after the first optimization step S2, the second optimization step S3 is performed. In the second optimization step S3, V5 is optimized.

As shown in FIG. 3 , the moving speed of the actuating disk portion 816 is maintained in the interval of V5, which corresponds to the “steady discharge period” shown in FIG. 4(b) . The "steady discharge period" is a period in which the discharge speed (discharge pressure) of the coating liquid from the nozzle 71 is maintained at a substantially constant speed (steady discharge speed). That is, the second optimization step S3 of optimizing V5 corresponds to a step of optimizing parameters corresponding to the constant discharge period.

In addition, among the parameters other than V5, V1 to V4 and T1 to T9 are parameters corresponding to the "rising period" shown in Fig. 4(b). The "rising period" is the period during which the discharge speed increases from zero to a constant discharge speed. The first optimization step S2 of optimizing the parameters V1 to V4 and T1 to T9 corresponds to a step of optimizing the parameters corresponding to the rising period.

＜First optimization (optimization by large area search)＞ FIG. 7 is a flowchart showing details of the first optimization step S2 shown in FIG. 6 . As shown in FIG. 7 , in the first optimization step S2, first, the above-mentioned 16 parameters are set (step S21). The initial value of the parameter is a value generated from a random number, or a value specified by the user. After step S21, the discharge characteristic measuring unit 911 measures the pressure waveform which is the discharge characteristic (step S22). After step S22, the cost value derivation unit 913 derives a cost value based on the measured pressure waveform (step S23).

The cost value represents the evaluation result of the pressure waveform as a numerical value. As will be described later, the cost value derivation unit 913 derives a cost value based on a cost function using a pressure waveform as an input and a cost value as an output. In this embodiment, the cost function is set so that the greater the difference between the pressure waveform (Fig. 4(b)) and the target pressure waveform (Fig. 4(a)), the greater the cost value.

After step S23, it is determined whether the cost value is less than a predetermined threshold value (step S24). When it is determined that the cost value is above the predetermined threshold value (No in step S24), the first optimization unit 915 obtains the next search point (i.e., based on the currently set parameters and the cost value derived in step S23). , new parameters) (step S25). And, after step S25, step S21 is executed again. Thus, the pressure waveform is measured again by performing simulation output based on the next search point, that is, the new parameters (step S22).

On the other hand, in step S24, when it is determined that the cost value is less than the predetermined threshold value (Yes in step S24), the first optimization unit 915 sets the parameter as the optimizer and ends the first optimization process. to step S2.

＜Second Optimization Step (Optimization by Local Search)＞ FIG. 8 is a flowchart showing details of the second optimization step S3 shown in FIG. 6 . When the second optimization step S3 starts, first, the second optimization unit 917 calculates the feature amount Fv from the pressure waveform whose parameters are optimized in the first optimization step S2 (step S31). The procedure for calculating the feature value Fv will be described with reference to FIG. 9 .

FIG. 9 is a diagram showing the pressure waveform after the parameters are optimized in the first optimization step S2. In order to calculate the feature value Fv, the second optimization unit 917 acquires data during the steady discharge period in the pressure waveform. Furthermore, the second optimization unit 917 performs linear regression on the data during the constant discharge period. Through this linear regression, the regression straight line L1 shown in Figure 9 can be obtained. Furthermore, the second optimization unit 917 obtains the pressure Ps at the start time of the constant discharge period and the pressure Pe at the end time of the constant discharge period based on the regression line L1. Furthermore, the second optimization unit 917 calculates the ratio of the pressure Ps to the pressure Pe (=Ps/Pe) as the feature amount Fv. The pressure Ps corresponds to the discharge speed at the beginning of the steady discharge period. The pressure Pe corresponds to the discharge speed at the end of the steady discharge period.

Returning to FIG. 8 , after step S31, the second optimization unit 917 updates V5 (step S32). Specifically, the second optimization unit 917 multiplies the current V5 by the feature amount Fv as a new V5.

After step S32, simulated discharge is performed, and the discharge characteristic measuring unit 911 measures the pressure waveform (step S33). Then, the second optimization unit 917 calculates the feature amount Fv of the pressure waveform obtained in step S33 (step S34). Step S34 is performed in the same sequence as step S31.

After step S34, the second optimization unit 917 determines whether the feature value Fv is within the range of ±α (step S35). Here, "α" is an arbitrarily set decimal. As mentioned above, the steady discharge period is a period in which the coating liquid is discharged at a certain speed, so the pressure Ps at the beginning and the pressure Pe at the end should be consistent. Therefore, in step S35, it is determined whether the current V5 is appropriate by determining whether the feature value Fv is within the range of 1±α.

In step S35, when it is determined that the feature value Fv is within the range of 1±α (Yes in step S35), the second optimization unit 917 selects V5 as the optimizer and ends the second optimization step S3. . On the other hand, in step S35, when it is determined that the feature value Fv is outside the range of 1±α (No in step S35), the second optimization unit 917 Linear regression is performed (step S36).

FIG. 10 is a graph showing the results of linear regression on the feature quantity Fv. In FIG. 10 , the horizontal axis represents V5 and the vertical axis represents the feature amount Fv. The plurality of points (three) shown in FIG. 10 represent the feature value Fv obtained in step S31 or step S34. As shown in FIG. 10 , by performing linear regression on the feature quantity Fv, the regression straight line L2 can be obtained.

Returning to FIG. 8 , after step S36, the second optimization unit 917 updates V5 (step S37). Specifically, the second optimization unit 917 calculates the value of V5 (=V5′) where Fv is 1 based on the regression line L2 obtained in step S36. Then, the second optimization unit 917 updates V5 to the calculated value. And, based on the updated V5, step S33 is executed again. In this way, in the second optimization step S3, steps S33 to S37 are repeatedly executed until the feature value Fv is within the range of 1±α.

As described above, among all the parameters related to the discharge of the coating liquid in the coating device 1 , optimization by local search is applied to the parameter V5 which is relatively easy to optimize. This makes it possible to reduce the amount of calculation compared to the case where optimization by a large area search, such as Bayesian optimization, is applied to all parameters. Therefore, parameter optimization can be performed appropriately and efficiently in the coating device 1 that discharges the coating liquid. In addition, since the number of simulated discharge trials can be reduced, the consumption of coating fluid can be suppressed.

In addition, optimization by local search can also be applied to parameters other than parameter V5.

＜Calculation method of cost value＞ Next, a method of calculating the cost value used for optimization in the first optimization step S2 will be described. The cost value is obtained by calculating characteristic quantities from the pressure waveform for each given evaluation item and adding the characteristic quantities Fv1 to Fv10. The following describes the characteristic quantities Fv1 to Fv10 of each evaluation item.

FIG. 11 is a diagram for explaining each period of the pressure waveform. In FIG. 11 , the horizontal axis represents time and the vertical axis represents discharge pressure. In addition, similarly to each of the subsequent figures in Fig. 11 , the horizontal axis represents time and the vertical axis represents discharge pressure.

As shown in FIG. 11 , the discharge pressure at the time ta when the coating liquid is discharged from the nozzle 71 and the discharge pressure at the time te when the coating liquid is finished being discharged from the nozzle 71 are the initial pressure Pi. However, the pressures at the beginning and end of discharging may not always be consistent with the initial pressure Pi.

As shown in FIG. 11 , the discharge period Tt is divided into a rising period Ta, a transition period Tb, a steady period Tc, and a falling period Td. The rising period Ta is from the time ta when the coating liquid supply mechanism 8 starts discharging the coating liquid from the nozzle 71 (that is, the time ta when the coating liquid supply mechanism 8 starts moving the disk part 816) until the discharge pressure reaches the target pressure Pt. The period of time tb. That is, when the coating liquid starts to be discharged from the nozzle 71 at time ta, the discharge pressure increases from the initial pressure Pi to the target pressure Pt between time ta and time tb.

The transition period Tb is a period from time tb to time tc when a predetermined vibration attenuation period has passed. The vibration attenuation period is a period required for the time change of the discharge pressure to stabilize. For example, it is preset by the user's input operation on the user interface 95 and is stored in the storage unit 93 .

The steady period Tc is a period from time tc to time td when the coating liquid supply mechanism 8 starts reducing the discharge pressure (ie, time td when the coating liquid supply mechanism 8 starts decelerating from the target speed of the actuating plate portion 816 ). That is, from time tc to time td, the coating liquid supply mechanism 8 moves the actuating disk portion 816 at a constant speed (V5 mentioned above), and starts decelerating the actuating disk portion 816 at time td. In addition, during the steady period Tc, the discharge pressure is basically stabilized at the target pressure Pt. However, even in the steady period Tc, the time change of the discharge pressure includes minute vibrations. Therefore, during the steady period Tc, the discharge pressure is larger or smaller than the target pressure Pt.

The transition period Tb and the steady period Tc constitute a constant voltage period Tbc. That is, the constant pressure period Tbc is a period from time tb to time td.

The descending period Td is a period from time td to time te when the coating liquid supply mechanism 8 ends discharging the coating liquid from the nozzle 71 (that is, time te when the coating liquid supply mechanism 8 stops the actuating plate portion 816). That is, the discharge pressure decreases to the initial pressure Pi between time td and time te, and at time te, the discharge of the coating liquid from the nozzle 71 is stopped.

FIG. 12 is a diagram schematically showing an example of the operation performed by the cost value derivation unit 913 on the pressure waveform. As shown in FIG. 12 , the cost value derivation unit 913 calculates the first differential D1 of the pressure waveform by temporally differentiating the pressure waveform. Furthermore, the cost value derivation unit 913 differentiates the first differential D1 of the time change of the discharge pressure with time to calculate the second derivative D2 of the time change of the discharge pressure. Furthermore, the cost value derivation unit 913 calculates the mean absolute error MAE and the root mean square error RMSE based on the following formulas. MEA(α,β)=(1/n)・(∑|α-β|) RMSE(α,β)=((1/n)・(∑(α-β)2))1/2 n is the number of data.

FIG. 13 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv1. In the evaluation items shown in FIG. 13 , errors based on the trapezoidal waveform having an amplitude corresponding to the difference between the average discharge pressure in the steady period Tc (that is, the steady pressure Pm) and the initial pressure Pi and the actual pressure waveform (ideal trapezoidal absolute error) to evaluate the pressure waveform.

Specifically, during the rise period Ta, a linear regression analysis is performed on the time change of the discharge pressure between a predetermined lower reference pressure and a predetermined upper reference pressure greater than the lower reference pressure, and the rise regression is calculated. Straight line Lr_R. Between time t11 and time t12, the rising regression line Lr_R linearly increases from the initial pressure Pi to the steady pressure Pm.

Similarly, during the decrease period Td, linear regression analysis is performed on the time change of the discharge pressure between the upper reference pressure and the lower reference pressure, and the decrease regression straight line Lr_F is calculated. Between time t13 and time t14, the descending regression line Lr_F linearly decreases from the steady pressure Pm to the initial pressure Pi.

In addition, the lower reference pressure and the upper reference pressure are larger than the initial pressure Pi and smaller than the target pressure Pt. For example, they are set by the user's input operation on the user interface 95 and are stored in the storage unit 93 . For example, the lower reference pressure may be a pressure obtained by adding 20% of the absolute value of the difference between the initial pressure Pi and the target pressure Pt to the initial pressure Pi. In addition, the upper reference pressure may be a pressure obtained by adding 80% of the absolute value of the difference between the initial pressure Pi and the target pressure Pt to the initial pressure Pi.

Furthermore, for the interval from time ta to time t11, a starting approximate straight line Lr_s is set. The initial approximate straight line Lr_s is a straight line representing the initial pressure Pi with a slope of zero. That is, the initial approximate straight line Lr_s is a straight line connecting the discharge start time point (time ta) when the coating liquid is discharged from the nozzle 71 to the start time point of the rising regression straight line Lr_R. In addition, depending on the state (slope) of the regression line, time t11 may be further forward than time ta, and time t12 may be later than time tb. In this way, in the case of t11<ta, the approximate straight line Lr_s at the beginning is omitted.

Furthermore, for the interval from time t14 to time te, the end approximation straight line Lr_e is set. The end-time approximate straight line Lr_e is a straight line indicating that the slope of the initial pressure Pi is zero. That is, the end approximation straight line Lr_e is a straight line connecting the end time point of the descending regression line Lr_F to the end time point (time te) of stopping the discharge of the coating liquid from the nozzle 71 . In addition, in the case of te<t14, the end approximation straight line Lr_e is omitted.

Furthermore, a constant straight line Lr_m is set for the interval from time t12 to time t13. This steady straight line Lr_m is a straight line with a slope of zero indicating the steady pressure Pm. That is, the steady straight line Lr_m is a straight line representing the steady pressure Pm, and connects the end time point (time t12) of the rising regression straight line Lr_R and the starting time point (time t13) of the falling regression straight line Lr_F.

As described above, the cost value derivation unit 913 calculates the approximate waveform WF1 composed of the start approximate straight line Lr_s, the rising regression straight line Lr_R, the steady straight line Lr_m, the falling regression straight line Lr_F, and the ending approximate straight line Lr_e arranged in time series. Then, during the entire discharge period Tt from time ta to time te, the cost value derivation unit 913 calculates the mean absolute error MAE (ideal trapezoidal absolute error) between the pressure value of the pressure waveform and the approximate waveform WF1 as the feature amount Fv1. The cost value derivation unit 913 stores the calculated feature amount Fv1 in the storage unit 93 .

According to the evaluation based on the characteristic amount Fv1, when the time change of the discharge pressure in the entire discharge period Tt greatly deviates from the ideal shape (i.e., trapezoidal shape), a large score (i.e., negative evaluation) can be given to the discharge pressure ).

FIG. 14 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv2. In the evaluation item of Fig. 14, the smoothness of the increase in discharge pressure is evaluated. Specifically, during the rising period Ta, curve regression analysis is performed on the time change in the discharge pressure between the lower reference pressure P2_l and the upper reference pressure P2_u which is greater than the lower reference pressure P2_l, and the rising regression curve Nr is calculated. The curve regression analysis is performed using a quadratic curve.

The lower reference pressure P2_l is set as the initial pressure Pi. In addition, the upper reference pressure P2_u is a pressure greater than the lower reference pressure P2_l and smaller than the target pressure Pt. The upper reference pressure P2_u is set, for example, by the user's input operation on the user interface 95, and is stored in the storage unit 93. The upper reference pressure P2_u may be a pressure obtained by adding 20% of the absolute value of the difference between the initial pressure Pi and the target pressure Pt to the initial pressure Pi. Between time t21 and time t22, the rising regression curve Nr increases from the lower reference pressure P2_l (initial pressure Pi) to the upper reference pressure P2_u. In addition, time t21 coincides with time ta, and time t22 is a time later than time ta and earlier than time tb.

The cost value derivation unit 913 calculates the waveform WF2 composed of the rising regression curve Nr. Then, the cost value derivation unit 913 calculates the root mean square error RMSE between the pressure value of the measured pressure waveform and the waveform WF2 as the feature amount Fv2 during the initial rise period Ta_s from time t21 to time t22. Furthermore, the cost value derivation unit 913 stores the calculated feature amount Fv2 in the storage unit 93 .

Based on the evaluation based on the characteristic amount Fv2, when the discharge pressure immediately after the start of discharge is abnormal due to the influence of the state of the coating liquid from the nozzle 71 before the start of discharge, a larger score can be given to the discharge pressure (i.e., , negative evaluation). In addition, the curves that can be used for curve regression analysis are not limited to quadratic curves, but can also be other curves such as exponential functions.

FIG. 15 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv3. In the evaluation item in Figure 15, it is evaluated whether the rising period Ta converges within a certain period. Specifically, the cost value derivation unit 913 calculates the length of the rising period Ta (=tb-ta) from time ta to time tb required for the discharge pressure to increase from the initial pressure Pi to the target pressure Pt as the feature amount Fv3. Furthermore, the cost value derivation unit 913 stores the calculated feature amount Fv3 in the storage unit 93 .

Based on the evaluation based on the characteristic amount Fv3, a larger score (ie, a negative evaluation) can be given to the discharge pressure in which the rising period to reach the target pressure Pt is shorter or longer than a predetermined certain period.

FIG. 16 is a diagram for explaining the feature value Fv4. FIG. 16(A) is a diagram illustrating evaluation items for evaluating the time change of the discharge pressure based on the characteristic amount Fv4. FIG. 16(B) is a diagram showing an example of time change of the discharge pressure determined to be inappropriate by evaluation based on the characteristic amount Fv4. In the evaluation item shown in Figure 16(A), it is evaluated whether there is any abnormality in the increase in discharge pressure.

Specifically, the cost value derivation unit 913 calculates the first differential D1 of the time change of the discharge pressure for the rising period Ta from time ta to time tb, and obtains the first differential waveform WF4. Furthermore, the cost value derivation unit 913 determines the number of times the primary differential waveform WF4 crosses the predetermined threshold value Th4 during the rising period Ta as the feature amount Fv4. In the example of FIG. 16(A) , the first-order differential waveform WF4 intersects with the threshold value Th4 (for example, 0.002) at time t41 and time t42 respectively, and the number of intersections (feature amount Fv4) is two. The cost value derivation unit 913 stores the calculated feature amount Fv4 in the storage unit 93 .

According to the evaluation based on the characteristic amount Fv4, when the time change of the discharge pressure during the rising period Ta occurs in a stage (for example, FIG. 16(B) ), a large score can be given to the discharge pressure (that is, a negative evaluation).

FIG. 17 is a diagram for explaining the feature amount Fv5. FIG. 17(A) is a diagram illustrating evaluation items for evaluating temporal changes in discharge pressure based on the characteristic amount Fv5. FIG. 17(B) is a diagram showing an example of time change of the discharge pressure determined to be inappropriate by evaluation based on the characteristic amount Fv5. In the evaluation item shown in Figure 17(A), it is evaluated whether there is any abnormality in the increase in discharge pressure.

Specifically, the cost value derivation unit 913 calculates the second differential D2 of the time change of the discharge pressure for the rising period Ta from time ta to time tb, and obtains the second differential waveform WF5. Furthermore, the cost value derivation unit 913 determines the number of times the absolute value of the secondary differential waveform WF5 crosses the predetermined threshold value Th5 during the rising period Ta as the characteristic amount Fv5. In the example of FIG. 17(A) , the absolute value of the second-order differential waveform WF5 intersects with the threshold value Th5 (for example, 0.0002) at each of times t51, t52, t53, and t54, and the number of intersections (feature amount Fv5) is 4 times. The cost value derivation unit 913 stores the calculated feature amount Fv5 in the storage unit 93 .

Based on the evaluation based on the characteristic amount Fv5, when the time change of the discharge pressure during the rising period Ta generates a stage (for example, as shown in Fig. 17(B)), a large score can be given to the discharge pressure (that is, a negative evaluate).

FIG. 18 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv6. In the evaluation item in Figure 18, it is evaluated whether the increase in discharge pressure stalls in the second half. Specifically, the cost value derivation unit 913 calculates the second differential D2 of the time change of the discharge pressure for the rising period Ta from time ta to time tb, and obtains the second differential waveform WF6.

In addition, the cost value derivation unit 913 respectively obtains the time T_1st when the secondary differential waveform WF6 is larger than the predetermined positive threshold value (Th5) during the rising period Ta, and the time when the secondary differential waveform WF6 is larger than the predetermined negative threshold value (Th5). -Th5) smaller time T_2nd. Here, the positive threshold value and the negative threshold value have the same absolute value (Th5), but have different signs. The absolute value (Th5) of the positive threshold value and the negative threshold value is equal to the threshold value Th5 used in the evaluation of the above-mentioned feature quantity Fv5. Then, the cost value derivation unit 913 obtains the ratio of these times (=T_1st/T_2nd) as the feature amount Fv6. Furthermore, the cost value derivation unit 913 converts the feature value Fv6 based on the following equation. Fv6=|1-Fv6| The cost value derivation unit 913 stores the converted feature amount Fv6 in the storage unit 93 .

The conveyance speed of the substrate S to be coated with the coating liquid reaches the target speed without stalling in the second half of the acceleration period. Therefore, it is preferable that the discharge pressure applied to the coating liquid reaches the target pressure Pt without stalling during the rising period Ta. According to the evaluation based on the characteristic amount Fv6, when the discharge pressure Ta stalls during the rising period, a large score can be given to the discharge pressure (that is, a negative evaluation).

FIG. 19 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv7. In the evaluation item of Figure 19, the sharpness of the time change of the discharge pressure at the end of the rise is evaluated. Specifically, during the rising period Ta, linear regression analysis is performed on the time change in the discharge pressure between the lower reference pressure P7_l and the upper reference pressure P7_u which is greater than the lower reference pressure P7_l, and the rising regression straight line Lr is calculated. Here, the lower reference pressure P7_l is a pressure obtained by adding 80% of the absolute value of the difference between the initial pressure Pi and the target pressure Pt to the initial pressure Pi, and the upper reference pressure P7_u is a pressure obtained by adding the initial pressure Pi and the target pressure Pt The discharge pressure increases from the lower reference pressure P7_l to the upper reference pressure P7_u between time t71 and time t72, which is a pressure obtained by adding 90% of the absolute value of the difference to the initial pressure Pi.

This rising terminal regression line Lr increases as time passes, and reaches the steady pressure Pm (the average value of the discharge pressure during the steady period Tc) at time t73. In this way, the rising end regression straight line Lr is set for the interval from time t71 to time t73. Furthermore, the cost value derivation unit 913 sets an extended straight line Lm with a slope of zero indicating the constant pressure Pm between time t73 and time tb. As mentioned above, time tb is the time when the discharge pressure reaches the target pressure Pt, and corresponds to the end time of the rising period Ta. That is, the extended straight line Lm is set so as to extend from the end time point of the rise terminal regression straight line Lr to the end time point of the rise period Ta. In addition, when tb<t73, the extended straight line Lm is omitted.

As described above, the approximate waveform WF7 composed of the ascending terminal regression straight line Lr and the extended straight line Lm arranged in time series is calculated. Furthermore, the cost value derivation unit 913 calculates the difference between the pressure value P_measure indicating the pressure waveform and the approximate waveform WF7 in the rising end period Ta_e between the time t72 when the discharge pressure is 90% of the target pressure Pt and the time tb when it is 100%. The value is used as the feature quantity Fv7. Specifically, the weighted reference time width Tw=t73-t72 is set. And, the weighted root mean square error sum is calculated based on the following equation. Fv7=(∑(P_measure-WF7) ² ×W) ^1/2 W=1 in the range of time t≤t73+2×Tw W=w in the range of time t≤t73+2×Tw w is greater than 1 Weighting factor, for example 10.

The cost value derivation unit 913 stores the calculated feature amount Fv7 in the storage unit 93 . According to the evaluation based on the characteristic amount Fv7, when the time change of the discharge pressure shows a weak upward trend and a waveform with rounded edges, a large score can be given to the discharge pressure (that is, a negative evaluation).

FIG. 20 is a diagram illustrating an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv8. In the evaluation item of Fig. 20, the degree of overshoot that occurs when the discharge pressure rises is evaluated. Specifically, the cost value derivation unit 913 obtains the sign (positive/negative) of the second derivative D2 of the discharge pressure at time t81 when the discharge pressure reaches the maximum value Pmax. Furthermore, the cost value derivation unit 913 calculates time t82 when the sign of the second order differential D2 of the discharge pressure switches twice from the sign at time t81. Furthermore, the time change of the discharge pressure in the initial vibration period Tb_s from time t81 to time t82 is evaluated.

Specifically, the minimum value P8min of the time change of the discharge pressure during the initial vibration period Tb_s is found, and the smaller pressure among the steady pressure Pm and the pressure P8min is selected as the target pressure Pg. Then, based on the following equation, the difference between the maximum pressure Pmax and the target pressure Pg, that is, the characteristic amount Fv8 is calculated. Fv8=Pmax-Pg

The cost value derivation unit 913 stores the calculated feature amount Fv8 in the storage unit 93 . According to the evaluation based on the characteristic quantity Fv8, when the time change of the discharge pressure shows a strong upward trend and a large overshoot, a large score can be given to the discharge pressure (ie, a negative evaluation).

FIG. 21 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv9. In the evaluation item of Fig. 21, the stability of the time change of the discharge pressure Tb during the transition period is evaluated. Specifically, the cost value derivation unit 913 calculates the root mean square error RMSE (P_measure, Pm) as the feature amount Fv9 based on the following equation with respect to the steady pressure Pm, which is the average value of the discharge pressure in the transition period Tb and the discharge pressure in the steady period Tc. . Fv9=RMSE(P_measure,Pm)

The cost value derivation unit 913 stores the calculated feature amount Fv9 in the storage unit 93 . According to the evaluation based on the feature amount Fv9, if the time change of the discharge pressure shows ringing during the transition period Tb, a large score can be given to the discharge pressure (that is, a negative evaluation).

FIG. 22 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv10. In the evaluation item shown in Fig. 22, the stability of the time change of the discharge pressure in Tbc during the constant pressure period is evaluated. Specifically, the cost value derivation unit 913 obtains the maximum value Pmax and the minimum value P10min of the discharge pressure during the constant pressure period Tbc. Furthermore, the cost value derivation unit 913 calculates the difference between the maximum pressure Pmax and the minimum pressure P10min during the constant pressure period Tbc, that is, the characteristic amount Fv10. Fv10=Pmax-P10min

The cost value derivation unit 913 stores the calculated feature amount Fv10 in the storage unit 93 . According to the evaluation based on the characteristic amount Fv10, in the case where the time change of the discharge pressure shows a large deviation in the steady period Tc which has a large influence on the film thickness of the coating liquid, a large score can be assigned to the discharge pressure. (i.e., negative evaluation).

The cost value derivation unit 913 derives the sum of the feature quantities Fv1 to Fv10 as a cost value. However, the cost value derivation unit 913 may weight each of the feature quantities Fv1 to Fv10. That is, the cost value derivation unit 913 may derive the weighted sum of the feature quantities Fv1 to Fv10 as the cost value.

In addition, the above-mentioned feature values Fv1 to Fv10 are examples. Therefore, other characteristic quantities can also be used in the calculation of cost values. In addition, part of the feature quantities Fv1 to Fv10 can also be used for calculation of the cost value.

Although the invention has been described in detail, the above description is an illustration in every case and the invention is not limited thereto. It should be understood that numerous modifications that are not illustrated can be deduced without departing from the scope of the invention. The components described in the above embodiments and modifications may be appropriately combined or omitted as long as they do not conflict with each other.

1: Coating device (substrate processing device) 2: Input transfer part 3: Floating platform part 4:Output transfer part 5:Substrate transport department 7: Coating mechanism 8: Coating liquid supply mechanism 9:Control unit 13. 811: Flexible tube 21, 41, 101, 111: Roller conveyor 22: Rotation and lifting drive mechanism 31: Entrance floating platform 32: Coating platform 33: Exit floating platform 34: Lift pin driving mechanism 35: Floating control mechanism 36:Lifting drive mechanism 42: Rotation and lifting drive mechanism 51:Chuck mechanism 52: Adsorption and migration control mechanism 61, 62: Sensor 71:Nozzle 72: Nozzle cleaning standby unit 81:Pump 82, 84: Piping 83: Coating fluid replenishment unit 85, 833: Open and close valve 86: Pressure gauge 87:Drive Department 91:Operation Department 93:Storage Department 95:User interface 100:Input conveyor 102, 112: Rotary drive mechanism 110:Output conveyor 721:Roller 722:Cleaning Department 723:Roller groove 812: Bellows 813:Small bellows department 814:Large corrugated pipe department 815:Pump room 816: Actuator plate 831:Storage tank 910: Discharge control unit 911: Discharge characteristics measurement department 913: Cost value derivation department (cost value calculation department) 915: 1st Optimization Department 917:Second Optimization Department 931:Program D1: 1st differential D2: 2nd derivative EL:organic Fv, Fv1～Fv10: feature amount L1, L2: Regression straight line Lm: extended straight line Lr: rising regression line (regression line at the end of rising period) Lr_e: Approximate straight line at the end Lr_F: Descending regression line Lr_m: steady straight line Lr_R: rising regression line Lr_s: approximate straight line at the beginning M: recording medium Nr: rising regression curve P2_l, P7_l: Lower side reference pressure P2_u, P7_u: Upper side reference pressure P8min, P10min: minimum value (of pressure) Pmax: (the maximum value of pressure) Pe, Ps: pressure Pi: initial pressure Pm: steady pressure Pt: target pressure S:Substrate Sb: lower surface Sf: upper surface T1, T3, T5, T7, T9: acceleration time T2, T4, T6, T8, T10: constant speed time T11: deceleration time t11, t12, t13, t14, t21, t22, t41, t42, t51, t52, t53, t54, t71, t72, t73, t81, t82, ta, tb, tc, td, te: time Ta: rising period Ta_e: During the final period of rising Ta_s: Early rising period Tb: transitional period Tbc: During constant pressure period Tb_s: initial vibration period Tc: steady period Td: falling period Th4, Th5: threshold value Tt: spitting period Tw: weighted base time width T_1st, T_2nd: time V1, V2, V3, V4, V5: steady speed V5＇:value WF1, WF7: Approximate waveform WF2: Waveform WF4: 1st differential waveform WF5, WF6: 2nd differential waveform

FIG. 1 is a diagram schematically showing the overall structure of the coating device according to the embodiment. FIG. 2 is a diagram showing the structure of the coating liquid supply mechanism. FIG. 3 is a line diagram showing the movement pattern of the actuating disk portion of the pump shown in FIG. 2 . Figures 4(a) and (b) are graphs showing discharge characteristics. FIG. 5 is a block diagram showing an example of the structure of the control unit. Figure 6 is a flowchart showing the parameter optimization process performed in the coating device. FIG. 7 is a flowchart showing details of the first optimization step shown in FIG. 6 . FIG. 8 is a flowchart showing details of the second optimization step shown in FIG. 6 . FIG. 9 is a diagram showing the pressure waveform after the parameters are optimized in the first optimization step. FIG. 10 is a graph showing the results of linear regression on the feature quantity Fv. FIG. 11 is a diagram for explaining each period of the pressure waveform. FIG. 12 is a diagram schematically showing an example of the operation performed by the cost value derivation unit on the pressure waveform. FIG. 13 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv1. FIG. 14 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv2. FIG. 15 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv3. 16(A) and (B) are diagrams for explaining the feature amount Fv4. 17(A) and (B) are diagrams for explaining the feature amount Fv5. FIG. 18 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv6. FIG. 19 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv7. FIG. 20 is a diagram illustrating an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv8. FIG. 21 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv9. FIG. 22 is a diagram for explaining an evaluation item for evaluating the time change of the discharge pressure based on the characteristic amount Fv10.

1: Coating device (substrate processing device)

9:Control unit

81:Pump

86: Pressure gauge

91:Operation Department

93:Storage Department

95:User interface

910: Discharge control unit

911: Discharge characteristics measurement department

913: Cost value calculation department (cost value calculation department)

915: 1st Optimization Department

917:Second Optimization Department

931:Program

M: recording medium

Claims (9)

A parameter optimization method that optimizes parameters for controlling the discharge of the processing liquid in a substrate processing apparatus that supplies the processing liquid discharged from a nozzle to a substrate; This parameter optimization method includes: a) a first optimization step that optimizes the first parameter through a large area search; and b) a second optimization step, which optimizes the second parameter through local search; The first parameter includes a parameter corresponding to a rising period during which the discharge speed of the treatment liquid from the nozzle increases to a constant discharge speed, The second parameter includes a parameter corresponding to a constant discharge period in which the discharge speed is maintained at the constant discharge speed. For example, the parameter optimization method of request item 1, where, The aforementioned step b) is performed after the aforementioned step a). For example, the parameter optimization method of request item 1, where, The first optimization step includes a step of optimizing the first parameter through Bayesian optimization. Such as requesting a parameter optimization method for any one of items 1 to 3, where, The aforementioned parameter is a control amount that controls the operation of the pump that supplies the aforementioned treatment liquid to the aforementioned nozzle. Such as requesting a parameter optimization method for any one of items 1 to 3, where, The step a) includes the step of optimizing the first parameter based on a cost value derived from a characteristic amount of the discharge characteristics when the treatment liquid is discharged from the nozzle. Such as requesting a parameter optimization method for any one of items 1 to 3, where, The step b) includes the step of optimizing the second parameter based on the ratio of the discharge speed at the beginning of the steady discharge period and the discharge speed at the end of the steady discharge period. A program for optimizing computer execution parameters for controlling the discharge of treatment liquid from the nozzle; This program causes the aforementioned computer to execute: a) a first optimization step, which optimizes the first parameter through a large area search; and b) the second optimization step, which optimizes the second parameter through local search; The first parameter includes a parameter corresponding to a rising period during which the discharge speed of the treatment liquid from the nozzle increases to a constant discharge speed, The second parameter includes a parameter corresponding to a constant discharge period in which the discharge speed is maintained at the constant discharge speed. A computer-readable recording medium on which the program of claim 7 is recorded. A substrate processing device that supplies processing liquid discharged from a nozzle to a substrate; it has: a discharge control unit that controls the discharge of the processing liquid from the nozzle based on a plurality of parameters including a first parameter and a second parameter; a discharge characteristic measuring unit that measures the discharge characteristics when the nozzle discharges the treatment liquid; a first optimization unit that optimizes the first parameter through a large area search based on the aforementioned discharge characteristics; and a second optimization unit that optimizes the aforementioned second parameter through local search based on the aforementioned discharge characteristics; The first parameter includes a parameter corresponding to a rising period during which the discharge speed of the treatment liquid from the nozzle increases to a constant discharge speed, The second parameter includes a parameter corresponding to a constant discharge period in which the discharge speed is maintained at the constant discharge speed.