Discharge pressure monitoring device, discharge pressure monitoring method, computer program, and coating device

Abstract

To provide a technology capable of appropriately detecting unknown abnormalities in discharge pressure that have not been anticipated in advance.SOLUTION: A discharge pressure measuring unit 911 acquires pressure data. A feature amount calculation unit 913 calculates a feature amount of pressure data. An abnormality level calculation unit 915 uses an unsupervised learning model M1, which takes the feature amount as input and outputs an abnormality level indicating the degree of deviation from the distribution of normal feature amounts, to calculate the abnormality level for the feature amount calculated by the feature calculation unit 913. An abnormality probability calculation unit 917 uses a supervised learning model M2, which takes the feature amount as input and outputs an abnormality probability indicating the probability corresponding to a specific abnormality A or B, to calculate an abnormality probability for the feature amount calculated by the feature calculation unit 913. An abnormality determination unit 919 determines whether the pressure data is abnormal by using the abnormality level calculated by the abnormality level calculation unit 915 and the abnormality probability calculated by the abnormality probability calculation unit 917 .SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The subject matter disclosed herein relates to a discharge pressure monitoring device, a discharge pressure monitoring method, a computer program, and a coating device. [Background technology]

[0002] In the manufacturing process of flat panel displays, a device called a coater is used. The coater discharges a processing liquid from a slit nozzle by driving a pump, coating the processing liquid over the entire substrate being transported. With the recent trend toward higher product quality, such coaters are required to apply the processing liquid so that the film thickness of the processing liquid is uniform over the entire substrate. In order to maintain a constant film thickness uniformity, it is considered important to monitor the discharge pressure (discharge flow rate) of the processing liquid during production. For example, Patent Document 1 attempts to optimize parameters related to the discharge pressure.

[0003] However, it is difficult to detect minute changes in the discharge pressure obtained from a pressure sensor using a simple threshold. To address this issue, many techniques and systems for detecting anomalies using machine learning have been proposed.

[0004] For example, Patent Document 2 proposes building a system that can determine the type (mode) of abnormality from given sensor information. Building such a system not only makes it possible to plan specific countermeasures such as part replacement, but also allows the system to function as a failure prediction system that can detect minor changes (signs) that could potentially develop into a breakdown. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2020-040046 [Patent Document 2] Japanese Patent Publication No. 2022-125288 Summary of the Invention [Problem to be solved by the invention]

[0006] Patent Document 2 proposes a method using unsupervised learning and a method using supervised learning as a system for predicting failures. However, unsupervised learning is a method of learning data of normal states and evaluating the degree of deviation of newly measured data from the normal state, so although it is possible to detect anomalies, it is not possible to determine the type of anomaly. Furthermore, supervised learning is capable of determining the type of anomaly by learning from training data that has been pre-labeled with the type of anomaly, but it is unable to respond to unknown anomalies because any anomaly is classified into a type of anomaly that has been pre-assumed during learning.

[0007] An object of the present invention is to provide a technique capable of appropriately detecting unknown abnormalities in discharge pressure that have not been anticipated in advance. [Means for solving the problem]

[0008] In order to solve the above problem, the first aspect is A coating apparatus comprising: a substrate holding unit that holds a substrate; a nozzle that ejects a processing liquid toward the substrate held by the substrate holding unit; and a pressure sensor that measures a pressure inside the nozzle. Discharge pressure monitoring device and , The discharge pressure monitoring device is Pressure data showing the time change of pressure inside the nozzle The pressure sensoran anomaly probability calculation unit that calculates the anomaly probability for the feature calculated by the feature calculation unit using a supervised learning model that takes the feature as an input and outputs an anomaly probability that indicates the degree of deviation from a normal distribution of the feature; an anomaly probability calculation unit that calculates the anomaly probability for the feature calculated by the feature calculation unit using a supervised learning model that takes the feature as an input and outputs an anomaly probability that indicates the probability that the pressure data corresponds to a specific anomaly; and an anomaly determination unit that obtains the anomaly degree calculated by the anomaly degree calculation unit and the anomaly probability calculated by the anomaly probability calculation unit, and determines whether the pressure data is normal, an anomaly close to a normal distribution, an unknown anomaly, or an anomaly based on a comparison of the anomaly degree and the anomaly probability with a threshold value. the characteristic amount is the degree of overshoot that occurs during a rise period of the ejection pressure, which is a period from the time when the ejection of the treatment liquid from the nozzle starts to the time when the ejection pressure reaches a target pressure. .

[0009] The second aspect is the same as the first aspect. Coating The unsupervised learning model is a model obtained by unsupervised learning using, as input data, feature quantities of only the plurality of normal pressure data.

[0010] The third aspect is the first or second aspect Coating In the apparatus, the unsupervised learning model outputs a Mahalanobis distance as the degree of anomaly.

[0011] The fourth aspect is the first or second aspect Coating In the apparatus, the supervised learning model outputs probabilities of multiple types of specific anomalies.

[0012] The fifth aspect is A coating apparatus comprising: a substrate holding unit that holds a substrate; a nozzle that ejects a processing liquid toward the substrate held by the substrate holding unit; and a pressure sensor that measures a pressure inside the nozzle. Discharge pressure monitoring device and , The discharge pressure monitoring device is Pressure data showing the time change of pressure inside the nozzle The pressure sensoran anomaly probability calculation unit that uses the feature amount as an input and calculates the anomaly probability for the feature amount calculated by the feature amount calculation unit using a supervised learning model that outputs an anomaly probability that indicates the probability that the pressure data corresponds to a specific anomaly; and an anomaly determination unit that obtains the anomaly degree calculated by the anomaly degree calculation unit and the anomaly probability calculated by the anomaly probability calculation unit, and determines whether the pressure data is normal, an anomaly close to a normal distribution, an unknown anomaly, or an anomaly based on a comparison of the anomaly degree and the anomaly probability with a threshold value. the characteristic amount is the degree of overshoot that occurs during a rise period of the ejection pressure, which is a period from the time when the ejection of the treatment liquid from the nozzle starts to the time when the ejection pressure reaches a target pressure. . [Effects of the Invention]

[0017] First to second aspects 5 According to this aspect, when a previously anticipated abnormality is determined, the abnormality can be determined by calculating the abnormality probability. Furthermore, even when an unknown abnormality that has not been previously anticipated occurs, the unknown abnormality can be appropriately detected by calculating the abnormality degree.

[0018] The second aspect Coating According to the device, only the distribution of normal features can be learned, so that anomalies can be detected appropriately.

[0019] The third aspect Coating The device can calculate the degree of abnormality by taking into account the correlation between each dimension of the feature values ​​indicated by the pressure data, thereby enabling more accurate detection of characteristic patterns and abnormal behavior in the pressure data.

[0020] The fourth aspect Coating The device can calculate the probability of multiple types of specific abnormalities, making it possible to determine whether pressure data corresponds to any of multiple types of abnormalities. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a diagram schematically illustrating an overall configuration of a coating apparatus according to an embodiment. [Figure 2] FIG. 2 is a diagram showing the configuration of a coating liquid supply mechanism. [Figure 3] FIG. 4 is a diagram showing a pressure waveform of a discharge pressure. [Figure 4] FIG. 2 is a block diagram showing an example of the configuration of a control unit. [Figure 5] FIG. 10 is a diagram illustrating an example of a feature amount. [Figure 6] FIG. 10 is a diagram for explaining another example of feature amounts. [Figure 7] FIG. 1 is a block diagram showing a control unit that performs machine learning. [Figure 8] FIG. 10 is a diagram showing the flow of machine learning processing executed by the control unit. [Figure 9] FIG. 10 is a block diagram showing a control unit that monitors abnormalities in pressure data. [Figure 10] FIG. 10 is a diagram showing a flow of a monitoring process for monitoring a discharge pressure executed by a control unit. [Figure 11] FIG. 10 is a diagram conceptually showing how the degree of abnormality (Mahalanobis distance) is calculated. [Figure 12] FIG. 10 is a diagram conceptually illustrating the output of an abnormality probability calculation unit. [Figure 13] FIG. 10 is a diagram conceptually illustrating an example of comprehensive determination of an abnormality using an abnormality degree and an abnormality probability. DETAILED DESCRIPTION OF THE INVENTION

[0022] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. Note that the components described in the embodiment are merely examples and are not intended to limit the scope of the present invention. In the drawings, the dimensions and numbers of each part may be exaggerated or simplified as necessary to facilitate understanding.

[0023] FIG. 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 applies a coating liquid to the upper surface Sf of a substrate S. The substrate S is, for example, a glass substrate for a liquid crystal display device. 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 or optical disk, a glass substrate for an organic EL display, a glass or silicon substrate for a solar cell, or various other substrates to be processed for electronic devices such as flexible substrates and printed circuit boards. The coating apparatus 1 is, for example, a slit coater.

[0024] In FIG. 1, an XYZ coordinate system is defined to explain the positional relationship of each element of the coating apparatus 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.

[0025] The coating apparatus 1 includes, 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 apparatus 1 also includes a substrate transport unit 5, a coating mechanism 7, a coating liquid supply mechanism 8, and a control unit 9.

[0026] The substrate S is transported to the input conveyor 100 from a device upstream of the coating device 1. 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. Due to the rotation of each roller of the roller conveyor 101, the substrate S is transported downstream (+X direction) in a horizontal position. The "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).

[0027] The input transfer section 2 is equipped with a roller conveyor 21 and a rotation / 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. The rotation of the roller conveyor 21 transports the substrate S downstream (+X direction) in a horizontal position. The elevation of the roller conveyor 21 also changes the position of the substrate S in the Z direction. The substrate S is transferred from the input conveyor 100 to the floating stage section 3 via the input transfer section 2.

[0028] As shown in FIG. 1 , the floating stage unit 3 is substantially flat. The floating stage unit 3 is divided into three sections along the X direction. The floating stage unit 3 includes, in order along the +X direction, an entrance floating stage 31, a coating stage 32, and an exit floating stage 33. The upper surfaces of the entrance floating stage 31, the coating stage 32, and the exit floating stage 33 are on the same plane. The floating stage unit 3 further includes a lift pin drive mechanism 34, a floating 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 floating stage 31. The floating control mechanism 35 supplies compressed air to the entrance floating stage 31, the coating stage 32, and the exit floating stage 33 to float the substrate S. The elevation drive mechanism 36 raises and lowers the exit floating stage 33.

[0029] A large number of nozzle holes for ejecting 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 ejected from each nozzle hole, the substrate S is levitated upward relative to the levitation stage part 3. Then, the lower surface Sb of the substrate S is supported in a horizontal position while being spaced apart from the upper surface of the levitation stage part 3. When the substrate S is in a levitated state, the distance (levitation amount) between the lower surface Sb of the substrate S and the upper surface of the levitation stage part 3 is, for example, 10 μm or more and 500 μm or less.

[0030] On the upper surface of the coating stage 32, jet holes for ejecting compressed air supplied from the levitation control mechanism 35 and suction holes for sucking gas are alternately arranged 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 through 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 becomes 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 a sensor 61 or a sensor 62, which will be described later. Preferably, the amount of levitation of the substrate S relative to the coating stage 32 can be adjusted with high precision by airflow control.

[0031] The substrate S carried into the floating stage unit 3 is imparted with a propulsive force in the +X direction by the roller conveyor 21, and is transported onto the entrance floating stage 31. The entrance floating stage 31, the coating stage 32, and the exit floating stage 33 support the substrate S in a floating state. For example, the configuration described in Japanese Patent No. 5346643 may be adopted as the floating stage unit 3.

[0032] The substrate transport unit 5 is disposed below the floating stage unit 3. The substrate transport unit 5 includes a chuck mechanism 51 and a suction / travel control mechanism 52. The chuck mechanism 51 includes a suction pad (not shown) provided on 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.

[0033] The chuck mechanism 51 holds the substrate S in a state where the lower surface Sb of the substrate S is positioned higher than the upper surface of the floating stage part 3. With the peripheral edge of the substrate S held by the chuck mechanism 51, the buoyancy applied by the floating stage part 3 keeps the substrate S in a horizontal position.

[0034] 1, the coating device 1 is equipped with a sensor 61 for measuring plate thickness. The sensor 61 is disposed 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. In addition, a chuck (not shown) that is not holding the substrate S is positioned directly below the sensor 61, so that 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.

[0035] The chuck mechanism 51 moves in the +X direction while holding the substrate S that has been carried into the floating stage section 3. As a result, the substrate S is transported from above the entrance floating stage 31, via above the coating stage 32, to above the exit floating stage 33. Then, the substrate S is moved from the exit floating stage 33 to the output transfer section 4.

[0036] 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 also 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 rises and falls, the substrate S is displaced in the Z direction.

[0037] 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 the rotation of each roller of the roller conveyor 111, and delivers the substrate S to the outside of the coating apparatus 1. The input conveyor 100 and the output conveyor 110 are part of the coating apparatus 1. However, the input conveyor 100 and the output conveyor 110 may be incorporated into a device separate from the coating apparatus 1.

[0038] The coating mechanism 7 coats the upper surface Sf of the substrate S with a coating 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 having a slit-shaped outlet on its lower surface. 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 FIG. 1) and a maintenance position, which will be described later. 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, causing the coating liquid to be discharged from an outlet disposed on the lower surface of the nozzle 71.

[0039] FIG. 2 is a diagram showing the configuration of the coating liquid supply mechanism 8. The coating liquid supply mechanism 8 includes a pump 81, a pipe 82, a coating liquid replenishment unit 83, a pipe 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 coating liquid to the nozzle 71 and supplies the coating liquid by changing its volume. For example, the pump 81 may be a bellows-type pump described in Japanese Patent Laid-Open No. 10-61558. As shown in FIG. 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 coating liquid replenishment unit 83 via the pipe 82. The other end of the flexible tube 811 is connected to the nozzle 71 via the pipe 84.

[0040] 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 operating 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 operating disk section 816 is connected to the drive section 87.

[0041] The coating liquid replenishment unit 83 has a storage tank 831 that stores the coating liquid. The storage tank 831 is connected to the pump 81 via a pipe 82. An on-off valve 833 is inserted in the pipe 82. The on-off valve 833 opens and closes in response to a command from the control unit 9. When the on-off valve 833 is opened, the coating 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 the coating liquid from the storage tank 831 to the flexible tube 811 of the pump 81 is restricted.

[0042] The pipe 84 is connected to the output side of the pump 81. An on-off valve 85 is inserted in the pipe 84. The on-off valve 85 opens and closes in response to commands from the control unit 9. The on-off valve 85 opens and closes to switch between sending and stopping the coating liquid to the nozzle 71. A pressure sensor 86 is disposed in the pipe 84. The pressure sensor 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.

[0043] 3 is a diagram showing the pressure waveform of the discharge pressure. In FIG. 3, the horizontal axis represents time, and the vertical axis represents pressure value. In the coating device 1, an optimization process is appropriately performed to approximate the pressure waveform of the coating liquid discharged from the nozzle 71 to an ideal pressure waveform by adjusting various parameters (acceleration time, steady-state speed, steady-state speed time, deceleration time, etc.) that define the movement of the operating disk portion 816.

[0044] As shown in Fig. 3, the discharge pressure is measured from before the nozzle 71 starts discharging the coating liquid to after the nozzle 71 finishes discharging the coating liquid. In the example shown in Fig. 3, the discharge pressure at time ta when the nozzle 71 starts discharging the coating liquid and the discharge pressure at time te when the nozzle 71 finishes discharging the coating liquid are the initial pressure Pi. However, the pressures at the start and end of discharging do not always match the initial pressure Pi. As shown in Fig. 3, the discharge period is divided into a rise period T1, a transition period T2, a steady period T3, and a fall period T4.

[0045] The rise period T1 is the period from time ta when the coating liquid supply mechanism 8 starts discharging the coating liquid from the nozzle 71 (i.e., time when the coating liquid supply mechanism 8 starts moving the operating disk portion 816) to time tb when the discharge pressure reaches the target pressure Pt. In other words, when the discharge of the coating liquid from the nozzle 71 starts at time ta, the discharge pressure increases from the initial pressure Pi to the target pressure Pt between time ta and time tb.

[0046] The transition period T2 is the period from time tb to time tc, which is the time required for the change in the discharge pressure over time to stabilize. This vibration damping period is set, for example, by the user through an input operation on the input device 97 and stored in the storage unit 93.

[0047] The steady period T3 is the period from time tc to time td when the coating solution supply mechanism 8 starts to reduce the discharge pressure (i.e., the time when the coating solution supply mechanism 8 starts to decelerate the operating disc portion 816 from the target speed). In other words, the coating solution supply mechanism 8 moves the operating disc portion 816 at a constant speed from time tc to time td, and starts to decelerate the operating disc portion 816 at time td. Note that during the steady period T3, the discharge pressure basically stabilizes at the target pressure Pt. However, even during the steady period T3, the change in the discharge pressure over time includes minute vibrations, and the discharge pressure may be greater or smaller than the target pressure Pt.

[0048] The falling period T4 is the period from time td to time te when the coating liquid supply mechanism 8 finishes discharging the coating liquid from the nozzle 71 (i.e., time te when the coating liquid supply mechanism 8 stops the operating disk portion 816). In other words, 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 stops.

[0049] As shown in FIGS. 1 and 2, a sensor 62 is disposed on the nozzle 71 to which the coating liquid is supplied 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. Based on the detection result 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. Then, based on the measured separation distance, the control unit 9 adjusts the coating position of the nozzle 71 using the positioning mechanism. Note that an optical sensor or an ultrasonic sensor can be used as the sensor 62.

[0050] The coating mechanism 7 includes 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 includes a roller 721, a cleaning section 722, and a roller vat 723. The nozzle cleaning standby unit 72 cleans the nozzle 71 and forms a liquid pool, thereby preparing the discharge port of the nozzle 71 for a coating process. Furthermore, in the coating device 1, in order to evaluate the discharge pressure applied to the coating liquid, a simulated discharge is performed in which the coating liquid is discharged from the nozzle 71 while the nozzle 71 is positioned at the maintenance position.

[0051] FIG. 4 is a block diagram showing an example of the configuration of the control unit 9. The control unit 9 controls the operation of each element of the coating apparatus 1. The control unit 9 includes a calculation unit 91, a storage unit 93, a display 95, and an input device 97. The control unit 9 can be, for example, a desktop, laptop, or tablet computer. As will be described later, the control unit 9 functions as a discharge pressure monitoring device that monitors abnormalities in the discharge pressure.

[0052] The calculation unit 91 is a processor including a CPU (Central Processing Unit), etc. The storage unit 93 includes a transient storage device such as a RAM (Random Access Memory), and a non-transient auxiliary storage device such as an HDD (Hard Disk Drive) and an SDD (Solid State Drive).

[0053] The display 95 is a device that displays information to the user, and specifically is a liquid crystal display, etc. The input device 97 is a device that accepts input operations by the user, and is a mouse, keyboard, etc.

[0054] The storage unit 93 stores a computer program 931. The computer program 931 is provided by a recording medium M. That is, the recording medium M records the computer program 931 so as to be readable by the control unit 9, which is a computer. The recording medium M is, for example, a USB (Universal Serial Bus) memory, an optical disk such as a DVD (Digital Versatile Disc), a magnetic disk, or the like.

[0055] The calculation unit 91 executes the computer program 931 to function as a discharge control unit 910 , a discharge pressure measurement unit 911 , a feature calculation unit 913 , an abnormality degree calculation unit 915 , an abnormality probability calculation unit 917 , and an abnormality determination unit 919 .

[0056] The discharge control unit 910 controls the operation (feeding operation) of the pump 81 that feeds the application liquid to the nozzle 71 based on preset parameters.

[0057] The discharge pressure measurement unit 911 measures the discharge pressure. Specifically, the discharge pressure measurement unit 911 periodically acquires the discharge pressure measured by the pressure sensor 86 at a predetermined sampling period. The discharge pressure measurement unit 911 acquires the time change (time series data) of the discharge pressure applied to the coating liquid during the period in which the coating liquid is discharged from the nozzle 71, and stores the acquired data as pressure data in the storage unit 93. The pressure data is data indicating each time and the pressure measured at each time. The discharge pressure measurement unit 911 is an example of a pressure data acquisition unit.

[0058] The feature amount calculation unit 913 derives the feature amount from the discharge pressure measured by the discharge pressure measurement unit 911. As the feature amount, for example, some feature amounts described in Japanese Patent Application Laid-Open No. 2022-138109 can be adopted.

[0059] FIG. 5 is a diagram illustrating an example of a feature amount. In this example, the degree of overshoot that occurs when the discharge pressure rises is calculated as the feature amount F1. Specifically, the feature amount calculation unit 913 calculates the sign (positive or negative) of the second derivative Dif2 of the discharge pressure at time t11 when the discharge pressure reaches the maximum value Pmax. Then, the feature amount calculation unit 913 calculates the time t12 when the sign of the second derivative switches twice from the sign at time t11. Then, the feature amount calculation unit 913 calculates the feature amount F1 of the time change of the discharge pressure during the initial vibration period T2_s from time t11 to t12.

[0060] For example, the feature amount calculation unit 913 selects the smaller of the minimum value Pmin of the discharge pressure during the initial vibration period T2_s and the steady pressure Pm (average value of the discharge pressure during the steady period T3) as the target pressure Pg. Then, the feature amount calculation unit 913 may calculate the difference between the maximum pressure Pmax and the target pressure Pg (=Pmax-Pg) as the feature amount F1.

[0061] Such a feature value F1 becomes relatively larger as the overshoot of the time change in the discharge pressure increases due to the momentum of the rise in the discharge pressure.

[0062] 6 is a diagram illustrating another example of a feature quantity. In this example, the stability of the time change of the discharge pressure during the transition period T2 is calculated as the feature quantity F2. Specifically, the feature quantity calculation unit 913 calculates the root mean square error RMSE(P_measure, Pm) between the discharge pressure during the transition period T2 and the steady pressure Pm, which is the average value of the discharge pressure during the steady period T3, as the feature quantity F2. The feature quantity F2 becomes relatively larger as the ringing (waveform oscillation) of the time change of the discharge pressure during the transition period T2 becomes larger.

[0063] The abnormality degree calculation unit 915 inputs the feature amount calculated by the feature amount calculation unit 913 into the unsupervised learning model M1 to calculate the abnormality degree of the pressure data.

[0064] The anomaly probability calculation unit 917 inputs the feature calculated by the feature calculation unit 913 into the supervised learning model M2 to calculate the probability of an anomaly. Specifically, the pressure data can be classified into a normal state and one or more pre-specified abnormal states. The feature calculation unit 913 calculates the probability that the pressure data corresponds to each of the one or more pre-specified abnormal states (hereinafter also referred to as "anomaly probability"). For example, if two types of abnormalities ("anomaly A" and "anomaly B") are pre-specified during learning of the supervised learning model M2, the pressure data is classified into a normal state, an abnormal state A, and an abnormal state B. Then, the anomaly probability calculation unit 917 calculates an anomaly probability indicating the probability that the pressure data corresponds to anomaly A or B.

[0065] The abnormality determination unit 919 determines whether the pressure data is abnormal using the degree of abnormality calculated by the abnormality degree calculation unit 915 and the abnormality probability calculated by the abnormality probability calculation unit 917 .

[0066] <Learning stage> Fig. 7 is a block diagram showing the control unit 9 that performs machine learning. Fig. 8 is a diagram showing the flow of the machine learning process executed by the control unit 9. Note that the machine learning shown in Figs. 8 and 9 may be performed by a computer device different from the control unit 9.

[0067] 7 and 8, in order to perform machine learning, the discharge pressure measurement unit 911 first acquires a considerable number of normal pressure data D1, a considerable number of pressure data D2 corresponding to abnormality A, and a considerable number of pressure data D3 corresponding to abnormality B (FIG. 8: step S11). The acquired pressure data D1 to D3 are stored in the storage unit 93. Then, the feature calculation unit 913 acquires the feature of each of the pressure data D1 to D3 (FIG. 8: step S12).

[0068] The anomaly degree calculation unit 915 executes machine learning (unsupervised learning) to obtain the unsupervised learning model M1 (FIG. 8: step S13). The anomaly degree calculation unit 915 stores the unsupervised learning model M1 (more specifically, learned parameters) obtained by the machine learning in the storage unit 93 (step S14).

[0069] Specifically, in unsupervised learning, a set of features of multiple normal pressure data D1 is prepared as training data. Then, machine learning based on the k-nearest neighbor method is performed using the training data. The unsupervised learning model M1 takes the features as input and outputs an anomaly level indicating the degree of deviation from the distribution of the features of normal pressure data. The anomaly level is preferably the Mahalanobis distance from the k-nearest neighbors, but may also be the Euclidean distance or Manhattan distance.

[0070] The anomaly probability calculation unit 917 executes machine learning (supervised learning) to obtain the supervised learning model M2 (FIG. 8: step S15). The anomaly probability calculation unit 917 also stores the supervised learning model M2 (more specifically, the learned parameters) obtained by the machine learning in the storage unit 93 (FIG. 8: step S16).

[0071] In supervised learning, first, multiple feature values ​​of normal pressure data, multiple feature values ​​of abnormal pressure data A, and multiple feature values ​​of abnormal pressure data B are prepared as input data. The supervised learning model M2 is based on, for example, a linear regression model. In supervised learning, optimal parameters for predicting target values ​​(labels indicating "normal," "abnormal A," and "abnormal B") from the input data are found. Specifically, in order to distinguish between the three states of normal, abnormal A, and abnormal B, the target value for normal is set to "0," the target value for abnormal A is set to "1," and the target value for abnormal B is set to "-1," and learning proceeds so that the model outputs the target values ​​of the input data.

[0072] It is also possible to use the rising period T1 as a feature value. However, when there are several ejection waveform patterns, such as when the target pressure Pt is different, the rising period T1 may vary from pattern to pattern even under normal conditions. For this reason, if there is variation in the rising period T1, it is preferable not to use it as a feature value.

[0073] <Prediction stage> Fig. 9 is a block diagram showing the control unit 9 for monitoring abnormalities in the pressure data, and Fig. 10 is a diagram showing the flow of a monitoring process executed by the control unit 9 for monitoring the discharge pressure.

[0074] In this monitoring process, first, the discharge pressure measurement unit 911 of the control unit 9 acquires pressure data (FIG. 10: step S21). Then, the feature calculation unit 913 calculates the feature of the acquired pressure data (FIG. 10: step S22).

[0075] The anomaly degree calculation unit 915 inputs the feature amounts calculated by the feature amount calculation unit 913 into the unsupervised learning model M1 to calculate the anomaly degree (FIG. 10: step S23). Also, the anomaly probability calculation unit 917 inputs the feature amounts calculated by the feature amount calculation unit 913 into the supervised learning model M2 to calculate the probability of each anomaly (FIG. 10: step S24).

[0076] FIG. 11 is a diagram conceptually illustrating how the degree of anomaly (Mahalanobis distance) is calculated. In the example shown in FIG. 11, multiple open circles ("○") indicate the position (distribution) in the feature space of normal pressure data used in machine learning. Open triangles ("△") indicate the position in the feature space of newly acquired pressure data. As shown in FIG. 11, the degree of anomaly calculation unit 915 calculates the Mahalanobis distance between the newly acquired pressure data (△) and the k-nearest (here, nearest) normal pressure data (○) as the degree of anomaly. The degree of anomaly is an index that indicates how much the newly acquired pressure data (△) deviates from the normal pressure data (○).

[0077] Fig. 12 is a diagram conceptually showing the output of the abnormality probability calculation unit 917. It is a diagram illustrating pressure waveforms of normal, abnormal A, and abnormal B. In the example shown in Fig. 12, a state in which the discharge pressure overshoots, rising more excessively than in the normal state, is regarded as abnormal A. On the other hand, a state in which the discharge pressure does not rise sufficiently compared to the normal state and it takes a longer time for the discharge pressure to reach the steady pressure Pm is regarded as abnormal B.

[0078] The abnormality probability calculation unit 917 is configured to output a numerical value between -1 and +1 for newly acquired pressure data. As described above, machine learning is performed so that normal is 0, the output value of abnormality A is +1, and the output of abnormality B is -1. Therefore, the closer the output value is to +1, the higher the probability of abnormality A, and the closer the output value is to -1, the higher the probability of abnormality B.

[0079] 9, the degree of abnormality calculated by the abnormality degree calculation unit 915 and the abnormality probability (a numerical value between -1 and 1) calculated by the abnormality probability calculation unit 917 are sent to the abnormality determination unit 919. The abnormality determination unit 919 compares the degree of abnormality and the abnormality probability with threshold values ​​to determine whether the newly obtained pressure data is normal or abnormal (FIG. 10: step S25).

[0080] Specifically, the abnormality determination unit 919 determines whether the degree of abnormality exceeds a predetermined threshold value Th1 (see FIG. 11). If the degree of abnormality exceeds the threshold value Th1, the abnormality determination unit 919 determines that the pressure data is abnormal.

[0081] Furthermore, the abnormality determination unit 919 determines whether the abnormality probability exceeds a predetermined threshold value. For example, as shown in FIG. 12, when determining whether the data corresponds to abnormality A or abnormality B, threshold values ​​Th2 and Th3 are determined in advance. Threshold value Th2 is a numerical value greater than 0 and less than 1, and threshold value Th3 is a numerical value greater than -1 and less than 0. When the abnormality probability exceeds threshold value Th2 on the positive side (i.e., when the abnormality probability value is greater than threshold value Th2), the abnormality determination unit 919 determines that the new pressure data corresponds to abnormality A. When the abnormality probability exceeds threshold value Th3 on the negative side (i.e., when the abnormality probability is below threshold value Th3), the abnormality determination unit 919 determines that the new pressure data corresponds to abnormality B.

[0082] For example, in the example shown in Figure 12, the abnormality probability of the first pressure data (data 1) does not exceed thresholds Th2 and Th3, so the pressure data is determined to be normal. The abnormality probability of the second pressure data (data 2) exceeds threshold Th2 on the positive side, so the pressure data is determined to be abnormal A. The abnormality probability of the third pressure data (data 3) exceeds threshold Th3 on the negative side, so the pressure data is determined to be abnormal B.

[0083] Furthermore, the anomaly determination unit 919 may combine the results of the anomaly determinations using the anomaly degree and the anomaly probability to make a final anomaly determination for the pressure data. FIG. 13 is a conceptual diagram illustrating an example of a comprehensive anomaly determination using the anomaly degree and the anomaly probability. In FIG. 13, the horizontal axis represents the anomaly probability, and the vertical axis represents the anomaly degree. If neither the anomaly degree nor the anomaly probability exceeds a threshold (i.e., both are normal), the comprehensive determination of the pressure data is determined to be "normal" (corresponding to the third quadrant in FIG. 13). If both the anomaly degree and the anomaly probability exceed a threshold (i.e., both are abnormal), the comprehensive determination of the new pressure data is determined to be "anomaly." Furthermore, if the anomaly probability is high and the anomaly degree is low, the comprehensive determination of the new pressure data is determined to be "anomaly close to a normal distribution." Conversely, if the anomaly probability is low and the anomaly degree is high, the comprehensive determination of the new pressure data is determined to be "unknown anomaly," i.e., an anomaly not anticipated during learning.

[0084] The abnormality determination unit 919 outputs the determination result obtained in step S25 to the outside. As an example, the abnormality determination unit 919 displays the determination result on the display 95 (step S26). The abnormality determination unit 919 may print out the determination result using a printer. Alternatively, the abnormality determination unit 919 may output the determination result by turning on a lamp, outputting an alarm sound from a speaker, or the like.

[0085] As described above, the control unit 9 (discharge pressure monitoring device) includes a discharge pressure measurement unit 911 as a pressure data acquisition unit, a feature calculation unit 913, an abnormality degree calculation unit 915, an abnormality probability calculation unit 917, and an abnormality determination unit 919. The discharge pressure measurement unit 911 acquires pressure data indicating a temporal change in pressure inside the nozzle 71 that discharges the treatment liquid. The feature calculation unit 913 calculates a feature of the pressure data. The abnormality degree calculation unit 915 receives the feature and calculates an abnormality degree for the feature calculated by the feature calculation unit 913 using an unsupervised learning model M1 that outputs an abnormality degree indicating the degree of deviation from a normal distribution of the feature. The abnormality probability calculation unit 917 receives the feature and calculates an abnormality probability for the feature calculated by the feature calculation unit 913 using a supervised learning model M2 that receives the feature and outputs an abnormality probability indicating the probability that the feature corresponds to a predetermined abnormality. The abnormality determination unit 919 determines whether the pressure data is abnormal by using the degree of abnormality calculated by the abnormality degree calculation unit 915 and the abnormality probability calculated by the abnormality probability calculation unit 917 .

[0086] The control unit 9 also executes a pressure monitoring method, which includes the steps of: a) acquiring pressure data indicating a time change in pressure inside the nozzle 71 that discharges the processing liquid; b) calculating a feature value of the pressure data; c) calculating an anomaly level for the feature value calculated in step b) using an unsupervised learning model M1 that receives the feature value as an input and outputs an anomaly level indicating the degree of deviation from a normal distribution of feature values; d) calculating an anomaly probability for the feature value calculated in step b) using a supervised learning model M2 that receives the feature value as an input and outputs an anomaly probability indicating the probability that the feature value corresponds to a specific anomaly; and e) determining an anomaly in the pressure data using the anomaly level calculated in step c) and the anomaly probability calculated in step d).

[0087] With this configuration, when a previously anticipated anomaly is detected, the anomaly can be identified by calculating the anomaly probability. Even when an unknown anomaly that has not been previously anticipated occurs, the unknown anomaly can be appropriately detected by calculating the anomaly degree.

[0088] The unsupervised learning model M1 is a model obtained by unsupervised learning using the feature quantities of only a plurality of normal pressure data as input data.

[0089] According to this configuration, only the distribution of normal feature quantities can be learned, and therefore, abnormality detection can be performed appropriately.

[0090] The unsupervised learning model M1 outputs the Mahalanobis distance as the degree of anomaly.

[0091] According to this configuration, the degree of abnormality is calculated taking into consideration the correlation between the dimensions of the feature values ​​indicated by the pressure data, so that characteristic patterns and abnormal behavior of the pressure data can be more accurately captured.

[0092] The supervised learning model M2 outputs the probability of multiple types of specific anomalies (for example, anomalies A and B).

[0093] According to this configuration, it is possible to calculate a plurality of types of probabilities, and therefore it is possible to determine whether the pressure data corresponds to any of the plurality of types of abnormality.

[0094] <Other embodiments> In the above embodiment, the anomaly degree calculation unit 915 calculates the anomaly degree using the unsupervised learning model M1. However, it is not essential to calculate the anomaly degree using the unsupervised learning model M1. For example, the anomaly degree calculation unit 915 may calculate the difference between a normal feature amount and a feature amount of newly obtained pressure data using a predetermined calculation formula. The difference corresponds to the anomaly degree indicating the degree of deviation of the feature amount of the newly obtained pressure data from the normal feature amount. Furthermore, the normal feature amount to be compared may be defined from the feature amounts of multiple normal pressure data, or may be the feature amount of a single normal pressure data.

[0095] The abnormality determination unit 919 compares the degree of abnormality (difference) calculated by the abnormality degree calculation unit 915 with a preset threshold value. If the degree of abnormality exceeds the threshold value, the abnormality determination unit 919 determines that the newly acquired pressure data is abnormal.

[0096] For example, Japanese Patent Application Laid-Open Publication No. 2012-098133 describes a method for detecting an abnormality in an inverter device based on the impulse component of a current waveform by calculating the similarity between the feature amount of the impulse component under normal conditions and the feature amount of the impulse component to be determined. Japanese Patent Application Laid-Open Publication No. 2006-026584 also describes a method for detecting an ink ejection abnormality based on the voltage applied to an actuator that ejects ink by calculating the difference between the voltage under normal conditions and the voltage to be determined. These similarities and differences may be used as the abnormality level.

[0097] Although the present invention has been described in detail, the above description is merely illustrative in all respects and does not limit the present invention. It is understood that countless variations not illustrated can be envisioned without departing from the scope of the present 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. [Explanation of symbols]

[0098] 1 Coating device 51 Chuck mechanism (substrate holding part) 52 Travel control mechanism 7 Application mechanism 71 nozzle 86 Pressure Sensor 9 Control unit (discharge pressure monitoring device) 91 Arithmetic section 911 Discharge pressure measurement unit (pressure data acquisition unit) 913 Feature Calculation Unit 915 Abnormality calculation unit 917 Abnormality Probability Calculation Unit 919 Abnormality determination unit 931 Computer Programs M1 Unsupervised Learning Model M2 supervised learning model

Claims

1. A coating device, a substrate holder for holding a substrate; a nozzle that ejects a processing liquid toward the substrate held by the substrate holder; a pressure sensor for measuring the pressure in the nozzle; a discharge pressure monitoring device; Equipped with The discharge pressure monitoring device a pressure data acquisition unit that acquires pressure data indicating a time change in pressure inside the nozzle using the pressure sensor; a feature amount calculation unit that calculates a feature amount of the pressure data; an anomaly degree calculation unit that calculates the anomaly degree for the feature calculated by the feature calculation unit using an unsupervised learning model that receives the feature as an input and outputs an anomaly degree that indicates the degree of deviation from a normal distribution of the feature; an abnormality probability calculation unit that uses the feature amount as an input and calculates the abnormality probability for the feature amount calculated by the feature amount calculation unit using a supervised learning model that outputs an abnormality probability indicating the probability that the feature amount corresponds to a specific abnormality; an abnormality determination unit that acquires the degree of abnormality calculated by the abnormality degree calculation unit and the abnormality probability calculated by the abnormality probability calculation unit, and determines whether the pressure data is in a normal state, an abnormality close to a normal distribution, an unknown abnormality, or an abnormal state based on a comparison of the degree of abnormality calculated by the abnormality degree calculation unit and the abnormality probability with thresholds; Including, The coating apparatus, wherein the characteristic amount is the degree of overshoot that occurs during a rise period of the discharge pressure, which is the period from the time when the discharge of the treatment liquid from the nozzle starts to the time when the discharge pressure reaches a target pressure.

2. The coating device according to claim 1 , The unsupervised learning model is a model obtained by unsupervised learning using, as input data, feature quantities of only the plurality of normal pressure data.

3. The coating device according to claim 1 or 2, The coating apparatus, wherein the unsupervised learning model outputs a Mahalanobis distance as the degree of abnormality.

4. The coating device according to claim 1 or 2, The supervised learning model outputs probabilities of multiple types of specific anomalies.

5. A coating device, a substrate holder for holding a substrate; a nozzle that ejects a processing liquid toward the substrate held by the substrate holder; a pressure sensor for measuring the pressure in the nozzle; a discharge pressure monitoring device; Equipped with The discharge pressure monitoring device a pressure data acquisition unit that acquires pressure data indicating a time change in pressure inside the nozzle using the pressure sensor; a feature amount calculation unit that calculates a feature amount of the pressure data; an abnormality degree calculation unit that calculates an abnormality degree indicating a degree of deviation from a normal feature amount for the feature amount calculated by the feature amount calculation unit; an abnormality probability calculation unit that uses the feature amount as an input and calculates the abnormality probability for the feature amount calculated by the feature amount calculation unit using a supervised learning model that outputs an abnormality probability indicating the probability that the feature amount corresponds to a specific abnormality; an abnormality determination unit that acquires the degree of abnormality calculated by the abnormality degree calculation unit and the abnormality probability calculated by the abnormality probability calculation unit, and determines whether the pressure data is in a normal state, an abnormality close to a normal distribution, an unknown abnormality, or an abnormal state based on a comparison of the degree of abnormality calculated by the abnormality degree calculation unit and the abnormality probability with thresholds; Including, The coating apparatus, wherein the characteristic amount is the degree of overshoot that occurs during a rise period of the discharge pressure, which is the period from the time when the discharge of the treatment liquid from the nozzle starts to the time when the discharge pressure reaches a target pressure.

Images