Control method, control device, and computer program
The control method and device use pressure difference estimation models to accurately adjust valve apertures, addressing the challenge of gas discharge flow rate control in substrate processing, ensuring precise chamber pressure for effective processing.
Patent Information
- Application Number
- JP2024041549
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-03-15
- Publication Date
- 2025-09-29
AI Technical Summary
Accurately adjusting the gas discharge flow rate from a tank to a chamber in substrate processing is difficult due to challenges in controlling the pressure inside the chamber.
A control method and device that utilize pressure difference estimation models to predict and adjust the opening degree of valves to minimize errors in gas discharge flow rate, using a control device with a tank pressure difference estimation model and a chamber pressure difference estimation model to determine optimal valve apertures.
Enables precise control of gas discharge flow rate, ensuring accurate pressure adjustment within the chamber for effective substrate processing.
Smart Images

Figure 2025141552000001_ABST
Abstract
Description
[Technical Field]
[0001] The present disclosure relates to a control method, a control device, and a computer program. [Background technology]
[0002] In substrate processing, which involves etching, film formation, or the like, on substrates such as semiconductor wafers, glass substrates, or flat panel substrates, the processing is carried out in a chamber. For example, a tank that stores a predetermined gas required for the processing is disposed upstream of the chamber, and with a substrate placed in the chamber, the gas flows from the tank into the chamber to perform the processing. Patent Document 1 discloses an example of a substrate processing apparatus that performs substrate processing. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Application Publication No. 2022-53439 Summary of the Invention [Problem to be solved by the invention]
[0004] To perform appropriate substrate processing, it is necessary to appropriately adjust the pressure inside the chamber, which in turn requires adjusting the flow rate of gas discharged from the tank to the chamber, but it is difficult to accurately adjust the flow rate of gas discharged from the tank.
[0005] The present disclosure provides a control method, a control device, and a computer program for accurately adjusting the gas discharge flow rate from a tank. [Means for solving the problem]
[0006] A control method according to one embodiment of the present disclosure is a control method for controlling a substrate processing apparatus having a tank for storing a predetermined gas, a first valve for discharging the gas from the tank, and a chamber to which the gas is supplied from the tank via the first valve and in which substrate processing is performed, the control method comprising: calculating a predicted value of a tank pressure difference, which is the difference between the tank pressure and the tank pressure after a predetermined time, based on a tank pressure, which is the pressure inside the tank, a chamber pressure, which is the pressure inside the chamber, and an opening degree of the first valve; calculating a predicted value of a gas discharge flow rate from the tank to the chamber after a predetermined time based on the calculated predicted value of the tank pressure difference; determining an opening degree of the first valve so as to reduce an error between the calculated predicted value of the gas discharge flow rate and a target value of the gas discharge flow rate; and adjusting an actual opening degree of the first valve to match the determined opening degree of the first valve. [Effects of the Invention]
[0007] According to the present disclosure, it is possible to provide a control method, a control device, and a computer program for accurately adjusting the gas discharge flow rate from a tank. [Brief explanation of the drawings]
[0008] [Figure 1] FIG. 2 is a block diagram showing an example of a functional configuration of the substrate processing apparatus. [Figure 2] FIG. 2 is a block diagram showing an example of an internal functional configuration of a control device. [Figure 3] 6 is a flowchart illustrating an example of a procedure of a process executed by the control device according to the first embodiment to collectively determine opening degrees of the first valve at a plurality of time points. [Figure 4] FIG. 3 is a conceptual diagram illustrating an example of the function of a tank pressure difference estimation model according to the first embodiment. [Figure 5] FIG. 2 is a conceptual diagram showing an example of the configuration of a tank pressure difference estimation model according to the first embodiment. [Figure 6] 10 is a chart showing an example of the contents of a tank pressure difference table. [Figure 7] FIG. 4 is a conceptual diagram illustrating an example of the function of a chamber pressure difference estimation model according to the first embodiment. [Figure 8] FIG. 2 is a conceptual diagram showing an example of the configuration of a chamber pressure difference estimation model according to the first embodiment. [Figure 9] 10 is a chart showing an example of the contents of a chamber pressure difference table. [Figure 10] FIG. 4 is a conceptual diagram showing an example of the contents of opening degree data. [Figure 11] 6 is a flowchart showing an example of a processing procedure in which the control device actually adjusts the opening degree of the first valve. [Figure 12] FIG. 10 is a conceptual diagram showing an example of the contents of opening data after the opening of the first valve is corrected. [Figure 13] 10 is a flowchart illustrating an example of a procedure of a process executed by a control device according to a second embodiment to collectively determine opening degrees of the first valve at a plurality of time points. [Figure 14] FIG. 10 is a conceptual diagram illustrating an example of the function of a tank pressure difference estimation model according to the second embodiment. [Figure 15] FIG. 10 is a conceptual diagram illustrating an example of the function of a chamber pressure difference estimation model according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0009] The present disclosure will now be described in detail with reference to the drawings showing embodiments thereof. <Embodiment 1> 1 is a block diagram showing an example of the functional configuration of a substrate processing apparatus 100. The substrate processing apparatus 100 includes a chamber 4 in which substrate processing such as etching or film formation is performed. A substrate is placed inside the chamber 4, and a predetermined gas such as an etching gas or a film formation gas is introduced into the chamber 4, where the substrate processing such as etching or film formation is performed inside the chamber 4. A tank 2 that stores the predetermined gas is connected to the chamber 4 via a pipe. A first valve 3 is provided in the pipe connecting the chamber 4 and the tank 2. The first valve 3 is a valve that opens and closes. A mass flow controller (MFC) 61 is connected to the tank 2 via a pipe.
[0010] The MFC 61 supplies a predetermined gas to the tank 2. For example, the MFC 61 supplies the gas to the tank 2 at a constant flow rate. When the first valve 3 is closed, the tank 2 does not discharge gas, the supply of gas from the MFC 61 continues, and the tank pressure, which is the pressure inside the tank 2, increases. When the first valve 3 is open, the gas is discharged from the tank 2 through the first valve 3. That is, when the first valve 3 is open, the gas is discharged from the tank 2. When the first valve 3 is open, the gas is supplied from the tank 2 to the chamber 4 via the piping and the first valve 3.
[0011] The first valve 3 is a valve whose opening can be adjusted. For example, the first valve 3 is a proportional control valve. The tank pressure changes depending on the supply of gas to the tank 2 and the discharge of gas from the tank 2. By adjusting the opening of the first valve 3, the tank pressure is adjusted, and the gas discharge flow rate is adjusted. The gas discharge flow rate is the flow rate of gas discharged from the tank 2 to the chamber 4, i.e., the amount of gas discharged from the tank 2 per unit time. Normally, the larger the opening of the first valve 3, the larger the gas discharge flow rate, and the smaller the opening, the smaller the gas discharge flow rate.
[0012] A pump 62 is connected to the chamber 4 through piping. A second valve 5 is provided in the middle of the piping connecting the chamber 4 and the pump 62. The second valve 5 is a valve that opens and closes, and its opening degree can be adjusted. For example, the second valve 5 is an APC (Automatic Pressure Control) valve. The pump 62 operates to discharge gas from the chamber 4. When the second valve 5 is open, the pump 62 discharges gas from the chamber 4 through the piping and the second valve 5. When the second valve 5 is open, the gas is discharged from the chamber 4. By adjusting the opening degree of the second valve 5, the amount of gas discharged from the chamber 4 is adjusted, and the chamber pressure, which is the pressure inside the chamber 4, is adjusted.
[0013] A pressure gauge 21 is provided in the tank 2, and a pressure gauge 41 is provided in the chamber 4. The pressure gauge 21 measures the tank pressure, and the pressure gauge 41 measures the chamber pressure. A valve controller 31 is connected to the first valve 3. The valve controller 31 opens and closes the first valve 3 and changes the opening degree. A valve controller 51 is connected to the second valve 5. The valve controller 51 opens and closes the second valve 5 and changes the opening degree.
[0014] The control device 1 is connected to the pressure gauge 21, the valve controller 31, the pressure gauge 41, the valve controller 51, and the MFC 61. The control device 1 acquires the tank pressure measured by the pressure gauge 21 and the chamber pressure measured by the pressure gauge 41. The control device 1 controls the valve controller 31, the valve controller 51, and the MFC 61. The control device 1 adjusts the aperture of the first valve 3 by controlling the valve controller 31. The tank pressure is adjusted by adjusting the aperture of the first valve 3. The control device 1 adjusts the aperture of the second valve 5 by controlling the valve controller 51.
[0015] FIG. 2 is a block diagram showing an example of the internal functional configuration of the control device 1. The control device 1 executes a control method for controlling the substrate processing apparatus 100. The control device 1 is configured using a computer such as a personal computer or a server device. The control device 1 includes a calculation unit 11, a memory 12, a storage unit 13, a reading unit 14, and an interface unit 15. The calculation unit 11 is configured using a processor, such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a multi-core CPU. The calculation unit 11 may also be configured using a quantum computer. The memory 12 stores temporary data generated in conjunction with calculations. The memory 12 is, for example, a RAM (Random Access Memory). The storage unit 13 is non-volatile, such as a hard disk or a non-volatile semiconductor memory. The reading unit 14 reads information from a recording medium 10, such as an optical disc or a portable memory.
[0016] The interface unit 15 is connected to the pressure gauge 21, the valve controller 31, the pressure gauge 41, the valve controller 51, and the MFC 61. The calculation unit 11 acquires the tank pressure measured by the pressure gauge 21 and the chamber pressure measured by the pressure gauge 41 through the interface unit 15. The calculation unit 11 controls the valve controller 31, the valve controller 51, and the MFC 61 by sending and receiving control signals through the interface unit 15.
[0017] The calculation unit 11 causes the reading unit 14 to read the computer program (program product) 131 recorded on the recording medium 10, and stores the read computer program 131 in the storage unit 13. The calculation unit 11 executes processing to realize the functions of the control device 1 in accordance with the computer program 131. The computer program 131 may be stored in the storage unit 13 in advance, or may be downloaded from outside the control device 1. In this case, the control device 1 does not need to be equipped with the reading unit 14.
[0018] The computer program 131 can be deployed to run on a single computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network. That is, the control device 1 may be configured with multiple computers, and the computer program 131 may be executed on multiple computers connected via a communication network. The control device 1 may be configured using a cloud server.
[0019] The processing of each step described below for executing the control method can be executed by multiple computers. The processing of each step can also be executed by different computers. Data used during the processing can be stored in multiple computers. The processing of each step can also be executed using a virtual machine. The processing of each step can be executed by multiple calculation units. The processing of each step can also be executed by different calculation units. For example, a part of the processing can be executed by a computer included in the substrate processing apparatus 100, and another part of the processing can be executed by a computer external to the substrate processing apparatus 100.
[0020] With a substrate placed inside chamber 4, a predetermined gas is supplied from tank 2 to chamber 4, and substrate processing is performed in chamber 4. In order to perform appropriate substrate processing, the pressure inside chamber 4 needs to be appropriately adjusted. To adjust the pressure inside chamber 4, the gas discharge flow rate from tank 2 to chamber 4 needs to be adjusted. The control device 1 adjusts the aperture of first valve 3 to adjust the gas discharge flow rate. Before actually starting to adjust the aperture of first valve 3, the control device 1 performs a process of collectively determining the aperture of first valve 3 at multiple future time points so as to minimize the error between the predicted value and the target value of the gas discharge flow rate. After determining the aperture of first valve 3 at multiple future time points, the control device 1 actually performs a process of adjusting the aperture of first valve 3 to match the determined aperture.
[0021] FIG. 3 is a flowchart showing an example of the procedure of a process executed by the control device 1 according to the first embodiment to collectively determine the opening degree of the first valve 3 at multiple points in time. Hereinafter, steps are abbreviated as S. The control device 1 executes the following process by having the calculation unit 11 execute information processing in accordance with the computer program 131. The control device 1 acquires the latest tank pressure and chamber pressure (S101). In S101, the calculation unit 11 acquires the value of the tank pressure measured by the pressure gauge 21 through the interface unit 15. The calculation unit 11 also acquires the value of the chamber pressure measured by the pressure gauge 41 through the interface unit 15. At this time, the calculation unit 11 may acquire the tank pressure and chamber pressure at multiple past points in time. The tank pressure and chamber pressure at multiple past points in time are stored in the memory unit 13, and the calculation unit 11 reads out the stored past tank pressure and chamber pressure.
[0022] The control device 1 calculates a predicted value of the tank pressure difference, which is the difference between the tank pressure at a certain point in time and the tank pressure at the next point in time (S102). The time from one point in time to the next point in time is a predetermined time. The control device 1 calculates the predicted value of the tank pressure difference using a trained model. The control device 1 is equipped with a tank pressure difference estimation model 132, which is a trained model. The tank pressure difference estimation model 132 is realized by the calculation unit 11 executing information processing in accordance with a computer program 131. The storage unit 13 stores data for realizing the tank pressure difference estimation model 132. The tank pressure difference estimation model 132 may be configured using hardware. The tank pressure difference estimation model 132 may be realized using a quantum computer. Alternatively, the tank pressure difference estimation model 132 may be provided external to the control device 1, and the control device 1 may execute processing using the external tank pressure difference estimation model 132. For example, the tank pressure difference estimation model 132 may be configured using the cloud.
[0023] 4 is a conceptual diagram showing an example of the function of the tank pressure difference estimation model 132 according to the first embodiment. A certain point in time is defined as t, the previous point in time is defined as t-1, the point in time two times before is defined as t-2, and the point in time N times before is defined as tN. N is a positive integer and is an arbitrary constant. The tank pressure at a certain point in time is defined as P t [t], the tank pressure at the previous time is P t [t-1], the tank pressure at the Nth time point is P t Let [tN] be the chamber pressure at a certain time. c [t], the chamber pressure at the previous time point is P c [t-1], the chamber pressure at the time N times before is P c [tN]. The opening degree of the first valve 3 at a certain time point is A1[t], the opening degree of the first valve 3 at the previous time point is A1[t-1], and the opening degree of the first valve 3 at the Nth time point is A1[tN]. The tank pressure difference estimation model 132 calculates the N+1 tank pressures P t [t],P t [t-1],…,P t [tN] and the N+1 chamber pressure P c [t],P c [t-1],…,P c [tN] and the openings A1[t], A1[t-1], ..., A1[tN] of the N+1 first valves 3 are input, the tank pressure difference ΔP t It has been trained in advance to output [t+1]. Tank pressure difference ΔP t [t+1] is the tank pressure P at a certain time t [t] and the tank pressure P at the next time t This is the difference from [t+1].
[0024] The tank pressure difference is determined by the tank pressure at a certain point in time and the tank pressure at the next point in time, and the tank pressure at the next point in time is affected by the aperture of first valve 3 and the chamber pressure. For this reason, a tank pressure difference estimation model 132 is established that outputs a tank pressure difference according to the tank pressure, the aperture of first valve 3, and the chamber pressure. Furthermore, the tank pressure is affected by the past tank pressure, and the past tank pressure is affected by the past aperture of first valve 3 and the chamber pressure. For this reason, a tank pressure difference estimation model 132 is established that outputs a tank pressure difference according to the current and past tank pressures, the aperture of first valve 3, and the chamber pressure. By using the tank pressure difference estimation model 132, it is possible to easily obtain the tank pressure difference.
[0025] 5 is a conceptual diagram showing an example of the configuration of the tank pressure difference estimation model 132 according to the first embodiment. The tank pressure difference estimation model 132 includes linear calculation units 1321, 1322, and 1323, and a neural network 1324. The linear calculation unit 1321 calculates the tank pressure P t [t],P t [t-1],…,P t The linear calculation unit 1322 receives the input of [tN] and outputs the value x1. c [t],P c [t-1],…,P c The linear calculation unit 1323 receives the openings A1[t], A1[t-1], ..., A1[tN] of the first valve 3 and outputs a value x3. The linear calculation units 1321, 1322, and 1323 calculate a 10 ,a 11 ,…,a 1N ,b 10 ,b 11 ,…,b 1N ,c 10 ,c 11 ,…,c 1N With these as predetermined coefficients, the values x1, x2, and x3 are calculated using the following linear calculations. x1=a 10 P t [t]+a 11 P t [t-1]+…+a1N P t [tN] x2=b 10 P c [t]+b 11 P c [t-1]+…+b 1N P c [tN] x3=c 10 A1[t]+c 11 A1[t-1]+…+c 1N A1[tN]
[0026] The neural network 1324 receives the values x1, x2, and x3 as inputs and calculates the tank pressure difference ΔP t [t+1] is output. The tank pressure difference estimation model 132 may have another configuration. The tank pressure difference estimation model 132 is trained in advance using data in which the actually measured tank pressure, chamber pressure, opening degree of the first valve 3, and tank pressure difference are associated with each other as training data.
[0027] In S102, the calculation unit 11 calculates the tank pressure P t [t],P t [t-1],…,P t [tN] and chamber pressure P c [t],P c [t-1],…,P c [tN] and the openings A1[t], A1[t-1], ..., A1[tN] of the first valve 3 are input to the tank pressure difference estimation model 132, and the tank pressure difference estimation model 132 executes processing. The tank pressure difference estimation model 132 performs calculations in response to the inputs of the tank pressure, chamber pressure, and openings of the first valve 3 at multiple points in time, and outputs the tank pressure difference. The calculation unit 11 calculates the tank pressure difference ΔP output by the tank pressure difference estimation model 132. t [t+1] is acquired as the predicted value of the tank pressure difference. In this way, the calculation unit 11 calculates the predicted value of the tank pressure difference.
[0028] In S102, the calculation unit 11 calculates multiple predicted values of the tank pressure difference based on multiple possible values for the degree of opening of the first valve 3. That is, the calculation unit 11 inputs each of the multiple possible values for the degree of opening of the first valve 3 to the tank pressure difference estimation model 132 as the value of the degree of opening of the first valve 3 at a certain point in time, and obtains a predicted value of the tank pressure difference corresponding to each value. In this way, the calculation unit 11 calculates a predicted value of the tank pressure difference for each of the multiple possible values for the degree of opening of the first valve 3.
[0029] The control device 1 may be configured to calculate a predicted value of the tank pressure difference using a regression model other than the trained model. The regression model is a model generated using the actually measured tank pressure, chamber pressure, opening of the first valve 3, and tank pressure difference. The regression model may be realized by a function.
[0030] The control device 1 may be configured to calculate a predicted value of the tank pressure difference using a table instead of a trained model. In this configuration, the control device 1 uses a tank pressure difference table 133 that records the relationship between the tank pressure, chamber pressure, opening degree of the first valve 3, and the tank pressure difference, instead of the tank pressure difference estimation model 132. The storage unit 13 stores the tank pressure difference table 133.
[0031] FIG. 6 is a chart showing an example of the contents of the tank pressure difference table 133. In the figure, the unit of pressure is Torr, and the unit of the opening of the first valve 3 is %. The "***" in the figure indicates a tank pressure difference. A positive tank pressure difference value indicates that the tank pressure at a certain point in time is lower than the tank pressure at the next point in time. In the tank pressure difference table 133, a table in which tank pressure difference values associated with each combination of tank pressure and chamber pressure values are recorded is associated with each opening value of the first valve 3. The opening of the first valve 3 can take multiple values. Therefore, each opening value of the first valve 3 is associated with a combination of tank pressure, chamber pressure, and tank pressure difference.
[0032] The value of the tank pressure difference obtained when the tank pressure, chamber pressure, and aperture of the first valve 3 are a certain combination of values is theoretically or experimentally investigated and specified in advance. The tank pressure difference table 133 stores the previously specified tank pressure difference values. In S102, the calculation unit 11 reads out the tank pressure difference associated with the tank pressure and chamber pressure at a certain point in time and the aperture of the first valve 3 from the tank pressure difference table 133. The calculation unit 11 sets the read tank pressure difference as the predicted value of the tank pressure difference. In this manner, the calculation unit 11 calculates the predicted value of the tank pressure difference. In this embodiment, the calculation unit 11 also calculates the predicted value of the tank pressure difference for each of multiple possible values for the aperture of the first valve 3. The calculation unit 11 stores the calculated predicted value of the tank pressure difference in the memory unit 13.
[0033] The control device 1 calculates a predicted value of the gas discharge flow rate at the next time point (S103). In S13, the calculation unit 11 calculates a predicted value of the gas discharge flow rate at the next time point based on the predicted value of the tank pressure difference. The volume of gas in the tank is V, the amount of substance of gas is n, the gas constant is R, and the temperature is T. The predetermined time from a certain time point to the next time point is Δt. The amount of substance of gas at a certain time point is n[t]. The pressure of the gas at a certain time point is the tank pressure P t [t].
[0034] Gas equation of state P t [t]V=nRT, the amount of gas at a certain time is n[t]=P t [t]V / RT, and the amount of gas at the next time is n[t+1]=P t [t+1]V / RT. The change in the amount of gas until the next time point is Δn, and the change in gas pressure is ΔP. Δn=n[t+1]-n[t]=(P t [t+1]-P t[t]) / RT = ΔPV / RT. The gas discharge flow rate is Δn / Δt = C × ΔPV / ΔtRT. Here, C is a conversion coefficient for converting the unit of discharge flow rate from [mol / sec] to [sccm (standard cubic centimeter per minute)]. Specifically, C = 1.34484 × 10 6 The change in gas pressure ΔP is the tank pressure difference ΔP t The predicted value for [t+1] can be used. Therefore, the gas discharge flow rate is expressed by the following equation (1).
[0035] Gas discharge flow rate = C × ΔP t [t+1]V / ΔtRT …(1)
[0036] The tank 2 is provided with a temperature sensor, and the control device 1 acquires the temperature inside the tank 2 measured by the temperature sensor. The control device 1 stores in advance in the storage unit 13 the values of C, the internal volume V of the tank 2, the predetermined time Δt, and the gas constant R. The calculation unit 11 calculates the tank pressure difference ΔP t The predicted value of the gas discharge flow rate is calculated by performing the calculation of equation (1) using the predicted value of [t+1]. At this time, the calculation unit 11 calculates multiple predicted values of the gas discharge flow rate according to multiple predicted values of the tank pressure difference. That is, the calculation unit 11 calculates the predicted value of the gas discharge flow rate for each of multiple possible values for the opening of the first valve 3. The calculation unit 11 stores the calculated predicted value of the gas discharge flow rate in the memory unit 13.
[0037] The control device 1 then determines whether or not the predicted values of the gas discharge flow rate have been calculated for a predetermined number of time points (S104). The predetermined number is set in advance and is, for example, several hundred. In S104, the calculation unit 11 identifies the number of time points at which the predicted values of the gas discharge flow rate have been calculated, and determines whether the number of identified time points has reached the predetermined number.
[0038] If the predicted value of the gas discharge flow rate at the predetermined number of points in time has not yet been calculated (S104: NO), the control device 1 calculates the predicted value of the tank pressure at the next point in time (S105). t [t] is the tank pressure difference ΔP t By adding the predicted value of [t+1], the tank pressure P t [t+1] is calculated. The calculation unit 11 sets the calculated tank pressure as the predicted value of the tank pressure at the next time point. At this time, the calculation unit 11 calculates multiple predicted values of the tank pressure at the next time point according to multiple predicted values of the tank pressure difference. The calculation unit 11 stores the calculated predicted values of the tank pressure at the next time point in the memory unit 13.
[0039] The control device 1 calculates a predicted value of a chamber pressure difference, which is the difference between the chamber pressure at a certain point in time and the chamber pressure at the next point in time (S106). The control device 1 calculates the predicted value of the chamber pressure difference using a trained model. The control device 1 is equipped with a chamber pressure difference estimation model 134, which is a trained model.
[0040] The chamber pressure difference estimation model 134 is realized by the calculation unit 11 executing information processing in accordance with the computer program 131. The storage unit 13 stores data for realizing the chamber pressure difference estimation model 134. The chamber pressure difference estimation model 134 may be configured using hardware. The chamber pressure difference estimation model 134 may be realized using a quantum computer. Alternatively, the chamber pressure difference estimation model 134 may be provided outside the control device 1, and the control device 1 may execute processing using the external chamber pressure difference estimation model 134. For example, the chamber pressure difference estimation model 134 may be configured using the cloud.
[0041] 7 is a conceptual diagram showing an example of the function of the chamber pressure difference estimation model 134 according to the first embodiment. g[t+1]. The opening degree of the second valve 5 at a certain time point is A2[t], the opening degree of the second valve 5 at the previous time point is A2[t-1], and the opening degree of the second valve 5 at the Nth time point is A2[tN]. The chamber pressure difference estimation model 134 calculates the N+1 gas discharge flow rates F g [t+1],F g [t],…,F g [t-(N-1)] and the N+1 chamber pressure P c [t],P c [t-1],…,P c [tN] and the openings A2[t], A2[t-1], ..., A2[tN] of the N+1 second valves 5 are input, the chamber pressure difference ΔP c It has been trained in advance to output [t+1]. Chamber pressure difference ΔP c [t+1] is the chamber pressure P c [t] and the chamber pressure P at the next time point c This is the difference from [t+1].
[0042] 8 is a conceptual diagram showing an example of the configuration of the chamber pressure difference estimation model 134 according to the first embodiment. The chamber pressure difference estimation model 134 includes linear calculation units 1341, 1342, and 1343, and a neural network 1344. The linear calculation unit 1341 calculates a gas discharge flow rate F g [t+1],F g [t],…,F g [t-(N-1)] is input and the linear calculation unit 1342 outputs the value y1. c [t],P c [t-1],…,P c The linear calculation unit 1343 receives the openings A2[t], A2[t-1], ..., A2[tN] of the second valve 5 and outputs a value y3. The linear calculation units 1341, 1342, and 1343 calculate a 20 ,a 21 ,…,a 2N ,b 20 ,b 21 ,…,b 2N ,c 20 ,c 21 ,…,c 2NWith these as predetermined coefficients, the values y1, y2, and y3 are calculated by the following linear calculation. x1=a 20 P t [t]+a 21 P t [t-1]+…+a 2N P t [tN] x2=b 20 P c [t]+b 21 P c [t-1]+…+b 2N P c [tN] x3=c 20 A1[t]+c 21 A1[t-1]+…+c 2N A1[tN]
[0043] The neural network 1344 receives the values y1, y2, and y3 as inputs and calculates the chamber pressure differential ΔP c [t+1] is output. The chamber pressure difference estimation model 134 may have other configurations. The chamber pressure difference estimation model 134 is trained in advance using data that associates the actually measured gas discharge flow rate, chamber pressure, opening of the second valve 5, and chamber pressure difference as training data.
[0044] In S106, the calculation unit 11 calculates the gas discharge flow rate F g [t+1],F g [t],…,F g [t-(N-1)] and the chamber pressure P c [t],P c [t-1],…,P c [tN] and the openings A2[t], A2[t-1], ..., A2[tN] of the second valve 5 are input to the chamber pressure difference estimation model 134, and the chamber pressure difference estimation model 134 is caused to execute processing. The calculation unit 11 calculates the predicted value of the gas discharge flow rate calculated in S103 as the gas discharge flow rate F g[t+1]. The chamber pressure difference estimation model 134 performs calculations in response to inputs of the gas discharge flow rate, the chamber pressure, and the opening of the second valve 5 at multiple points in time, and outputs the chamber pressure difference. The calculation unit 11 calculates the chamber pressure difference ΔP output by the chamber pressure difference estimation model 134. c [t+1] is acquired as the predicted value of the chamber pressure difference. In this way, the calculation unit 11 calculates the predicted value of the chamber pressure difference.
[0045] In S106, the calculation unit 11 calculates multiple predicted values of the chamber pressure difference in accordance with multiple predicted values of the gas discharge flow rate. The calculation unit 11 also calculates multiple predicted values of the chamber pressure difference based on multiple possible values of the aperture of the second valve 5. That is, the calculation unit 11 inputs each of multiple possible values of the aperture of the second valve 5 to the chamber pressure difference estimation model 134 as the value of the aperture of the second valve 5 at a certain point in time, and obtains a predicted value of the chamber pressure difference corresponding to each value. In this way, the calculation unit 11 calculates a predicted value of the chamber pressure difference for each of multiple possible values of the aperture of the second valve 5. The calculation unit 11 stores the calculated predicted value of the chamber pressure difference in the memory unit 13.
[0046] The control device 1 may be configured to calculate a predicted value of the chamber pressure difference using a regression model other than the trained model. The regression model is a model generated using data correlating the actually measured gas discharge flow rate, chamber pressure, opening of the second valve 5, and chamber pressure difference. The regression model may be realized by a function.
[0047] The control device 1 may be configured to calculate a predicted value of the chamber pressure difference using a table instead of a trained model. In this configuration, the control device 1 uses a chamber pressure difference table 135 that records the relationship between the gas discharge flow rate, chamber pressure, opening of the second valve 5, and the chamber pressure difference, instead of the chamber pressure difference estimation model 134. The memory unit 13 stores the chamber pressure difference table 135.
[0048] FIG. 9 is a chart showing an example of the contents of the chamber pressure difference table 135. In the figure, the unit of pressure is Torr, the unit of the aperture of the second valve 5 is %, and the unit of the gas discharge flow rate is sccm. The "****" in the figure indicates a chamber pressure difference. A positive chamber pressure difference value indicates that the chamber pressure at a certain point in time is lower than the chamber pressure at the next point in time. In the chamber pressure difference table 135, a table in which chamber pressure difference values associated with each combination of chamber pressure and gas discharge flow rate values are recorded is associated with each aperture value of the second valve 5. The aperture of the second valve 5 can take multiple values. Therefore, each aperture value of the second valve 5 is associated with a combination of chamber pressure, gas discharge flow rate, and chamber pressure difference.
[0049] The chamber pressure difference value obtained when the chamber pressure, gas discharge flow rate, and aperture of the second valve 5 are a certain combination of values has been theoretically or experimentally investigated and specified in advance. The chamber pressure difference table 135 records the pre-specified chamber pressure difference values. In S106, the calculation unit 11 reads from the chamber pressure difference table 135 the chamber pressure difference associated with the chamber pressure at a certain time, the predicted value of the gas discharge flow rate obtained in S103, and the aperture of the second valve 5. The calculation unit 11 sets the read chamber pressure difference as the predicted value of the chamber pressure difference. In this way, the calculation unit 11 calculates the predicted value of the chamber pressure difference.
[0050] In this embodiment as well, the calculation unit 11 calculates multiple predicted values of the chamber pressure difference in accordance with multiple predicted values of the gas discharge flow rate. The calculation unit 11 also calculates multiple predicted values of the chamber pressure difference based on multiple possible values for the opening of the second valve 5. The calculation unit 11 stores the calculated predicted values of the chamber pressure difference in the memory unit 13.
[0051] The control device 1 calculates a predicted value of the chamber pressure at the next time point (S107). In S107, the calculation unit 11 calculates the chamber pressure P c[t] chamber pressure difference ΔP c By adding the predicted value of [t+1], the chamber pressure P c [t+1] is calculated. The calculation unit 11 sets the calculated chamber pressure as the predicted value of the chamber pressure at the next time point. At this time, the calculation unit 11 calculates multiple predicted values of the chamber pressure at the next time point according to multiple predicted values of the chamber pressure difference. The calculation unit 11 stores the calculated predicted values of the chamber pressure at the next time point in the memory unit 13.
[0052] The control device 1 then advances the time point to be calculated to the next time point (S108) and returns the process to S102. The calculation unit 11 changes the time point at which the predicted value of the gas discharge flow rate should be calculated to the next time point and repeats the processes of S102 to S108. That is, the previous "next time point" becomes "a certain time point", and the processes of S102 to S108 are performed for the "certain time point". The calculation unit 11 uses the predicted value of the tank pressure calculated in S105 and the predicted value of the chamber pressure calculated in S107 as the tank pressure and chamber pressure at the certain time point in the next processes of S102 to S108.
[0053] The calculation unit 11 calculates predicted values of the gas discharge flow rate at multiple time points by repeating the processes of S102 to S108. For each time point, a predicted value of the tank pressure difference and multiple predicted values of the gas discharge flow rate and tank pressure at the time point following that time point are calculated based on multiple possible values of the aperture of the first valve 3. Furthermore, a predicted value of the chamber pressure difference and chamber pressure at the time point following that time point are calculated based on multiple possible values of the aperture of the second valve 5. The predicted values of the tank pressure and chamber pressure are used in the calculation for the time point following that time point. Therefore, the aperture of the second valve 5 also affects the predicted value of the gas discharge flow rate. For one time point, a predicted value of the gas discharge flow rate is calculated for each of multiple possible combinations of the aperture of the first valve 3 and the aperture of the second valve 5, and a predicted value of the gas discharge flow rate is calculated similarly for each time point. As a result, predicted values of the gas discharge flow rate at multiple points in time are calculated for each of multiple possible combinations of the opening degrees of the first valve 3 and the second valve 5 at multiple points in time.
[0054] When the control device 1 has calculated the predicted values of the gas discharge flow rate at a predetermined number of time points (S104: YES), it acquires the target values of the gas discharge flow rate (S109). The target values of the gas discharge flow rate at a plurality of time points are stored in advance in the storage unit 13. In S109, the calculation unit 11 acquires the target values of the gas discharge flow rate at a plurality of time points by reading them from the storage unit 13. The control device 1 may be configured so that the target values are input by the user.
[0055] The control device 1 then calculates the error between the predicted value of the gas discharge flow rate and the target value of the gas discharge flow rate (S110). In S110, the calculation unit 11 calculates the square of the difference between the predicted value of the gas discharge flow rate at each time point and the target value, and calculates the error by summing the calculated square values over multiple time points. The calculation unit 11 may also calculate the error by summing the absolute values of the differences between the predicted value of the gas discharge flow rate at each time point and the target value over multiple time points. The calculation unit 11 may also calculate the error by summing the absolute value of the differences between the predicted value of the gas discharge flow rate at each time point and the target value over multiple time points. The calculation unit 11 calculates the error for each of multiple possible combinations of the aperture of the first valve 3 and the aperture of the second valve 5 at multiple time points. That is, the calculation unit 11 calculates the error using the predicted values of the gas discharge flow rate at multiple time points calculated for each of the multiple combinations.
[0056] The control device 1 then determines the aperture of the first valve 3 and the aperture of the second valve 5 at multiple time points so as to minimize the error in the gas discharge flow rate (S111). In S111, the calculation unit 11 selects, from multiple possible combinations of the aperture of the first valve 3 and the aperture of the second valve 5 at multiple time points, a combination that minimizes the calculated error. The calculation unit 11 determines the aperture of the first valve 3 and the aperture of the second valve 5 at each time point according to the selected combination. In this way, the control device 1 collectively determines the aperture of the first valve 3 at multiple future time points.
[0057] The control device 1 may also determine the aperture of the first valve 3 and the aperture of the second valve 5 using the chamber pressure error. In this case, the memory unit 13 stores target chamber pressure values at multiple time points, and the calculation unit 11 calculates the error between the predicted chamber pressure value and the target value. The error may be, for example, the sum of the squared or absolute values of the difference between the predicted and target chamber pressure values at each time point, or the absolute value of the sum of the differences between the predicted and target chamber pressure values at each time point. The calculation unit 11 selects, from multiple possible combinations of the aperture of the first valve 3 and the aperture of the second valve 5 at multiple time points, a combination that minimizes the sum of the error in the gas discharge flow rate and the error in the chamber pressure. The calculation unit 11 determines the aperture of the first valve 3 and the aperture of the second valve 5 at each time point according to the selected combination.
[0058] The control device 1 stores the opening degrees of the first valve 3 at the determined multiple time points (S112). The calculation unit 11 generates opening degree data recording the opening degrees of the first valve 3 at the determined multiple time points, and stores the generated opening degree data 136 in the storage unit 13. FIG. 10 is a conceptual diagram showing an example of the contents of the opening degree data 136. Each of the multiple time points is indicated by t1, t2, .... In the opening degree data 136, the opening degree of the first valve 3 is recorded in association with each time point. As shown in FIG. 10, the opening degree data 136 may also record a predicted value and a target value of the gas discharge flow rate. In addition, the opening degree data 136 may also record the opening degree of the second valve 5.
[0059] After S112 is completed, the control device 1 ends the process of collectively determining the opening degree of the first valve 3 at multiple points in time. The opening degree of the first valve 3 at multiple points in time in the future is determined by the processes of S101 to S112. After the processes of S101 to S112 are completed, the control device 1 actually performs a process of adjusting the opening degree of the first valve 3.
[0060] 11 is a flowchart showing an example of the procedure of the process in which the control device 1 actually adjusts the opening of the first valve 3. The control device 1 adjusts the actual opening of the first valve 3 to match the determined opening of the first valve 3 (S21). In S21, the calculation unit 11 reads out the value of the opening of the first valve 3 associated with the current time from the opening data 136. The calculation unit 11 transmits a control signal from the interface unit 15 to the valve controller 31 to set the opening of the first valve 3 to the read opening. In accordance with the control signal, the valve controller 31 controls the first valve 3 so that the value of the opening of the first valve 3 matches the value read out from the opening data 136. In this way, the actual opening of the first valve 3 is adjusted to match the determined opening of the first valve 3.
[0061] The control device 1 may adjust the opening degree of the second valve 5 in parallel with adjusting the opening degree of the first valve 3. For example, the opening degree of the second valve 5 at each time point determined by the processes of S101 to S112 is recorded in the opening degree data 136, and the control device 1 adjusts the actual opening degree of the second valve 5 to match the determined opening degree of the second valve 5.
[0062] The control device 1 acquires an actual measurement value of the gas discharge flow rate from the tank 2 to the chamber 4 (S22). In S22, the calculation unit 11 acquires the actual measurement value of the gas discharge flow rate by converting the differential pressure of the tank 2 into a flow rate. Specifically, the calculation unit 11 acquires the current tank pressure using the pressure gauge 21, and calculates the differential pressure of the tank 2 by subtracting the current tank pressure from the predicted value of the tank pressure at the next time point. The calculation unit 11 calculates the actual measurement value of the gas discharge flow rate by multiplying the differential pressure of the tank 2 by a conversion coefficient that converts pressure to flow rate. The conversion coefficient is stored in advance in the storage unit 13. The calculation unit 11 stores the actual measurement value of the gas discharge flow rate in the storage unit 13. For example, the calculation unit 11 records the actual measurement value of the gas discharge flow rate in the opening data 136 in association with the current time point.
[0063] In S22, the calculation unit 11 may acquire an actual measured value of the gas discharge flow rate using an equation for the conductance of the tank 2. Specifically, the calculation unit 11 acquires the current tank pressure and chamber pressure using the pressure gauges 21 and 41, calculates the differential pressure of the tank 2, and calculates the differential pressure of the chamber 4 by subtracting the current chamber pressure from the predicted value of the chamber pressure at the next time point. The calculation unit 11 calculates the actual measured value of the gas discharge flow rate by multiplying the value obtained by subtracting the differential pressure of the chamber 4 from the differential pressure of the tank 2 by the conductance. The conductance value is stored in advance in the storage unit 13. The calculation unit 11 stores the actual measured value of the gas discharge flow rate in the storage unit 13.
[0064] The control device 1 determines whether the opening degree of the first valve 3 has been adjusted at all time points for which the opening degree of the first valve 3 has been determined (S23). If there is a time point for which the opening degree of the first valve 3 has not been adjusted (S23: NO), the control device 1 returns to S21 and adjusts the opening degree of the first valve 3 at the next time point. If the opening degree of the first valve 3 has been adjusted at all time points for which the opening degree of the first valve 3 has been determined (S23: YES), the control device 1 calculates the error between the target value and the actual measured value of the gas discharge flow rate (S24). In S24, the calculation unit 11 calculates the error between the target value and the actual measured value of the gas discharge flow rate by subtracting the actual measured value of the gas discharge flow rate from the target value of the gas discharge flow rate at each time point. The calculation unit 11 records the error at each time point in the opening degree data 136 in association with each time point.
[0065] The control device 1 then corrects the aperture of the first valve 3 based on the calculated error (S25). In S25, the calculation unit 11 corrects the aperture of the first valve 3 by subtracting a value obtained by multiplying the error between the target value and the actual measurement value of the gas discharge flow rate at each time point by a predetermined coefficient from the aperture of the first valve 3 at each time point. Other methods for correcting the aperture of the first valve 3 may also be used. For example, the calculation unit 11 may calculate an aperture correction amount based on the error between the target value and the actual measurement value of the gas discharge flow rate as a control value for a feedback control method such as PID (Proportional-Integral-Differential) control, and correct the aperture of the first valve 3 by subtracting the aperture correction amount from the aperture of the first valve 3. The calculation unit 11 records the corrected aperture value of the first valve 3 at each time point in the aperture data 136.
[0066] 12 is a conceptual diagram showing an example of the contents of the opening data 136 after the opening of the first valve 3 has been corrected. A plurality of time points at which the opening of the first valve 3 is adjusted by the processes of S21 to S25 are collectively referred to as the first cycle. Next, a plurality of time points at which the opening of the first valve 3 should be adjusted are collectively referred to as the second cycle. Each time point included in the first cycle is associated with an error between the target value and the actual measured value of the gas discharge flow rate. Each time point included in the second cycle is associated with a corrected value of the opening of the first valve 3.
[0067] After S25 ends, the control device 1 ends the process of actually adjusting the opening degree of the first valve 3. By executing the processes of S21 to S25, the control device 1 sequentially applies the opening degrees of the first valve 3 at the determined multiple time points to the first valve 3. In this way, the control device 1 adjusts the opening degree of the first valve 3 at the multiple time points. Thereafter, the control device 1 adjusts the opening degree of the first valve 3 at each time point included in the second cycle by executing the processes of S21 to S25 again using the opening degree data 136 after the opening degree of the first valve 3 has been corrected. In the same manner, the control device 1 repeats the processes of S21 to S25 to adjust the opening degree of the first valve 3 at each time point included in the third cycle and thereafter.
[0068] As described above in detail, the control device 1 determines the aperture of the first valve 3 so as to minimize the error between the predicted value of the gas discharge flow rate, which is based on the tank pressure, the chamber pressure, and the aperture of the first valve 3, and the target value of the gas discharge flow rate. A tank pressure difference is calculated based on the tank pressure, the chamber pressure, and the aperture of the first valve 3, and a predicted value of the gas discharge flow rate is calculated based on the tank pressure difference. The control device 1 adjusts the actual aperture of the first valve 3 to match the determined aperture of the first valve 3. Since the aperture of the first valve 3 is determined so as to minimize the error between the predicted value of the gas discharge flow rate, which is obtained based on the aperture of the first valve 3, and the target value, it is possible to accurately adjust the aperture of the first valve 3. By accurately adjusting the aperture of the first valve 3, it is possible to accurately adjust the gas discharge rate from the tank 2 to the chamber 4.
[0069] The chamber pressure is adjusted precisely by precisely adjusting the amount of gas discharged from the tank 2 to the chamber 4. Since the substrate processing apparatus 100 can precisely adjust the chamber pressure, it can stabilize the chamber pressure while substrate processing is being performed inside the chamber 4, enabling stable substrate processing. Furthermore, the control apparatus 1 can arbitrarily adjust the change in the gas discharge flow rate over time by appropriately setting a target value for the gas discharge flow rate.
[0070] In this embodiment, the control device 1 collectively determines the opening degrees of the first valve 3 at multiple points in time before adjusting the actual opening degree of the first valve 3. The control device 1 adjusts the actual opening degree of the first valve 3 at the multiple points in time according to the determined opening degrees. A certain amount of processing time is required to accurately determine the opening degree of the first valve 3. By collectively determining the opening degrees of the first valve 3 at multiple points in time and then adjusting the actual opening degree of the first valve 3, the control device 1 can accurately adjust the opening degree of the first valve 3 at an appropriate timing without being affected by the processing time required to determine the opening degree.
[0071] By determining the aperture of the first valve 3 at multiple time points simultaneously, it is possible to use the absolute value of the sum of the differences between the predicted value and the target value over multiple time points, or the sum of the squares of the differences over multiple time points, as the error between the predicted value and the target value of the gas discharge flow rate. By utilizing such an error, the aperture of the first valve 3 is determined so that the difference between the predicted value and the target value of the gas discharge flow rate over multiple time points is small on average. Therefore, the control device 1 can accurately adjust the aperture of the first valve 3 over a certain period of time, and accurately adjust the gas discharge rate from the tank 2 to the chamber 4.
[0072] In this embodiment, the control device 1 uses the determined opening degree of the first valve 3 at multiple points in time to repeat multiple cycles of adjusting the actual opening degree of the first valve 3. This allows the control device 1 to adjust the opening degree of the first valve 3 over a long period of time and adjust the amount of gas discharged from the tank 2 to the chamber 4. The control device 1 also corrects the opening degree of the first valve at multiple points in time based on the error between the target value and the actual measured value of the gas discharge flow rate. Even if an error occurs between the target value and the actual measured value of the gas discharge flow rate, the opening degree of the first valve is corrected in accordance with the error, so the gas discharge flow rate can be adjusted with greater precision. This allows the control device 1 to adjust the gas discharge rate with high precision over a long period of time.
[0073] <Embodiment 2> The configuration of the substrate processing apparatus 100 according to the second embodiment is the same as that according to the first embodiment. In the second embodiment, the control device 1 also performs a process of collectively determining the aperture of the first valve 3 at multiple future time points before actually starting to adjust the aperture of the first valve 3. Fig. 13 is a flowchart showing an example of the procedure of the process of collectively determining the aperture of the first valve 3 at multiple future time points, which is executed by the control device 1 according to the second embodiment. The control device 1 acquires the tank pressure and the chamber pressure (S301).
[0074] The control device 1 calculates a predicted value of the tank pressure difference (S302). The control device 1 calculates the predicted value of the tank pressure difference using the tank pressure difference estimation model 132. FIG. 14 is a conceptual diagram showing an example of the function of the tank pressure difference estimation model 132 according to the second embodiment. The tank pressure difference estimation model 132 calculates the predicted value of the tank pressure difference P t [t] and the chamber pressure P at a certain time c [t] and the opening A1[t] of the first valve 3 at a certain time are input, the tank pressure difference ΔP t The tank pressure difference estimation model 132 is trained in advance using data in which the actually measured tank pressure, chamber pressure, opening degree of the first valve 3, and tank pressure difference are associated as training data.
[0075] In S302, the calculation unit 11 calculates the tank pressure P t [t] and chamber pressure P c [t] and the opening A1[t] of the first valve 3 are input to the tank pressure difference estimation model 132, and the tank pressure difference estimation model 132 executes processing. The tank pressure difference estimation model 132 performs calculations in response to the inputs of the tank pressure, chamber pressure, and opening of the first valve 3, and outputs the tank pressure difference. The calculation unit 11 calculates the tank pressure difference ΔP t [t+1] is acquired as the predicted value of the tank pressure difference. In S302, the calculation unit 11 calculates the predicted value of the tank pressure difference for each of a plurality of values that can be taken as the opening degree of the first valve 3.
[0076] The control device 1 may be configured to calculate the predicted value of the tank pressure difference using a tank pressure difference table 133 instead of the tank pressure difference estimation model 132. The contents of the tank pressure difference table 133 are the same as in the first embodiment. In this configuration, the calculation unit 11 reads out a tank pressure difference associated with the tank pressure and chamber pressure at a certain point in time and the aperture of the first valve 3 from the tank pressure difference table 133. The calculation unit 11 uses the read tank pressure difference as the predicted value of the tank pressure difference. In this configuration as well, the calculation unit 11 calculates the predicted value of the tank pressure difference for each of multiple possible values for the aperture of the first valve 3. The calculation unit 11 stores the calculated predicted value of the tank pressure difference in the memory unit 13.
[0077] The control device 1 calculates a predicted value of the gas discharge flow rate at the next time point (S303). In S33, the calculation unit 11 calculates a predicted value of the gas discharge flow rate at the next time point in the same manner as in embodiment 1. At this time, the calculation unit 11 calculates a predicted value of the gas discharge flow rate for each of a plurality of possible values for the opening degree of the first valve 3. The calculation unit 11 stores the calculated predicted value of the gas discharge flow rate in the memory unit 13.
[0078] The control device 1 acquires the target value of the gas discharge flow rate (S304). In S304, the calculation unit 11 acquires the target value of the gas discharge flow rate by reading it from the storage unit 13. The control device 1 may be configured so that the user inputs the target value. The control device 1 then calculates the error between the predicted value of the gas discharge flow rate and the target value of the gas discharge flow rate (S305). In S305, the calculation unit 11 calculates the absolute value or square value of the difference between the predicted value and the target value of the gas discharge flow rate as the error. At this time, the calculation unit 11 calculates the error for each of multiple combinations of the opening degree of the first valve 3 that can be taken.
[0079] The control device 1 then determines the aperture of the first valve 3 so as to minimize the error in the gas discharge flow rate (S306). In S306, the calculation unit 11 determines the aperture of the first valve 3 by selecting a value that minimizes the calculated error from among multiple possible values that the aperture of the first valve 3 can take. The calculation unit 11 stores the determined aperture of the first valve 3 in the memory unit 13. Specifically, the calculation unit 11 records the determined value of the aperture of the first valve 3 in the aperture data 136 in association with a certain point in time.
[0080] The control device 1 calculates the predicted value of the tank pressure at the next time point (S307). In S307, the calculation unit 11 calculates the predicted value of the tank pressure P t At [t], the tank pressure difference ΔP obtained according to the determined opening degree of the first valve 3 t By adding the predicted value of [t+1], the tank pressure P t [t+1] is calculated. The calculation unit 11 sets the calculated tank pressure as the predicted value of the tank pressure at the next time point. The calculation unit 11 stores the calculated predicted value of the tank pressure in the storage unit 13.
[0081] The control device 1 then calculates a predicted value of the chamber pressure difference (S308). The control device 1 calculates the predicted value of the chamber pressure difference using the chamber pressure difference estimation model 134. FIG. 15 is a conceptual diagram showing an example of the function of the chamber pressure difference estimation model 134 according to the second embodiment. The chamber pressure difference estimation model 134 calculates the predicted value of the chamber pressure difference using the gas discharge flow rate F g [t+1] and chamber pressure P c [t] of the second valve 5 and the opening A2[t] of the second valve 5 are input, the chamber pressure difference ΔP c The chamber pressure difference estimation model 134 is trained in advance using data in which the actually measured gas discharge flow rate, chamber pressure, opening of the second valve 5, and chamber pressure difference are associated as training data.
[0082] In S308, the calculation unit 11 calculates the gas discharge flow rate F g [t+1] and chamber pressure Pc [t] of the second valve 5 and the opening degree A2[t] of the second valve 5 are input to the chamber pressure difference estimation model 134, and the chamber pressure difference estimation model 134 is caused to execute processing. The calculation unit 11 calculates the predicted value of the gas discharge flow rate calculated in S303 as the gas discharge flow rate F g [t+1]. The chamber pressure difference estimation model 134 performs calculations in response to inputs of the gas discharge flow rate, the chamber pressure, and the opening of the second valve 5, and outputs the chamber pressure difference. The calculation unit 11 calculates the chamber pressure difference ΔP output by the chamber pressure difference estimation model 134. c [t+1] is acquired as the predicted value of the chamber pressure difference. In S308, the calculation unit 11 calculates the predicted value of the chamber pressure difference for each of a plurality of values that can be taken as the opening degree of the second valve 5.
[0083] The control device 1 may be configured to calculate the predicted value of the chamber pressure difference using a chamber pressure difference table 135 instead of the chamber pressure difference estimation model 134. The contents of the chamber pressure difference table 135 are the same as in the first embodiment. In this configuration, the calculation unit 11 reads out the chamber pressure difference associated with the chamber pressure at a certain point in time, the predicted value of the gas discharge flow rate obtained in S303, and the aperture of the second valve 5 from the chamber pressure difference table 135. In this configuration as well, the calculation unit 11 calculates the predicted value of the chamber pressure difference for each of a plurality of possible values for the aperture of the second valve 5. The calculation unit 11 stores the calculated predicted value of the chamber pressure difference in the memory unit 13.
[0084] The control device 1 calculates a predicted value of the chamber pressure at the next time point (S309). In S309, the calculation unit 11 calculates a predicted value of the chamber pressure at the next time point in the same manner as in embodiment 1. At this time, the calculation unit 11 calculates a predicted value of the chamber pressure for each of a plurality of possible values for the opening degree of the second valve 5. The calculation unit 11 stores the calculated predicted value of the chamber pressure in the memory unit 13.
[0085] The control device 1 acquires the target value of the chamber pressure (S310). In S310, the calculation unit 11 acquires the target value of the chamber pressure by reading it from the storage unit 13. The control device 1 may be configured so that the user inputs the target value. The control device 1 then calculates the error between the predicted value of the chamber pressure and the target value of the chamber pressure (S311). In S311, the calculation unit 11 calculates the absolute value or square value of the difference between the predicted value and the target value of the chamber pressure as the error. At this time, the calculation unit 11 calculates the error for each of multiple possible combinations of the opening degree of the second valve 5.
[0086] The control device 1 then determines the aperture of the second valve 5 so as to minimize the error in the chamber pressure (S312). In S312, the calculation unit 11 determines the aperture of the second valve 5 by selecting a value that minimizes the calculated error from among multiple possible values that the aperture of the second valve 5 can take. The calculation unit 11 stores the determined aperture of the second valve 5 in the memory unit 13. For example, the calculation unit 11 records the determined value of the aperture of the second valve 5 in the aperture data 136 in association with a certain point in time.
[0087] After S312 is completed, the control device 1 ends the processing. The control device 1 repeats the processing of S301 to S312 at the next time point. The predicted value of the tank pressure calculated in S307 and the predicted value of the chamber pressure calculated in S309 are acquired as the tank pressure and the chamber pressure in S301 at the next time point. By repeating the processing of S301 to S312 multiple times, the control device 1 collectively determines the opening degree of the first valve 3 at multiple future time points. After the repetition of the processing of S301 to S312 is completed, the control device 1 actually adjusts the opening degree of the first valve 3 by executing the processing of S21 to S25, as in the first embodiment.
[0088] The control device 1 may be configured to determine the aperture of the first valve 3 at each point in time and execute a process of adjusting the aperture of the first valve 3 in real time. In this configuration, the control device 1 executes the processes of S301 to S306, and after S306, actually adjusts the aperture of the first valve 3 to match the determined aperture of the first valve 3. Thereafter, the control device 1 executes the processes of S307 to S312, and after S312, adjusts the actual aperture of the second valve 5 to match the determined aperture of the second valve 5. The control device 1 repeats the above processes. In this configuration as well, the flow rate of gas discharged from the tank 2 can be adjusted by adjusting the aperture of the second valve 5.
[0089] In this embodiment as well, the aperture of the first valve 3 is determined so as to reduce the error between the predicted value of the gas discharge flow rate obtained based on the aperture of the first valve 3 and the target value, so that the control device 1 can accurately adjust the aperture of the first valve 3. Therefore, the control device 1 can accurately adjust the gas discharge rate from the tank 2 to the chamber 4. The substrate processing apparatus 100 can accurately adjust the chamber pressure and can stably perform substrate processing.
[0090] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. In other words, embodiments obtained by combining technical means modified appropriately within the scope of the claims are also included in the technical scope of the present invention.
[0091] The matters described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in any combination, regardless of the reference format. Furthermore, although the claims use a format in which a claim references two or more other claims (multiple claim format), this is not limited to this format. A multiple claim (multi-multi claim) that references at least one other multiple claim may also be used. [Explanation of symbols]
[0092] 100 Substrate processing apparatus 1. Control device 10 Recording media 11 Arithmetic section 13 Storage section 131 Computer Programs 132 Tank pressure differential estimation model 133 Tank Pressure Differential Table 134 Chamber pressure differential estimation model 135 Chamber Pressure Differential Table 2 Tanks 3 First Valve 4 chambers 5 Second valve
Claims
1. 1. A control method for controlling a substrate processing apparatus including: a tank for storing a predetermined gas; a first valve for discharging the gas from the tank; and a chamber for processing a substrate, the chamber receiving the gas from the tank via the first valve, the method comprising: calculating a predicted value of a tank pressure difference, which is the difference between the tank pressure and the tank pressure after a predetermined time, based on a tank pressure, which is the pressure inside the tank, a chamber pressure, which is the pressure inside the chamber, and an opening degree of the first valve; calculating a predicted value of the gas discharge flow rate from the tank to the chamber after a predetermined time based on the calculated predicted value of the tank pressure difference; determining an opening degree of the first valve so as to reduce an error between the calculated predicted value of the gas discharge flow rate and a target value of the gas discharge flow rate; The actual opening of the first valve is adjusted to match the determined opening of the first valve. Control method.
2. Calculating predicted values of gas discharge flow rates at multiple points in time; The error is an absolute value of the sum of the differences between the predicted values and the target values of the gas discharge flow rate at each of the plurality of time points over the plurality of time points, or a value of the sum of the squares of the differences between the predicted values and the target values of the gas discharge flow rate at each of the plurality of time points over the plurality of time points. The control method according to claim 1 .
3. the substrate processing apparatus further includes a second valve configured to exhaust the gas from the chamber; calculating a plurality of predicted values of the tank pressure difference based on a plurality of possible values of the tank pressure, the chamber pressure, and the opening degree of the first valve; Based on the multiple predicted values of the tank pressure difference, multiple predicted values of the tank pressure and the gas discharge flow rate at the next time point are calculated, calculating a plurality of predicted chamber pressure values at a next time point based on a plurality of possible values of the predicted gas discharge flow rate, the chamber pressure, and the opening degree of the second valve for each of the plurality of predicted gas discharge flow rate values; repeatedly calculating a predicted value of a tank pressure difference, and a plurality of predicted values of the tank pressure, gas discharge flow rate, and chamber pressure at a time point subsequent to the time point, based on the predicted value of the tank pressure, the predicted value of the chamber pressure, a plurality of possible values for the opening of the first valve, and a plurality of possible values for the opening of the second valve; The opening of the first valve is determined by selecting a combination that minimizes the error from among a plurality of possible combinations of the opening of the first valve at a plurality of time points. The control method according to claim 2 .
4. calculating a predicted chamber pressure difference, which is a difference between the chamber pressure and the chamber pressure after a predetermined time, based on the predicted gas discharge flow rate, the chamber pressure, and the opening of the second valve; Calculating a predicted chamber pressure after a predetermined time based on the calculated predicted chamber pressure difference The control method according to claim 3 .
5. Before adjusting the actual opening degree of the first valve, the opening degree of the first valve at a plurality of time points is determined collectively; The opening degrees of the first valve at the plurality of determined time points are sequentially applied to the first valve, thereby adjusting the actual opening degree of the first valve. The control method according to claim 2 .
6. The process of sequentially applying the opening degrees of the first valve at a plurality of time points to the first valve is repeated a plurality of times. The control method according to claim 5 .
7. When the opening degrees of the first valve at a plurality of time points are sequentially applied to the first valve, actual measured values of the gas discharge flow rate at the plurality of time points are obtained; Calculating the error between the target value and the actual measured value of the gas discharge flow rate at multiple points in time; correcting the opening degree of the first valve at a plurality of time points using the calculated error; In the next cycle, the corrected opening is applied to the first valve. The control method according to claim 6.
8. A predicted value of the tank pressure difference is calculated by inputting the tank pressure, the chamber pressure, and the opening of the first valve into a trained model that outputs a predicted value of the tank pressure difference when the tank pressure, the chamber pressure, and the opening of the first valve are input, and obtaining the predicted value of the tank pressure difference output by the trained model. A control method according to any one of claims 1 to 7.
9. A predicted value of the tank pressure difference is calculated by reading out the tank pressure, chamber pressure, and tank pressure difference corresponding to the tank pressure, chamber pressure, and opening degree of the first valve from a table in which the relationships between the tank pressure, chamber pressure, opening degree of the first valve, and tank pressure difference are recorded. A control method according to any one of claims 1 to 7.
10. A control device for controlling a tank that stores a predetermined gas, a first valve that discharges the gas from the tank, and a chamber that receives the gas from the tank via the first valve and performs substrate processing, the control device comprising: A calculation unit is provided, The calculation unit calculating a predicted value of a tank pressure difference, which is the difference between the tank pressure and the tank pressure after a predetermined time, based on a tank pressure, which is the pressure inside the tank, a chamber pressure, which is the pressure inside the chamber, and an opening degree of the first valve; calculating a predicted value of the gas discharge flow rate from the tank to the chamber after a predetermined time based on the calculated predicted value of the tank pressure difference; determining an opening degree of the first valve so as to reduce an error between the calculated predicted value of the gas discharge flow rate and a target value of the gas discharge flow rate; The actual opening of the first valve is adjusted to match the determined opening of the first valve. Control device.
11. A computer program that causes a computer to execute a process of calculating numerical values used to control a tank that stores a predetermined gas, a first valve that discharges the gas from the tank, and a chamber that receives the gas from the tank via the first valve and performs substrate processing, the computer program comprising: calculating a predicted value of a tank pressure difference, which is the difference between the tank pressure and the tank pressure after a predetermined time, based on a tank pressure, which is the pressure inside the tank, a chamber pressure, which is the pressure inside the chamber, and an opening degree of the first valve; calculating a predicted value of the gas discharge flow rate from the tank to the chamber after a predetermined time based on the calculated predicted value of the tank pressure difference; The opening of the first valve is determined so as to reduce the error between the calculated predicted value of the gas discharge flow rate and the target value of the gas discharge flow rate. A computer program that causes a computer to perform a process.
Citation Information
Patent Citations
Apparatus for supplying gas, system for processing substrate, and method for supplying gas
JP2022053439A