Control system, control method, computer program product, and processing system

Abstract

The problem of the present invention is to stably control the state within the processing device. The method for solving the problem is that the control system has a determination unit, a simulation unit, a first control signal generation unit, a second control signal generation unit, a first adjustment unit, and a second adjustment unit. The determination unit is based on a scenario determination model and a control algorithm. The simulation unit simulates the state of the processing device using a model. The first control signal generation unit generates a control signal from a measurement value using the control algorithm and inputs the generated control signal to the processing device. The second control signal generation unit generates a control signal from the output value of the simulation unit using the control algorithm and inputs the generated control signal to the simulation unit. The first adjustment unit adjusts the value of the model parameters included in the model based on the measurement value and the output value. The second adjustment unit adjusts the value of the control parameters included in the control algorithm using the model including the adjusted value of the model parameters.

Description

Technical Field

[0001] Aspects and embodiments of the present invention relate to a control system, a control method, a control program, and a processing system. Background Art

[0002] In a processing apparatus that processes a substrate using plasma, such as etching, it is required to stably ignite plasma in the processing apparatus. During the process of generating plasma in the processing apparatus, the impedance of the plasma changes at all times, and for each moment, the value of the optimum constant of the matching circuit provided between the plasma and the power supply source is different. Regarding the method of changing the constant of the matching circuit for stably igniting the plasma, it is determined by, for example, repeated experiments.

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2019-71270. Summary of the Invention

[0006] Technical Problem to be Solved by the Invention

[0007] The present invention provides a control system, a control method, a control program, and a processing system capable of stably controlling the state in a processing apparatus.

[0008] Technical Solution for Solving the Technical Problem

[0009] One aspect of the present invention relates to a control system having a determination unit, a simulation unit, a first control signal generation unit, a second control signal generation unit, a first adjustment unit, and a second adjustment unit. The determination unit determines a model and a control algorithm corresponding to a processing apparatus for processing a substrate based on a recipe that describes conditions for processing the substrate. The control algorithm is an algorithm for generating a control signal based on a measurement value measured by a measuring device provided in the processing apparatus, and the control signal is used to control the processing apparatus so that the state of the processing apparatus becomes a predetermined state. The simulation unit simulates the state of the processing apparatus using the model. The first control signal generation unit generates a control signal based on the measurement value using the control algorithm determined by the determination unit, and inputs the generated control signal to the processing apparatus. The second control signal generation unit generates a control signal based on the output value of the simulation unit corresponding to the measurement value using the control algorithm determined by the determination unit, and inputs the generated control signal to the simulation unit. The first adjustment unit adjusts the value of a model parameter included in the model so that the difference between the measurement value and the output value of the simulation unit becomes smaller. The second adjustment unit adjusts the value of a control parameter included in the control algorithm used by the second control signal generation unit so that an evaluation value calculated for the output value of the simulation unit using the model including the adjusted value of the model parameter approaches a target value. In addition, the first control signal generation unit generates a control signal based on the measurement value using the value of the control parameter adjusted by the second adjustment unit.

[0010] Advantages of the Invention

[0011] By using the aspects and embodiments of the present invention, the state inside the processing apparatus can be stably controlled. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 FIG. is an example of a processing system according to an embodiment of the present invention.

[0013] Figure 2 FIG. is an example of a control system according to the first embodiment.

[0014] Figure 3 FIG. is an example of a control table according to the first embodiment.

[0015] Figure 4 FIG. is an example of a model.

[0016] Figure 5 FIG. is a flowchart of an example of processing of the control system.

[0017] Figure 6 FIG. is an example of a computer that implements the functions of the control system.

[0018] Figure 7 FIG. is an example of a control table according to the second embodiment.

[0019] Figure 8 This is a diagram showing an example of a control table for the second embodiment.

[0020] Figure 9 This is a diagram showing an example of a history record table.

[0021] Figure 10 This is a diagram for explaining an example of a method for estimating an initial value of a control parameter.

[0022] Figure 11 This is a diagram showing an example of a control system for the fourth embodiment.

[0023] Symbol Explanation

[0024] W: Substrate; 1: Processing system; 100: Processing device; 10: Chamber; 10e: Exhaust port; 10s: Processing space; 11: Support part; 111: Lower electrode; 112: Electrostatic chuck; 113: Edge ring; 12: Upper electrode showerhead component; 12a: Gas inlet; 12b: Gas diffusion chamber; 12c: Gas outlet; 20: Gas supply unit; 21: Gas source; 22: Flow controller; 30: RF power supply unit; 31: RF generation unit; 32: Matching circuit; 40: Exhaust system; 200: Control system; 2000: First device; 2001: Second device; 201: Decision unit; 2010: Control table; 2012: Plan ID; 2013: Individual table; 2020: History record table; 2021: Plan ID; 2022: Individual table; 202: First control signal generation unit; 203: Second control signal generation unit; 204: Simulation unit; 205: First adjustment unit; 206: Second adjustment unit; 207: Holding unit; 208: Feature quantity generation unit; 50: Value; 51: Approximation curve; 52: Initial value; 90: Computer; 91: CPU; 92: RAM; 93: ROM; 94: Auxiliary storage device; 95: Communication I / F; 96: Input / output I / F; 97: Medium I / F; 98: Recording medium. Detailed Embodiment

[0025] Hereinafter, embodiments of a control system, a control method, a control program, and a processing system will be described in detail based on the drawings. Note that the disclosed control system, control method, control program, and processing system are not limited to the following embodiments.

[0026] When the substrate is repeatedly processed, it causes the consumption of components in the processing apparatus and the deposition of reaction by-products (so-called deposits) in the processing apparatus. As a result, the state in the processing apparatus changes, and the impedance of the plasma further changes. For this reason, a method of changing the constants of the matching circuit according to the consumption amount of components in the processing apparatus and the deposition amount of deposits in the processing apparatus has been considered, but it is necessary to conduct experiments on all conditions of the consumption amount of components and the deposition amount of deposits, and the number of experiments is extremely large. Therefore, it is difficult to change the method of changing the constants of the matching circuit according to the deposition amount of deposits in the processing apparatus.

[0027] In addition, since the dimensional errors or assembly errors of the components of each processing apparatus are different, the method of optimally changing the constants of the matching circuit for stable plasma ignition is different for each processing apparatus. In addition, even for the same processing apparatus, when replacing the consumable components, the dimensional errors or assembly errors may sometimes be different before and after the replacement of the consumable components. Therefore, when the method of changing the constants of the matching circuit is the same before and after the replacement of the consumable components, the plasma may sometimes not be able to ignite stably after the replacement of the consumable components. Thus, when changing the method of changing the constants of the matching circuit according to the dimensional errors or assembly errors of the consumable components in the processing apparatus, it is necessary to conduct experiments on all conditions of the dimensional errors or assembly errors of all consumable components, and the number of experiments is extremely large. Therefore, it is difficult to change the method of changing the constants of the matching circuit according to the dimensional errors or assembly errors of the consumable components in the processing apparatus.

[0028] In addition, in the processing of the substrate, in addition to the plasma, the state in the processing apparatus such as the temperature distribution of the substrate and the concentration distribution of the gas in the processing apparatus also changes constantly. In order to stably control the state in the processing apparatus to the desired state, it is required to control the controllable values such as the heater power, the gas flow rate, and the pressure to the optimal values according to the state in the processing apparatus at this time. Regarding the method of changing these values, it is considered to be determined by, for example, repeated experiments, but it is difficult to conduct experiments on all combinations of factors such as the mechanical differences of the processing apparatus, the state in the processing apparatus, the type of gas used, the gas flow rate, the temperature, and the pressure.

[0029] Therefore, the present invention provides a technique capable of stably controlling the state in the processing apparatus.

[0030] (First Embodiment)

[0031] [Configuration of Processing System 1]

[0032] Figure 1FIG. 0 is a diagram showing an example of a processing system 1 according to an embodiment of the present invention. In one embodiment, the processing system 1 includes a processing apparatus 100 and a control system 200. In the present embodiment, the processing apparatus 100 is an apparatus for processing a substrate W by using plasma, such as etching, film formation, or modification. The processing apparatus 100 includes a chamber 10, a gas supply unit 20, an RF (Radio Frequency) power supply unit 30, and an exhaust system 40. Each part of the processing apparatus 100 is controlled by the control system 200.

[0033] In the present embodiment, the chamber 10 includes a support portion 11 and an upper electrode showerhead member 12. The support portion 11 is disposed in a lower region of a processing space 10s inside the chamber 10. The upper electrode showerhead member 12 is disposed above the support portion 11 and can function as a part of a top plate of the chamber 10.

[0034] The support portion 11 is configured to support the substrate W in the processing space 10s. In the present embodiment, the support portion 11 includes a lower electrode 111, an electrostatic chuck 112, and an edge ring 113. The electrostatic chuck 112 is disposed on the lower electrode 111 and is configured to support the substrate W by an upper surface of the electrostatic chuck 112. A heater (not shown) is provided inside the electrostatic chuck 112, and the temperature of the substrate W disposed on the electrostatic chuck 112 is controlled by the heater. The edge ring 113 is disposed to surround the substrate W on an upper surface of a peripheral portion of the lower electrode 111. A temperature sensor (not shown) for measuring the temperature of the substrate W disposed on the electrostatic chuck 112 is provided on the electrostatic chuck 112. A measured value of the temperature obtained by the temperature sensor is output to the control system 200.

[0035] The upper electrode showerhead member 12 is configured to supply one or more kinds of gases from the gas supply unit 20 into the processing space 10s. In the present embodiment, the upper electrode showerhead member 12 includes a gas inlet 12a, a gas diffusion chamber 12b, and a plurality of gas outlets 12c. The gas supply unit 20 and the gas diffusion chamber 12b are in fluid communication via the gas inlet 12a. The gas diffusion chamber 12b and the processing space 10s are in fluid communication via the plurality of gas outlets 12c. In the present embodiment, the upper electrode showerhead member 12 is configured to supply one or more kinds of gases from the gas inlet 12a into the processing space 10s via the gas diffusion chamber 12b and the plurality of gas outlets 12c.

[0036] The gas supply unit 20 includes one or more gas sources 21 and flow controllers 22. In the present embodiment, the gas supply unit 20 is configured to supply one or more process gases from each gas source 21 to the gas inlet 12a via each flow controller 22. The flow controller 22 may include, for example, a mass flow controller or a pressure-controlled flow controller. In addition, the gas supply unit 20 may also include one or more flow modulation devices that modulate or pulse the flow rate of one or more process gases.

[0037] The RF power supply unit 30 is configured to supply RF power, such as one or more RF signals, to one or more electrodes such as the lower electrode 111, the upper electrode showerhead component 12, or both the lower electrode 111 and the upper electrode showerhead component 12. In the present embodiment, the RF power supply unit 30 includes an RF generation unit 31 and a matching circuit 32. The RF power supply unit 30 of the present embodiment is configured to supply a first RF signal from the RF generation unit 31 to the upper electrode showerhead component 12 via the matching circuit 32.

[0038] The RF spectrum includes a part of the electromagnetic spectrum in the range of 3 [Hz] to 3000 [GHz]. For electronic material processes such as semiconductor processes, the frequency of the RF spectrum used to generate plasma is preferably in the range of 100 [kHz] to 3 [GHz], more preferably in the range of 200 [kHz] to 150 [MHz]. For example, the frequency of the first RF signal may be in the range of 27 [MHz] to 100 [MHz].

[0039] In the present embodiment, a sensor (not shown) is provided in the matching circuit 32 to measure the magnitude of the reflected power and the like. The measured value obtained by the sensor (not shown) in the matching circuit 32 is output to the control system 200.

[0040] Herein, although not shown, other embodiments are considered. For example, in place of the RF power supply unit 30 of the embodiment, it may be configured that another RF generation unit supplies a second RF signal to the lower electrode 111. The frequency of the second RF signal may be, for example, in the range of 400 [kHz] to 13.56 [MHz]. In addition, a DC (direct current) pulse may be supplied to the lower electrode 111.

[0041] In addition, although not shown in the figures, other embodiments are considered herein. For example, in the RF power supply unit 30 of the alternative embodiment, it may be configured such that the RF generation unit supplies the first RF signal to the lower electrode 111, and another RF generation unit supplies the second RF signal to the lower electrode 111. Further, it may be configured such that another RF generation unit supplies the third RF signal to the upper electrode shower head member 12. In addition, in other alternative embodiments, a DC voltage may be applied to the upper electrode shower head member 12. Additionally, in various embodiments, the amplitude of one or more types of RF signals (i.e., the first RF signal, the second RF signal, etc.) may be pulsed or modulated. The amplitude modulation may include pulsing the amplitude of the RF signal between an on state and an off state or between multiple different on states. Further, the phase matching of the RF signal may be controlled, and the phase matching of the amplitude modulation of multiple RF signals may be synchronized or asynchronous.

[0042] The exhaust system 40 may be connected, for example, to an exhaust port 10e provided at the bottom of the chamber 10. The exhaust system may include a vacuum pump such as a pressure valve, a turbo molecular pump, a roughing pump, or a combination thereof.

[0043] [Configuration of Control System 200]

[0044] Figure 2 FIG. is an example of a control system 200 according to the first embodiment. The control system 200 includes a determination unit 201, a first control signal generation unit 202, a second control signal generation unit 203, an analog unit 204, a first adjustment unit 205, and a second adjustment unit 206. A control signal generated by the first control signal generation unit 202 for controlling a control object is supplied to the processing device 100. As control objects, for example, the frequency of the RF signal, the power of the RF signal, the control amount of the variable circuit constants (such as variable capacitance, etc.) included in the matching circuit 32, the power supplied to the heater in the electrostatic chuck 112, the flow rate of the gas, the pressure in the chamber 10, etc. can be cited. In Figure 2 FIG., a functional module for generating a control signal for controlling one of the control objects is shown.

[0045] The determination unit 201 holds, for example, Figure 3 a control table 2010 as shown. Figure 3 FIG. is an example of a control table 2010 according to the first embodiment. In the control table 2010, corresponding to a scenario ID that identifies a scenario recording the conditions when processing the substrate W, a control algorithm, an initial value of a control parameter, a model, and an initial value of a model parameter are stored in advance. In the present embodiment, the scenario records the conditions when processing the substrate W using plasma.

[0046] The control algorithm is an algorithm for generating a control signal based on measured values obtained by various sensors provided in the processing device 100. The control signal is used to control the processing device 100 so that the state of the processing device 100 becomes a predetermined state. The control algorithm includes one or more control parameters.

[0047] The model is used to simulate the state of the processing device 100. In the present embodiment, the model is a model for simulating the state of the plasma generated in the processing device 100 and is represented by, for example, one or more mathematical expressions. The model includes one or more model parameters. Figure 4 is a diagram showing an example of the model. In the present embodiment, the model is defined as an electrical equivalent circuit representing the state of the controlled object. In Figure 4 , the impedances of terminals 1 and 4 of the transformer T1 are referred to as Zin and Zc, respectively. For example, Figure 4 the inductances L1, L2, and L3, capacitors C1, C2, and the mutual inductance of the transformer T1 shown in

[0048] When a plan ID is input from a higher-level device that controls the selection and implementation of the plan, etc., the determination unit 201 extracts from the control table 2010 the control algorithm, the initial values of the control parameters, the model, and the initial values of the model parameters corresponding to the plan ID. Then, the determination unit 201 outputs the extracted control algorithm and the initial values of the control parameters to the first control signal generation unit 202 and the second control signal generation unit 203. In addition, the determination unit 201 outputs the extracted model and the initial values of the model parameters to the simulation unit 204.

[0049] The first control signal generation unit 202 generates a control signal based on the measured values obtained by the sensors provided in the processing device 100, using the control algorithm and the initial values of the control parameters output from the determination unit 201. Then, the first control signal generation unit 202 inputs the generated control signal to the processing device 100. In the present embodiment, the first control signal generation unit 202 generates a control signal x using, for example, any of the mathematical expressions shown in the following formula (1).

[0050]

[0051] In the above formula (1), x n is the control signal input to the nth controlled object, f n is the control algorithm for controlling the nth controlled object, a nm is the nmth control parameter, and y m is the mth type of measured value.

[0052] The simulation unit 204 simulates the state of the processing device 100 by using the model and the initial values of the model parameters output from the determination unit 201. In the present embodiment, the simulation unit 204 simulates the state of the plasma in the processing device 100 by using the model and the initial values of the model parameters output from the determination unit 201. Further, the simulation unit 204 outputs an output value corresponding to the measurement value output from the processing device 100 to the second control signal generation unit 203, the first adjustment unit 205, and the second adjustment unit 206. In the present embodiment, the simulation unit 204 outputs the output value y' by using, for example, the mathematical formula shown in the following formula (2).

[0053]

[0054] In the above formula (2), y' m is the output value corresponding to the m-th measurement value, M m is the model corresponding to the m-th measurement value, b mn is the mn-th model parameter, x' n is the control signal corresponding to the n-th control object.

[0055] The second control signal generation unit 203 generates a control signal based on the output value output from the simulation unit 204 by using the control algorithm and the initial values of the control parameters output from the determination unit 201. Further, the second control signal generation unit 203 inputs the generated control signal to the simulation unit 204. In the present embodiment, the second control signal generation unit 203 generates the control signal x' by using, for example, any mathematical formula shown in the following formula (3).

[0056]

[0057] In the above formula (3), x' n is the control signal corresponding to the n-th control object, y' m is the output value of the simulation unit 204 corresponding to the m-th measurement value.

[0058] The first adjustment unit 205 adjusts the value of the model parameter of the model used by the simulation unit 204 so as to reduce the difference between the measurement value output from the processing device 100 and the output value of the simulation unit 204 corresponding to the measurement value. For example, the first adjustment unit 205 calculates an evaluation value E1 for evaluating the difference between the measurement value and the output value based on the mathematical formula shown in the following formula (4).

[0059] E1 = e1(Δy1, Δy2…, Δy m ) …(4)

[0060] In the above formula (4), e1 is an evaluation function, Δy mis the difference between the measured value of the m-th type and the output value of the simulation unit 204 corresponding to the measured value. In the present embodiment, the smaller the difference between the measured value output from the processing device 100 and the output value from the simulation unit 204 corresponding to the measured value, the smaller the evaluation value E1.

[0061] The first adjustment unit 205 adjusts the value of the model parameter so that the evaluation value E1 based on the above formula (4) becomes below a predetermined threshold value. The first adjustment unit 205 adjusts the value of the model parameter by using a method of statistically solving the likelihood value such as the MIN-MAX method, the weighted average method, the Fuzzy control method, etc. The first adjustment unit 205 repeatedly calculates the output value of the simulation unit 204, calculates the evaluation value E1 based on the above formula (4), and changes the value of the model parameter, thereby adjusting the value of the model parameter.

[0062] When the evaluation value E1 based on the above formula (4) is below the threshold value, the difference between the measured value output from the processing device 100 and the output value from the simulation unit 204 corresponding to the measured value becomes smaller, and the state of the model including the adjusted value of the model parameter approaches the state of the processing device 100.

[0063] When the evaluation value E1 based on the above formula (4) is below the threshold value, the first adjustment unit 205 updates the initial value of the model parameter in the control table 2010 by using the adjusted value of the model parameter. Thereby, it is possible to follow the change in the state of the processing device 100 including the change over time, and perform simulation using a model in a state closer to the state of the processing device 100.

[0064] The second adjustment unit 206 calculates an evaluation value E2 for the output value of the simulation unit 204 that uses the model including the adjusted value of the model parameter. And the second adjustment unit 206 adjusts the value of the control parameter included in the control algorithm used by the second control signal generation unit 203 so that the calculated evaluation value E2 approaches the target value. After the first adjustment unit 205 finishes adjusting the value of the model parameter, the second adjustment unit 206 calculates the evaluation value E2 relative to the target value for the output value of the simulation unit 204 that uses the model including the adjusted value of the model parameter by using the following formula (5).

[0065] E2 = e2(Δc1, Δc2,..., Δc k ) …(5)

[0066] In the above formula (5), e2 is an evaluation function, and Δc k is the difference between the k-th output value or the eigenvalue calculated using the output value and the target value. The output value is a value corresponding to the measured value of the processing device 100, for example, the magnitude of the reflected power, etc. The eigenvalue calculated using the output value is, for example, the time required until the reflected power becomes below a predetermined value, the magnitude of overshoot or fluctuation, etc.

[0067] The second adjustment unit 206 adjusts the value of the control parameter included in the control algorithm used by the second control signal generation unit 203 so that the evaluation value E2 based on the above formula (5) approaches the target value E0. For example, the second adjustment unit 206 adjusts the value of the control parameter so that the difference between the evaluation value E2 based on the above formula (5) and the target value E0 becomes below a predetermined threshold value. The second adjustment unit 206 adjusts the value of the control parameter by using a statistically likelihood value solving method such as the MIN-MAX method, the weighted average method, the Fuzzy control method, etc. The second adjustment unit 206 adjusts the value of the control parameter by repeatedly using the generation of the control signal by the second control signal generation unit 203, the generation of the output value of the simulation unit 204 that inputs the generated control signal, the calculation of the evaluation value E2, and the change of the value of the control parameter.

[0068] Adjustment is made in such a way that the difference between the evaluation value E2 based on the above formula (5) and the target value E0 becomes below the threshold value. By using the control signal generated by the control algorithm including the adjusted value of the control parameter, the state of the model including the adjusted model parameter can be made to approach the target state. The model including the adjusted value of the model parameter is a model in a state closer to the state of the processing device 100. Therefore, adjustment is made in such a way that the difference between the evaluation value E2 based on the above formula (5) and the target value E0 becomes below the threshold value. By using the control signal generated by the control algorithm including the adjusted value of the control parameter, the state of the processing device 100 can be made to approach the target state.

[0069] The second adjustment unit 206 outputs the adjusted control parameter to the first control signal generation unit 202 and the second control signal generation unit 203. The first control signal generation unit 202 generates a control signal based on the measured value measured by the sensor provided in the processing device 100 by using the control algorithm including the adjusted value of the control parameter output from the second adjustment unit 206. Thereby, it is possible to follow the change in the state of the processing device 100 including the change over time and stably control the state of the processing device 100 to approach the target state.

[0070] The second control signal generation unit 203 generates a control signal based on the output value output from the simulation unit 204 by using the control algorithm including the adjusted value of the control parameter output from the second adjustment unit 206, and inputs the generated control signal to the simulation unit 204.

[0071] In addition, the second adjustment unit 206 updates the initial value of the control parameter in the control table 2010 by using the adjusted value of the control parameter. Thereby, it is possible to follow the change in the state of the processing device 100 including the change over time and quickly control the state of the processing device 100 to approach the target state.

[0072] [Processing of the control system 200]

[0073] Figure 5 It is a flowchart showing an example of the processing of the control system 200. For example, when a plan ID is input from a higher-level device, the control system 200 starts the processing shown in this flowchart.

[0074] First, the determination unit 201 extracts the control algorithm, the initial values of the control parameters, the model, and the initial values of the model parameters corresponding to the plan ID input from the higher-level device from the control table 2010 (S100). Then, the determination unit 201 outputs the extracted control algorithm and the initial values of the control parameters to the first control signal generation unit 202 and the second control signal generation unit 203. In addition, the determination unit 201 outputs the extracted model and the initial values of the model parameters to the simulation unit 204.

[0075] The first control signal generation unit 202 generates a control signal using the control algorithm and the initial values of the control parameters output from the determination unit 201 (S101). In addition, the second control signal generation unit 203 generates a control signal using the control algorithm and the initial values of the control parameters output from the determination unit 201 (S101).

[0076] Next, the first control signal generation unit 202 inputs the generated control signal to the processing device 100, and the second control signal generation unit 203 inputs the generated control signal to the simulation unit 204 (S102). The processing device 100 operates the controlled object according to the input control signal. As a result, the state of the processing device 100 changes. The simulation unit 204 changes the state of the model according to the input control signal. Thereafter, the first control signal generation unit 202 generates a control signal based on the measurement value measured by the sensor provided in the processing device 100 according to the control algorithm, and inputs the generated control signal to the processing device 100. In addition, the second control signal generation unit 203 generates a control signal based on the output value output from the simulation unit 204 according to the control algorithm, and inputs the generated control signal to the simulation unit 204.

[0077] Next, the first adjustment unit 205 acquires the measurement value from the processing device 100 (S103), and acquires the output value from the simulation unit 204 (S104). Then, the first adjustment unit 205 adjusts the value of the model parameters of the model used by the simulation unit 204 to reduce the difference between the measurement value output from the processing device 100 and the output value from the simulation unit 204 corresponding to the measurement value (S105).

[0078] Next, the second adjustment unit 206 calculates an evaluation value E2(S106) for the output value of the simulation unit 204 of the model using the value of the adjusted model parameters. Then, the second adjustment unit 206 adjusts the value of the control parameter included in the control algorithm used by the second control signal generation unit 203 so that the calculated evaluation value E2 approaches the target value E0(S107).

[0079] Next, the second adjustment unit 206 outputs the adjusted value of the control parameter to the first control signal generation unit 202 and the second control signal generation unit 203. The first control signal generation unit 202 generates a control signal based on the measurement value measured by the sensor provided in the processing device 100, using the control algorithm including the adjusted value of the control parameter output from the second adjustment unit 206(S108). In addition, the second control signal generation unit 203 generates a control signal based on the output value output from the simulation unit 204, using the control algorithm including the adjusted value of the control parameter output from the second adjustment unit 206.

[0080] Next, the first adjustment unit 205 and the second adjustment unit 206 determine whether to end the control of the processing device 100 corresponding to the plan ID input from the upper-level device(S109). When the control of the processing device 100 is not ended(S109 is "no"), the process shown in step S102 is performed again.

[0081] On the other hand, when the control of the processing device 100 ends(S109 is "yes"), the first adjustment unit 205 updates the initial value of the model parameter in the control table 2010 using the adjusted value of the model parameter(S110). In addition, the second adjustment unit 206 updates the initial value of the control parameter in the control table 2010 using the adjusted value of the control parameter(S110). And the process shown in this flowchart ends.

[0082] [Hardware]

[0083] The control system 200 is implemented by a computer 90 having a configuration as shown, for example Figure 6 FIG. is a diagram showing an example of a computer 90 that implements the functions of the control system 200. The computer 90 includes a CPU(Central Processing Unit)91, a RAM(Random Access Memory)92, a ROM(ReadOnly Memory)93, an auxiliary storage device 94, a communication I / F(Interface)95, an input / output I / F96, and a medium I / F97. Figure 6

[0084] ​The CPU 91 operates based on programs stored in the ROM 93 or the auxiliary storage device 94, and controls each part. The ROM 93 stores a boot program executed by the CPU 91 when the computer 90 starts up, programs dependent on the hardware of the computer 90, and so on.

[0085] The auxiliary storage device 94 is, for example, an HDD (Hard Disk Drive) or an SSD (Solid State Drive), and stores programs executed by the CPU 91 and data used by such programs. The CPU 91 reads out the program from the auxiliary storage device 94 and loads it onto the RAM 92, and executes the loaded program.

[0086] The communication I / F 95 communicates with the processing device 100 via a communication line such as a LAN (Local Area Network). The communication I / F 95 receives data from the processing device 100 via the communication line and sends it to the CPU 91, and sends the data generated by the CPU 91 to the processing device 100 via the communication line.

[0087] The CPU 91 controls input devices such as a keyboard and output devices such as a display via the input / output I / F 96. The CPU 91 obtains signals input from the input device via the input / output I / F 96 and sends them to the CPU 91. In addition, the CPU 91 outputs the generated data to the output device via the input / output I / F 96.

[0088] The medium I / F 97 reads a program or data stored in the recording medium 98 and stores it in the auxiliary storage device 94. The recording medium 98 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0089] The CPU 91 of the computer 90 executes the program loaded onto the RAM 92, thereby realizing the respective functions of the determination unit 201, the first control signal generation unit 202, the second control signal generation unit 203, the analog unit 204, the first adjustment unit 205, and the second adjustment unit 206. In addition, data of the control table 2010 is stored in the auxiliary storage device 94.

[0090] The CPU 91 of the computer 90 reads the program loaded onto the RAM 92 from the recording medium 98 and stores it in the auxiliary storage device 94. As another example, the program may also be obtained from another device via a communication line and stored in the auxiliary storage device 94.

[0091] As described above, the first embodiment has been explained. As described above, the control system 200 of the present embodiment includes a determination unit 201, a first control signal generation unit 202, a second control signal generation unit 203, a simulation unit 204, a first adjustment unit 205, and a second adjustment unit 206. The determination unit 201 determines a model and a control algorithm corresponding to the processing apparatus 100 for processing the substrate W based on a recipe that describes the conditions for processing the substrate W. The control algorithm is an algorithm for generating a control signal based on a measurement value measured by a measuring device provided in the processing apparatus 100, and the control signal is used to control the processing apparatus 100 so that the state of the processing apparatus 100 becomes a predetermined state. The simulation unit 204 simulates the state of the processing apparatus 100 using the model. The first control signal generation unit 202 generates a control signal based on the measurement value using the control algorithm determined by the determination unit 201, and inputs the generated control signal to the processing apparatus 100. The second control signal generation unit 203 generates a control signal based on the output value of the simulator 204 corresponding to the measurement value using the control algorithm determined by the determination unit 201, and inputs the generated control signal to the simulation unit 204. The first adjustment unit 205 adjusts the value of the model parameter included in the model so that the difference between the measurement value and the output value of the simulation unit 204 becomes smaller. The second adjustment unit 206 adjusts the value of the control parameter included in the control algorithm used by the second control signal generation unit 203 so that the evaluation value calculated from the output value of the simulation unit 204 using the model including the adjusted value of the model parameter approaches the target value. In addition, the first control signal generation unit 202 generates a control signal using the value of the control parameter adjusted by the second adjustment unit 206. Thereby, the state in the processing apparatus 100 can be stably controlled.

[0092] In addition, in the above-described embodiment, the determination unit 201 determines the initial value of the control parameter based on the recipe. The first control signal generation unit 202 generates a control signal based on the measurement value using the control algorithm and the initial value of the control parameter determined by the determination unit 201, and inputs the generated control signal to the processing apparatus 100. In addition, the determination unit 201 determines the value of the control parameter adjusted by the second adjustment unit 206 as the initial value of the control parameter. Thereby, it is possible to follow the change in the state of the processing apparatus 100 including the change over time, and quickly control the state of the processing apparatus 100 to be close to the target state.

[0093] In addition, in the above-described embodiment, the conditions for processing the substrate W using plasma are described in the solution. The processing apparatus 100 is an apparatus for processing the substrate W using plasma, and the model is a model showing the state of the plasma. The simulation unit 204 simulates the state of the plasma in the processing apparatus 100 using the model. Thus, it is possible to follow the change in the state of the processing apparatus 100 including the change over time and stably generate plasma in the processing apparatus 100.

[0094] In addition, the control method of the above-described embodiment includes: a step of determining a model and a control algorithm corresponding to the processing apparatus 100 for processing the substrate W based on a solution that describes the conditions for processing the substrate W; the control algorithm generates a control signal based on a measurement value measured by a measuring device provided in the processing apparatus 100, and the control signal is used to control the processing apparatus 100 so that the state of the processing apparatus 100 becomes a predetermined state; a step of generating a control signal based on the measurement value using the determined control algorithm and inputting the generated control signal to the processing apparatus 100; a step of generating a control signal based on the output value of the simulation unit 204 that simulates the state of the processing apparatus 100 using the model, that is, the output value corresponding to the measurement value, using the determined control algorithm, and inputting the generated control signal to the simulation unit 204; a step of adjusting the value of the model parameter included in the model so that the difference between the measurement value and the output value of the simulation unit 204 becomes smaller; and a step of adjusting the value of the control parameter included in the control algorithm so that the evaluation value calculated for the output value of the simulation unit 204 using the model including the adjusted value of the model parameter approaches the target value. In addition, in the step of inputting the generated control signal to the processing apparatus 100, the control signal is generated using the adjusted value of the control parameter. Thus, it is possible to stably control the state in the processing apparatus 100.

[0095] In addition, the control program of the above-described embodiment causes the control system 200 to perform the following processing: based on a recipe that records conditions for processing the substrate W, determine a model and a control algorithm corresponding to the processing apparatus 100 for processing the substrate W, the control algorithm generating a control signal based on a measurement value measured by a measuring device provided in the processing apparatus 100, the control signal being used to control the processing apparatus 100 so that the state of the processing apparatus 100 becomes a predetermined state; generate a control signal based on the measurement value using the determined control algorithm and input the generated control signal to the processing apparatus 100; generate a control signal based on an output value of the simulation unit 204 that simulates the state of the processing apparatus 100, i.e., an output value corresponding to the measurement value, using the determined control algorithm and input the generated control signal to the simulation unit 204; adjust the value of a model parameter included in the model so that the difference between the measurement value and the output value of the simulation unit 204 becomes smaller; perform processing to adjust the value of a control parameter included in the control algorithm so that an evaluation value calculated for the output value of the simulation unit 204 using the model including the adjusted value of the model parameter approaches a target value. In addition, in the processing of inputting the generated control signal to the processing apparatus 100, a control signal is generated using the adjusted value of the control parameter. Thereby, the state within the processing apparatus 100 can be stably controlled.

[0096] In addition, the processing system 1 of the above-described embodiment includes a processing apparatus 100 that processes a substrate W and a control system 200 that controls the processing apparatus 100. The control system 200 includes a determination unit 201, a first control signal generation unit 202, a second control signal generation unit 203, a simulation unit 204, a first adjustment unit 205, and a second adjustment unit 206. The determination unit 201 determines a model and a control algorithm corresponding to the processing apparatus 100 for processing the substrate W based on a recipe that records the conditions for processing the substrate W. The control algorithm is an algorithm that generates a control signal based on a measurement value measured by a measuring device provided in the processing apparatus 100, and the control signal is used to control the processing apparatus 100 so that the state of the processing apparatus 100 becomes a predetermined state. The simulation unit 204 simulates the state of the processing apparatus 100 using the model. The first control signal generation unit 202 generates a control signal based on the measurement value using the control algorithm determined by the determination unit 201 and inputs the generated control signal to the processing apparatus 100. The second control signal generation unit 203 generates a control signal based on the output value of the simulation unit 204 corresponding to the measurement value using the control algorithm determined by the determination unit 201 and inputs the generated control signal to the simulation unit 204. The first adjustment unit 205 adjusts the value of the model parameter included in the model so that the difference between the measurement value and the output value of the simulation unit 204 becomes smaller. The second adjustment unit 206 adjusts the value of the control parameter included in the control algorithm used by the second control signal generation unit 203 so that the evaluation value calculated for the output value of the simulation unit 204 using the model including the adjusted value of the model parameter approaches a target value. In addition, the first control signal generation unit 202 generates a control signal using the value of the control parameter adjusted by the second adjustment unit 206. Thus, the state inside the processing apparatus 100 can be stably controlled.

[0097] (Second Embodiment)

[0098] In the above-described first embodiment, one control algorithm and one model are pre-corresponded to a recipe ID, and when the recipe ID is input from a higher-level device, one control algorithm and one model corresponding to the recipe ID are determined. In contrast, in the present embodiment, a plurality of control algorithms and a plurality of models are pre-corresponded to a recipe ID, and when the recipe ID is input from a higher-level device, a plurality of control algorithms and a plurality of models corresponding to the recipe ID are determined.

[0099] Figure 7 and Figure 8 FIG. is an example of a control table 2010 showing the second embodiment. In the control table 2010 of the present embodiment, a single table 2013 is pre-stored corresponding to the recipe ID 2012. In the single table 2013, for example Figure 7As shown, it stores multiple control algorithms, initial values of control parameters included in each control algorithm, and flags. The flag is a flag for identifying the control algorithm and the initial value of the control parameter used to generate the control signal supplied to the processing device 100. In the present embodiment, the flag with a value of "1" corresponds to the combination of the control algorithm and the initial value of the control parameter used to generate the control signal supplied to the processing device 100, and the flag with a value of "0" corresponds to other combinations.

[0100] In addition, in a single table 2013, for example Figure 8 as shown, it stores multiple models and initial values of model parameters included in each model.

[0101] In the present embodiment, when a plan ID is input from a higher-level device, the determination unit 201 extracts multiple control algorithms, control parameters, flag values, models, and model parameters corresponding to the plan ID from the control table 2010. And among the combinations of the extracted control algorithms and the initial values of the control parameters, the determination unit 201 outputs the combination corresponding to the flag with a value of "1" to the first control signal generation unit 202 and the second control signal generation unit 203. In addition, the determination unit 201 outputs the initial values of the multiple control algorithms and control parameters it extracts to the second adjustment unit 206. In addition, the determination unit 201 outputs the initial values of the multiple models and model parameters it extracts to the simulation unit 204.

[0102] The second control signal generation unit 203 uses the combination of the control algorithm and the initial value of the control parameter output from the determination unit 201 to generate a control signal based on the output value output from the simulation unit 204, and inputs the generated control signal to the simulation unit 204. And according to the instruction from the second adjustment unit 206, it changes the combination of the control algorithm and the initial value of the control parameter, generates a control signal based on the output value output from the simulation unit 204, and inputs the generated control signal to the simulation unit 204.

[0103] For each model output from the determination unit 201, the simulation unit 204 outputs the output value based on the control signal output from the second control signal generation unit 203 to the first adjustment unit 205 and the second adjustment unit 206.

[0104] The first adjustment unit 205 adjusts the value of the model parameter for each model so that the evaluation value E1 based on the aforementioned formula (4) becomes below a predetermined threshold value. Among them, even for a model where the evaluation value E1 is below the threshold value, the minimum value of the evaluation value E1 may be different for each model. Among the combinations of the model where the evaluation value E1 is below the threshold value and the value of the model parameter, the first adjustment unit 205 determines the combination with the minimum evaluation value E1 as the adjusted value of the model and the model parameter.

[0105] Further, the first adjustment unit 205 updates the initial value of the model parameter in the single table 2013 stored in the control table 2010 corresponding to the determined model by using the value of the adjusted model parameter.

[0106] The second adjustment unit 206 adjusts the value of the control parameter for each control algorithm so that the difference between the evaluation value E2 based on the aforementioned formula (5) and the target value E0 becomes equal to or less than a predetermined threshold value. Among them, even for a control algorithm in which the difference between the evaluation value E2 and the target value E0 is equal to or less than the threshold value, the minimum value of the difference between the evaluation value E2 and the target value E0 may be different for each control algorithm. Among the combinations of the control algorithm and the control parameter in which the difference between the evaluation value E2 and the target value E0 is equal to or less than the threshold value, the first adjustment unit 205 determines the combination with the smallest difference as the values of the adjusted control algorithm and the control parameter.

[0107] Further, the second adjustment unit 206 outputs the determined values of the control algorithm and the control parameter to the first control signal generation unit 202 and the second control signal generation unit 203. In addition, the second adjustment unit 206 updates the initial value of the control parameter in the single table 2013 stored in the control table 2010 corresponding to the determined control algorithm by using the value of the adjusted control parameter. Further, the second adjustment unit 206 sets the value of the flag corresponding to the updated initial value of the control parameter to "1", and sets the value of the flag corresponding to the initial values of the other control parameters to "0".

[0108] In the control table 2010 of the present embodiment, a plurality of control algorithms and models correspond to the solution ID, respectively. However, as another method, any of the plurality of control algorithms and models may correspond to the solution ID.

[0109] As described above, the second embodiment has been described. As described above, in the control system 200 of the present embodiment, the determination unit 201 determines a plurality of models based on the solution. The first adjustment unit 205 adjusts the values of the model parameters included in the models determined by the determination unit 201, respectively, so that the difference between the measurement value and the output value of the simulation unit 204 becomes smaller. Among the combinations of the adjusted models and the values of the model parameters, the combination with the smallest difference between the measurement value and the output value of the simulation unit 204 corresponding to the measurement value is determined as the values of the adjusted model and the model parameters. In addition, the second adjustment unit 206 adjusts the value of the control parameter used by the second control signal generation unit 203 so that the evaluation value E2 calculated from the output value of the simulation unit 204 using the model including the value of the model parameter determined by the first adjustment unit 205 approaches the target value E0. Thereby, a model closer to the state of the processing device 100 can be generated.

[0110] In addition, in the above-described embodiment, the determination unit 201 determines multiple control algorithms based on the scenarios. For the multiple control algorithms determined by the determination unit 201, the second adjustment unit 206 adjusts the values of the control parameters included in the control algorithms used by the second control signal generation unit 203 respectively, so that the evaluation value E2 calculated for the output value of the simulation unit 204 using the model including the value of the model parameter determined by the first adjustment unit 205 approaches the target value E0. Among the combinations of the adjusted control algorithms and the values of the control parameters, the combination for which the evaluation value E2 calculated for the output value of the simulation unit 204 is closest to the target value E0 is determined as the adjusted control algorithm and the value of the control parameter. The first control signal generation unit 202 generates a control signal input to the processing device 100 based on the measured value using the control algorithm and the value of the control parameter determined by the second adjustment unit 206. Thereby, the processing device 100 can be controlled with higher precision.

[0111] (Third Embodiment)

[0112] In the above-described first embodiment, before the processing of the processing device 100 ends, the value of the control parameter after the last adjustment is updated to the initial value of the control parameter. In contrast, in the present embodiment, each time the value of the control parameter is adjusted, the adjusted value of the control parameter is saved as a history record. And when starting the processing of the processing device 100, the initial value of the control parameter is estimated from the history record of the adjusted values of the control parameter, and the control of the processing device 100 is started using the estimated initial value of the control parameter. Thereby, the control of the processing device 100 can be started from a state close to the target state, and the state of the processing device 100 can be made closer to the target state more quickly.

[0113] In the present embodiment, the determination unit 201 holds, for example, Figure 9 a history record table 2020 as shown. Figure 9 FIG. is an example showing the history record table 2020. In the history record table 2020, a single table 2022 is stored corresponding to the scenario ID 2021. In the single table 2022, for example, Figure 9 as shown, the adjusted values of the control parameters are stored in time series.

[0114] When a scenario ID is input from the upper-level device, the determination unit 201 refers to the history record table 2020 and determines whether two or more adjusted values of the control parameters are stored in the single table 2022 corresponding to the input scenario ID. When the number of the adjusted values of the control parameters stored in the single table 2022 corresponding to the scenario ID is 1 or less, the determination unit 201 extracts the initial value of the control parameter corresponding to the scenario ID from the control table 2010 (refer to Figure 3 ).

[0115] On the other hand, when the number of values of the adjusted control parameters corresponding to the scenario ID and stored in the single table 2022 is two or more, the determination unit 201 extracts the values of the adjusted control parameters corresponding to the scenario ID from the single table 2022. Then, the determination unit 201 presumes the initial value of the control parameter as the value conforming to the change tendency of the extracted multiple control parameter values.

[0116] For example Figure 10 As shown, the determination unit 201 determines an approximation curve 51 that approximates the change tendency of the values 50 of the adjusted control parameters arranged in time series. Figure 10 This is a diagram for explaining an example of the method for presuming the initial value of the control parameter. Among them, the change tendency of the values 50 of the adjusted control parameters arranged in time series can also be approximated by a straight line. Then, the determination unit 201 presumes the initial value 52 of the control parameter for the values on the determined approximation curve 51.

[0117] Above, the third embodiment has been described. As described above, in the control system 200 of the present embodiment, the determination unit 201 presumes the value conforming to the tendency of the history of the values of the control parameter adjusted by the second adjustment unit 206 as the initial value of the control parameter. The first control signal generation unit 202 uses the control algorithm determined by the determination unit 201 and the initial value of the control parameter presumed by the determination unit 201 to generate a control signal based on the measured value, and inputs the generated control signal to the processing device 100. Thereby, the control of the processing device 100 can start from a state close to the target state, and the state of the processing device 100 can be made closer to the target state more quickly.

[0118] (Fourth Embodiment)

[0119] The control system 200 of the above-described first embodiment is implemented by one device. In contrast, the control system 200 of the present embodiment is implemented by two devices.

[0120] Figure 11 This is a diagram showing an example of the control system 200 of the fourth embodiment. The control system 200 of the present embodiment includes a first device 2000 and a second device 2001. The first device 2000 includes a determination unit 201, a second control signal generation unit 203, an analog unit 204, a first adjustment unit 205, and a second adjustment unit 206. The second device 2001 includes a first control signal generation unit 202, a holding unit 207, and a feature quantity generation unit 208. Among them, except for the aspects described below, in Figure 10 which, the components marked with the Figure 2 same symbols as Figure 2 have the same configuration or the same function, so the description thereof is omitted.

[0121] The holding unit 207 holds measurement values measured by various sensors provided in the processing device 100 in each first cycle (e.g., several microseconds). The feature quantity generation unit 208 generates a feature quantity representing the features of these measurement values in each second cycle (e.g., several hundred microseconds) longer than the first cycle based on a plurality of measurement values of the same type held by the holding unit 207. Then, the feature quantity generation unit 208 outputs the generated feature quantity to the first device 2000. The feature quantity is, for example, the maximum value, minimum value, and average value of the displayed measurement values, an approximate curve showing the change tendency of the measurement values, etc. By outputting the feature quantity generated based on the plurality of measurement values to the first device 2000, the amount of data transmitted between the first device 2000 and the second device 2001 can be reduced compared to the case of outputting all the plurality of measurement values to the first device 2000.

[0122] The first adjustment unit 205 restores the measurement value corresponding to the feature quantity generated by the feature quantity generation unit 208, and adjusts the value of the model parameter included in the model so that the difference between the restored measurement value and the output value of the simulation unit 204 becomes smaller. Additionally, the first adjustment unit 205 may calculate a feature quantity based on the output value of the simulation unit 204, and adjust the value of the model parameter included in the model so that the difference between the calculated feature quantity and the feature quantity generated by the feature quantity generation unit 208 becomes smaller.

[0123] Therefore, the calculation amounts of the second control signal generation unit 203, the simulation unit 204, the first adjustment unit 205, and the second adjustment unit 206 are larger than the calculation amount of the first control signal generation unit 202. Thus, a device that implements the functions of the second control signal generation unit 203, the simulation unit 204, the first adjustment unit 205, and the second adjustment unit 206 requires a higher processing capacity than a device that implements the function of the first control signal generation unit 202. However, such a device is large-sized, so it is difficult to arrange it near the processing device 100. Therefore, it can be considered to arrange a device that implements the functions of the second control signal generation unit 203, the simulation unit 204, the first adjustment unit 205, and the second adjustment unit 206 at a location far from the processing device 100, and connect this device and the processing device 100 via a communication cable.

[0124] In addition, the state of the processing device 100 changes at all times. Especially when generating plasma, the state inside the processing device 100 changes in a shorter time. Therefore, the sensors provided in the processing device 100 perform measurements in a cycle of several microseconds and output the measurement values to the control system 200. Additionally, a plurality of sensors are provided in the processing device 100, and measurement values are output from each sensor. Therefore, the amount of data of the measurement values output from the processing device 100 to the control system 200 per unit time is huge.

[0125] Therefore, when connecting the control system 200 and the processing device 100 via a communication cable, it is necessary to transmit the measured value data using a communication method that utilizes the high bandwidth of the communication cable. However, such a communication method has the problem of high cost.

[0126] Therefore, in the present embodiment, the control system 200 is divided into a first device 2000 and a second device 2001. The second device 2001 and the processing device 100 are connected via a bus, thereby ensuring the bandwidth between the second device 2001 and the processing device 100. Moreover, the first device 2000 and the second device 2001 are connected via a communication cable such as a LAN cable. As a result, the degree of freedom in configuring the first device 2000 can be improved, and the cost of the processing system 1 can be reduced.

[0127] As described above, the fourth embodiment has been explained. As mentioned above, the control system 200 of the present embodiment further includes a feature quantity generation unit that generates, in each second cycle longer than the first cycle, a feature quantity characterizing the features of the measured values measured in each first cycle. The first adjustment unit 205 adjusts the values of the model parameters included in the model so that the difference between the measured value corresponding to the feature quantity and the output value of the simulation unit 204 becomes smaller. The determination unit 201, the second control signal generation unit 203, the simulation unit 204, the first adjustment unit 205 and the second adjustment unit 206, the first control signal generation unit 202, and the feature quantity generation unit 208 are implemented using different devices. As a result, the degree of freedom in configuring the first device 2000 can be improved, and the cost of the processing system 1 can be reduced.

[0128] [Other]

[0129] Among them, the technology disclosed in the present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of its gist.

[0130] For example, in the above-described embodiments, as an example of the plasma source used in the processing device 100, capacitively coupled plasma (CCP) has been described, but the plasma source is not limited thereto. As plasma sources other than capacitively coupled plasma, for example, inductively coupled plasma (ICP), microwave-excited surface wave plasma (SWP), electron cyclotron resonance plasma (ECP), and helicon wave-excited plasma (HWP) can be cited.

[0131] In addition, in the above-described embodiments, as the processing device 100, a device for etching a substrate W using plasma or the like has been described as an example, but it is not limited to the disclosed technology. For example, for processing devices such as heat treatment devices and cleaning devices that do not use plasma, the disclosed technology can also be applied to the control of distributions such as heat, pressure, and flow rate.

[0132] In addition, the embodiments disclosed herein should be considered illustrative in all respects and not restrictive. In fact, the above-described embodiments can be implemented in various ways. Additionally, as long as the above-described embodiments do not depart from the scope and gist of the invention claimed in this application, various omissions, substitutions, and changes can be made.

Claims

1. A control system, characterized in that, comprising: a determination unit that determines, based on a scenario that records conditions for processing a substrate, a model and a control algorithm corresponding to a processing apparatus for processing the substrate, the control algorithm generating a control signal based on a measurement value measured by a measuring device provided in the processing apparatus, the control signal being used to control the processing apparatus such that a state of the processing apparatus becomes a predetermined state; a simulation unit that simulates a state of the processing apparatus using the model; a first control signal generation unit that generates the control signal based on the measurement value using the control algorithm determined by the determination unit and inputs the generated control signal to the processing apparatus; a feature quantity generation unit that generates, in each second period longer than a first period, a feature quantity characterizing the feature of the measurement value measured in each of the first periods; a second control signal generation unit that generates the control signal based on an output value of the simulation unit corresponding to the measurement value using the control algorithm determined by the determination unit and inputs the generated control signal to the simulation unit; a first adjustment unit that adjusts a value of a model parameter included in the model such that a difference between the measurement value corresponding to the feature quantity and the output value of the simulation unit becomes smaller; and a second adjustment unit that adjusts a value of a control parameter included in the control algorithm used by the second control signal generation unit such that an evaluation value calculated for the output value of the simulation unit using the model including the adjusted value of the model parameter approaches a target value, the first control signal generation unit generates the control signal using the value of the control parameter adjusted by the second adjustment unit, the determination unit, the simulation unit, the second control signal generation unit, the first adjustment unit, and the second adjustment unit are implemented by a first device, and the first control signal generation unit and the feature quantity generation unit are implemented by a second device.

2. The control system according to claim 1, wherein: the determination unit determines a plurality of the models based on the scenario, the first adjustment unit adjusts, for each of the plurality of models determined by the determination unit, the value of the model parameter included in the model such that the difference between the measurement value and the output value of the simulation unit becomes smaller, and determines, among combinations of the adjusted model and the value of the model parameter, a combination having the smallest difference between the measurement value and the output value of the simulation unit corresponding to the measurement value as the adjusted model and the value of the model parameter, the second adjustment unit adjusts the value of the control parameter used by the second control signal generation unit such that the evaluation value calculated for the output value of the simulation unit using the model including the value of the model parameter determined by the first adjustment unit approaches the target value.

3. The control system according to claim 2, wherein: the determination unit determines a plurality of the control algorithms based on the scenario, The second adjustment unit adjusts the values of the control parameters included in the control algorithms determined by the determination unit for the plurality of control algorithms, respectively, so that the evaluation value calculated from the output value of the simulation unit using the model with the value of the model parameters determined by the first adjustment unit approaches the target value. Among the combinations of the adjusted control algorithms and the values of the control parameters, the combination for which the evaluation value calculated from the output value of the simulation unit is closest to the target value is determined as the adjusted control algorithm and the values of the control parameters. The first control signal generation unit generates the control signal input to the processing device based on the measurement value by using the control algorithm and the values of the control parameters determined by the second adjustment unit.

4. The control system according to any one of claims 1 to 3, characterized in that: The determination unit determines the initial values of the control parameters based on the plan. The first control signal generation unit generates the control signal based on the measurement value by using the control algorithm and the initial values of the control parameters determined by the determination unit, and inputs the generated control signal to the processing device. The determination unit determines the value of the control parameter adjusted by the second adjustment unit as the initial value of the control parameter.

5. The control system according to any one of claims 1 to 3, characterized in that: The determination unit presumes, based on the history of the values of the control parameters adjusted by the second adjustment unit, the value conforming to the tendency of the history as the initial value of the control parameter. The first control signal generation unit generates the control signal based on the measurement value by using the control algorithm determined by the determination unit and the initial value of the control parameter presumed by the determination unit, and inputs the generated control signal to the processing device.

6. The control system according to any one of claims 1 to 3, characterized in that: The plan records the conditions when the substrate is processed using plasma. The processing device is a device for processing the substrate using plasma. The model is a model showing the state of the plasma. The simulation unit simulates the state of the plasma in the processing device by using the model.

7. A control method, characterized in that, Comprising: A step of, through a determination unit, determining a model and a control algorithm corresponding to a processing device for processing a substrate based on a plan recording the conditions for processing the substrate, the control algorithm generating a control signal based on a measurement value measured by a measuring device provided in the processing device, the control signal being used to control the processing device so that the state of the processing device becomes a predetermined state; A step of, through a first control signal generation unit, generating the control signal based on the measurement value by using the determined control algorithm and inputting the generated control signal to the processing device; A step of, through a feature quantity generation unit, generating a feature quantity characterizing the feature of the measurement value measured in each first period within each second period longer than the first period. A process in which a second control signal generation unit generates the control signal by using the determined control algorithm based on the output value of a simulation unit that simulates the state of the processing device by using the model, i.e., the output value corresponding to the measured value, and inputs the generated control signal to the simulation unit; A process in which a first adjustment unit adjusts the value of a model parameter included in the model so that the difference between the measured value corresponding to the feature quantity and the output value of the simulation unit becomes smaller; and A process in which a second adjustment unit adjusts the value of a control parameter included in the control algorithm so that an evaluation value calculated from the output value of the simulation unit that uses the model including the adjusted value of the model parameter approaches a target value, In the process of inputting the generated control signal to the processing device, the control signal is generated by using the adjusted value of the control parameter, The determination unit, the simulation unit, the second control signal generation unit, the first adjustment unit, and the second adjustment unit are implemented by a first device, and the first control signal generation unit and the feature quantity generation unit are implemented by a second device.

8. A computer program product, comprising a computer program, characterized in that: When the computer program is executed by a processor, it causes a control system to perform the following processing: A determination unit determines a model and a control algorithm corresponding to a processing device for processing a substrate based on a recipe that records conditions for processing the substrate. The control algorithm generates a control signal based on a measured value measured by a measuring device provided in the processing device, and the control signal is used to control the processing device so that the state of the processing device becomes a predetermined state. A first control signal generation unit generates the control signal by using the determined control algorithm based on the measured value, and inputs the generated control signal to the processing device. A process in which a feature quantity generation unit generates a feature quantity representing the feature of the measured value measured in each first cycle in each second cycle that is longer than the first cycle; A process in which a second control signal generation unit generates the control signal by using the determined control algorithm based on the output value of a simulation unit that simulates the state of the processing device, i.e., the output value corresponding to the measured value, and inputs the generated control signal to the simulation unit. A first adjustment unit adjusts the value of a model parameter included in the model so that the difference between the measured value corresponding to the feature quantity and the output value of the simulation unit becomes smaller. A process of adjusting the value of a control parameter included in the control algorithm so that an evaluation value calculated from the output value of the simulation unit that uses the model including the adjusted value of the model parameter approaches a target value. In the process of inputting the generated control signal to the processing device, the control signal is generated by using the adjusted value of the control parameter. The determination unit, the simulation unit, the second control signal generation unit, the first adjustment unit, and the second adjustment unit are implemented by a first device, and the first control signal generation unit and the feature quantity generation unit are implemented by a second device.

9. A processing system, characterized in that, It has: A processing apparatus for processing a substrate; and A control system for controlling the processing apparatus, The control system includes: A determination unit that determines a model and a control algorithm corresponding to the processing apparatus based on a recipe that records conditions for processing the substrate. The control algorithm generates a control signal based on measurement values measured by a measuring device provided in the processing apparatus, and the control signal is used to control the processing apparatus so that the state of the processing apparatus becomes a predetermined state; A simulation unit that simulates the state of the processing apparatus using the model; A first control signal generation unit that generates the control signal based on the measurement values using the control algorithm determined by the determination unit and inputs the generated control signal to the processing apparatus; A feature quantity generation unit that generates, in each second cycle longer than the first cycle, a feature quantity characterizing the features of the measurement values measured in each of the first cycles; A second control signal generation unit that generates the control signal based on the output value of the simulation unit corresponding to the measurement values using the control algorithm determined by the determination unit and inputs the generated control signal to the simulation unit; A first adjustment unit that adjusts the value of a model parameter included in the model so that the difference between the measurement value corresponding to the feature quantity and the output value of the simulation unit becomes smaller; and A second adjustment unit that adjusts the value of a control parameter included in the control algorithm used by the second control signal generation unit so that an evaluation value calculated for the output value of the simulation unit using the model including the adjusted value of the model parameter approaches a target value, The first control signal generation unit generates the control signal using the value of the control parameter adjusted by the second adjustment unit, The determination unit, the simulation unit, the second control signal generation unit, the first adjustment unit, and the second adjustment unit are implemented by a first device, and the first control signal generation unit and the feature quantity generation unit are implemented by a second device.

Images