Computer program, information processing method, and information processing device

Abstract

Provided are a computer program, an information processing method, and an information processing device that can be expected to reduce power consumption of a substrate processing device.　A computer program according to the present embodiment causes a computer to execute processing of: acquiring device information including a set temperature of a heater of a substrate processing device and setting information related to processing performed by the substrate processing device or observation information observed during the processing; predicting power consumption of the heater and a chiller of the substrate processing device on the basis of the acquired device information; searching for a set temperature of the chiller that satisfies a constraint condition related to operations of the heater and the chiller and can reduce power consumption compared to the predicted power consumption; and changing the set temperature of the chiller to the searched set temperature.

Description

Computer Program, Information Processing Method, and Information Processing Apparatus

[0001] The present disclosure relates to a computer program, an information processing method, and an information processing apparatus.

[0002] In Patent Document 1, an integrated management system has been proposed that accumulates various information collected from a substrate processing apparatus and displays information necessary for energy saving of each substrate processing apparatus installed in a semiconductor manufacturing factory using the accumulated data. This integrated management system accumulates various information including power consumption information, gas consumption information, or operation information of the substrate processing apparatus, acquires information that satisfies predetermined conditions from the accumulated information, and calculates and displays at least one of the power consumption amount, inert gas consumption amount, and apparatus operation rate of the substrate processing apparatus consumed by the substrate processing apparatus.

[0003] International Publication No. 2014 / 050808

[0004] The present disclosure provides a computer program, an information processing method, and an information processing apparatus that can be expected to reduce the power consumption of a substrate processing apparatus.

[0005] A computer program according to an embodiment causes a computer to acquire device information including a set temperature of a heater of a substrate processing apparatus and set information related to a process performed by the substrate processing apparatus or observation information observed along with the process, predict power consumption amounts of the heater and a chiller of the substrate processing apparatus based on the acquired device information, search for a set temperature of the chiller that satisfies constraint conditions related to operations of the heater and the chiller and can reduce the power consumption amount compared to the predicted power consumption amount, and execute a process of changing the set temperature of the chiller to the searched set temperature.

[0006] According to the present disclosure, it can be expected to reduce the power consumption of a substrate processing apparatus.

[0007] This is a diagram illustrating an example configuration of a capacitively coupled plasma processing apparatus. This is a schematic diagram showing an example configuration of an information processing system according to this embodiment. This is a block diagram illustrating an example configuration of an information processing apparatus in this embodiment. This is a schematic diagram illustrating an example configuration of a first learning model generated in this embodiment. This is a schematic diagram illustrating an example configuration of a second learning model generated in this embodiment. This is a schematic diagram illustrating an example configuration of a third learning model generated in this embodiment. This is a flowchart illustrating an example of a processing procedure performed by the information processing apparatus according to this embodiment. This is a flowchart illustrating an example of a processing procedure performed by the information processing apparatus according to this embodiment. This is a schematic diagram illustrating an example of chiller temperature control by the information processing system according to this embodiment.

[0008] Specific examples of information processing systems according to the embodiments of this disclosure will be described below with reference to the drawings. However, this disclosure is not limited to these examples and is intended to include all changes within the meaning and scope of the claims as indicated by the claims.

[0009] <Substrate Processing System> The following describes an example of the configuration of a plasma processing system. Figure 1 is a diagram illustrating an example of the configuration of a capacitively coupled plasma processing apparatus.

[0010] The plasma processing system includes a capacitively coupled plasma processing apparatus 1 and a control unit 2. The capacitively coupled plasma processing apparatus 1 includes a plasma processing chamber 10, a gas supply unit 20, a power supply 30, and an exhaust system 40. The plasma processing apparatus 1 also includes a substrate support unit 11 and a gas introduction unit. The gas introduction unit is configured to introduce at least one processing gas into the plasma processing chamber 10. The gas introduction unit includes a shower head 13. The substrate support unit 11 is located inside the plasma processing chamber 10. The shower head 13 is located above the substrate support unit 11. In one embodiment, the shower head 13 constitutes at least a portion of the ceiling of the plasma processing chamber 10. The plasma processing chamber 10 has a plasma processing space 10s defined by the shower head 13, the side walls 10a of the plasma processing chamber 10, and the substrate support unit 11. The plasma processing chamber 10 has at least one gas supply port for supplying at least one processing gas to the plasma processing space 10s, and at least one gas outlet for discharging gas from the plasma processing space. The plasma processing chamber 10 is grounded. The shower head 13 and the substrate support portion 11 are electrically insulated from the housing of the plasma processing chamber 10.

[0011] The substrate support portion 11 includes a main body portion 111 and a ring assembly 112. The main body portion 111 has a central region 111a for supporting the substrate W and an annular region 111b for supporting the ring assembly 112. A wafer is an example of a substrate W. The annular region 111b of the main body portion 111 surrounds the central region 111a of the main body portion 111 in a plan view. The substrate W is placed on the central region 111a of the main body portion 111, and the ring assembly 112 is placed on the annular region 111b of the main body portion 111 so as to surround the substrate W on the central region 111a of the main body portion 111. Therefore, the central region 111a is also called the substrate support surface for supporting the substrate W, and the annular region 111b is also called the ring support surface for supporting the ring assembly 112.

[0012] In one embodiment, the main body 111 includes a base 1110 and an electrostatic chuck 1111. The base 1110 includes a conductive member. The conductive member of the base 1110 can function as a lower electrode. The electrostatic chuck 1111 is placed on the base 1110. The electrostatic chuck 1111 includes a ceramic member 1111a and an electrostatic electrode 1111b placed within the ceramic member 1111a. The ceramic member 1111a has a central region 111a. In one embodiment, the ceramic member 1111a also has an annular region 111b. Other members surrounding the electrostatic chuck 1111, such as an annular electrostatic chuck or an annular insulating member, may also have an annular region 111b. In this case, the ring assembly 112 may be placed on the annular electrostatic chuck or the annular insulating member, or on both the electrostatic chuck 1111 and the annular insulating member. Furthermore, at least one RF / DC electrode, coupled to an RF (Radio Frequency) power supply 31 and / or a DC (Direct Current) power supply 32 (described later), may be placed within the ceramic member 1111a. In this case, at least one RF / DC electrode functions as a lower electrode. When a bias RF signal and / or DC signal (described later) is supplied to at least one RF / DC electrode, the RF / DC electrode is also called a bias electrode. Note that the conductive member of the base 1110 and at least one RF / DC electrode may function as multiple lower electrodes. Also, the electrostatic electrode 1111b may function as a lower electrode. Therefore, the substrate support portion 11 includes at least one lower electrode.

[0013] The ring assembly 112 includes one or more annular members. In one embodiment, the one or more annular members include one or more edge rings and at least one covering ring. The edge rings are formed of a conductive or insulating material, and the covering rings are formed of an insulating material.

[0014] The substrate support section 11 may also include a temperature control module configured to adjust at least one of the electrostatic chuck 1111, the ring assembly 112, and the substrate to a target temperature. The temperature control module may include a heater, a heat transfer medium, a flow path 1110a, or a combination thereof. A heat transfer fluid such as brine or gas flows through the flow path 1110a. In one embodiment, the flow path 1110a is formed within the base 1110, and one or more heaters are arranged within the ceramic member 1111a of the electrostatic chuck 1111. The substrate support section 11 may also include a heat transfer gas supply section configured to supply heat transfer gas to the gap between the back surface of the substrate W and the central region 111a.

[0015] The showerhead 13 is configured to introduce at least one processing gas from the gas supply unit 20 into the plasma processing space 10s. The showerhead 13 has at least one gas supply port 13a, at least one gas diffusion chamber 13b, and a plurality of gas inlet ports 13c. The processing gas supplied to the gas supply port 13a passes through the gas diffusion chamber 13b and is introduced into the plasma processing space 10s through the plurality of gas inlet ports 13c. The showerhead 13 also includes at least one upper electrode. In addition to the showerhead 13, the gas introduction unit may also include one or more side gas injectors (SGIs) attached to one or more openings formed in the side wall 10a.

[0016] The gas supply unit 20 may include at least one gas source 21 and at least one flow controller 22. In one embodiment, the gas supply unit 20 is configured to supply at least one processing gas to the shower head 13 from a corresponding gas source 21 via a corresponding flow controller 22. Each flow controller 22 may include, for example, a mass flow controller or a pressure-controlled flow controller. Furthermore, the gas supply unit 20 may include one or more flow modulation devices that modulate or pulse the flow rate of at least one processing gas.

[0017] The power supply 30 includes an RF power supply 31 coupled to the plasma processing chamber 10 via at least one impedance matching circuit. The RF power supply 31 is configured to supply at least one RF signal (RF power) to at least one lower electrode and / or at least one upper electrode. This causes plasma to be formed from at least one processing gas supplied to the plasma processing space 10s. Thus, the RF power supply 31 can function as at least part of a plasma generation unit configured to generate plasma from one or more processing gases in the plasma processing chamber 10. Furthermore, by supplying a bias RF signal to at least one lower electrode, a bias potential is generated on the substrate W, and ionic components in the formed plasma can be drawn into the substrate W.

[0018] In one embodiment, the RF power supply 31 includes a first RF generation unit 31a and a second RF generation unit 31b. The first RF generation unit 31a is coupled to at least one lower electrode and / or at least one upper electrode via at least one impedance matching circuit and is configured to generate a source RF signal (source RF power) for plasma generation. In one embodiment, the source RF signal has a frequency in the range of 10 MHz to 150 MHz. In one embodiment, the first RF generation unit 31a may be configured to generate a plurality of source RF signals having different frequencies. One or more generated source RF signals are supplied to at least one lower electrode and / or at least one upper electrode.

[0019] The second RF generation unit 31b is coupled to at least one lower electrode via at least one impedance matching circuit and is configured to generate a bias RF signal (bias RF power). The frequency of the bias RF signal may be the same as or different from the frequency of the source RF signal. In one embodiment, the bias RF signal has a frequency lower than the frequency of the source RF signal. In one embodiment, the bias RF signal has a frequency in the range of 100 kHz to 60 MHz. In one embodiment, the second RF generation unit 31b may be configured to generate a plurality of bias RF signals having different frequencies. One or more generated bias RF signals are supplied to at least one lower electrode. In various embodiments, at least one of the source RF signal and the bias RF signal may be pulsed.

[0020] The power supply 30 may also include a DC power supply 32 coupled to the plasma processing chamber 10. The DC power supply 32 includes a first DC generation unit 32a and a second DC generation unit 32b. In one embodiment, the first DC generation unit 32a is connected to at least one lower electrode and configured to generate a first DC signal. The generated first bias DC signal is applied to at least one lower electrode. In one embodiment, the second DC generation unit 32b is connected to at least one upper electrode and configured to generate a second DC signal. The generated second DC signal is applied to at least one upper electrode.

[0021] In various embodiments, at least one of the first and second DC signals may be pulsed. In this case, a sequence of voltage pulses is applied to at least one lower electrode and / or at least one upper electrode. The voltage pulses may have a rectangular, trapezoidal, triangular, or combination thereof pulse waveform. In one embodiment, a waveform generation unit for generating a sequence of voltage pulses from a DC signal is connected between the first DC generation unit 32a and at least one lower electrode. Thus, the first DC generation unit 32a and the waveform generation unit constitute a voltage pulse generation unit. When the second DC generation unit 32b and the waveform generation unit constitute a voltage pulse generation unit, the voltage pulse generation unit is connected to at least one upper electrode. The voltage pulses may have positive or negative polarity. Furthermore, the sequence of voltage pulses may include one or more positive voltage pulses and one or more negative voltage pulses within one period. The first and second DC generation units 32a and 32b may be provided in addition to the RF power supply 31, and the first DC generation unit 32a may be provided in place of the second RF generation unit 31b.

[0022] The exhaust system 40 may be connected to, for example, a gas outlet 10e located at the bottom of the plasma processing chamber 10. The exhaust system 40 may include a pressure regulating valve and a vacuum pump. The pressure regulating valve regulates the pressure in the plasma processing space 10s. The vacuum pump may include a turbomolecular pump, a dry pump, or a combination thereof.

[0023] The control unit 2 processes computer-executable instructions that cause the plasma processing apparatus 1 to perform various processes described herein. The control unit 2 may be configured to control each element of the plasma processing apparatus 1 to perform the various processes described herein. In one embodiment, part or all of the control unit 2 may be included in the plasma processing apparatus 1. The control unit 2 may include a processing unit 2a1, a storage unit 2a2, and a communication interface 2a3. The control unit 2 is implemented, for example, by a computer 2a. The processing unit 2a1 may be configured to perform various control operations by reading a program from the storage unit 2a2 and executing the read program. This program may be stored in the storage unit 2a2 in advance, or it may be obtained via a medium when needed. The obtained program is stored in the storage unit 2a2 and read from the storage unit 2a2 and executed by the processing unit 2a1. The medium may be various storage media readable by the computer 2a, or it may be a communication line connected to the communication interface 2a3. The processing unit 2a1 may be a CPU (Central Processing Unit). The memory unit 2a2 may include RAM (Random Access Memory), ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof. The communication interface 2a3 may communicate with the plasma processing device 1 via a communication line such as a LAN (Local Area Network).

[0024] <Overview of Information Processing System> Figure 2 is a schematic diagram showing one example of the configuration of the information processing system according to this embodiment. The information processing system according to this embodiment is configured to include an information processing device 201 and a substrate processing device 203. The substrate processing device 203 is a device that performs various processing on semiconductor substrates (wafers), such as CVD (Chemical Vapor Deposition), sputtering, or etching, and is, for example, the plasma processing system shown in Figure 1. In this embodiment, the substrate processing device 203 is equipped with an ESC (Electric Static Chuck) heater 204 and a chiller 205 for controlling the temperature of the substrate to be processed, within a chamber that houses the substrate to be processed.

[0025] The ESC heater 204 is positioned near the ESC, which adsorbs and holds the substrate to be processed, and is a device that heats the substrate held by the ESC to maintain a set temperature. The ESC heater 204 is, for example, a heater provided on the electrostatic chuck 1111 in the plasma processing system shown in Figure 1. The ESC heater 204 generates heat from the power supplied from the power supply and heats the substrate 100. The temperature of the ESC heater 204 is controlled by the information processing device 201 to maintain a temperature set by the user in a recipe or the like. The information processing device 201 determines a control amount to control the amount of heat generated by the ESC heater 204 based on information such as the temperature inside the chamber or the temperature of the substrate W measured by a sensor provided on the substrate processing device 203. Various values ​​can be used as the control amount, for example, the voltage value or current value of the power supplied to the ESC heater 204, or the duty cycle when the ESC heater 204 is controlled by PWM (Pulse Width Modulation). The information processing device 201 appropriately adjusts the control amount of the ESC heater 204 so that the temperature of the ESC heater 204 or the temperature of the substrate W is maintained at a temperature set by the user.

[0026] The chiller 205 is a device that adjusts the temperature of the substrate to be processed and its surroundings by circulating a heat transfer medium. The chiller 205 according to this embodiment can perform both cooling and heating by controlling the compression and expansion of the heat transfer medium. The chiller 205 is a device that adjusts the temperature by circulating a heat transfer medium in the flow path 1110a of the base 1110 in the plasma processing system shown in Figure 1, for example. The chiller 205 comprises a flow path 1110a of the base 1110 provided inside the chamber and an external unit provided outside the chamber. The heat transfer medium is circulated between the internal unit and the external unit, and the external unit adjusts the temperature of the internal unit by performing heat exchange. In this way, the chiller 205 can adjust the temperature inside the chamber and the temperature of the substrate W, and can perform both cooling and heating by controlling the compression and expansion of the heat transfer medium by the external unit. In this embodiment, the chiller 205 has the external unit perform heat exchange so that the temperature reaches a set temperature given by the information processing device 201.

[0027] In this embodiment, the substrate processing apparatus 203 is configured to have a heater and chiller for temperature control located below the substrate W, but it is not limited to this configuration. The substrate processing apparatus 203 may also be configured to have a heater or chiller located above the substrate W, such as on the ceiling of the chamber, or it may be configured to have a heater or chiller located to the side of the substrate W, such as on the side wall of the chamber. Furthermore, the substrate processing apparatus 203 may be equipped with multiple heaters or chillers, and these multiple heaters or chillers may be arranged in any location.

[0028] The information processing device 201 according to this embodiment is a device that acquires and collects data such as device logs (device information) output by the substrate processing device 203, and monitors and controls the operation of the substrate processing device 203. There may be multiple substrate processing devices 203 that the information processing device 201 monitors and controls. The device logs acquired by the information processing device 201 may include various types of data such as process log data, recipe data, wafer transport history data, and error data. In this embodiment, the device log may also include the set temperature (target temperature) of the ESC heater 204 set in a recipe, the temperature of the ESC heater 204 or the substrate held by the ESC measured by a sensor, the control amount input to the ESC heater 204, the power consumption of the ESC heater 204 measured by a sensor or the amount of electricity (voltage value or current value, etc.) from which the power consumption can be calculated, the set temperature of the chiller 205 set in a recipe or set by automatic control, setting information such as the pressure inside the chamber or the voltage of the high-frequency power supply set in a recipe, the temperature and pressure inside the chamber measured by a sensor, and measurement information such as the measured value of a physical quantity by a sensor that can measure the amount of heat of the plasma generated inside the chamber.

[0029] The information processing device 201 according to this embodiment collects device logs from the substrate processing device 203 and records them in a database, and generates various learning models by performing machine learning using the information in the recorded device logs. The learning models generated by the information processing device 201 include, for example, a learning model that predicts the power consumption of the ESC heater 204 based on the device logs, a learning model that predicts the power consumption of the chiller 205 based on the device logs, and a learning model that predicts the control amount of the ESC heater 204 based on the device logs.

[0030] The information processing device 201 uses these learning models, which have been generated in advance by machine learning, to predict power consumption and control amounts based on the device logs acquired from the substrate processing device 203, and controls the substrate processing device 203 based on the prediction results. In this embodiment, the information processing device 201 determines the set temperature of the chiller 205 so that the control amount of the ESC heater 204, the set temperature of the ESC heater 204, and the set temperature of the chiller 205 satisfy predetermined constraints, and so that the sum of the power consumption of the ESC heater 204 and the power consumption of the chiller 205 is as small as possible, and controls the temperature of the substrate processing device 203 by operating the chiller 205 at the determined set temperature.

[0031] <Information Processing Device> Figure 3 is a block diagram showing an example configuration of the information processing device 201 in this embodiment. The information processing device 201 according to this embodiment can be realized by installing a predetermined application program on a general-purpose information processing device such as a personal computer or a server computer. The information processing device 201 according to this embodiment is configured to include a processing unit 211, a storage unit 212, a communication unit 213, a display unit 214, and an operation unit 215. In this embodiment, the explanation will be given assuming that processing is performed by one information processing device 201, but the processing of the information processing device 201 may be distributed among multiple devices.

[0032] The processing unit 211 is composed of a arithmetic processing unit such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), GPU (Graphics Processing Unit), or quantum processor, as well as ROM (Read Only Memory) and RAM (Random Access Memory). The processing unit 211 reads and executes a program 212a stored in the storage unit 212, performing various processes such as controlling the ESC heater 204 and chiller 205 of the substrate processing unit 203, and generating a learning model used for this control.

[0033] The storage unit 212 is configured using a large-capacity storage device such as a hard disk or an SSD (Solid State Drive). The storage unit 212 stores various programs executed by the processing unit 211, and various data necessary for the processing of the processing unit 211. In this embodiment, the storage unit 212 stores the program 212a executed by the processing unit 211. The storage unit 212 is also provided with a device log storage unit 212b that stores device logs acquired from the substrate processing device 203, and a model information storage unit 212c that stores information about learned learning models used in the processing performed by the information processing device 201.

[0034] In this embodiment, the program (computer program, program product) 212a is provided in a form recorded on a recording medium 99 such as a memory card or optical disc, and the information processing device 201 reads the program 212a from the recording medium 99 and stores it in the storage unit 212. However, the program 212a may also be written to the storage unit 212 during the manufacturing stage of the information processing device 201, for example. Alternatively, the program 212a may be obtained by the information processing device 201 via communication from a remote server device or the like that distributes it. For example, the program 212a may be read from the recording medium 99 by a writing device and written to the storage unit 212 of the information processing device 201. The program 212a may be provided in a form distributed via a network, or it may be provided in a form recorded on the recording medium 99.

[0035] The device log storage unit 212b stores the device log acquired from the substrate processing device 203, along with information such as the date and time the device log was acquired, the identification information of the substrate processing device 203, and the identification information of the substrate processed by the substrate processing device 203. The device log may include various types of data, such as process log data, recipe data, wafer transport history data, and error data.

[0036] The model information storage unit 212c stores information about a learning model that has been pre-machine-learned. The information about the learning model may include, for example, information indicating the configuration of the learning model and information such as the values ​​of internal parameters determined by machine learning. In this embodiment, the model information storage unit 212c stores information about multiple learning models, such as a learning model that predicts the power consumption of the ESC heater 204 of the substrate processing device 203, a learning model that predicts the power consumption of the chiller 205, and a learning model that predicts the control amount of the ESC heater 204. In this embodiment, the information processing device 201 stores the information about the learning model and performs the processing by the learning model, but it is not limited to this. The information about the learning model may be stored in a device other than the information processing device 201, and this device may perform the processing by the learning model, and the information processing device 201 may obtain the processing results from this device. Furthermore, the machine learning processing of the learning model may be performed in the information processing device 201 or in a device other than the information processing device 201.

[0037] The communication unit 213 is connected to the substrate processing device 203, for example, via a communication line, and exchanges data with the substrate processing device 203. In this embodiment, the communication unit 213 receives device log data transmitted from the substrate processing device 203 and provides it to the processing unit 211. The communication unit 213 also transmits data such as control commands provided by the processing unit 211 to the substrate processing device 203.

[0038] The display unit 214 is configured using a liquid crystal display or the like, and displays various images and characters based on the processing of the processing unit 211. The display unit 214 displays various information such as the device log acquired from the substrate processing device 203, information about the generated learning model, and the operating status of the substrate processing device 203 that it is controlling.

[0039] The operation unit 215 receives user input and notifies the processing unit 211 of the received input. For example, the operation unit 215 receives user input via a mechanical button or an input device such as a touch panel provided on the surface of the display unit 214. Alternatively, the operation unit 215 may be an input device such as a mouse and a keyboard, and these input devices may be configured to be detachable from the information processing device 201.

[0040] The memory unit 212 may be an external storage device connected to the information processing device 201. The information processing device 201 may be a multicomputer comprising multiple computers, or it may be a virtual machine virtually constructed by software. Furthermore, the information processing device 201 is not limited to the above configuration, and for example, it may not include a display unit 214 and an operation unit 215.

[0041] Furthermore, in the information processing device 201 according to this embodiment, the processing unit 211 reads and executes the program 212a stored in the storage unit 212, thereby realizing the device log acquisition unit 211a, power consumption prediction unit 211b, control amount determination unit 211c, chiller temperature determination unit 211d, control processing unit 211e, and model generation unit 211f, etc., as software-based functional units in the processing unit 211. In this figure, the functional units of the processing unit 211 that are related to information collection and control of the substrate processing device 203 are shown, and functional units related to other processing are omitted from the illustration.

[0042] The device log acquisition unit 211a performs the process of acquiring device log data created by the substrate processing device 203 when it performs substrate processing by communicating with the substrate processing device 203 via the communication unit 213. The device log acquisition unit 211a acquires device log data by communicating with the substrate processing device 203 at a predetermined interval, for example, once per second or once per minute, while the substrate processing device 203 is performing substrate processing such as etching on the target substrate. Alternatively, the device log acquisition unit 211a acquires device log data by communicating with the substrate processing device 203 at an appropriate timing, such as after the substrate processing on the target substrate has been completed. The device log acquisition unit 211a stores the device log data acquired from the substrate processing device 203 in the device log storage unit 212b of the storage unit 212, adding appropriate information such as the acquisition date and time and identification information.

[0043] The period and timing for the device log acquisition unit 211a to acquire device logs from the substrate processing device 203 may be determined as appropriate by the designer of this system. However, if the information processing device 201 controls the operation of the substrate processing device 203 in real time based on the acquired device logs, it is desirable that the information processing device 201 acquires device logs repeatedly while the substrate processing device 203 is performing substrate processing. On the other hand, if the information processing device 201 does not perform real-time control and is intended, for example, to collect device log data for machine learning to generate a learning model, the device logs may be acquired all at once after the completion of substrate processing. In this case, the information processing device 201 may acquire the device logs via a recording medium, for example, instead of via communication.

[0044] The power consumption prediction unit 211b performs a process of predicting the power consumption of the ESC heater 204 and the chiller 205 of the substrate processing apparatus 203 based on the device log acquired by the device log acquisition unit 211a. In the present embodiment, the power consumption prediction unit 211b predicts the power consumption using a learning model generated in advance by machine learning. The model information storage unit 212c stores information regarding a learning model for predicting the power consumption of the ESC heater 204 based on the device log and a learning model for predicting the power consumption of the chiller 205 based on the device log. The power consumption prediction unit 211b constructs a learning model based on the information stored in the model information storage unit 212c, inputs the acquired device log into the learning model, and acquires a predicted value of the power consumption output by the learning model, thereby predicting the power consumption of the ESC heater 204 and the chiller 205.

[0045] The control amount determination unit 211c performs a process of determining a control amount for operating the ESC heater 204 of the substrate processing apparatus 203 at a set temperature based on the device log acquired by the device log acquisition unit 211a. In the present embodiment, the control amount determination unit 211c determines the control amount of the ESC heater 2 using a learning model generated in advance by machine learning. The model information storage unit 212c stores information regarding a learning model for predicting the control amount of the ESC heater 204 based on the device log, The control amount determination unit 211c constructs a learning model based on the information stored in the model information storage unit 212c, inputs the acquired device log into the learning model, and acquires a predicted value of the control amount output by the learning model, and determines this predicted value as the control amount for the ESC heater 204.

[0046] The chiller temperature determination unit 211d performs a process to determine the set temperature of the chiller 205 that minimizes power consumption, based on the power consumption of the ESC heater 204 and chiller 205 predicted by the power consumption prediction unit 211b and the control amount of the ESC heater 204 determined by the control amount determination unit 211c. In this embodiment, for example, upper and lower limit constraints are predetermined for the control amount of the ESC heater 204. The chiller temperature determination unit 211d searches for a set temperature of the chiller 205 that satisfies these constraints and minimizes the power consumption of the ESC heater 204 and chiller 205, using a method such as multi-objective optimization or Bayesian optimization. If the power consumption at the set temperature obtained through the search is less than the power consumption at the current set temperature, the chiller temperature determination unit 211d determines the set temperature obtained through the search as the new set temperature of the chiller 205.

[0047] The control processing unit 211e controls the temperature of the substrate processing device 203 using the ESC heater 204 and chiller 205 based on the control amount of the ESC heater 204 determined by the control amount determination unit 211c and the set temperature of the chiller 205 determined by the chiller temperature determination unit 211d. The control processing unit 211e communicates with the substrate processing device 203 via the communication unit 213 and notifies the substrate processing device 203 of the determined control amount of the ESC heater 204 and the set temperature of the chiller 205. As a result, the control processing unit 211e can operate the ESC heater 204 with the determined control amount and operate the chiller 205 to reach the determined set temperature.

[0048] The model generation unit 211f performs a process of generating a learning model used by the power consumption prediction unit 211b and the control amount determination unit 211c for processing by machine learning using the device logs stored in the device log storage unit 212b. The model generation unit 211f appropriately extracts a plurality of pieces of information included in the device logs to generate learning data (teacher data) for machine learning. The model generation unit 211f performs so-called supervised machine learning on a learning model whose structure and the like are determined in advance using the generated learning data, and determines a plurality of parameters of the learning model, thereby generating a desired learning model. In the present embodiment, the model generation unit 211f generates three learning models: a learning model for estimating the power consumption of the ESC heater 204, a learning model for estimating the power consumption of the chiller 205, and a learning model for estimating the control amount of the ESC heater 204. The model generation unit 211f stores information such as the parameters of the generated learning model in the model information storage unit 212c.

[0049] <Learning Model Generation Process> In the present embodiment, the information processing device 201 acquires device logs from the substrate processing device 203 and stores them in the device log storage unit 212b, and performs a machine learning process of generating a learning model at an appropriate timing after sufficient information has been accumulated. The learning models generated by the information processing device 201 are a learning model for estimating the power consumption of the ESC heater 204, a learning model for estimating the power consumption of the chiller 205, and a learning model for estimating the control amount of the ESC heater 204. For these learning models, learning models with various configurations such as, for example, neural networks, SVM (Support Vector Machine), or random forests can be adopted. Since the configurations of these learning models and the methods of machine learning and the like are existing technologies, detailed descriptions thereof are omitted.

[0050] Figure 4 is a schematic diagram illustrating one example configuration of the first learning model generated in this embodiment. The first learning model 261 according to this embodiment is a learning model that predicts the power consumption of the ESC heater 204. The first learning model 261 is pre-machine-trained to receive, for example, the set temperature of the ESC heater 204, the set temperature of the chiller 205, and observation information obtained by observing the state of the substrate processing apparatus 203 with sensors, etc., as input, and to output a predicted value of the power consumption of the ESC heater 204. Various types of information can be used as observation information, for example, the temperature measurement value of the ESC heater 204, the temperature inside the chamber, the pressure inside the chamber, and the output voltage value of the high-frequency power supply.

[0051] The above information corresponding to the input and output of the first learning model 261 is information contained in the device log acquired by the information processing device 201 from the substrate processing device 203. The information processing device 201 extracts the set temperature of the ESC heater 204, the set temperature of the chiller 205, the information contained in the observation information, and the power consumption of the ESC heater 204 from the device log stored in the device log storage unit 212b. The information processing device 201 uses the extracted set temperature of the ESC heater 204, the set temperature of the chiller 205, and the information contained in the observation information as input data and generates learning data that associates the power consumption of the ESC heater 204 with the output data (correct value). The information processing device 201 performs so-called supervised machine learning processing on a learning model whose configuration is predetermined and whose internal parameters have initial values ​​set, using the learning data generated based on the device log. As a result, the information processing device 201 can determine the values ​​of the internal parameters of the learning model and generate the first learning model 261.

[0052] Figure 5 is a schematic diagram illustrating one example configuration of the second learning model generated in this embodiment. The second learning model 262 according to this embodiment is a learning model that predicts the power consumption of the chiller 205. The second learning model 262 is pre-machine-trained to receive, for example, the set temperature of the ESC heater 204, the set temperature of the chiller 205, and observation information obtained by observing the state of the substrate processing apparatus 203 with sensors, etc., as input, and to output a predicted value of the power consumption of the chiller 205. Various types of information can be used as observation information, for example, the temperature measurement value of the ESC heater 204, the temperature inside the chamber, the pressure inside the chamber, and the output voltage value of the high-frequency power supply. The types of observation information included in the learning data for generating the first learning model 261 and the types of observation information included in the learning data for generating the second learning model 262 may be the same or different. One or more pieces of information to be included as observation information in the learning data are appropriately selected by the designer of this system from among multiple pieces of information included in the device log.

[0053] The information processing device 201 extracts the set temperature of the ESC heater 204, the set temperature of the chiller 205, information included in the observation data, and the power consumption of the chiller 205 from the device log stored in the device log storage unit 212b. The information processing device 201 uses the extracted set temperature of the ESC heater 204, the set temperature of the chiller 205, and the information included in the observation data as input data and generates training data that associates the power consumption of the chiller 205 with the output data (correct value). The information processing device 201 performs so-called supervised machine learning processing on a training model whose configuration is predetermined and whose internal parameters have initial values ​​set, using the training data generated based on the device log. As a result, the information processing device 201 can determine the values ​​of the internal parameters of the training model and generate a second training model 262.

[0054] Figure 6 is a schematic diagram illustrating one example configuration of the third learning model generated in this embodiment. The third learning model 263 according to this embodiment is a learning model that predicts the control amount of the ESC heater 204. The third learning model 263 is pre-machine-trained to receive, for example, the set temperature of the ESC heater 204, the set temperature of the chiller 205, and observation information obtained by observing the state of the substrate processing apparatus 203 with sensors, etc., as input, and to output a predicted value of the control amount of the ESC heater 204. Various types of information can be used as observation information, for example, the temperature measurement value of the ESC heater 204, the temperature inside the chamber, the pressure inside the chamber, and the output voltage value of the high-frequency power supply. The types of observation information included in the learning data for generating the third learning model 263 may be the same as, or different from, the types of observation information included in the learning data for generating the first learning model 261, or the types of observation information included in the learning data for generating the second learning model 262.

[0055] The information processing device 201 extracts the set temperature of the ESC heater 204, the set temperature of the chiller 205, information contained in the observation data, and the control amount of the ESC heater 204 from the device log stored in the device log storage unit 212b. The information processing device 201 uses the extracted set temperature of the ESC heater 204, the set temperature of the chiller 205, and the information contained in the observation data as input data and generates training data that associates the control amount of the ESC heater 204 with the output data (correct value). The information processing device 201 performs so-called supervised machine learning processing on a training model whose configuration is predetermined and whose internal parameters have initial values ​​set, using the training data generated based on the device log. As a result, the information processing device 201 can determine the values ​​of the internal parameters of the training model and generate a third training model 263.

[0056] The learning models shown in Figures 4 to 6 are inputs of the set temperature of the ESC heater 204, the set temperature of the chiller 205, and observation information, but are not limited to these. These learning models may also be input, in lieu of or along with observation information, setting information such as the pressure inside the chamber or the output voltage of the high-frequency power supply, which is set in a recipe included in the device log. A learning model that uses observation information as input is suitable, for example, when the substrate processing apparatus 203 is performing substrate processing such as etching on a substrate and making real-time predictions. A learning model that uses setting information as input is suitable, for example, when the substrate processing apparatus 3 is making predictions before starting substrate processing.

[0057] <Chiller Control Processing> In this embodiment, the information processing device 201 uses a learning model generated in advance by machine learning to control the temperature of the chiller 205 in order to reduce the (total) power consumption of the ESC heater 204 and chiller 205 of the substrate processing device 203. In this embodiment, the substrate processing device 203 is subject to constraints on the temperature setting of the ESC heater 204, the temperature setting of the chiller 205, and the control amount of the ESC heater 204. The information processing device 201 controls the set temperature of the chiller 205 within a range that satisfies the constraints defined in the substrate processing device 203. In this embodiment, the following two constraints are defined. However, this is just one example of constraints, and other constraints may be appropriately defined by the designer of the substrate processing device 203, etc.

[0058] (Constraint 1) 0 < Control amount of ESC heater 204 < 100 (Constraint 2) Set temperature of ESC heater 204 > Set temperature of chiller 205

[0059] Constraint 1 above indicates that, for example, the control amount of the ESC heater 204 is a numerical value defined in a range from 0% to 100%, like the duty cycle of PWM control, but it is prohibited to set it to the lower limit of 0% or the upper limit of 100%. Constraint 2 indicates that it is prohibited to set the set temperature of the ESC heater 204 to a temperature lower than or equal to the set temperature of the chiller 205.

[0060] The information processing device 201 acquires a device log from the substrate processing device 203, extracts necessary information (such as the set temperature of the ESC heater 204, the set temperature of the chiller 205, observation information, and setting information) from the acquired device log, and inputs it into the first learning model 261, the second learning model 262, and the third learning model 263, respectively. This allows the information processing device 201 to obtain predicted values ​​for the power consumption of the ESC heater 204, the power consumption of the chiller 205, and the control amount of the ESC heater 204 at that time. By changing the set temperature of the chiller 205 among the input information to each learning model, the information processing device 201 can determine the changes in the power consumption of the ESC heater 204, the power consumption of the chiller 205, and the control amount of the ESC heater 204 in response to this change.

[0061] The information processing device 201 can search for a range of chiller 205 set temperatures that satisfy constraints 1 and 2 by changing the input of the chiller 205 set temperature to the third learning model 263 and determining whether the control amount of the ESC heater 204 output by the third learning model 263 satisfies the above constraints 1 and 2. Furthermore, within the range of chiller 205 set temperatures that satisfy constraints 1 and 2, the information processing device 201 can search for a chiller 205 set temperature that minimizes (minimal) power consumption by changing the input of the chiller 205 set temperature to the first learning model 261 and the second learning model 262 and examining the change in the total power consumption output by the first learning model 261 and the second learning model 262.

[0062] The information processing device 201 notifies the substrate processing device 203 of the set temperature of the chiller 205 that minimizes power consumption obtained through the above search, and causes the substrate processing device 203 to operate the chiller 205 to maintain this set temperature. The information processing device 201 also uses the third learning model 263 to obtain the control amount of the ESC heater 204 corresponding to the set temperature of the chiller 205, and notifies the substrate processing device 203 of the control amount of the ESC heater 204, causing the substrate processing device 203 to operate the ESC heater 204 with this control amount.

[0063] Figure 7 is a flowchart showing an example of the processing procedure performed by the information processing device 201 according to this embodiment. The flowchart in Figure 7 shows that the information processing device 201 determines the set temperature of the chiller 205 at a predetermined timing, such as before or immediately after the start of substrate processing by the substrate processing device 203, and thereafter the substrate processing device 203 performs substrate processing according to this set temperature without changing it.

[0064] In this embodiment, the device log acquisition unit 211a of the processing unit 211 of the information processing device 201 acquires a device log from the substrate processing device 203 by communicating with the substrate processing device 203 via the communication unit 213 (step S1). If this process is performed before the substrate processing device 203 starts substrate processing such as etching, the device log acquired in step S1 includes setting information (recipe information) related to the substrate processing performed by the substrate processing device 203, and does not need to include observation information observed by sensors, etc., during substrate processing. The device log acquisition unit 211a stores the device log acquired in step S1 in the device log storage unit 212b, along with information such as the identification information of the substrate processing device 203, the identification information of the substrate to be processed, and a timestamp (step S2).

[0065] Next, the power consumption prediction unit 211b of the processing unit 211 uses the device log acquired in step S1 and the first learning model 261 and the second learning model 262 stored in the model information storage unit 212c to predict the power consumption of the ESC heater 204 and chiller 205 of the substrate processing apparatus 203 (step S3). In this example, the first learning model 261 and the second learning model 262 receive the set temperature of the ESC heater 204, the set temperature of the chiller 205, and other setting information related to substrate processing as input and output a predicted value for the power consumption of the ESC heater 204 or the chiller 205. The power consumption prediction unit 211b inputs the set temperature of the ESC heater 204, the set temperature of the chiller 205, and other setting information related to substrate processing, which are included in the acquired device log, into the first learning model 261 and the second learning model 262. By obtaining the power consumption of the ESC heater 204 or the power consumption of the chiller 205 output by these learning models, the power consumption can be predicted. The set temperature of the chiller 205 input to the learning model at this time may be the set temperature of the chiller 205 set by the user in a recipe, or the set temperature set as an initial value for the substrate processing device 203.

[0066] The chiller temperature determination unit 211d of the processing unit 211 uses the device log acquired in step S1 and the first learning models 261 to the third learning models 263 stored in the model information storage unit 212c to search for a chiller 205 setting temperature that can reduce the power consumption predicted in step S3 (step S4). At this time, the chiller temperature determination unit 211d, for example, changes the chiller 205 setting temperature input to the third learning model 263 and examines the change in the control amount of the ESC heater 204 to determine a range of chiller 205 setting temperatures that satisfy predetermined constraints for the control amount of the ESC heater 204 and predetermined constraints for the setting temperature of the ESC heater 204 and the chiller 205 setting temperature. The chiller temperature determination unit 211d changes the set temperature of the chiller 205 within this range, examines the change in the total power consumption of the ESC heater 204 predicted by the first learning model 261 and the chiller 205 predicted by the second learning model 262, and determines the set temperature of the chiller 205 that minimizes the total power consumption.

[0067] The control processing unit 211e of the processing unit 211 compares the power consumption when the chiller 205 set temperature determined in step S4 is adopted with the power consumption predicted in step S3 to determine whether or not the power consumption can be reduced (step S5). If the power consumption can be reduced (S5: YES), the control processing unit 211e notifies the substrate processing unit 203 of the chiller 205 set temperature determined in step S4 and issues a command to change the temperature, thereby changing the chiller 205 set temperature of the substrate processing unit 203 (step S6), and terminates the process. If the power consumption cannot be reduced (S5: NO), the control processing unit 211e terminates the process without changing the chiller 205 set temperature in order to maintain the current chiller 205 set temperature.

[0068] Figure 8 is a flowchart showing an example of the processing procedure performed by the information processing device 201 according to this embodiment. The flowchart shown in Figure 8 is a procedure in which, for example, while the substrate processing device 203 is performing substrate processing, the information processing device 201 repeatedly acquires a device log and determines the set temperature of the chiller 205, thereby controlling the temperature of the chiller 205 in real time.

[0069] The processing unit 211 of the information processing device 201 according to this embodiment performs the following processes in the same manner as the procedure shown in the flowchart in Figure 7: acquiring a device log (step S1), storing the device log (step S2), predicting power consumption (step S3), searching for the set temperature of the chiller 205 (step S4), determining whether power consumption can be reduced (step S5), and changing the set temperature of the chiller 205 (step S6). However, when performing control processing in real time, the device log acquired from the substrate processing device 203 includes various observation information observed by sensors, etc., during substrate processing, and the first learning model 261 to the third learning model 263 receive this observation information as input and output predicted values.

[0070] The control amount determination unit 211c of the processing unit 211 determines the set temperature of the chiller 205 in steps S5 and S6, and then uses the set temperature of the chiller 205, the device log of the substrate processing device 203 acquired in step S1, and the third learning model 263 to determine the control amount of the ESC heater 204 of the substrate processing device 203 (step S7). The control processing unit 211e of the processing unit 211 provides the control amount determined in step S7 to the substrate processing device 203 to control the operation of the ESC heater 204 (step S8).

[0071] The processing unit 211 determines whether the substrate processing, such as etching, on the target substrate by the substrate processing device 203 has been completed (step S9). If the substrate processing has not been completed (S9: NO), the processing unit 211 returns to step S1, obtains a device log from the substrate processing device 203, and repeats the processes in steps S1 to S8. If the substrate processing has been completed (S9: YES), the processing unit 211 terminates the process.

[0072] Figure 9 is a schematic diagram illustrating an example of temperature control of the chiller 205 by the information processing system according to this embodiment. Figure 9 schematically shows the correspondence between the ambient temperature of the substrate processing apparatus 203, the temperature of the ESC heater 204, and the temperature of the chiller 205. The ambient temperature in the figure is, for example, the temperature inside the chamber or the temperature around the chiller 205. The temperature of the ESC heater 204 in the figure is the temperature observed by a sensor, and the information processing apparatus 201 controls the operation of the ESC heater 204 of the substrate processing apparatus 203 to maintain the temperature observed by the sensor at a temperature set by the user. Similarly, the temperature of the chiller 205 in the figure is the temperature observed by a sensor, and the substrate processing apparatus 203 controls the operation of the chiller 205 to maintain the temperature observed by this sensor at a set temperature provided by the information processing apparatus 201.

[0073] The upper part of Figure 9 shows the case where the set temperature of the ESC heater 204 is set to a temperature lower than the ambient temperature. In this case, the information processing device 201 controls the set temperature of the chiller 205 by executing the flowchart shown in Figure 8, so that the difference between the temperature of the ESC heater 204 and the temperature of the chiller 205 becomes small. At this time, there is a possibility that the operation of the ESC heater 204 may stop (the control amount becomes 0) because the difference between the temperature of the ESC heater 204 and the chiller 205 becomes small, but the information processing device 201 determines the set temperature of the chiller 205 in a way that satisfies the constraints on the control amount of the ESC heater 204, and thus prevents the operation of the ESC heater 204 from stopping.

[0074] The lower part of Figure 9 shows the case where the set temperature of the ESC heater 204 is set to a temperature higher than the ambient temperature. In this case, the information processing device 201 controls the set temperature of the chiller 205 by executing the flowchart shown in Figure 8, so that the difference between the temperature of the ESC heater 204 and the temperature of the chiller 205 increases, that is, so that the temperature of the chiller 205 approaches the ambient temperature. At this time, the large difference between the temperature of the ESC heater 204 and the chiller 205 may cause the ESC heater 204 to operate at maximum output (the control amount becomes 100), but the information processing device 201 determines the set temperature of the chiller 205 in a way that satisfies the constraints on the control amount of the ESC heater 204, thus preventing the ESC heater 204 from operating at maximum output.

[0075] <Summary> In the information processing system according to this embodiment with the above configuration, the information processing device 201 acquires a device log (device information) from the substrate processing device 203, which includes the set temperature of the ESC heater 204 and the setting information or observation information of the substrate processing device 203, and predicts the power consumption of the ESC heater 204 and the chiller 205 based on the acquired device log. The information processing device 201 searches for a chiller setting temperature that satisfies the constraints on the operation of the ESC heater 204 and the chiller 205 and can reduce the power consumption from the predicted power consumption, and changes the chiller 205 setting temperature to the searched setting temperature. As a result, the information processing system according to this embodiment can search for a chiller 205 setting temperature that can be expected to reduce the power consumption predicted from the setting information or observation information of the substrate processing device 203, and is expected to reduce the power consumption of the substrate processing device 3 by changing the chiller 205 setting temperature.

[0076] Furthermore, in the information processing system according to this embodiment, the information processing device 201 repeatedly performs tasks such as acquiring device logs, predicting power consumption, searching for the set temperature of the chiller 205, and changing the set temperature. As a result, the information processing system according to this embodiment is expected to reduce the power consumption of the substrate processing device 203 by allowing the information processing device 201 to control the operation of the substrate processing device 203 in real time.

[0077] Furthermore, in the information processing system according to this embodiment, the information processing device 201 predicts the power consumption of the ESC heater 204 and the chiller 205 using a first learning model 261 and a second learning model 262 that have been generated in advance by machine learning. The first learning model 261 is a learning model that has been pre-machine-trained to predict the power consumption of the ESC heater 204 by receiving the set temperature of the ESC heater 204, the set temperature of the chiller 205, and the setting information or observation information of the substrate processing device 203 as input. The second learning model 262 is a learning model that has been pre-machine-trained to predict the power consumption of the chiller 205 by receiving the set temperature of the ESC heater 204, the set temperature of the chiller 205, and the setting information or observation information of the substrate processing device 203 as input. By using these learning models, the information processing system according to this embodiment is expected to accurately predict the power consumption of the ESC heater 204 and the chiller 205.

[0078] Furthermore, in the information processing system according to this embodiment, the information processing device 201 controls the ESC heater 204 using a third learning model 263 that has been generated in advance by machine learning. The third learning model 263 is a learning model that has been pre-machine-trained to receive the set temperature of the ESC heater 204, the set temperature of the chiller 205, and the setting information or observation information of the substrate processing device 203 as input, and predict the amount of control of the ESC heater 204. By using the third learning model 263, the information processing system according to this embodiment is expected to accurately predict the amount of control of the ESC heater 204.

[0079] Furthermore, in the information processing system according to this embodiment, the information processing device 201 searches for a chiller 205 setting temperature that satisfies the constraints of the control amount output by the third learning model 263 and reduces the sum of the power consumption of the ESC heater 204 output by the first learning model 261 and the power consumption of the chiller 205 output by the second learning model 262. As a result, the information processing system according to this embodiment is expected to accurately determine a chiller 205 setting temperature that can reduce power consumption by utilizing multiple learning models generated in advance by machine learning, thereby reducing the power consumption of the substrate processing device 203.

[0080] Furthermore, in the information processing system according to this embodiment, the observation information included in the device log acquired by the information processing device 201 from the substrate processing device 203 includes measured values ​​of the temperature of the ESC heater 204, the pressure inside the chamber of the substrate processing device 203, or the output power of the high-frequency power supply. As a result, the information processing system according to this embodiment can acquire measured values ​​related to the power consumption of the ESC heater 204 or the power consumption of the chiller 205 and predict the power consumption, and is expected to predict and reduce the power consumption of the substrate processing device 203 with greater accuracy.

[0081] Furthermore, in the information processing system according to this embodiment, the information processing device 201 changes the set temperature of the chiller 205 so that if the set temperature of the ESC heater 204 is lower than the ambient temperature, the set temperature of the chiller 205 is brought closer to the set temperature of the ESC heater 204, and if the set temperature of the ESC heater 204 is higher than the ambient temperature, the set temperature of the chiller 205 is brought closer to the ambient temperature. As a result, the information processing system according to this embodiment is expected to reduce the power consumption of the substrate processing device 203.

[0082] In this embodiment, the information contained in the device log is directly input to the learning model, but this is not the only configuration. The information contained in the device log may be used to perform appropriate calculations, and the results may be input to the learning model. For example, the learning model may be used to input statistical values ​​such as the mean, minimum, maximum, variance, or standard deviation of multiple temperature measurements contained in the observation information. Alternatively, the information contained in the device log may be input to another learning model, and the results of classification or regression may be input to the first learning model 261 to the third learning model 263 described in this embodiment.

[0083] The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of this disclosure is indicated by the claims, not in the sense described above, and all modifications within the meaning and scope equivalent to the claims are intended.

[0084] The matters described in each embodiment can be combined with each other. Furthermore, the independent and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. In addition, the claims use a form in which claims referencing two or more other claims (multi-claim form), but are not limited to this. A form in which multi-claims referencing at least one multi-claim (multi-multi-claim) may also be used.

[0085] 1 Plasma processing apparatus 2 Control unit 2a Computer 2a1 Processing unit 2a2 Memory unit 2a3 Communication interface 2a3 10 Plasma processing chamber 10a Side wall 10e Gas outlet 10s Plasma processing space 11 Substrate support unit 13 Shower head 13a Gas supply port 13b Gas diffusion chamber 13c Gas inlet 20 Gas supply unit 21 Gas source 22 Flow rate controller 30 Power supply 31 RF power supply 31a First RF generation unit 31b Second RF generation unit 32 DC power supply 32a First DC generation unit 32b Second DC generation unit 40 Exhaust system 99 Recording medium 111 Main unit 111a Central region 111b Annular region 112 Ring assembly 201 Information processing apparatus (computer) 203 Substrate processing apparatus 204 ESC heater 205 Chiller 211 Processing unit 211a Device log acquisition unit 211b Power consumption prediction unit 211c Control amount determination unit 211d Chiller temperature determination unit 211e Control processing unit 211f Model generation unit 212 Storage unit 212a Program (computer program) 212b Device log storage unit 212c Model information storage unit 213 Communication unit 214 Display unit 215 Operation unit 261 First learning model 262 Second learning model 263 Third learning model 1110 Base 1110a Flow channel 1111 Electrostatic chuck 1111a Ceramic member 1111b Electrostatic electrode W Substrate

Claims

1. A computer program that causes a computer to acquire device information including the set temperature of the heater of a substrate processing apparatus and setting information related to the processing performed by the substrate processing apparatus or observation information observed in connection with the processing; predict the power consumption of the heater and the chiller of the substrate processing apparatus based on the acquired device information; search for a set temperature for the chiller that satisfies constraints on the operation of the heater and the chiller and reduces the power consumption from the predicted power consumption; and execute a process to change the set temperature of the chiller to the searched set temperature.

2. The computer program according to claim 1, which repeatedly performs the acquisition of device information, the prediction of power consumption, the search for the set temperature, and the change of the set temperature.

3. A computer program according to claim 1, which predicts the power consumption of the heater and the chiller using: a first learning model that has been pre-trained to receive the set temperature of the heater, the set temperature of the chiller, and the setting information or the observation information as inputs and output a predicted value of the power consumption of the heater; and a second learning model that has been pre-trained to receive the set temperature of the heater, the set temperature of the chiller, and the setting information or the observation information as inputs and output a predicted value of the power consumption of the chiller.

4. The computer program according to claim 3, which determines the control amount of the heater using a third learning model that has been pre-trained to receive the set temperature of the heater, the set temperature of the chiller, and the setting information or the observation information as inputs and output a control amount for the heater, and controls the operation of the heater based on the determined control amount.

5. The computer program according to claim 4, which searches for a chiller setting temperature such that the control quantity output by the third learning model satisfies the constraints and reduces the sum of the predicted power consumption output by the first learning model and the predicted power consumption output by the second learning model.

6. The computer program according to claim 1, wherein the observation information includes measured values ​​of the heater temperature, the pressure inside the substrate processing apparatus, or the output power of the high-frequency power supply.

7. The computer program according to claim 1, wherein if the set temperature of the heater is lower than the ambient temperature, the set temperature of the chiller is adjusted to bring it closer to the set temperature of the heater, and if the set temperature of the heater is higher than the ambient temperature, the set temperature of the chiller is adjusted to bring it closer to the ambient temperature.

8. An information processing method comprising: an information processing device acquiring device information including the set temperature of a heater of a substrate processing device and setting information relating to a process performed by the substrate processing device or observation information observed in connection with the process; predicting the power consumption of the heater and the chiller of the substrate processing device based on the acquired device information; searching for a set temperature for the chiller that satisfies constraints relating to the operation of the heater and the chiller and reduces the power consumption from the predicted power consumption; and changing the set temperature of the chiller to the searched set temperature.

9. An information processing device comprising a processing unit, wherein the processing unit acquires device information including the set temperature of the heater of the substrate processing device and setting information relating to the processing performed by the substrate processing device or observation information observed in connection with the processing; predicts the power consumption of the heater and the chiller of the substrate processing device based on the acquired device information; searches for a set temperature of the chiller that satisfies constraints relating to the operation of the heater and the chiller and reduces the power consumption from the predicted power consumption; and changes the set temperature of the chiller to the searched set temperature.

Images