Apparatus for calculating control parameter, method for calculating control parameter, and program for calculating control parameter
The control parameter calculation device addresses the challenge of adjusting fluid control device parameters by using correlation data to quickly and efficiently tune parameters across different devices, regardless of user experience.
Patent Information
- Application Number
- JP2023189823
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-11-07
- Publication Date
- 2025-05-19
AI Technical Summary
Existing fluid control devices require time-consuming and user-experience-dependent adjustments of control parameters to achieve optimal performance, as settings that work in one device may not work in another due to instrument differences.
A control parameter calculation device that calculates and adjusts control parameters by using correlation data from a reference device to determine the necessary adjustments for a target device, allowing for quick and experience-independent parameter tuning.
Enables rapid adjustment of control parameters in fluid control devices, reducing the need for multiple adjustments and improving efficiency, while minimizing the impact of device differences between the reference and target devices.
Smart Images
Figure 2025077546000001_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a control parameter calculation device, a control parameter calculation method, and a control parameter calculation program.
Background Art
[0002] Conventionally, a fluid control device for controlling a fluid flowing through a flow path has been proposed. This type of fluid control device includes, for example, as shown in Patent Document 1, a control valve provided in the flow path, a flow rate sensor for measuring the flow rate of the fluid flowing through the flow path, and a valve controller for controlling the valve based on the measured flow rate measured by the flow rate sensor.
[0003] In the above fluid control device, a set flow rate of the fluid flowing through the flow path is input to the valve controller, and the valve controller compares the set flow rate with the measured flow rate and performs PID control on the opening degree of the control valve. Here, in general PID control, control parameters such as a proportional gain, an integral gain, and a derivative gain are used, and the valve controller performs PID control on the opening degree of the control valve based on the control parameters.
Prior Art Documents
Patent Documents
[0004]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0005] Here, in order for the above fluid control device to show a good response, it is necessary to set appropriate control parameters. However, since there are instrument differences in the above fluid control device, even if a control parameter shows a good response in one fluid control device, when the same control parameter is used in another fluid control device, for example, overshoot may occur or the rise may be slow, and it may not show a good response. As a result, it is necessary to adjust the control parameters for the fluid control device to show a good response, and the adjustment of the conventional control parameters has been carried out based on the user's experience.
[0006] However, when the adjustment of the control parameters is carried out based on the user's experience, depending on the user's ability, the user may adjust the control parameters many times, and it takes time to set the control parameters.
[0007] Therefore, the present invention has been made in view of the above problems, and in a control parameter calculation device that calculates control parameters of a fluid control device, its main problem is to adjust the control parameters in a short time regardless of the user's experience.
Means for Solving the Problems
[0008] That is, the control parameter calculation device according to the present invention is a control parameter calculation device that calculates control parameters of a fluid control device that controls a fluid, and stores correlation data indicating the correlation between the reference control parameters of a reference device that is a reference fluid control device and the reference response signal output using the reference control parameters, a target response signal acquisition unit that acquires a target response signal output using the target control parameters of a target device that is a fluid control device different from the reference device, a correlation control parameter calculation unit that acquires the correlation data and the target response signal, and calculates a correlation control parameter corresponding to the target response signal in the reference device by using the correlation data, and a target control parameter adjustment amount calculation unit that calculates an adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter.
[0009] With such a control parameter calculation device, the correlation control parameter is calculated by using the correlation data, and based on the correlation control parameter and the reference control parameter, the adjustment amount of the target control parameter is calculated. Therefore, the target control parameter can be adjusted regardless of the user's experience. Then, in the target fluid control device, by adjusting the target control parameter based on the calculated adjustment amount of the target control parameter, it is no longer necessary to adjust the target control parameter multiple times, and the adjustment of the target control parameter can be performed more efficiently. In addition, since the adjustment amount of the target control parameter is calculated based on the correlation control parameter and the reference control parameter, compared with the configuration for calculating the control parameter itself of the target fluid control device, it is less affected by the device differences between the reference fluid control device and the target fluid control device. Furthermore, since the target control parameter is calculated by using the correlation data of the reference fluid control device, the correlation data of the target fluid control device can be made unnecessary when calculating the target control parameter.
[0010] The target response signal acquisition unit acquires a plurality of the target response signals, and it is preferable that the correlation control parameter calculation unit calculates one or a set of the correlation control parameters from the plurality of the target response signals.
[0011] With such a configuration, since the correlation control parameter calculation unit calculates one or a set of correlation control parameters from a plurality of target response signals, the accuracy of calculating the correlation control parameter can be improved compared with the case of calculating a set of correlation control parameters based on one target response signal.
[0012] It is desirable that the target control parameter adjustment amount calculation unit obtains the difference between the correlation control parameter and the reference control parameter, and uses the obtained difference as the adjustment amount of the target control parameter.
[0013] With such a configuration, since the difference between the correlation control parameter and the reference control parameter becomes the adjustment amount of the target control parameter, the target control parameter can be adjusted by simply changing the target control parameter based on the difference, and the target control parameter can be easily adjusted.
[0014] As a specific aspect of calculating the correlation control parameter, examples of the correlation control parameter calculation unit include those that calculate the correlation control parameter from the target response signal using a Gaussian mixture regression model.
[0015] With such a configuration, particularly when calculating one or a set of correlation control parameters from a plurality of target response signals, the correlation control parameter can be accurately calculated by using a Gaussian mixture regression model.
[0016] Here, since there is no deterioration in the target device at the first setting when the target control parameter is set for the first time, it is considered that the variation of the control parameter due to deterioration is small. Therefore, in the target device at the first setting, it is considered that the difference in the control parameters between the target device and the reference device is mainly due to the device difference between the target device and the reference device. Therefore, it is preferable that the target response signal acquisition unit acquires the target response signal output using the target control parameter of the target device at the first setting, and the correlation control parameter calculation unit calculates the correlation control parameter from the target response signal of the target device at the first setting.
[0017] With such a configuration, since the difference between the correlation control parameter and the reference control parameter is considered to be due to the device difference between the reference device and the target device, the adjustment amount of the target control parameter can be accurately calculated.
[0018] Examples of the correlation data storage unit include those that store the correlation data created using machine learning.
[0019] With such a configuration, since the correlation data created using machine learning is stored, the accuracy of the correlation data can be improved.
[0020] Further, the control parameter calculation method is a control parameter calculation method for calculating the control parameters of a fluid control device that controls a fluid, and stores correlation data indicating the correlation between the reference control parameters of a reference device, which is a reference fluid control device, and the reference response signal output using the reference control parameters, obtains a target response signal output using the target control parameters of a target device, which is a fluid control device different from the reference device, obtains the correlation data and the target response signal, and by using the correlation data, calculates the correlation control parameter corresponding to the target response signal in the reference device, and calculates the adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter.
[0021] With such a configuration, the same operational effects as those of the above control parameter calculation device can be obtained.
[0022] Furthermore, a control parameter calculation program used for a fluid control device that controls a fluid and calculates the control parameters of the fluid control device causes a computer to exhibit a function as a correlation data storage unit that stores correlation data indicating the correlation between the reference control parameters of a reference device, which is a reference fluid control device, and the reference response signal output using the reference control parameters, a function as a target response signal acquisition unit that acquires a target response signal output using the target control parameters of a target device, which is a fluid control device different from the reference device, a function as a correlation control parameter calculation unit that acquires the correlation data and the target response signal and calculates the correlation control parameter corresponding to the target response signal in the reference device by using the correlation data, and a function as a target control parameter adjustment amount calculation unit that calculates the adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter.
[0023] With such a configuration, the same operational effects as those of the above control parameter calculation device can be obtained.
Advantages of the Invention
[0024] According to the present invention configured as described above, in a control parameter calculation device that calculates control parameters of a fluid control device, the control parameters can be adjusted in a short time regardless of the user's experience.
Brief Description of the Drawings
[0025]
Figure 1
Figure 2
Figure 3
Modes for Carrying Out the Invention
[0026] Hereinafter, an embodiment of a control parameter calculation device that calculates control parameters of a fluid control device according to the present invention will be described with reference to the drawings. Note that, for the sake of clarity, some of the figures shown below may be schematically drawn with appropriate omissions or exaggerations. The same reference numerals are assigned to the same components, and the description thereof will be omitted as appropriate.
[0027] As shown in FIG. 1, the control parameter calculation device 200 according to the present embodiment calculates control parameters of a fluid control device 100 that controls a fluid flowing through a flow path.
[0028] Here, the fluid control device 100 targeted by the control parameter calculation device 200 is a so-called differential pressure type mass flow controller (differential pressure type MFC). As shown in FIG. 1, it includes a flow path block 110 in which a plurality of internal flow paths 1R are formed, a fluid control device 120 provided in the flow path block 110, and a control unit 130 that controls the fluid control device 120. Hereinafter, each part of the fluid control device 100 targeted by the control parameter calculation device 200 will be described.
[0029] The flow path block 110 is provided with an introduction port 111 for introducing fluid into the internal flow path 1R and a discharge port 112 for discharging fluid from the internal flow path 1R. An upstream piping H1 is connected to the introduction port 111, and an upstream pneumatic valve V1 is provided in the upstream piping H1. Further, a downstream piping H2 is connected to the discharge port 112, and a downstream pneumatic valve V2 is provided in the downstream piping H2.
[0030] The fluid control device 120 controls the fluid in the internal flow path 1R, and includes a flow rate sensor 121 that measures the flow rate of the fluid flowing through the internal flow path 1R and a fluid control valve 122 provided upstream of the flow rate sensor 121. The fluid control valve 122 performs PID control on the flow rate of the fluid flowing through the internal flow path 1R by a control unit 130 described later.
[0031] The flow rate sensor 121 is a differential pressure type flow rate sensor, and includes an upstream pressure sensor 121a provided upstream of a fluid resistance element 123 such as a restrictor or an orifice provided in the internal flow path 1R, and a downstream pressure sensor 121b provided downstream of the fluid resistance element 123. Then, the flow rate of the fluid flowing through the internal flow path 1R is calculated by a flow rate calculation unit 131 of the control unit 130 described later using the upstream pressure P1 of the fluid resistance element 123 detected by the upstream pressure sensor 121a and the downstream pressure P2 of the fluid resistance element 123 detected by the downstream pressure sensor 121b.
[0032] The fluid control valve 122 is provided upstream of the flow rate sensor 121. Specifically, the fluid control valve 122 controls the flow rate by moving a valve body forward and backward with respect to a valve seat by a piezo actuator. Note that the fluid control valve 122 is controlled by a valve control unit 132 of the control unit 130.
[0033] The control unit 130 includes a flow rate calculation unit 131 that calculates the flow rate flowing through the internal flow path 1R based on the upstream pressure P1 and the downstream pressure P2, and a valve control unit 132 that controls the fluid control valve 122 based on the flow rate calculated by the flow rate calculation unit 131. Note that the control unit 130 is a so-called computer including, for example, a CPU, a memory, an A / D·D / A converter, and input / output means, and by executing a flow rate control program stored in the memory and causing various devices to cooperate, functions as the flow rate calculation unit 131, the valve control unit 132, etc.
[0034] The flow rate calculation unit 131 calculates the flow rate flowing through the internal flow path 1R using an existing flow rate calculation formula. Examples of the existing flow rate calculation formula include those in which the flow rate is calculated by multiplying the difference between the square of the upstream pressure P1 and the square of the downstream pressure P2 by a predetermined coefficient, but other flow rate calculation formulas may also be used.
[0035] The valve control unit 132 acquires a set flow rate, performs PID control based on the deviation between the calculated flow rate and the set flow rate, and controls the flow rate flowing through the internal flow path 1R. The valve control unit 132 stores control parameters such as a proportional gain, an integral gain, or a derivative gain, and the valve control unit 132 performs PID control using the control parameters.
[0036] Next, the configuration of the control parameter calculation device 200 will be described.
[0037] The control parameter calculation device 200 calculates the control parameters used by the valve control unit 132, and is, for example, a so-called computer equipped with a CPU, a memory, an A / D·D / A converter, and input / output means. When the flow control program stored in the memory is executed and various devices cooperate, as shown in FIG. 2, it functions at least as a correlation data storage unit 210, a target response signal acquisition unit 240, a correlation control parameter calculation unit 250, and a target control parameter adjustment amount calculation unit 260.
[0038] The correlation data storage unit 210 stores correlation data indicating the correlation between the reference control parameters of a reference fluid control device (hereinafter referred to as the reference device) and the reference response signal output using the reference control parameters. In the present embodiment, the reference device refers to a fluid control device in which the control parameters have not changed or the change in the control parameters is within the allowable range as compared with the control parameters when first set. Here, the reference control parameter is a control parameter for the valve control unit 132 of the reference device to perform PID control. The reference response signal corresponds to the reference control parameter according to the correlation data. Specifically, when the valve control unit 132 of the reference device performs PID control using the reference control parameter, for example, the response time until the flow rate measured by the flow rate sensor 121 reaches a predetermined flow rate, the overshoot amount when the flow rate measured by the flow rate sensor 121 exceeds the set flow rate, or the hunting amount which is the time required for the flow rate measured by the flow rate sensor 121 to stabilize. Also, in the present embodiment, the correlation data associates the reference control parameter and the reference response signal one-to-one. In other words, when the reference control parameter is determined, the reference response signal is determined based on the correlation data.
[0039] Here, the correlation data is created by the valve control unit 132 of the reference device correlating the reference control parameters and the reference response signal when the valve control unit 132 of the reference device performs PID control on the flow rate of the fluid flowing through the internal flow path 1R using the reference control parameters. Specifically, the valve control unit 132 of the reference device performs PID control using the reference control parameters. Then, the control parameter calculation device 200 acquires the response waveform from the flow rate measured by the flow rate sensor 121, acquires the reference response signal from the response waveform, and correlates the reference control parameters and the reference response signal at that time. The above operations are performed for all reference control parameters within a predetermined range, and correlation data is created by correlating all control parameters and reference response signals within the predetermined range. The created correlation data is stored in the correlation data storage unit 210.
[0040] The target response signal acquisition unit 240 acquires the target response signal output using the target control parameters of a fluid control device (hereinafter referred to as the target device) different from the reference device. Here, the target control parameters are the control parameters for the valve control unit 132 of the target device to perform PID control. The target response signal is a response signal such as the response time, overshoot amount, or hunting amount when the valve control unit 132 of the target device performs PID control using the target control parameters.
[0041] In the present embodiment, in order for the target response signal acquisition unit 240 to acquire the target response signal, the target control parameter acquisition unit 220 acquires the target control parameters, and the target response signal calculation unit 230 causes the valve control unit 132 of the target device to perform PID control based on the target control parameters, acquires the response waveform from the flow rate measured by the flow rate sensor 121 at that time, and calculates the target response signal in the response waveform. Then, the target response signal acquisition unit 240 acquires the target response signal calculated by the target response signal calculation unit 230.
[0042] The correlation control parameter calculation unit 250 calculates a correlation control parameter, which is a control parameter of a reference device corresponding to a target response signal, by using correlation data. Specifically, the correlation control parameter is a reference control parameter when it is assumed that the reference device outputs the target response signal, and the correlation control parameter calculation unit 250 calculates the correlation control parameter from the target response signal by using the correlation data. In the present embodiment, the correlation data used by the correlation control parameter calculation unit 250 is, for example, a Gaussian mixture regression model, but is not limited thereto.
[0043] In the present embodiment, the correlation control parameter calculation unit 250 calculates a set of correlation control parameters from a plurality of target response signals. Specifically, the target response signal acquisition unit 240 acquires a plurality of target response signals. Here, the plurality of target response signals are, for example, at least two or more of a response time, an overshoot amount, or a hunting amount. Then, the correlation control parameter calculation unit 250 acquires these plurality of target response signals and calculates a set of correlation control parameters including a proportional gain P and an integral gain I by using the correlation data.
[0044] Also in the present embodiment, the correlation control parameter calculated by the correlation control parameter calculation unit 250 is calculated based on the target response signal of the target device at the first setting when the target control parameter is set for the first time. In the present embodiment, the first setting means setting the target control parameter from when the target device is manufactured until it is first installed in the flow path. Specifically, the target response signal acquisition unit 240 acquires the target response signal of the target device at the first setting. Then, the correlation control parameter calculation unit 250 acquires the target response signal of the target device at the first setting and calculates the correlation control parameter by using the correlation data.
[0045] The target control parameter adjustment amount calculation unit 260 calculates the adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter. Specifically, the target control parameter adjustment amount calculation unit 260 obtains the difference between the correlation control parameter and the reference control parameter, and uses this difference as the adjustment amount of the target control parameter.
[0046] <Calculation method of control parameter> Next, a control parameter calculation method for calculating control parameters using the control parameter calculation device 200 of the present embodiment will be described with reference to FIG. 3.
[0047] FIG. 3(a) is a graph showing the correlation between the reference control parameter and the reference response signal in the reference device. FIG. 3(a) is a graph of control parameters with the proportional gain P on the horizontal axis and the integral gain I on the vertical axis. In FIG. 3(a), the index of the reference response signal is shown by contour lines indicating the region of the reference control parameter where the same reference response signal is output, using the same line.
[0048] Here, the index of the reference response signal is a value evaluated by, for example, assigning a score to a combination of the overshoot amount and the response time. The more ideal the reference response signal is, the higher the evaluated value. In FIG. 3(a), the region surrounded by more contour lines indicates a more ideal reference response signal, and the reference control parameter corresponding to the most ideal reference response signal is the optimal value of the reference control parameter. The optimal value of the reference control parameter mentioned here is, for example, the reference control parameter when a physical quantity indicating the reference response signal, such as the response time, overshoot amount, or hunting amount, becomes the minimum value.
[0049] Further, FIG. 3(b) is a graph showing an example of the correlation between the target control parameter and the target response signal in the target device. Similar to FIG. 3(a), FIG. 3(b) is a graph of control parameters with the horizontal axis being the proportional gain P and the vertical axis being the integral gain I. In FIG. 3(b), similar to FIG. 3(a), the index of the target response signal is indicated by contour lines showing the region of the target control parameter where an equivalent target response signal is output, using the same line.
[0050] In FIG. 3(b), the distribution shape of the graph of the target device showing the region of the target control parameter and the index of the target response signal is largely due to the deterioration of the target device. Particularly for the target device at the time of initial setting, it is considered that the distribution shape of the graph of the target device will be substantially the same among devices. That is, in the case of the target device at the time of initial setting, as shown in FIG. 3(b), the distribution shape of the graph of the target device is substantially the same as the distribution shape of the graph of the reference device shown in FIG. 3(a), but due to the difference between the target device and the reference device, the proportional gain P and the integral gain I of the target device are shifted from the proportional gain P and the integral gain I of the reference device.
[0051] The control parameter calculation device 200 of the present embodiment calculates the adjustment amount of the target control parameter by using only the correlation data of the reference device without creating the correlation data of the target device by utilizing the difference between the graph of the target device and the graph of the reference device due only to the device difference, particularly for the target device at the time of initial setting. The calculation of the specific adjustment amount of the target control parameter is shown below.
[0052] The target control parameter acquisition unit 220 acquires the target control parameter of the target device. Here, the target device from which the target control parameter is acquired is the target device at the time of initial setting. Also, the target control parameter acquired by the target control parameter acquisition unit 220 is the optimal value of the reference control parameter. Note that the target control parameter acquired by the target control parameter acquisition unit 220 is not limited to the optimal value of the reference control parameter and may be other values.
[0053] The target response signal calculation unit 230 acquires a response waveform from the flow rate measured by the flow rate sensor 121 when the valve control unit 132 of the target device performs PID control based on the target control parameter, and calculates the target response signal. In the present embodiment, as shown in FIG. 3(b), the target response signal is the response signal of the target device when the valve control unit 132 of the target device performs PID control based on the optimum value of the reference control parameter. Then, the target response signal acquisition unit 240 acquires the target response signal calculated by the target response signal calculation unit 230. Here, the target response signal acquisition unit 240 acquires a plurality of target response signals such as the response time and the overshoot amount.
[0054] The correlation control parameter calculation unit 250 calculates the correlation control parameter using the correlation data stored in the correlation data storage unit 210 from the target response signal acquired by the target response signal acquisition unit 240. In the present embodiment, the correlation control parameter calculation unit 250 acquires a plurality of target response signals and calculates a set of correlation control parameters including the proportional gain P and the integral gain I as shown in FIG. 3(a) using the Gaussian mixture regression model.
[0055] The target control parameter adjustment amount calculation unit 260 acquires the correlation data from the correlation data storage unit 210, acquires the optimum value of the reference control parameter, and acquires the correlation control parameter from the correlation control parameter calculation unit 250. Then, as shown in FIG. 3(a), the target control parameter adjustment amount calculation unit 260 obtains the difference between the correlation control parameter and the optimum value of the reference control parameter, and sets the obtained difference as the adjustment amount of the target control parameter.
[0056] When the adjustment amount of the target control parameter is calculated, as shown in FIG. 3(b), the control parameter calculation device 200 calculates the optimal value of the target control parameter based on the calculated adjustment amount of the target control parameter. Specifically, the control parameter calculation device 200 sets the value obtained by adding the adjustment amount of the target control parameter to the optimal value of the reference control parameter as the optimal value of the target control parameter. That is, the difference between the optimal values of the correlation control parameter and the reference control parameter in FIG. 3(a) corresponds to the difference between the optimal value of the reference control parameter and the optimal value of the target control parameter in FIG. 3(b). In this embodiment, the control parameter calculation device 200 calculates the optimal value of the target control parameter, but the user may also calculate the optimal value of the target control parameter.
[0057] Then, the optimal value of the target control parameter can be output to a display unit D such as a display. When the valve control unit 132 performs PID control based on the optimal value of the target control parameter, an ideal response is shown in which the response time, overshoot amount, or hunting amount becomes, for example, the minimum value. In addition to the optimal value of the target control parameter, the adjustment amount of the target control parameter and other parameters may be displayed on the display unit D.
[0058] <Effect of this Embodiment> According to the control parameter calculation device 200 in this embodiment, the correlation control parameter calculation unit 250 calculates the correlation control parameter using the correlation data, and the target control parameter adjustment amount calculation unit 260 calculates the adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter. Therefore, the target control parameter can be adjusted regardless of the user's experience. Then, in the target device, by adjusting the target control parameter based on the calculated adjustment amount of the target control parameter, it is no longer necessary to adjust the target control parameter multiple times, and the adjustment of the target control parameter can be performed more efficiently. In addition, since the adjustment amount of the target control parameter is calculated based on the correlation control parameter and the reference control parameter, it is less likely to be affected by the differences between the reference device and the target device as compared with a configuration that calculates the control parameter itself of the target device. Furthermore, since the target control parameter is calculated using the correlation data of the reference device, it is possible to eliminate the need for the correlation data of the target device when calculating the target control parameter.
[0059] In addition, since the target control parameter adjustment amount calculation unit 260 obtains the difference between the correlation control parameter and the reference control parameter and uses the obtained difference as the adjustment amount of the target control parameter, the target control parameter can be adjusted simply by changing the target control parameter based on the difference, and the target control parameter can be easily adjusted.
[0060] Also, since the correlation control parameter calculation unit 250 in the present embodiment calculates a set of correlation control parameters from a plurality of target response signals, the accuracy of calculating the correlation control parameter can be improved as compared with the case of calculating a set of correlation control parameters based on one target response signal. In particular, since the correlation control parameter calculation unit 250 uses a Gaussian mixture regression model, the correlation control parameter can be accurately calculated when calculating a set of correlation control parameters from a plurality of target response signals.
[0061] Furthermore, since the target response signal acquisition unit 240 and the correlation control parameter calculation unit 250 use the target response signal of the target device at the time of initial setting, the difference between the correlation control parameter and the reference control parameter is considered to be due to the differences between the reference device and the target device, and the adjustment amount of the target control parameter can be accurately calculated.
[0062] <Other Embodiments> Note that the present invention is not limited to the above-described embodiment.
[0063] In this embodiment, the fluid control device 100 targeted by the control parameter calculation device 200 is a differential pressure type MFC, but it is not limited to this, and it may be a so-called thermal mass flow controller, a pressure control device, or other fluid control devices.
[0064] The correlation data storage unit 210 may store correlation data created by machine learning. Specifically, the control parameter calculation device 200 or an arithmetic device different from the control parameter calculation device 200 calculates a reference response signal using a reference control parameter within a predetermined range, and calculates correlation data by machine learning. Then, the correlation data storage unit 210 stores the correlation data created by machine learning. Thereby, the accuracy of the correlation data can be improved.
[0065] In this embodiment, the target response signal acquisition unit 240 and the correlation control parameter calculation unit 250 use a plurality of target response signals, but they may use one target response signal. Also, the correlation control parameter calculation unit 250 calculates a set of correlation control parameters consisting of a proportional gain P and an integral gain I, but it may calculate at least one of the proportional gain P, the integral gain I, or the derivative gain D, or may calculate other control parameters.
[0066] In this embodiment, the target control parameter adjustment amount calculation unit 260 adjusts the control parameter of the target device at the time of initial setting, but it is not limited to this. For example, the target control parameter adjustment amount calculation unit 260 may adjust the control parameter of the target device installed in the flow path and used for a predetermined time based on the reference control parameter and the correlation control parameter. Thereby, the target control parameter adjustment amount calculation unit 260 can adjust the control parameter that has deteriorated and changed due to the use of the target device.
[0067] In this embodiment, the target control parameter adjustment amount calculation unit 260 obtains the difference between the optimum values of the correlation control parameter and the reference control parameter, and uses this difference as the adjustment amount of the target control parameter. However, the present invention is not limited to this. For example, the target control parameter adjustment amount calculation unit 260 may obtain a reference control parameter other than the optimum value of the reference control parameter, obtain the difference between the correlation control parameter and the reference control parameter, and use this difference as the adjustment amount of the target control parameter.
[0068] In addition, various modifications and combinations of embodiments may be made as long as they do not contravene the spirit of the present invention.
Explanation of Reference Numerals
[0069] 100 ··· Fluid control device 121 ··· Flow rate sensor 122 ··· Flow rate control valve 132 ··· Valve control unit 200 ··· Control parameter calculation device 210 ··· Correlation data storage unit 220 ··· Target control parameter acquisition unit 230 ··· Target response signal calculation unit 240 ··· Target response signal acquisition unit 250 ··· Correlation control parameter calculation unit 260 ··· Target control parameter adjustment amount calculation unit
Claims
1. A control parameter calculation device for calculating a control parameter of a fluid control device that controls a fluid, a correlation data storage unit for storing correlation data indicating a correlation between a reference control parameter of a reference device, which is a reference fluid control device, and a reference response signal output using the reference control parameter; a target response signal acquisition unit that acquires a target response signal outputted using a target control parameter of a target device that is a fluid control device different from the reference device; a correlation control parameter calculation unit that acquires the correlation data and the target response signal, and calculates a correlation control parameter corresponding to the target response signal in the reference device by using the correlation data; a target control parameter adjustment amount calculation unit that calculates an adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter.
2. The target response signal acquisition unit acquires a plurality of the target response signals, The control parameter calculation device according to claim 1 , wherein the correlation control parameter calculation section calculates one or a set of the correlation control parameters from a plurality of the target response signals.
3. 3. The control parameter calculation device according to claim 1, wherein the target control parameter adjustment amount calculation unit calculates a difference between the correlation control parameter and the reference control parameter, and sets the calculated difference as the adjustment amount of the target control parameter.
4. The control parameter calculation device according to claim 1 , wherein the correlation control parameter calculation unit calculates the correlation control parameter from the target response signal by using a Gaussian mixture regression model.
5. The target response signal acquisition unit acquires the target response signal output using the target control parameters of the target device at the time of initial setting when the target control parameters are set for the first time, The control parameter calculation device according to claim 1 , wherein the correlation control parameter calculation unit calculates the correlation control parameter from the target response signal of the target device at the time of the initial setting.
6. The control parameter calculation device according to claim 1 , wherein the correlation data storage unit stores the correlation data created using machine learning.
7. A control parameter calculation method for calculating a control parameter of a fluid control device that controls a fluid, comprising: storing correlation data indicating a correlation between a reference control parameter of a reference device, which is the reference fluid control device, and a reference response signal output using the reference control parameter; A target response signal is obtained using a target control parameter of a target device, which is a fluid control device different from the reference device; acquiring the correlation data and the target response signal, and calculating a correlation control parameter corresponding to the target response signal in the reference device by using the correlation data; A control parameter calculation method comprising: calculating an adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter.
8. A control parameter calculation program for use in a fluid control device for controlling a fluid, the control parameter calculation program calculating a control parameter of the fluid control device, a function as a correlation data storage unit for storing a reference control parameter of a reference device, which is a reference fluid control device, and correlation data indicating a correlation between the reference response signal outputted using the reference control parameter; A function as a target response signal acquisition unit that acquires a target response signal output using a target control parameter of a target device that is a fluid control device different from the reference device; a function of a correlation control parameter calculation unit that acquires the correlation data and the target response signal, and calculates a correlation control parameter corresponding to the target response signal in the reference device by using the correlation data; and a target control parameter adjustment amount calculation unit that calculates an adjustment amount of the target control parameter based on the correlation control parameter and the reference control parameter.
Citation Information
Patent Citations
Fluid controller, fluid control method, and fluid controller program
JP2022084110A