Valve position control system of pneumatic diaphragm regulating valve and control method of valve position control system

Abstract

The invention discloses a pneumatic diaphragm regulating valve position control system and a control method thereof, and belongs to the technical field of valve control. The purpose of improving the response speed of a valve position control system is achieved. An upper computer module is connected with a signal detection module and a valve control module, and the valve control module is connected with the signal detection module, a pneumatic film execution mechanism module and a data acquisition and feedback module; the pneumatic diaphragm actuating mechanism module is respectively connected with the data acquisition and feedback module and the valve rod; the data acquisition and feedback module detects and acquires state parameters of the valve position control system of the pneumatic diaphragm regulating valve in real time, and feeds back and outputs a detection signal to the controller to form closed-loop control of the valve position of the regulating valve; the upper computer module is used for sending a set analog signal to the valve control module; the valve control module comprises a controller, an electrical conversion module and a pneumatic amplification module; the signal detection module generates a valve position information signal according to the detected opening degree of the valve and transmits the valve position information signal to a controller of the valve control module in real time.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of valve control, and particularly relates to a valve position control system of a pneumatic diaphragm regulating valve and a control method thereof. BACKGROUND

[0002] The valve position control capability is one of the core indexes for measuring the quality of the pneumatic regulating valve; in the production process, the accurate and rapid valve position control can ensure the smooth implementation of the process, ensure the quality of the final product, and reduce the waste rate and energy consumption; due to the high compressibility of air as the power source and the large friction force between the valve stem and the valve cover packing, the valve position control system presents nonlinear characteristics; meanwhile, the multiple signal conversions among the current, air pressure and valve stem displacement involved in the control process cause obvious time lag of the system, and these factors make it difficult for the conventional control algorithm to obtain ideal control effect.

[0003] At present, the valve position control of the pneumatic regulating valve is mostly realized by using the PID control to automatically adjust the valve stem, but the traditional PID controller has problems of difficult parameter setting and slow dynamic response in the nonlinear and time-varying system, and the PID control method based on the neural network also has phenomena of slow speed and low precision; with the wide application of the pneumatic diaphragm regulating valve, it is necessary to improve the traditional PID control mode. SUMMARY

[0004] The application aims to improve the response speed of the valve position control system, and provides a valve position control system of a pneumatic diaphragm regulating valve and a control method thereof.

[0005] To achieve the above-mentioned purpose, the application realizes the technical scheme as follows:

[0006] A valve position control system of a pneumatic diaphragm regulating valve, comprising an upper computer module, a signal detection module, a valve control module, a pneumatic diaphragm actuator module and a data acquisition feedback module, wherein the upper computer module is connected with the signal detection module and the valve control module respectively, the valve control module is connected with the signal detection module, the pneumatic diaphragm actuator module and the data acquisition feedback module respectively, and the pneumatic diaphragm actuator module is connected with the data acquisition feedback module and the valve stem respectively; the valve control module comprises a controller, an electrical conversion module and a pneumatic amplification module.

[0007] The data acquisition feedback module detects and acquires the state parameters of the valve position control system of the pneumatic diaphragm regulating valve in real time, and feeds back the detection signals to the controller to form a closed-loop control of the valve position of the regulating valve.

[0008] The upper computer module is used for sending the set analog signal to the valve control module.

[0009] The analog signal is a current signal in the range of 2-30 mA, and the current signal is sent to the controller by the host computer module;

[0010] The signal detection module detects the valve opening degree by using an analog Hall angle sensor, generates a valve position information signal based on the detected valve opening degree, and transmits the valve position information signal to the controller of the valve control module in real time.

[0011] Further, the controller in the valve control module receives the analog signal sent by the host computer module and converts it into a digital signal as a set target valve position value; during the valve position control process, the controller receives and processes the target valve position signal from the host computer module and the real-time valve position information signal collected by the analog Hall angle sensor in the signal detection module, calculates and outputs a control current signal according to the control algorithm;

[0012] The electrical conversion module converts the current signal output by the controller into a pneumatic signal;

[0013] The pneumatic amplification module receives the pneumatic signal output by the electrical conversion module and transmits it to the pneumatic diaphragm actuator module after amplification, and the pneumatic diaphragm actuator module controls the displacement of the valve stem to realize the opening control of the pneumatic diaphragm control valve.

[0014] Further, the controller is a PID controller.

[0015] A control method of a pneumatic diaphragm control valve position control system, comprising the following steps:

[0016] S1. The host computer module sends a set analog signal to the valve control module;

[0017] S2. The controller in the valve control module receives the analog signal sent by the host computer module and converts it into a digital signal as a set target valve position signal, and simultaneously receives the control system state parameters collected by the data acquisition feedback module;

[0018] S3. The controller performs online optimization of the control system state parameters based on the RBF neural network and the PSO particle swarm algorithm, establishes the mathematical model transfer function of each ring of the pneumatic diaphragm control valve position control system, and uses the gradient descent method to optimize the input parameters of the controller online. When the collected signal exceeds the preset threshold value, the data acquisition feedback module generates a displacement feedback control signal, adjusts the valve stem movement through closed-loop feedback, and controls the valve stem displacement.

[0019] Further, the target valve position signal in step S2 is the expected set specific control valve stem displacement value, and the collected control system state parameters include the valve stem displacement, the pneumatic diaphragm actuator thrust, and the actuator pushing speed.

[0020] Further, the structure of the RBF neural network in step S3 includes an input layer, a hidden layer and an output layer, wherein the input layer takes the collected control system state parameters as input, the hidden layer uses Gaussian radial basis function as activation function, and the output layer is the input parameter of the PID controller;

[0021] The RBF neural network adopts a self-supervised learning mechanism, and the center parameter of the radial basis function in the radial basis function network is optimized and adjusted by gradient descent method.

[0022] Further, in the PSO particle swarm algorithm adaptive optimization RBF neural network method in step S3, the center point, width factor and network connection weight of the RBF neural network radial basis function are taken as free motion particles in the PSO particle swarm algorithm, and the optimal solution is searched by the particle swarm optimization method, and the mean square error is selected as the fitness evaluation index of the PSO particle swarm algorithm.

[0023] Further, the transfer function of the mathematical model of each ring of the pneumatic diaphragm regulating valve position control system established in step S3 includes the following formula:

[0024] The mathematical model expression of the electric appliance conversion module is:

[0025] G1(s)=P b (s) / I(s)=K1

[0026] Wherein, G1(s) is the transfer function of the electric appliance conversion module, P b (s) is the converted control gas pressure, I(s) is the control current, and K1 is the first proportional coefficient;

[0027] The mathematical model expression of the pneumatic amplification module is:

[0028] G2(s)=P out (s) / P b (s)=K2

[0029] Wherein, G2(s) is the transfer function of the pneumatic amplification module, P out (s) is the output gas pressure of the pneumatic amplifier, and K2 is the second proportional coefficient;

[0030] The mathematical model expression of the pneumatic diaphragm actuator module is:

[0031] G3(s)=H s (s) / P out (s)=S / (m·s 2 +f·s+k)

[0032] Wherein, G3(s) is the transfer function of the pneumatic diaphragm actuator module, H s(s) is the valve stem displacement, S is the gain, the pressure-force conversion coefficient, m is the total mass of the actuator, s is the Laplace domain independent variable, f is the viscous damping coefficient, and k is the equivalent elastic stiffness of the system;

[0033] The transfer function expression of the pneumatic diaphragm control valve is:

[0034] G(s)=G1(s)G2(s)G3(s)=K1·K2·S / (m·s 2 +f·s+k)

[0035] Wherein, G(s) is the pneumatic diaphragm control valve transfer function;

[0036] The control expression of the controller for controlling the pneumatic control valve is:

[0037]

[0038] Wherein, u(t) is the output curve of the valve position angle of the pneumatic control valve, K p is the proportional coefficient, K i is the integral coefficient, K d is the differential coefficient, and e(t) is the deviation curve of the valve position set value and the actual value of the pneumatic control valve with time.

[0039] Further, in step S3, the PID parameter optimization of the PSO-RBF neural network is input with the current valve stem displacement, the pneumatic diaphragm actuator thrust and the actuator pushing speed of the valve control system, the network weight is adjusted by using the PSO-RBF neural network, and the optimized PID controller proportional parameter, integral parameter and differential parameter are output.

[0040] The beneficial effects of the application are:

[0041] The pneumatic diaphragm control valve position control system provided by the application fully utilizes the online learning ability of the RBF neural network to self-tune the PID parameter, the error signal is collected in real time in the input layer, the radial basis function is calculated in parallel in the hidden layer, the PID parameter is generated by linear combination in the output layer, and the self-adaptive adjustment ability is provided, so that the PID control response speed and the calculation efficiency are improved.

[0042] The pneumatic diaphragm control valve position control system provided by the application can dynamically optimize the PID parameter output by the RBF neural network according to the control effect, so that the control effect is improved, the robustness of the control valve position control system is effectively improved, the movement error of the valve stem of the control valve is reduced, and the control system precision is improved.

[0043] The valve position control system of the pneumatic diaphragm regulating valve uses a PSO particle swarm algorithm to adaptively optimize a RBF neural network to perform online optimization on PID control parameters, solves problems of the traditional RBF neural network method, such as difficulty in parameter optimization, limited training efficiency, the model being easily trapped in a local optimal state, slow algorithm convergence speed and the like, and effectively improves the algorithm convergence speed and response accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 A structure diagram of the valve position control system of the pneumatic diaphragm regulating valve;

[0045] Figure 2 A PSO adaptive optimization RBF neural network algorithm flowchart of the present application;

[0046] Figure 3 A PSO-RBF neural network PID pneumatic regulating valve control loop diagram of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present application clearer and more apparent, the present application is further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application, that is, the described specific embodiments are only a part of the embodiments of the present application, but not all the specific embodiments. The components of the specific embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations, and the present application can also have other embodiments.

[0048] Therefore, the detailed description of the specific embodiments of the present application provided below in the drawings is not intended to limit the scope of the claimed present application, but only represents selected specific embodiments of the present application. Based on the specific embodiments of the present application, all other specific embodiments obtained by those skilled in the art without making creative efforts fall within the scope of the present application.

[0049] In order to further understand the inventive content, characteristics and effects of the present application, the following specific embodiments are exemplified, and the drawings are Figure 1 -ATTACHMENT Figure 3 The detailed description is as follows:

[0050] Example 1:

[0051] A pneumatic diaphragm control valve position control system, comprising a host computer module, a signal detection module, a valve control module, a pneumatic diaphragm actuator module, a data acquisition feedback module, the host computer module is connected with the signal detection module and the valve control module respectively, the valve control module is connected with the signal detection module, the pneumatic diaphragm actuator module and the data acquisition feedback module respectively; the pneumatic diaphragm actuator module is connected with the data acquisition feedback module and the valve stem respectively; the valve control module comprises a controller, an electrical conversion module and a pneumatic amplification module.

[0052] The data acquisition feedback module detects the state parameters of the pneumatic diaphragm control valve position control system in real time, and feeds back the detection signal to the controller to form a closed-loop control of the valve position of the control valve.

[0053] The host computer module is used for sending a set analog signal to the valve control module.

[0054] The analog signal is a current signal with a range of 2-30 mA, which is sent from the host computer module to the controller.

[0055] The signal detection module detects the valve opening degree by using an analog Hall angle sensor, generates a valve position information signal according to the detected valve opening degree, and transmits the valve position information signal to the controller of the valve control module in real time.

[0056] Further, the controller in the valve control module receives the analog signal sent by the host computer module and converts it into a digital signal as a set target valve position value; during the valve position control process, the controller receives and processes the target valve position signal from the host computer module and the real-time valve position information signal collected by the analog Hall angle sensor in the signal detection module, calculates and outputs a control current signal according to a control algorithm.

[0057] The electrical conversion module converts the current signal output by the controller into a pneumatic signal.

[0058] The pneumatic amplification module receives the pneumatic signal output by the electrical conversion module, amplifies it and then transmits it to the pneumatic diaphragm actuator module, the pneumatic diaphragm actuator module controls the displacement of the valve stem to realize the opening degree control of the valve position of the pneumatic diaphragm control valve.

[0059] Further, the controller is a PID controller.

[0060] Embodiment 2

[0061] A control method of the pneumatic diaphragm control valve position control system according to embodiment 1, comprising the following steps:

[0062] S1. The host computer module sends a set analog signal to the valve control module.

[0063] S2. The controller in the valve control module receives the analog signal sent by the host computer module and converts it into a digital signal as the set target valve position signal, and receives the control system state parameters collected by the data acquisition feedback module;

[0064] Further, the target valve position signal in step S2 is the expected set specific control valve stem displacement value, and the collected control system state parameters include valve stem displacement, pneumatic diaphragm actuator thrust and actuator pushing speed.

[0065] S3. The controller performs online optimization of the control system state parameters based on the RBF neural network and the PSO particle swarm algorithm, establishes the transfer function of the mathematical model of each loop of the pneumatic diaphragm control valve position control system, and uses the gradient descent method to optimize the input parameters of the controller online. When the collected signal exceeds the preset threshold, the data acquisition feedback module generates a displacement feedback control signal to adjust the valve stem movement through closed-loop feedback, and controls the valve stem displacement.

[0066] Further, the structure of the RBF neural network in step S3 includes an input layer, a hidden layer and an output layer, wherein the collected control system state parameters are used as inputs for the input layer, the hidden layer uses Gaussian radial basis function as the activation function, and the output layer is the input parameter of the PID controller;

[0067] The RBF neural network uses a self-supervised learning mechanism to optimize and adjust the base function center parameters in the radial basis function network through the gradient descent method.

[0068] Further, the number of neurons in the hidden layer of the RBF neural network is 6, which is used to calculate the RBF radial basis function, and the Gaussian radial basis function is used as the activation function. The output layer is the input parameter of the PID controller, which is the proportional parameter, the integral parameter and the differential parameter, respectively. The output layer generates the final PID parameters through linear combination according to the calculation result of the hidden layer. In order to achieve the minimization of the error function, the RBF neural network uses a self-supervised learning mechanism to optimize and adjust the base function center parameters in the radial basis function network through the gradient descent method. The base function center parameter adjustment formula is formula (1):

[0069] (1)

[0070] Wherein, k is the iteration number, is the learning rate.

[0071] The base function width adjustment formula is formula (2):

[0072] (2)

[0073] The output connection weight adjustment formula is formula (3):

[0074] (3)

[0075] Further, in the PSO particle swarm algorithm adaptive optimization RBF neural network method in step S3, the center point, width factor and network connection weight of the RBF neural network radial basis function are taken as the free motion particles in the PSO particle swarm algorithm, and the optimal solution is searched through the particle swarm optimization method, and the mean square error is selected as the fitness evaluation index of the PSO particle swarm algorithm. The mean square error calculation formula is formula (4):

[0076] (4)

[0077] Wherein: N is the sample quantity, y i is the true value, is the predicted value.

[0078] The specific optimization steps are:

[0079] S3.1. Initialize the particle population, randomly distribute the initial particle population in the parameter space, set the size of the population, the number of iterations, the initial value and the end value of the weight factor and learning, the initial speed, the initial position of each particle and the individual best position and the global best position;

[0080] S3.2. According to the established evaluation index, the performance of each particle is quantitatively calculated, and the speed of each particle is calculated according to formula (5):

[0081] (5)

[0082] The position of each particle is calculated according to formula (6):

[0083] (6)

[0084] Wherein: and are the speed of the particle in dimension d at the k+1th and kth iteration. is the inertia weight, used to balance the global search and local search ability of the particle; c1 and c2 are learning factors, used to adjust the individual optimal solution of particle i in dimension d at the kth iteration; is the global optimal solution of the group in dimension d at the kth iteration; is the coordinate of the particle in dimension d at the kth iteration.

[0085] S3.3. Iterative optimization phase, calculate particle fitness value, particle individual extremum update and particle global extremum update, particle update its own speed and position;

[0086] S3.4. Determine the optimization process end condition, if the optimization process meets the termination condition, the system stops iteration operation; The specific termination condition is based on two criteria, one is to reach the maximum number of iterations set in advance, the second is lower than the set threshold value; Otherwise repeat steps S3.1-S3.4;

[0087] S3.5. Record the global extreme value and end PSO, the coordinate value in the global best position after reaching the requirements is used as the optimal solution as the required parameter value in the radial basis neural network, and the optimized RBF neural network is constructed.

[0088] Further, the transfer function of the mathematical model of each ring of the aerodynamic diaphragm regulating valve position control system established in step S3 includes the following formula:

[0089] The mathematical model expression of the electrical conversion module is as formula (7):

[0090] G1(s)=P b (s) / I(s)=K1 (7)

[0091] Wherein, G1(s) is the transfer function of the electrical conversion module, P b (s) is the converted control gas pressure, I(s) is the control current, and K1 is the first proportional coefficient;

[0092] The mathematical model expression of the pneumatic amplification module is as formula (8):

[0093] G2(s)=P out (s) / P b (s)=K2 (8)

[0094] Wherein, G2(s) is the transfer function of the pneumatic amplification module, P out (s) is the output gas pressure of the pneumatic amplifier, and K2 is the second proportional coefficient;

[0095] The mathematical model expression of the pneumatic diaphragm actuator module is as formula (9):

[0096] G3(s)=H s (s) / P out (s)=S / (m·s 2 +f·s+k) (9)

[0097] Wherein, G3(s) is the transfer function of the pneumatic diaphragm actuator module, H s(s) is the valve stem displacement, S is the gain, pressure-force conversion coefficient, m is the total mass of the actuator, s is the Laplace domain independent variable, f is the viscous damping coefficient, k is the equivalent elastic stiffness of the system;

[0098] The transfer function expression of the pneumatic diaphragm control valve is as formula (10):

[0099] G(s) = G1(s)G2(s)G3(s) = K1·K2·S / (m·s 2 +f·s+k) (10)

[0100] Wherein, G(s) is the pneumatic diaphragm control valve transfer function; K1, K2 are proportional coefficients, S is the gain.

[0101] The control expression of the PID controller for controlling the pneumatic control valve is as formula (11):

[0102] (11)

[0103] Wherein, u(t) is the valve position angle output curve of the pneumatic control valve, i.e. the change curve of the PID output value with time, K p is the proportional coefficient, K i is the integral coefficient, K d is the differential coefficient, and e(t) is the change curve of the deviation of the valve position set value of the pneumatic control valve from the actual value with time.

[0104] The parameters of the PID controller are optimized by the gradient descent method. When adjusting K p , K i and K d at time k, the expression is as formula (12):

[0105] (12)

[0106] Wherein, η p , η i and η d are the learning rates of the proportional, integral and differential, respectively;

[0107] The PID controller parameter expression at time k+1 is as formula (13):

[0108] (13)

[0109] Further, in step S3, the PSO-RBF neural network optimizes the PID parameters by taking the current valve stem displacement, pneumatic diaphragm actuator thrust and actuator thrust speed of the valve control system as input, adjusting the network weight by using the PSO-RBF neural network, and outputting the optimized PID controller proportional parameter, integral parameter and differential parameter.

[0110] It has to be noted that the terms "first", "second", etc. are used herein for distinguishing between similar elements and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without further constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0111] While the application has been described with reference to the specific implementation thereof, it should be understood by those skilled in the art that various changes can be made and equivalents can be substituted for elements thereof without departing from the scope of the application. Additionally, many modifications can be made to adapt a particular situation to the teachings of the application without departing from the central inventive concept described herein. Accordingly, the application is not limited to specific implementations described herein, but includes all implementations falling within the scope of the appended claims.

Claims

1. A valve position control system for a pneumatic diaphragm regulating valve, characterized in that, The system includes a host computer module, a signal detection module, a valve control module, a pneumatic diaphragm actuator module, and a data acquisition and feedback module. The host computer module is connected to the signal detection module and the valve control module, respectively. The valve control module is connected to the signal detection module, the pneumatic diaphragm actuator module, and the data acquisition and feedback module, respectively. The pneumatic diaphragm actuator module is connected to the data acquisition and feedback module and the valve stem, respectively. The valve control module includes a controller, an electrical conversion module, and a pneumatic amplification module. The data acquisition and feedback module detects and collects the status parameters of the pneumatic diaphragm regulating valve position control system in real time, and feeds back the detection signal to the controller to form a closed-loop control of the regulating valve position. The host computer module is used to send the set analog signal to the valve control module; The analog signal is a current in the range of 2-30mA, and the current signal is sent from the host computer module to the controller; The signal detection module uses an analog Hall effect angle sensor to detect the valve opening. The signal detection module generates a valve position information signal from the detected valve opening and transmits the valve position information signal to the controller of the valve control module in real time.

2. The valve position control system for a pneumatic diaphragm regulating valve according to claim 1, characterized in that, The controller in the valve control module receives analog signals sent by the host computer module and converts them into digital signals as the set target valve position value. During the valve position control process, the controller receives and processes the target valve position signal from the host computer module and the real-time valve position information signal collected by the analog Hall angle sensor in the signal detection module, and calculates and outputs the control current signal according to the control algorithm. The electrical conversion module converts the current signal output by the controller into a gas pressure signal; The pneumatic amplification module receives the pneumatic pressure signal output from the electrical conversion module, amplifies it, and transmits it to the pneumatic diaphragm actuator module. The pneumatic diaphragm actuator module controls the valve stem to move, thereby controlling the opening degree of the pneumatic diaphragm regulating valve.

3. The valve position control system for a pneumatic diaphragm regulating valve according to claim 1, characterized in that, The controller is a PID controller.

4. A control method for a pneumatic diaphragm regulating valve position control system according to any one of claims 1-3, characterized in that, Includes the following steps: S1. The host computer module sends the set analog signal to the valve control module; S2. The controller in the valve control module receives analog signals sent by the host computer module and converts them into digital signals as the set target valve position signals. At the same time, it receives control system status parameters collected by the data acquisition feedback module. S3. The controller optimizes the control system state parameters online based on the RBF neural network and PSO particle swarm optimization algorithm. By establishing the transfer function of the mathematical model of each link of the pneumatic diaphragm control valve position control system, the gradient descent method is used to optimize the controller input parameters online. When the acquired signal exceeds the preset threshold, the data acquisition feedback module generates a displacement feedback control signal, and controls the valve stem displacement by adjusting the valve stem movement through closed-loop feedback.

5. The control method for the pneumatic diaphragm regulating valve position control system according to claim 4, characterized in that, The control system state parameters collected in step S2 include valve stem displacement, pneumatic diaphragm actuator thrust, and actuator pushing speed.

6. The control method for the pneumatic diaphragm regulating valve position control system according to claim 5, characterized in that, The structure of the RBF neural network in step S3 includes an input layer, a hidden layer, and an output layer. The input layer uses the acquired control system state parameters as input, the hidden layer uses the Gaussian radial basis function as the activation function, and the output layer is the input parameters of the PID controller. The RBF neural network employs a self-supervised learning mechanism, using gradient descent to optimize and adjust the center parameters of the basis functions in the radial basis function network.

7. The control method for the pneumatic diaphragm regulating valve position control system according to claim 6, characterized in that, In step S3, the PSO particle swarm algorithm adaptive optimization of the RBF neural network method uses the center point, width factor, and network connection weights of the radial basis function of the RBF neural network as freely moving particles in the PSO particle swarm algorithm. The optimal solution is searched through the particle swarm optimization method, and the mean square error is selected as the fitness evaluation index of the PSO particle swarm algorithm.

8. The control method for the pneumatic diaphragm regulating valve position control system according to claim 7, characterized in that, The transfer functions of the mathematical models for each component of the pneumatic diaphragm control valve position control system established in step S3 include the following formulas: The mathematical model expression for the electrical conversion module is: G1(s)=P b (s) / I(s)=K1 Where G1(s) is the transfer function of the electrical conversion module, P b (s) is the converted control air pressure, I(s) is the control current, and K1 is the first proportional coefficient; The mathematical model expression for the pneumatic amplification module is: G2(s)=P out (s) / P b (s)=K2 Where G2(s) is the transfer function of the pneumatic amplification module, P out (s) represents the output air pressure of the pneumatic amplifier, and K2 is the second proportional coefficient; The mathematical model expression for the pneumatic diaphragm actuator module is: G3(s)=H s (s) / P out (s)=S / (m s 2 +f·s+k) Where G3(s) is the transfer function of the pneumatic diaphragm actuator module, H s (s) is the valve stem displacement, S is the gain, pressure-force conversion coefficient, m is the total mass of the actuator, s is the independent variable in the Laplace domain, f is the viscous damping coefficient, and k is the equivalent elastic stiffness of the system. The transfer function expression for the pneumatic diaphragm control valve is: G(s)=G1(s)G2(s)G3(s)=K1·K2·S / (m·s 2 +f·s+k) Wherein, G(s) is the transfer function of the pneumatic diaphragm control valve; The control expression for the controller to control the pneumatic regulating valve is as follows: Where u(t) is the output curve of the pneumatic control valve position angle, K p K is the proportionality coefficient. i Integral coefficient, K d The differential coefficient, e(t), is the curve showing the deviation between the set value and the actual value of the pneumatic control valve position as a function of time.

9. The control method for the pneumatic diaphragm regulating valve position control system according to claim 8, characterized in that, In step S3, the PSO-RBF neural network optimizes the PID parameters by taking the current valve stem displacement, pneumatic diaphragm actuator thrust, and actuator pushing speed of the valve control system as inputs. The PSO-RBF neural network is used to adjust the network weights and output the optimized proportional, integral, and derivative parameters of the PID controller.

Images