Electro-hydrostatic actuator simulation method and device based on RBF neural network control, medium and product

Abstract

The invention discloses an electro-hydrostatic actuator simulation method and device based on RBF neural network control, a medium and a product, and relates to electro-hydrostatic actuator emulation.The method comprises the steps that an electro-hydrostatic actuator mathematical model is established, important parameters of a plunger pump and a hydraulic cylinder are obtained, and the parameters of the plunger pump and the hydraulic cylinder are calculated; establishing an electro-hydrostatic actuator simulation model, a signal and interference module and an RBF (Radial Basis Function) neural network control model in the Matlab / Simulink; inputting the position input curves and the interference of the electro-hydrostatic actuator under different working conditions into an RBF neural network control model to realize the rotating speed control of the permanent magnet synchronous motor, thereby obtaining the tracking curves of the electro-hydrostatic actuator under different working conditions; and inputting the tracking curve into an electro-hydrostatic actuator simulation model to realize simulation of the electro-hydrostatic actuator. According to the invention, tracking of the position signal under different working conditions can be realized, influences of disturbance and the like are fully considered, anti-interference performance and tracking precision are improved, control parameters are optimized, and an optimal control effect is achieved.

Description

Technical Field

[0001] The present application relates to electrostatic hydraulic actuator simulation, and in particular to an electrostatic hydraulic actuator simulation method, device, medium and product based on RBF neural network control. Background Art

[0002] Electro-hydrostatic actuator (EHA) is a device that converts electrical energy into hydraulic energy and is widely used in industrial automation, aerospace and other fields. It has the advantages of fast response speed, high force density and high precision, so it has been widely used in applications with high precision and high response performance requirements. However, the control of electro-hydrostatic actuator is a complex problem. The traditional PID (proportional, integral, differential) controller is difficult to meet the requirements of control accuracy and system dynamic response. In order to overcome these problems, neural network control technology has been gradually introduced into the control of electro-hydrostatic actuators in recent years. For example, passive fault-tolerant control of EHA is designed using the evolutionary control method, but this method lacks pertinence and has general control performance. On the basis of applying adaptive Kalman filtering to estimate the system state and fault synchronization, state feedback is performed through fault information and state estimation, and pole configuration is performed on the closed-loop system, so as to correct the system error caused by actuator fault and realize fault-tolerant control, but it does not consider factors such as parameter uncertainty and parameter time variation, so there is still room for improvement. The EHA is controlled by using a radial basis function (RBF) neural network combined with a robust observer, but the consideration of control parameter selection and optimization issues needs to be improved. Summary of the invention

[0003] The purpose of this application is to provide an electrostatic hydraulic actuator simulation method, equipment, medium and product based on RBF neural network control, which can realize the tracking of position signals under different working conditions, and can fully consider the influence of disturbances, improve anti-interference and tracking accuracy, optimize control parameters, and thus achieve the best control effect.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a simulation method for an electrostatic hydraulic actuator based on RBF neural network control, comprising:

[0006] The mathematical model of the electrostatic hydraulic actuator is established according to the working principle of the permanent magnet synchronous motor, plunger pump, hydraulic cylinder and load;

[0007] Obtaining important parameters of the plunger pump and the hydraulic cylinder; the important parameters include at least: total load mass, viscous damping coefficient, hydraulic cylinder piston area, hydraulic pipeline and cylinder average volume, equivalent elastic modulus, leakage coefficient and pump displacement;

[0008] According to the electrostatic hydraulic actuator mathematical model and the important parameters, a simulation model of the electrostatic hydraulic actuator is established in Matlab / Simulink;

[0009] Referring to the working conditions of the electrostatic hydraulic actuator, the signal and interference module is built in Matlab / Simulink to obtain the position input curve and interference of the electrostatic hydraulic actuator under different working conditions;

[0010] According to the mathematical model of the electrostatic hydraulic actuator, a RBF neural network control model is built in Matlab / Simulink;

[0011] The position input curve and interference of the electrostatic hydraulic actuator under different working conditions are input into the RBF neural network control model, and the speed of the permanent magnet synchronous motor is taken as the control quantity to realize the speed control of the permanent magnet synchronous motor;

[0012] Based on the speed control result of the permanent magnet synchronous motor, the tracking results of the electrostatic hydraulic actuator under different working conditions are obtained to generate a tracking curve;

[0013] The tracking curve is input into the electrostatic hydraulic actuator simulation model to obtain the simulation result of the electrostatic hydraulic actuator.

[0014] Optionally, a mathematical model of the electrostatic hydraulic actuator is established according to the working principle of the permanent magnet synchronous motor, the plunger pump, the hydraulic cylinder and the load, including:

[0015] Under the condition of ignoring magnetic circuit saturation, eddy current and hysteresis loss and magnetic field high harmonics, a mathematical model of the permanent magnet synchronous motor is obtained.

[0016] According to Newton's law of motion, the plunger pump hydraulic cylinder and load are mathematically modeled to obtain the plunger pump and hydraulic cylinder model;

[0017] The mathematical model of the electrostatic hydraulic actuator is established based on the permanent magnet synchronous motor model and the plunger pump and hydraulic cylinder model.

[0018] Optionally, according to the electrostatic hydraulic actuator mathematical model and the important parameters, a simulation model of the electrostatic hydraulic actuator is established in Matlab / Simulink, including:

[0019] According to the mathematical model of the electrostatic hydraulic actuator, a permanent magnet synchronous motor simulation model is established in Matlab / Simulink, and the speed loop and the current loop are adjusted through PI control to enable the permanent magnet synchronous motor to complete speed tracking;

[0020] According to the important parameters, build the Simulink model of hydraulic pump, hydraulic cylinder and load in Matlab / Simulink;

[0021] The electrostatic hydraulic actuator simulation model is obtained based on the permanent magnet synchronous motor simulation model and the Simulink models of the hydraulic pump, hydraulic cylinder and load.

[0022] Optionally, referring to the working conditions of the electrostatic hydraulic actuator, a signal and interference module is built in Matlab / Simulink to obtain the position input curve and interference of the electrostatic hydraulic actuator under different working conditions, including:

[0023] Referring to the working condition of the electrostatic hydraulic actuator, a first working condition is set, and under the first working condition, a first sinusoidal position curve, a nonlinear term, and a fault phase are tracked to obtain a first position input curve and interference of the electrostatic hydraulic actuator;

[0024] Referring to the working condition of the electrostatic hydraulic actuator, a second working condition is set, and under the second working condition, a second sinusoidal position curve, a nonlinear term and a fault phase are tracked to obtain a second position input curve and interference of the electrostatic hydraulic actuator; wherein, within a set time period of the second working condition, a hydraulic line blockage fault occurs;

[0025] The first position input curve and the interference and the second position input curve and the interference form the position input curve and the interference of the electrostatic hydraulic actuator under different working conditions.

[0026] Optionally, the first sinusoidal position curve is expressed as:

[0027] x 1d =0.05+0.02×sin(0.5πt)(1-e -0.5t );

[0028] The nonlinear term is expressed as:

[0029] d = 0.35x 1 x 2 +2×10 -5 ;

[0030] The fault phase is expressed as:

[0031]

[0032] The second sinusoidal position curve is expressed as:

[0033] x 1d =0.05+0.02×sin(0.5πt)(1-e -0.5t );

[0034] In the formula, x 1d is a given displacement signal, x 1 is the displacement tracking signal output by the actual electrostatic hydraulic actuator module, x 2 is the speed of the actual electrostatic hydraulic actuator module output, t is the time, f(x) is the fault state, and d is the disturbance state.

[0035] Optionally, the process of obtaining the tracking results of the electrostatic hydraulic actuator under different working conditions includes:

[0036] The particle swarm optimization algorithm is used to optimize the control parameters, and the optimal tracking results of the electrostatic hydraulic actuator under different working conditions are determined based on the optimized control parameters.

[0037] Optionally, the mathematical model of the electrostatic hydraulic actuator, the signal and interference module and the RBF neural network control model are integrated to obtain an integrated simulation model of the electrostatic hydraulic actuator.

[0038] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned methods for simulating an electrostatic hydraulic actuator based on RBF neural network control.

[0039] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for simulating an electrostatic hydraulic actuator based on RBF neural network control.

[0040] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned electrostatic hydraulic actuator simulation methods based on RBF neural network control.

[0041] According to the specific embodiments provided in this application, this application has the following technical effects:

[0042] The present application provides a simulation method, device, medium and product of an electrostatic hydraulic actuator based on RBF neural network control. By constructing an RBF neural network control model, the position signal can be tracked under different working conditions. By building a signal and interference module in Matlab / Simulink, the position input curve and interference of the electrostatic hydraulic actuator under different working conditions are obtained, and the influence of disturbances can be fully considered to improve the anti-interference performance and tracking accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A schematic flow chart of a simulation method for an electrostatic hydraulic actuator based on RBF neural network control provided in one embodiment of the present application;

[0045] Figure 2 A schematic diagram of a permanent magnet synchronous motor model established according to an embodiment of the present application;

[0046] Figure 3 A schematic diagram of the EHA structure provided in one embodiment of the present application;

[0047] Figure 4 A schematic diagram of a plunger pump and hydraulic cylinder model established according to an embodiment of the present application;

[0048] Figure 5 A schematic diagram of an established RBF neural network controller module provided in an embodiment of the present application;

[0049] Figure 6 A schematic diagram of a signal generating module provided in an embodiment of the present application;

[0050] Figure 7 A schematic diagram of an interference generating module provided in an embodiment of the present application;

[0051] Figure 8 A schematic diagram of an electrostatic hydraulic actuator module provided in one embodiment of the present application;

[0052] Fig. 9 An algorithm flow chart provided for an embodiment of the present application;

[0053] Fig.10 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] In order to make the purpose, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0056] RBF neural network is a commonly used neural network structure, which has good approximation and generalization capabilities, and is widely used in function approximation and system modeling. By reasonably designing the structure and parameters of the RBF neural network, efficient modeling and control of the electrostatic hydraulic actuator system can be achieved. The electrostatic hydraulic actuator simulation model based on the RBF neural network can more accurately describe the dynamic characteristics and nonlinear behavior of the system, and achieve precise modeling and control of the system. Compared with traditional control methods, the control based on RBF neural network has better robustness and adaptability, and can effectively improve the control performance and stability of the system. Therefore, the development of an electrostatic hydraulic actuator simulation model based on RBF neural network control has important theoretical significance and practical application value, and is of great significance for improving the control accuracy and response speed of the electrostatic hydraulic actuator system. Based on this, in an exemplary embodiment, such as Figure 1 As shown, a simulation method for an electrostatic hydraulic actuator based on RBF neural network control is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to a server as an example for explanation, and includes the following steps 100 to 107. Among them:

[0057] Step 100: Establish a mathematical model of the electrostatic hydraulic actuator according to the working principles of the permanent magnet synchronous motor, the plunger pump, the hydraulic cylinder and the load.

[0058] Step 101: Obtain important parameters of the plunger pump and hydraulic cylinder. Among them, according to the actual situation, important parameters of the hydraulic cylinder such as the total mass of the hydraulic cylinder piston and load, viscous damping coefficient, hydraulic cylinder piston area, hydraulic pipeline and average volume of the oil cylinder are obtained. According to the actual situation, important parameters of the hydraulic pump such as equivalent elastic modulus, leakage coefficient, pump displacement, etc. are obtained.

[0059] Step 102: According to the mathematical model and important parameters of the electrostatic hydraulic actuator, a simulation model of the electrostatic hydraulic actuator is established in Matlab / Simulink.

[0060] Step 103: Referring to the working condition of the electrostatic hydraulic actuator, a signal and interference module is built in Matlab / Simulink to obtain the position input curve and interference of the electrostatic hydraulic actuator under different working conditions.

[0061] Step 104: Based on the mathematical model of the electrostatic hydraulic actuator, a RBF neural network control model is constructed in Matlab / Simulink. The established RBF neural network control model consists of the following: Figure 5 The RBF neural network controller module shown is implemented.

[0062] Step 105: Input the position input curve and disturbance of the electrostatic hydraulic actuator under different working conditions into the RBF neural network control model, and take the speed of the permanent magnet synchronous motor as the control variable to realize the speed control of the permanent magnet synchronous motor.

[0063] Step 106: Based on the permanent magnet synchronous motor speed control result, the tracking results of the electrostatic hydraulic actuator under different working conditions are obtained to generate a tracking curve.

[0064] Step 107: Input the tracking curve into the electrostatic hydraulic actuator simulation model to obtain the simulation result of the electrostatic hydraulic actuator.

[0065] In another exemplary embodiment of the present application, the implementation process of step 100 may include:

[0066] Step 1001: Perform mathematical modeling on the permanent magnet synchronous motor. The EHA structure used in this embodiment is as follows: Figure 3 As shown in Figure 1, the permanent magnet synchronous motor is a multi-input, strongly coupled, nonlinear system with very complex electromagnetic relationships. Therefore, under the condition of ignoring magnetic circuit saturation, eddy current and hysteresis loss and magnetic field high harmonics, the permanent magnet synchronous motor is mathematically modeled to obtain the permanent magnet synchronous motor model (as shown in Figure 1). Figure 2 shown).

[0067] In practical applications, the mathematical equation of the permanent magnet synchronous motor in the dp rotating coordinate system is used as the permanent magnet synchronous motor model and is expressed as:

[0068]

[0069] Where t is time. is the derivative of (·) with respect to time. θ is the motor rotation angle. ω is the motor speed. n p is the number of pole pairs of the motor. f is the magnetic flux amplitude of the rotor permanent magnet. J is the rotor moment of inertia. B is the viscous friction coefficient. T L is the load torque. s is the stator armature winding resistance. d 、i q are the stator armature currents respectively. L is the equivalent stator inductance. d 、u q are the stator armature voltages respectively.

[0070] In the electrostatic hydraulic actuator, The decoupling control realizes the speed regulation of the permanent magnet synchronous motor (hereinafter referred to as the motor system). for i dThe motor system adopts three-loop control. The position loop compares the actual position feedback value with the expected value, and obtains the ideal speed control signal through the position controller. The ideal speed control signal is then compared with the actual speed output, and the expected value of the stator armature current q-axis component is obtained through the speed controller. The final current loop is formed by feedback. d and i q The actual value is subtracted from the expected value, and then the torque is controlled through the current controller. The control system used in this control process can mainly include position, speed, rotation speed, current and other signal acquisition modules, intelligent power modules, control algorithm modules and permanent magnet synchronous AC servo motors. The control algorithm module can include a speed loop controller, a current loop controller, a coordinate transformation module and a space vector pulse width modulation module. The specific working process of the control system is: collect the three-phase current and obtain the stator armature current d-axis component i in the dq coordinate system through Clarke transformation and Park transformation. d and the q-axis component i q The expected value of the q-axis component of the stator armature current is obtained through the speed loop Given the expected value of the d-axis component The error between the d-axis and q-axis components of the stator armature current and their expected values ​​is used as the input of the speed loop to obtain the stator armature voltage u d and u q After the Park inverse transformation, the various control signals in IPM are calculated through SVPWM to drive the motor to rotate.

[0071] Step 1002: According to Newton's laws of motion, mathematical modeling is performed on the plunger pump hydraulic cylinder and the load to obtain a plunger pump and hydraulic cylinder model (such as Figure 4 ). For example, the plunger pump and hydraulic cylinder model is represented as:

[0072]

[0073] Where: P 1 , P 2 A is the pressure at the oil inlet and outlet of the oil cylinder. c is the area of ​​the hydraulic cylinder piston. M is the total mass of the hydraulic cylinder piston and the load. 1 is the viscous damping coefficient. k is the stiffness coefficient. x is the piston rod displacement. is the piston rod speed. is the piston rod acceleration. F f is the load change caused by the fault, F d The load transformation is caused by nonlinearity.

[0074]

[0075] Where: Q1 and Q 2 They are the hydraulic oil flow rates at the near oil port and the oil outlet respectively. P is the pump displacement. P is the pump speed, i.e. the actual control quantity. P P is the external leakage coefficient of the hydraulic pump. a , P b They are the pressure of the hydraulic pump oil outlet and oil return port respectively. 0 It is the internal leakage port pressure of the hydraulic pump.

[0076] According to the relationship between flow rate and pressure, we can get:

[0077]

[0078] Where: Q i and Q 0 V are the oil inlet and return flow rates of the cylinder respectively. a is the average volume of hydraulic pipelines and cylinders. e is the equivalent elastic modulus. ep is the leakage coefficient. Assuming that the cylinder and pipeline are well sealed and no hydraulic oil leaks to the outside of the system, that is:

[0079] Q i =Q 1 ,Q 0 =Q 2 ,L a =L ep +L p .

[0080] Arranged:

[0081]

[0082] Where: f and d are fault state and disturbance state respectively.

[0083] Step 1003: Establish a mathematical model of the electrostatic hydraulic actuator based on the permanent magnet synchronous motor model and the plunger pump and hydraulic cylinder model. This mathematical model of the electrostatic hydraulic actuator is essentially the state equation of the electrostatic hydraulic actuator, which is expressed as:

[0084]

[0085] Where X is the input state of the electrostatic hydraulic actuator, is the derivative of the input state X of the electrostatic hydraulic actuator, Y is the output state of the electrostatic hydraulic actuator, A, B 2 , U, F, Y, C are all state matrices, L a is the total leakage coefficient, and u is the controlled variable, i.e. the given speed of the motor.

[0086] In another exemplary embodiment of the present application, the implementation process of step 102 may include:

[0087] Step 1021: According to the mathematical model of the electrostatic hydraulic actuator, a permanent magnet synchronous motor simulation model is established in Matlab / Simulink, and the speed loop and the current loop are adjusted through PI control to enable the permanent magnet synchronous motor to complete speed tracking.

[0088] Step 1022: Based on the important parameters, build a Simulink model of the hydraulic pump, hydraulic cylinder and load in Matlab / Simulink.

[0089] Step 1023: Obtain a simulation model of the electrostatic hydraulic actuator based on the permanent magnet synchronous motor simulation model and the Simulink models of the hydraulic pump, hydraulic cylinder and load.

[0090] In another exemplary embodiment of the present application, the implementation process of step 103 may include:

[0091] Step 1031: Referring to the working condition of the electrostatic hydraulic actuator, a first working condition is set, and under the first working condition, a first sinusoidal position curve, a nonlinear term, and a fault phase are tracked to obtain a first position input curve and interference of the electrostatic hydraulic actuator.

[0092] Step 1032: Referring to the working condition of the electrostatic hydraulic actuator, a second working condition is set, and under the second working condition, a second sinusoidal position curve, a nonlinear term, and a fault phase are tracked to obtain a second position input curve and interference of the electrostatic hydraulic actuator. In which, a hydraulic line blockage fault occurs within a set time period of the second working condition.

[0093] Step 1033: The first position input curve and the interference and the second position input curve and the interference form the position input curve and the interference of the electrostatic hydraulic actuator under different working conditions.

[0094] Among them, the first sinusoidal position curve is expressed as:

[0095] x 1d =0.05+0.02×sin(0.5πt)(1-e -0.5t ).

[0096] The nonlinear term is expressed as:

[0097] d = 0.35x 1 x 2 +2×10 -5 .

[0098] The fault phase is expressed as:

[0099]

[0100] The second sinusoidal position curve is expressed as:

[0101] x 1d =0.05+0.02×sin(0.5πt)(1-e -0.5t ).

[0102] In the formula, x 1d is a given displacement signal, x 1 is the displacement tracking signal output by the actual electrostatic hydraulic actuator module, x 2 is the speed of the actual electrostatic hydraulic actuator module output, t is the time, f(x) is the fault state, and d is the disturbance state.

[0103] In another exemplary embodiment of the present application, step 104 and step 105 are based on the electrostatic hydraulic actuator mathematical model and the principle of the RBF neural network control method, and an RBF neural network control module is built in Matlab / Simulink. The interference is approximated by the RBF neural network control module, and the speed of the permanent magnet synchronous motor is used as the control quantity to achieve the speed control of the permanent magnet synchronous motor. Specifically:

[0104] Step 1: Define the position error z 1 =x 1 -x 1d ,but

[0105] where z 1 is the position error, x 1 It is the displacement tracking signal output by the actual electrostatic hydraulic actuator module. For z 1 The derivative of For x 1 The derivative of For a given displacement signal x 1d The derivative of .

[0106] Step 2: Define the Lyapunov function but

[0107] Where V 1 is the Lyapunov function, is the Lyapunov function V 1 The derivative of x 2 For x 1 The derivative of .

[0108] Step 3: Take Right now but

[0109] Step 4: Define the Lyapunov function because get

[0110] Where V 2 is the Lyapunov function, For z 2 The derivative of V 2 The derivative of x 3 is the second-order derivative of x, For x 1d The second derivative of .

[0111] Step 5: Take Take:

[0112] but

[0113] Among them, c 2 is the control parameter.

[0114] Step 6: Due to the universal approximation characteristics of the RBF neural network, the RBF neural network is used to approximate the fault state f(x). The network algorithm is:

[0115]

[0116] f=W *T h(x)+ξ.

[0117] Among them, x is the input of the network, j is the jth node of the hidden layer of the network, and h = [h j ] T is the Gaussian function output of the network, W * is the ideal weight of the network, ξ is the approximation error of the network, ξ≤ξ N .c j is the center vector of the jth node in the hidden layer, b j is the base width parameter of the j-th node.

[0118] The network input is x = [x 2 x 3 ] T , then the network output is:

[0119]

[0120] but:

[0121]

[0122] Where f(x) is a linear disturbance. It is an intermediate parameter.

[0123] Step 7: According to the RBF neural network principle in step 6, define the Lyapunov function:

[0124] From step 6 ,have to:

[0125]

[0126] Then we get:

[0127]

[0128] have to:

[0129]

[0130] The designed control law is:

[0131]

[0132] have to:

[0133]

[0134] Arranged:

[0135]

[0136] The adaptive law is taken as:

[0137]

[0138] It follows that:

[0139]

[0140] It can be proved that it is semi-globally uniformly bounded in a certain compact set. When t→∞, z 1 →0,z 2 →0,z 3 →0, so

[0141] Among them, γ is 0.5, For z 3 The derivative of , d is the nonlinear interference term, c 3 To control the parameters,

[0142] In another exemplary embodiment of the present application, for the problem of selecting parameters for the RBF neural network control algorithm, a particle swarm optimization algorithm can be used to optimize the control parameters to achieve the best control effect. Based on this, the particle swarm optimization algorithm is used to optimize the control parameters c 1 、c 2 、c 3, after iteration, the optimal tracking control effect is achieved. Specifically:

[0143] (1): Set the parameter movement range, set the learning factor z1 = 1.3, z2 = 1.7, the maximum evolution generation G = 500, kg represents the current evolution generation, the particle movement position range is min = 0, max = 1000, and the particle movement speed range is V max =1; V min = -1. In a D-dimensional parameter search space, the size of the particle population is Size = 100, and each particle represents a candidate solution in the solution space, where the position of the i-th particle in the entire space is represented by X i , speed is V i The optimal solution generated by the search of the i-th particle from the initial to the current iteration number, the individual value P i , the current optimal solution of the entire population is BestS. Size particles are randomly generated, and the position matrix and velocity matrix of the initial population are randomly generated.

[0144] (2): Individual fitness evaluation: Take the initial position of each particle as the individual value and calculate the initial fitness value f(X i ), f(X i ) is defined as where x 1 is a given position signal, x d is the position signal output by the electrostatic hydraulic actuator, and the optimal position of the population is obtained.

[0145] (3): Update the speed and position of the particles, generate a new population, and reduce the speed and position of the particles beyond the limit to avoid the algorithm falling into the local optimal solution. Add a local adaptive mutation operator for adjustment

[0146]

[0147] Where, kg = 1, 2, ..., G, i = 1, 2, ..., Size, r 1 and r 2 is a random number between 0 and 1, z 1 is the local learning factor, z 2 is the global learning factor.

[0148] (4): Compare the current fitness value f(X i ) and its own historical optimal value p i , if f(X i ) is better than p i , then set p i is the current f(X i ) and update the particle position.

[0149] (5): Compare the particle's current fitness value f(X i ) and the population optimal value BestS, if f(X i ) is better than BestS, then BestS is set to the current value f(X i ), update the global optimal value of the population.

[0150] (6): Check the end condition. If it is satisfied, the optimization ends. Otherwise, kg′=kg+1, and go to step (3). The end condition is that the optimization reaches the maximum evolutionary generation or is less than the given precision.

[0151] In another exemplary embodiment of the present application, the electrostatic hydraulic actuator mathematical model, the signal and interference module and the RBF neural network control model are integrated to obtain an integrated simulation model of the electrostatic hydraulic actuator. The integrated simulation model of the electrostatic hydraulic actuator can be modularized into an integrated simulation system of the electrostatic hydraulic actuator, and the integrated simulation system of the electrostatic hydraulic actuator includes: Figure 6 The signal generating module shown is as follows: Figure 7 The interference generation module shown is as follows: Figure 5 The RBF neural network controller module shown in Figure 8 The implementation process of the integrated simulation system of the entire electrostatic hydraulic actuator is as follows: Fig. 9 shown. Figures 2 to 9 In the present invention, since all chips used are existing chips, the chip unit names or pin interface names represented by English symbols can be obtained by simply looking up the instruction manuals corresponding to the chips, so they will not be described in detail here.

[0152] In summary, compared with the known electrostatic hydraulic actuator simulation method, the present application has the following advantages:

[0153] 1. The electrostatic hydraulic actuator simulation model based on RBF neural network control provided in this application establishes a total parameter model of the electrostatic hydraulic actuator based on a real physical model, which can realize the tracking of position signals under different working conditions.

[0154] 2. This application fully considers the influence of disturbances, and the proposed control method is more resistant to interference and has higher tracking accuracy than other classical control methods.

[0155] 3. In view of the parameter selection problem of RBF neural network control algorithm, the particle swarm optimization algorithm is used to optimize the control parameters to achieve the optimal control effect.

[0156] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig.10As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store electrostatic hydraulic actuator simulation data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a simulation method of an electrostatic hydraulic actuator based on RBF neural network control is implemented.

[0157] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0158] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0159] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0161] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0162] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0163] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0164] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A simulation method for an electrostatic hydraulic actuator based on RBF neural network control, characterized in that: The electrostatic hydraulic actuator simulation method based on RBF neural network control includes: The mathematical model of the electrostatic hydraulic actuator is established according to the working principle of the permanent magnet synchronous motor, plunger pump, hydraulic cylinder and load; Obtaining important parameters of the plunger pump and the hydraulic cylinder; the important parameters include at least: total load mass, viscous damping coefficient, hydraulic cylinder piston area, hydraulic pipeline and cylinder average volume, equivalent elastic modulus, leakage coefficient and pump displacement; According to the electrostatic hydraulic actuator mathematical model and the important parameters, a simulation model of the electrostatic hydraulic actuator is established in Matlab / Simulink; Referring to the working conditions of the electrostatic hydraulic actuator, the signal and interference module is built in Matlab / Simulink to obtain the position input curve and interference of the electrostatic hydraulic actuator under different working conditions; According to the mathematical model of the electrostatic hydraulic actuator, a RBF neural network control model is built in Matlab / Simulink; The position input curve and interference of the electrostatic hydraulic actuator under different working conditions are input into the RBF neural network control model, and the speed of the permanent magnet synchronous motor is taken as the control quantity to realize the speed control of the permanent magnet synchronous motor; Based on the speed control result of the permanent magnet synchronous motor, the tracking results of the electrostatic hydraulic actuator under different working conditions are obtained to generate a tracking curve; The tracking curve is input into the electrostatic hydraulic actuator simulation model to obtain the simulation result of the electrostatic hydraulic actuator.

2. The electrostatic hydraulic actuator simulation method based on RBF neural network control according to claim 1 is characterized in that: The mathematical model of the electrostatic hydraulic actuator is established according to the working principle of the permanent magnet synchronous motor, plunger pump, hydraulic cylinder and load, including: Under the condition of ignoring magnetic circuit saturation, eddy current and hysteresis loss and magnetic field high harmonics, a mathematical model of the permanent magnet synchronous motor is obtained. According to Newton's law of motion, the plunger pump hydraulic cylinder and load are mathematically modeled to obtain the plunger pump and hydraulic cylinder model; The mathematical model of the electrostatic hydraulic actuator is established based on the permanent magnet synchronous motor model and the plunger pump and hydraulic cylinder model.

3. The electrostatic hydraulic actuator simulation method based on RBF neural network control according to claim 1 is characterized in that: According to the electrostatic hydraulic actuator mathematical model and the important parameters, a simulation model of the electrostatic hydraulic actuator is established in Matlab / Simulink, including: According to the mathematical model of the electrostatic hydraulic actuator, a permanent magnet synchronous motor simulation model is established in Matlab / Simulink, and the speed loop and the current loop are adjusted through PI control to enable the permanent magnet synchronous motor to complete speed tracking; According to the important parameters, build the Simulink model of hydraulic pump, hydraulic cylinder and load in Matlab / Simulink; The electrostatic hydraulic actuator simulation model is obtained based on the permanent magnet synchronous motor simulation model and the Simulink models of the hydraulic pump, hydraulic cylinder and load.

4. The electrostatic hydraulic actuator simulation method based on RBF neural network control according to claim 1 is characterized in that: Referring to the working conditions of the electrostatic hydraulic actuator, the signal and interference module is built in Matlab / Simulink to obtain the position input curve and interference of the electrostatic hydraulic actuator under different working conditions, including: Referring to the working condition of the electrostatic hydraulic actuator, a first working condition is set, and under the first working condition, a first sinusoidal position curve, a nonlinear term, and a fault phase are tracked to obtain a first position input curve and interference of the electrostatic hydraulic actuator; Referring to the working condition of the electrostatic hydraulic actuator, a second working condition is set, and under the second working condition, a second sinusoidal position curve, a nonlinear term and a fault phase are tracked to obtain a second position input curve and interference of the electrostatic hydraulic actuator; wherein, within a set time period of the second working condition, a hydraulic line blockage fault occurs; The first position input curve and the interference and the second position input curve and the interference form the position input curve and the interference of the electrostatic hydraulic actuator under different working conditions.

5. The electrostatic hydraulic actuator simulation method based on RBF neural network control according to claim 4 is characterized in that: The first sinusoidal position curve is expressed as: x 1d =0.05+0.02×sin(0.5πt)(1-e -0.5t ); The nonlinear term is expressed as: d=0.35x1x2+2×10 -5 ; The fault phase is expressed as: The second sinusoidal position curve is expressed as: x 1d =0.05+0.02×sin(0.5πt)(1-e -0.5t ); In the formula, x 1d is the given displacement signal, x1 is the displacement tracking signal output by the actual electrostatic hydraulic actuator module, x2 is the speed output by the actual electrostatic hydraulic actuator module, t is the time, f(x) is the fault state, and d is the disturbance state.

6. The electrostatic hydraulic actuator simulation method based on RBF neural network control according to claim 1 is characterized in that: The process of obtaining the tracking results of the electrostatic hydraulic actuator under different working conditions includes: The particle swarm optimization algorithm is used to optimize the control parameters, and the optimal tracking results of the electrostatic hydraulic actuator under different working conditions are determined based on the optimized control parameters.

7. The electrostatic hydraulic actuator simulation method based on RBF neural network control according to claim 1 is characterized in that: The mathematical model of the electrostatic hydraulic actuator, the signal and interference module and the RBF neural network control model are integrated to obtain an integrated simulation model of the electrostatic hydraulic actuator.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the electrostatic hydraulic actuator simulation method based on RBF neural network control as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the electrostatic hydraulic actuator simulation method based on RBF neural network control described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the electrostatic hydraulic actuator simulation method based on RBF neural network control described in any one of claims 1 to 7 is implemented.

Images