Unlock instant, AI-driven research and patent intelligence for your innovation.

Parameter setting method of fractional order PID controller based on RBF neural network

A neural network and parameter tuning technology, applied to controllers with specific characteristics, electric controllers, etc., can solve problems such as difficult tuning of hierarchical PID controllers, achieve strong robustness and self-adaptability, and improve control efficiency , the effect of high control precision

Pending Publication Date: 2022-02-18
WUHAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the problem of difficult tuning of the fractional-order PID controller existing in the prior art, and provides a method for parameter tuning of the fractional-order PID controller based on the RBF neural network in a self-learning manner

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Parameter setting method of fractional order PID controller based on RBF neural network
  • Parameter setting method of fractional order PID controller based on RBF neural network
  • Parameter setting method of fractional order PID controller based on RBF neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0189] S1, establish the RBF neural network model, determine that the number of input layer neurons is n, the number of hidden layer neurons is m, and the number of output neurons is 1;

[0190] S2. Initialize each parameter of the RBF neural network, that is, determine the base width radius vector B of the neural network identifier, the center vector C, the initial weight vector W of the hidden layer corresponding to the output layer, the learning efficiency η of the network, the momentum factor α and the score The initial value of the parameters of the second-order PID controller: K P (0), K I (0), K D (0), λ(0), μ(0);

[0191] The input of RBF neural network is X=[x 1 ,x 2 ,...x i ,...x n ](i=1,2...n);

[0192] The Gaussian function inside the hidden layer neurons is H=[h 1 ,h 2 ,...h j ,...h m ] T (j=1,2,...m);

[0193] Among them, the Gaussian function inside the jth hidden layer neuron is:

[0194]

[0195] In the formula: C j is the center vector insid...

Embodiment 2

[0288] see image 3 , Figure 4 , is the structural block diagram of the permanent magnet synchronous motor vector control, and the given speed v is obtained by the drive system * Compare with the actual speed v to get the deviation, pass the deviation through the RBF fractional order PID neural network speed loop controller to get the current i q * , and the actual value i of the current state of the system q Contrast, output voltage given value u q and the output u of the speed loop controller dThrough the coordinate transformation together, the voltage value of the control system in the αβ coordinate system is obtained, and the trigger signal is output to the inverter through the space vector modulation (SVPWM) module. The inverter outputs three-phase voltage to directly control the motor. The output voltage of the inverter is at The actual current value can be obtained through coordinate transformation, so that the system forms a closed loop. A method for tuning para...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a parameter setting method of a fractional order PID controller based on an RBF neural network. The parameter setting method comprises the following steps: S1, initializing each parameter of the network; S2, performing sampling to obtain an input given r (k) and a system output y (k), and obtaining a system control error e (k); S3, constructing a dynamic RBF neural network on line, adjusting parameters of the dynamic RBF network at the same time, and obtaining output ym (k) of a neural network identifier and Jacobian identification information of a controlled object; S4, according to the system error function, adjusting a proportionality coefficient, an integral coefficient, a differential coefficient, an integral order lambda and a differential order of the fractional order PID controller by using a gradient descent method; S5, calculating the output u (k) of the controller through the time domain form of the fractional order PID controller; and S6, enabling k to be equal to k + 1, and carrying out next sampling control. According to the design, the optimal solution of the system is automatically approached in a self-learning mode, and the control efficiency is effectively improved.

Description

technical field [0001] The invention relates to a parameter setting method of a fractional-order PID controller based on an RBF neural network, and is particularly suitable for parameter setting in the field of automatic control. Background technique [0002] In recent years, with the development of fractional calculus theory, in the field of automatic control, experiments have proved that the dynamic performance and static performance of PID controller based on fractional calculus theory are better than integer order PID controller. The fractional-order PID controller is an extension of the traditional PID controller to the fractional-order field. It has two more parameters than the traditional PID controller, the integral order λ and the differential order μ, so it has a more flexible adjustment range. However, with the increase of parameters, parameter tuning of fractional order PID controller becomes more difficult. [0003] In actual field applications, such as in the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G05B11/42
CPCG05B11/42
Inventor 胡红明杨皓东刘勤
Owner WUHAN UNIV OF TECH