BP (back-propagation) neural network PID speed regulation control algorithm based on fuzzy control

Abstract

The invention relates to a motor speed regulation control algorithm, in particular to a BP (back-propagation) neural network PID speed regulation control algorithm based on fuzzy control. The BP neural network PID speed regulation control algorithm based on fuzzy control is designed in order to solve the problems of static difference and low convergence rate of a traditional dual closed-loop DC speed regulation system based on BP neural network PID control. The BP neural network PID speed regulation control algorithm based on the fuzzy control comprises steps as follows: firstly, the structureof a BP network is determined, input and output of each layer of the network are calculated, then output of a controller is calculated with an incremental PID control algorithm, parameters of the PIDcontroller are adjusted online in real time according to self-learning ability of the BP network, the optimal PID control parameter is obtained, static errors of the system are eliminated by the aidof the fuzzy control, and accordingly, adjustment of the rotating speed of the DC motor is realized. The BP neural network PID speed regulation control algorithm has beneficial effects as follows: theBP neural network PID controlled DC motor speed regulation system based on the fuzzy control can eliminate the static errors, the convergence speed is high, and good static and dynamic performance, anti-interference performance and robust performance are achieved.

Description

technical field [0001] The invention relates to a motor speed regulation control algorithm, in particular to a BP neural network PID speed regulation control algorithm based on fuzzy control. Background technique [0002] At present, industrial synthesis furnaces usually adopt conventional PID control, but the temperature control of industrial synthesis furnaces has the characteristics of nonlinearity, large inertia, and large hysteresis, and it is difficult to establish an accurate mathematical model, so conventional PID control is difficult to achieve good results. [0003] BP neural network is widely used as one of artificial intelligence algorithms to improve PID algorithm. The basic idea of ​​the BP algorithm is: the learning process is composed of two processes: the forward propagation of the signal and the back propagation of the error. During forward propagation, the input samples are passed in from the input layer, and after being processed by each hidden layer, th...

AI Technical Summary

Problems solved by technology

Since the BP neural network has the energy to approximate any nonlinear function, it is suitable to use this network structure to establish a PID controller, but the traditional BP neural network has shortcomings such as static errors, slow convergence speed, and weak robustness, so it cannot achieve Accurate speed control requirements

Images