Research On The Control System Of Rotational Speed Induction Motor Based On Neural Networks And Predictive Control

In recent years, with the development of power electronic technology, control technology and computer technology, using control system for AC drive replaces DC drive control system has become an indisputable fact, the induction motor has been widely used in the motion control system, research motor speed control technology of high performance become more and more important.Induction motor has the characteristics of high order, coupling and nonlinear, vector control technology is widely used in motor control system, the control system based on this case, seeking for the new control strategy for design with high performance, strong anti disturbance ability and strong adaptability is a hot research at home and abroad. In recent years, the predictive model technology has advantage of controlling with multi objectives,multi variable and strong constraint to improving characteristics of the control system'tracking performance, stability and robustness, caused widespread concern in motion control areas. in the speed control systems, scholar always using the basic vector to control Service system usually adopts the traditional controller PID, use and design through the debug controller PID coefficient to constantly find parameters to achieve the best performance, it is very trouble. But after the adjustment coefficient is fixed, while the influence of disturbance factors such as motor parameter variations and external load, good control system of the original will be greatly reduced. So people began to seek a new control algorithm, Intelligent control technology has strong anti disturbance and self adaptation, using the intelligent control technology in motor vector control system is of great significance.This paper researched from two aspects .On one hand, according to the basic principle and characteristics of model predictive control technology, combination the advantages of model predictive control system and method of according to the rotor field oriented together,with two level three phase voltage type inverter and induction motor as study of predictive control object, base on the current state of static coordinates ?? for the idea of optimization.design of induction motor serve system, to improve the performance of the system .designing the predictive current of induction motor servo system, and to improve the performance of the system is studied. On the other hand, for the external load disturbances factors which impact the performance of a motor control system, presents a neural network adaptive PID controller,And apply it speed ring.By building Simulation model of system in Matlab/Simulink environment and validated,simulation results show that compared with the PID controller ,the neural network PI speed controller has strong adaptability. Through the simulation comparison, when the moment of inertia and load torque changes ,the neural network speed controller enables the system to keep good control performance.