Research on the Application of Wavelet Neural Network in Temperature Control System

摘要

A rapid learning algorithm was put forward to realize complex system modeling and self-adaptive control with uncertainty, high nonlinear and lame time-delay. Merits of internal model control were combined, such as simple design, food regulation capacity, high robustness and the ability to eliminate the unknown disturbance to construct a internal model control system based on wavelets neural network, which was characterized by high robustness and quick response speed and then it can brim food control performance when controlled objects vary in a wide range. Finally, it was triumphantly used in simulation of the superheated steam temperature reduction control system of 500 MW unit and food performances are obtained.