THE RESEARCH OF FUZZY PID CONTROL STRATEGY BASED ON NEURAL NETWORK IN THE TENSION SYSTEM

摘要

Based on back-propagation (BP) arithmetic, a neural network Fuzzy PID control strategy is presented for the tension systems, the parameters of which are of deep coupling, nonlinearity, time-variability, and indeterminacy. In this control strategy, the parameters such as proportion, integration and differentiation of PID controller are adjusted on-line through self-learning of a network based on classical PID control algorithm. The decoupling control is carried out in the process. The performance of control strategy has been performed on the tension tested-bed under the varying load conditions. The experimental results show that the almost dynamic decoupling and completely static decoupling are obtained.