The GA-BP algorithm based controller of PID Neural Network and its application

Aiming at the shortages of traditional PID controller, and also the problems of easily falling into local minimum of BP algorithm, this paragraph proposes a design of PID Neural Network (PIDNN) controller based on GA-BP algorithm. This controller fully absorbs the global-searching capability of genetic algorithm, and the precisely local-positioning ability of the BP algorithm. So it helps the controller to confirm its network-weights and system parameters swiftly and accurately through self-learning and self-optimization. The simulation result shows, compared with traditional PID controller, this controller has greatly improved its control performances. This would have some theoretical and practical significance.