The simulation study of steady-state system identification based on BP neural network PID control algorithm

Abstract

For the controlled object whose system parameters are constant, the traditional PID control algorithm is difficult to achieve better results. BP neural network has strong ability of self-learning and self-adaptation. In this paper, BP neural network is used to establish the parameter identification model of the steady-state system. Combined with the calculation of the known model PID control parameters, the more adaptive PID control algorithm is deduced. The simulation results show that the system has fast dynamic response, small overshoot, high steady-state accuracy, strong anti-disturbance ability and good control effect.