PID+CMAC Neural Network Control of Micro Positioning Platform

Abstract

Because of some intrinsic properties of the PZT actuator, such as hysteresis, creep and nonlinearity effect, it’s difficult to achieve satisfactory results and control precision for conventional PID controller. In order to improve the control precision of the PZT driven of micro positioning platform, we proposed a CMAC neural network based on PID control scheme, which has the characteristics of realizing feed-forward control and obtaining the inverse dynamic model of controlled object by the CMAC neural network controller, and realizing feedback control by conventional controller, which can ensure the system stability and suppress disturbance. Form MATLAB simulation results, it demonstrates that the CMAC+PID control algorithm can be able to improve the control precision and response time of the system, and enhance the anti-interference ability and robustness, comparing with the traditional digit PID control algorithms.