Inverse modeling and control of a dielectric electro-active polymer smart actuator

Abstract

This study focuses on the design of an inverse model for a dielectric electro-active polymer (DEAP) smart actuator using the dynamic nonlinear auto regressive exogenous (NARX) structure and a fuzzy inference system. The unknown parameters of the proposed NARX fuzzy model was identified by the adaptive particle swarm optimization (APSO) algorithm. An augmented proportional-integral-derivative feed-forward inverse (APIDFFI) controller was then developed for position tracking control of the actuator. Finally, an experimental investigation was scrutinized in order to evaluate the effectiveness of the designed inverse model and the proposed controller. The results show that the designed controller based on the inverse model improves the tracking performance of the actuator significantly with the tracking accuracy of about 96% and reduces the tracking errors compared to the conventional proportional-integral-derivative (PID) controller.