A dynamic generalized regression neural network model based on inverse Duhem operator is proposed to characterize the rate-dependent hysteresis in piezoelectric actuators. As hysteresis is multi-valued mapping, and traditional neural network can only model the system with one-to-one mapping. An inverse Duhem operator is proposed to extract the dynamic property of the hysteresis. Moreover, it can transform the multi-valued mapping of the hysteresis into a one-to-one mapping to suit the input of neural network. In order to compensate the effect of the hysteresis in piezoelectric actuator, the adaptive sliding mode controller with a feedforward hysteresis compensator is developed for the tracking control of the piezoelectric actuator. Experimental results demonstrate superior tracking performance, which validate the practicability and effectiveness of the presented approach.
A new parameter identification method of Duhem model based on antlion-fish swarm hybrid algorithm is proposed to characterize the rate-dependent hysteresis. The unknown piecewise functions in Duhem model is identified by a hybrid algorithm. Antlion optimization (ALO) algorithm and artificial fish (AF) swarm algorithm are switched in order of execution and their iterative data are fused to form the antlion-fish swarm hybrid algorithm. The comparison experiment shows the hybrid algorithm has the advantages of fast convergence and high precision. In order to compensate the rate-dependent hysteresis of PEA, a robust backstepping sliding mode feedback controller with feedforward inverse Duhem model compensator are designed. The comparative experimental results of displacement tracking show that this method has good tracking performance. The practicability and effectiveness of the method are verified.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.