Premium
Hysteresis compensation and adaptive control based evolutionary neural networks for piezoelectric actuator
Author(s) -
Son Nguyen N.,
Van Kien Cao,
Anh Ho P. H.
Publication year - 2021
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/int.22519
Subject(s) - compensation (psychology) , hysteresis , control theory (sociology) , artificial neural network , actuator , computer science , control (management) , adaptive control , control engineering , artificial intelligence , engineering , physics , psychology , psychoanalysis , quantum mechanics
This manuscript introduces a new adaptive inverse neural (AIN) control method applied to precisely track the piezoelectric (PZT) actuator displacement. First, a 3‐layer neural network optimized by the enhanced differential evolution technique which modifies a mutation scheme and provides suggestions for selecting mutant coefficient F, crossover coefficient CR, and population size NP, is used to identify the inverse nonlinearity hysteresis structure of the PZT actuator. Second, a feed‐forward control based on the identified model is proposed to compensate for the PZT hysteresis effect. Third, the Lyapunov stability principle is used to design and implement an adaptive law‐based neural sliding mode model plus the feed‐forward compensator to ensure that the whole PZT plant is operated in asymptotical stability. The experiment results demonstrate the proposed AIN controller proves superiority in comparison with other advanced control methods.