Neural model of rate-dependent hysteresis in piezoelectric actuators based on expanded input space with rate-dependent hysteretic operator

Abstract

a neural networks based approach for the identification of the rate-dependent hysteresis in the piezoelectric actuators is proposed. In this method, a hysteresis operator dependent on the change-rate of the input is proposed to extract the change-tendency and rate-dependency of the dynamic hysteresis. With the introduction of the rate-dependent hysteresis operator into the input space, an expanded input space is constructed. Thus, based on the expanded input space, the multi-valued mapping of the rate-dependent hysteresis existing in the piezoelectric actuators can be transformed into a one-to-one mapping. Then the neural networks can be utilized to approximate the behavior of the rate-dependent hysteresis. Finally, the experimental results are presented to verify the effectiveness of the proposed approach.