关键词: 压电执行器, 迟滞, Duhem算子, 极限学习机

Abstract: Piezoelectric actuators (PEAs) have been widely used in the field of high-precision positioning, but there is inherent hysteresis nonlinearity which seriously degrades the tracking performance. In order to improve the control precision of the high-precision positioning system, the nonlinear hysteresis model is established. In this paper, an identification method using extreme learning machine based on Duhem operator is proposed. The Duhem operator is proposed to describe the relationship between the system input and the system output, and the hysteresis model is achieved by using extreme learning machine and Duhem operator. Finally, simulation results are given to evaluate the effectiveness of the proposed modeling method. The method has improved the identification speed and precision significantly.

Key words: Piezoceramic actuator, hysteresis, Duhem operator, extreme learning machine