多层神经网络改进Prandtl-Ishlinskii模型构建与压电迟滞补偿

打开文本图片集

关键词：压电作动器；非线性建模；多层神经网络；迟滞补偿中图分类号：TN384;TP273 文献标识码：Adoi：10.37188/OPE.20263402.0255 CSTR：32169.14.OPE.20263402.0255

Improvement of a Prandtl-Ishlinskii model via multilayer neural network and hysteresis compensation of piezoelectric actuators

HUANG Weiqing，WANG Wenjin，AN Dawei*， ZHANG Chen，CHEN Xiaoting， ZOU Tao* （School ofMechanical and Electrical Engineering，Guangzhou University，Guangzhou 5lOo06，China） * Corresponding author，E-mail： andavy@gzhu. edu. cn;tzou@gzhu. edu. cn

Abstract： Piezoelectric actuators （PEA） are widely used for micro-nano-positioning and precision manu facturing due to their high resolution and rapid response.Inherent hysteresis nonlinearity afects control performance and restricts high-accuracy applications.To overcome the limitations of the classical PrandtlIshlinskii （P-I） model in representing complex nonlinear hysteresis phenomena，a multilayer neural network-enhanced P-I modeling approach was proposed. The method used a neural network to dynamically map the weights of Play operators while ensuring that the model remained invertible and physically inter pretable.Bayesian regularization was adopted during training to improve the ability to fit nonlinear systems and enhance generalization.Based on the improved model，an inverse-model-based feedforward controler Was designed and validated in real-time experiments. Experimental results show that the proposed feedfor ward compensation reduces the normalized RMSE to 0.65% ， 0.76% ，and 1.82% under triangular，sinu soidal，and hybrid inputs，significantly outperforming the classical and its polynomial variants. The method exhibits strong robustness across diverse input conditions and demonstrates good engineering applicability in complex hysteresis modeling and high-precision control.

Key words ： piezoelectric actuators； nonlinear modeling； multilayer neural network ; hysteresis compensation

1引言

压电作动器因其结构紧凑、响应迅速与高精度输出等优势，广泛应用于微纳加工、半导体制造及航空航天等领域[1-3]，是高性能控制系统中的精密驱动核心部件。（剩余15391字）