摘要
针对压电陶瓷固有的迟滞非线性,设计了一种基于深度神经网络(DNN)的前馈补偿控制系统。该系统包含1个输入层、7个隐藏层和1个输出层。实验结果表明,开环情况下压电陶瓷的位移线性误差达8.91μm。施加神经网络前馈补偿后,压电陶瓷的最大位移误差降低到80 nm,稳态误差为±20 nm。进一步测试表明,在10~100 Hz输入频率下系统最大误差小于100 nm,均方根误差为0.01μm,验证了深度神经网络能够准确补偿压电陶瓷动态迟滞非线性,具有较好的频率泛化能力。
Aiming at the inherent hysteresis nonlinearity of piezoelectric ceramics,a feedforward compensation control system based on the deep neural network(DNN)is designed in this paper.The system consists of one input layer,seven hidden layers and one output layer.The experimental results show that the displacement linearity error of piezoelectric ceramics reaches 8.91μm in the open loop condition.After applying neural network feedforward compensation,the maximum displacement error of piezoelectric ceramics is reduced to 80 nm,and the steady-state error is±20 nm.Further tests show that the maximum error of the system is less than 100 nm at the input frequency of 10~100 Hz,and the root mean square error is 0.01μm,which verifies that the deep neural network can accurately compensate the dynamic hysteresis and nonlinearity of piezoelectric ceramics and has good frequency generalization ability.
作者
熊永程
贾文红
张丽敏
郑丽芳
XIONG Yongcheng;JIA Wenhong;ZHANG Limin;ZHENG Lifang(Shanghai Institute of Applied Physics,Chinese Academy of Sciences,Shanghai 201800,China;University of Chinese Academy of Sciences,Beijing 100049,China;Shanghai Advanced Research Institute,Chinese Academy of Sciences,Shanghai 201210,China)
出处
《压电与声光》
CAS
北大核心
2022年第1期35-41,共7页
Piezoelectrics & Acoustooptics
基金
国家自然科学基金青年科学基金资助项目(11805262)。
关键词
压电陶瓷
迟滞非线性
深度神经网络
前馈控制
piezoelectric ceramics
hysteresis nonlinearity
deep neural network
feedforward control
