基于递归神经网络的超声波电机力矩迟滞辨识

微特电机 ›› 2022, Vol. 50 ›› Issue (11): 8-15.

基于递归神经网络的超声波电机力矩迟滞辨识

傅平^1,2

1.闽江学院物理学与电子信息工程学院,福州 350121;
2.闽江学院福建省教育厅先进运动控制重点实验室,福州 350121

收稿日期:2022-07-04 出版日期:2022-11-28 发布日期:2022-11-22
作者简介:傅平(1974—),男,博士,教授,从事超声波电机及其伺服控制方面的研究。
基金资助:
国家自然科学基金项目(51277091);福建省自然科学基金资助项目(2020J01841)

Torque Hysteresis Identification of Ultrasonic Motor Based on Recurrent Neural Network

FU Ping^1,2

1. Department of Physics and Telecommunication Engineering,Minjiang University,Fuzhou 350121,China;
2. Fujian Provincial Education Department Key Laboratory of Advanced Motion Control, Minjiang University, Fuzhou 350121,China

Received:2022-07-04 Online:2022-11-28 Published:2022-11-22

摘要/Abstract

摘要： 超声波电机的输入输出变量呈现强非线性特性,其速度-力矩之间存在迟滞,且随着驱动频率和负载等因素改变,用通常的辨识难以取得满意的效果。针对超声波电机的速度-力矩迟滞,使用基于递归神经网络和李亚普诺夫稳定性的方法,可以在一定程度上反映电机的迟滞特性。整个系统使用基于半实物仿真的超声波电机测试平台,其中迟滞辨识采用递归神经网络辨识器(RNNI)。由于RNNI的参数可以在线进行调整,因此当电机输入输出参数发生变化时,通过改变RNNI的参数可以实现不同迟滞特性的辨识,同时利用李亚普诺夫稳定性方法进行RNNI的参数调整。实验结果表明,递归神经网络辨识器通过改变神经网络参数对超声波电机迟滞可以进行有效的辨识,MSE小于6×10^-4,不同负载下辨识误差小于0.11。

关键词: 超声波电机, 递归神经网络, 李雅普诺夫稳定性, 半实物仿真, 迟滞

Abstract: The input and output variables of ultrasonic motor show strong nonlinear characteristics, and there exits hysteresis between torque and velocity of motor. The satisfactory results are difficult to be obtained by conventional identification.A control method based on recursive neural network and Lyapunov stability was proposed to reflect the nonlinear hysteresis of ultrasonic motor to a certain extent. The whole system included the ultrasonic motor test platform based on the hardware-in-the-loop simulation, and the hysteresis was identified by the recursive neural network identifier (RNNI). Because recurrent neural network could adjust its online parameter values when operation conditions of the motor changed, control parameters could be adjusted by changing the parameters of neural network identification and the parameters could be adjusted by Lyapunov stability. Experimental results show that the hysteresis of ultrasonic motor can be identified effectively by changing the parameters of neural network. The MSEwas less than 6×10^-4, and the identification error was less than 0.11 under different loads.

Key words: ultrasonic motor, recurrent neural network(RNN), Lyapunov stability, semi-physical simulation, hysteresis

中图分类号:

TM355

傅平. 基于递归神经网络的超声波电机力矩迟滞辨识[J]. 微特电机, 2022, 50(11): 8-15.

FU Ping. Torque Hysteresis Identification of Ultrasonic Motor Based on Recurrent Neural Network[J]. Small & Special Electrical Machines, 2022, 50(11): 8-15.

参考文献

[1] HAGOOD N W,MCFARLAND A J.Modeling of a piezoelectric rotary ultrasonic motor[J].Transactions on Ultrasonics Ferroelectrics and Frequency Control,1995,42(2):210-224.
[2] 赵淳生.超声电机技术与应用[M].北京:科学出版社,2007.
[3] 胡敏强,金龙.超声波电机原理与设计[M].北京:科学出版社,2005.
[4] FURUYA S,MARUHASHI T,IZUNO Y.Load adaptive frequency tracking control implementation of two phase resonant inverter for ultrasonic motor[J].IEEE Transactions Power Electronics,1992,7 (3):542-550.
[5] IZUNO Y,TAKEDA R.New fuzzy reasoning-based high performance speed position servo control schemes incorporating ultrasonic motor[J].IEEE Transactions on Industry Applications,1992,28(3):613-618.
[6] SENJYU T,UEZATO K.Adjustable speed control of ultrasonic motors by adaptive control[C]//IEEE Power Electronics Specialists Conference.IEEE,1994:1237-1242.
[7] LIN F J,WAI R J,CHEN M P.Wavelet neural network control for linear ultrasonic motor drive via adaptive sliding-mode technique[J].IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control,2003,50(6):686-698.
[8] IZUNO Y,NAKAOKA M.High performance and high precision ultrasonic motor-actuated positioning servo drive system using improved fuzzy-reasoning controller.[C]//IEEE Power Electronics Specialists Conference.IEEE,1994:1269-1274.
[9] LIN F J.Fuzzy adaptive model-following position control for ultrasonic motor[J].IEEE Transactions on Power Electronics,1997,12(2):261-268.
[10] MAAS J,SCHULTE T.Model-based control for ultrasonic motors[J].IEEE/ASME Transactions on Mechatronics,2000,5(2):165-180.
[11] HIEU N T,ODOMARI S,YOSHIDA T,et al.Nonlinear adaptive control of ultrasonic motors considering dead-zone[J].IEEE Transactions on Industrial Informatics,2013,9(4):1847-1854.
[12] NAKAGAWA Y,SAITO A.Nonlinear dynamic analysis of traveling wave-type ultrasonic motors[J].IEEE Transactions on Ultrasonics,Ferroelectrics and Frequency Control,2008,55(3):717-725.
[13] GIRAUD F,SANDULESCU P,AMBERG M,et al.Modeling and compensation of the internal friction torque of a travelling wave ultrasonic motor[J]. IEEE Transactions on Haptics,2011,4(4):327-331.
[14] SHI J Z, ZHAO J P, HUANG J T,et al.Identification of ultrasonic motor’s nonlinear hammerstein model[J].Journal of Control Automation & Electrical Systems,2014,25(5):537-546.
[15] 傅平.基于LCC的超声波电机驱动电路理论分析与实验研究[J].电工电能新技术,2014,33(7):38-42,66.