基于支持向量机的压电微操作平台非线性特性描述

摘要/Abstract

摘要： 压电驱动器的迟滞现象会使微操作平台出现非线性问题，严重影响了其运动精度和重复定位精度。为了解决该问题，提出了一种基于Preisach模型与支持向量机的联合建模方法来描述微操作平台的非线性特性。以一种一维微操作平台为对象，以压电驱动电压和所对应的平台输出位移为样本点，采用支持向量机理论建立反映平台非线性回归模型，利用该模型预测非样本点所对应的平台输出位移，结合Preisach模型可精确预测平台在任意电压序列作用下的输出位移。为了验证所建立模型的有效性，进行了实验研究，任意选取2组不同的输入电压序列，利用支持向量机回归模型和Preisach模型分别得到所选取的电压序列对应的输出位移的预测值，在相同的电压序列作用下进行实验得到其实测值，将实测值与预测值进行比较分析，结果表明，2组实测值与预测值之间的相对误差范围分别为0.6%～2.1%、0.02%～2.1%，预测位移与实测位移非常接近，说明所建立的模型能精确描述微操作平台的非线性特性，以实现其精确运动。

关键词: 微操作平台, 压电驱动器, Preisach模型, 支持向量机, 非线性特性

Abstract: The nonlinear characteristics of micro-manipulation stage would be occurred due to the hysteresis of piezoelectric actuator, which might seriously affect the movement precision and repeated positioning accuracy of the stage. In order to solve the issue, a hybrid modeling method was proposed to describe the hysteresis characteristics based on Preisach and SVM. As for a one dimensional micro-manipulation stage, the sample points were chosen as the piezoelectric driving voltages and corresponding output displacements of the stage. The regression model of the hysteresis loop of the PEA was established by using SVM theory. The model might be used to predict the displacements corresponding to the voltages not at sample points. Combined with the Preisach model, the output displacement corresponding to any voltage sequence might be obtained. The experimental studies were carried out in order to verify the validity of the presented model. Arbitrarily selecting two sets of input voltage sequences, and the prediction value of the output displacements corresponding to the selected voltage sequences might be obtained by using the regression model and Preisach model. The measured values were obtained under the same voltage sequences by experimental tests. Comparing the measured values and predicted values, the results show that the relative error ranges of the two sets of the measured and predicted values are as 0.6%～2.1% and 0.02%～2.1%, respectively. Therefore, the predicted displacements are very close to the measured ones. It illustrates that the proposed model may accurately describe the nonlinear characteristics of the micro-manipulation stage in order to realize its precise movements.

Key words: micro-manipulation stage, piezoelectric actuator, Preisach model, support vector machine(SVM), nonlinear characteristics

中图分类号:

TH703
TP274

胡俊峰, 郑昌虎, 蔡建阳. 基于支持向量机的压电微操作平台非线性特性描述[J]. 中国机械工程.

Hu Junfeng, Zheng Changhu, Cai Jianyang. Description of Nonlinear Characteristics of Piezoelectric Micro-manipulation Stage Based on SVM[J]. China Mechanical Engineering.

参考文献

[1]Yue Yi, Gao Feng, Zhao Xianchao, et al. Relationship among Input-force, Payload, Stiffness and Displacement of a 3-DOF Perpendicular Parallel Micro-Manipulator [J]. Mechanism and Machine Theory, 2010, 45(5):756-771.

[2]胡俊峰, 徐贵阳, 郝亚洲.基于响应面法的微操作平台多目标优化[J].光学精密工程, 2015, 23(4):1096-1104.

Hu Junfeng, Xu Guiyang, Hao Yazhou. Multi-objective Optimization of a Novel Micro-manipulation Stage Based on Response Surface Method[J].Optics and Precision Engineering, 2015, 23(4): 1096-1104.

[3]Vominh T, Tjahjowidodo T, Ramon H, et al. A New Approach to Modeling Hysteresis in a Pneumatic Artificial Muscle Using the Maxwell-slip Model[J]. IEEE/ASME Transactions on Mechatronics, 2011, 16(1): 177-186.

[4]Lin C J, Lin P T.Tracking Control of a Biaxial Piezo-actuated Positioning Stage Using Generalized Duhem Model [J]. Computers & Mathematics with Applications, 2012, 64(5): 766-787.

[5]Jiang H, Ji H, Qiu J, et al. A Modified Prandtl-ishlinskii Model for Modeling Asymmetric Hysteresis of Piezoelectric Actuators [J]. IEEE Transactions on Ultrasonics Ferroelectrics & Frequency Control, 2010, 57(5): 1200-1210.

[6]Xiao Shunli, Li Yangmin. Modeling and High Dynamic Compensating the Rate-dependent Hysteresis of Piezoelectric Actuators via a Novel Modified Inverse Preisach Model[J]. IEEE Transactions on Control Systems Technology, 2013, 21(5): 1549-1557.

[7]Mohammad R Z, Mohsen F, Hassan S,et al. Hysteresis Nonlinearity Identification Using New Preisach Model-based Artificial Neural Network Approach [J]. Journal of Applied Mathematics, 2011, 2011(22):1-21.

[8]刘向东, 修春波, 李黎，等.迟滞非线性系统的神经网络建模[J].压电与声光, 2007, 29(1): 106-108. Liu Xiangdong, Xiu Chunbo, Li Li, et al. Hysteresis Modeling Using Neural Networks [J]. Piezoelectectrics & Acoustooptics, 2007, 29(1): 106-108.

[9]赵新龙, 谭永红.对Preisach类的迟滞非线性神经网络建模[J].控制理论与应用, 2006, 23(4): 581-585. Zhou Xinlong, Tan Yonghong. Modeling Preisach-type Hysteresis Nonlinearity Using Neural Networks[J]. Control Theory & Applications, 2006, 23(4): 581-585.

[10]张建华, 葛红宇, 李宏胜,等.压电致动器Preisach模型的模糊插值算法及实现[J].南京理工大学学报,2011, 35(6): 780-785.

Zhang Jianhua, Ge Hongyu, Li Hongsheng, et al. Fuzzy Interpolation Algorithm and Realization of Preisach Model for Piezo Actuator[J].Journal of Nanjing University of Science and Technology,2011, 35(6):780-785.

[11]赖志林, 刘向东, 耿洁,等.压电陶瓷执行器迟滞的滑模逆补偿控制[J].光学精密工程,2011,19(6):1281-1290. Lai Zhilin, Liu Xiangdong, Geng Jie, et al. Sliding Mode Control of Hysteresis of Piezoceramic Actuator Based on Inverse Preisach Compensation [J]. Optics and Precision Engineering, 2011, 19(6): 1281-1290.

[12]魏燕定, 陶惠峰.压电驱动器迟滞特性的Preisach模型研究[J].压电与声光, 2004, 26(5): 364-367.

Wei Yanding, Tao Huifeng. Study the Preisach Model of Hysteresis in Piezoelectric Actuator [J]. Piezoelectrics & Acoustooptics, 2004, 26(5): 364-367.

[13]李黎, 刘向东,王伟，等.压电陶瓷执行器迟滞特性的广义非线性Preisach模型及其数值实现[J].光学精密工程, 2007, 15(5): 706-712.

Li Li, Liu Xiangdong,Wang Wei,et al.Generalized Nonlinear Presach Model for Hysteresis Nonlinearity of Piezoceramic Actuator and Its Numerical Implementation [J].Optics and Precision Engineering,2007,15(5):706-712.

[14]陈辉, 谭永红, 周杏鹏,等.压电陶瓷执行器的动态模型辨识与控制[J].光学精密工程, 2012, 20(1):88-95.

Chen Hui, Tan Yonghong, Zhou Xingpeng, et al. Identification and Control of Dynamic Modeling for Piezoceramic Actuator[J].Optics and Precision Engineering, 2012, 20(1): 88-95.

[15]Smola A J, Schlkopf B. A Tutorial on Support Vector Regression [J]. Statistics and Computing, 2004, 14(3): 199-222.

[16]韩彦彬, 白广忱, 李晓颖,等.基于支持向量机柔性机构动态可靠性分析[J].机械工程学报,2014,50(11):86-92.

Han Yanbin, Bai Guangchen, Li Xiaoying,et al. Dynamic Reliability Analysis of Flexible Mechanism Based on Support Vector Machine[J].Journal of Mechanical Engineering, 2014, 50(11): 86-92.