压电工作台的神经网络建模与控制

张栋; 张承进; 魏强; 田艳兵; 赵景波; 李现明

doi:10.3788/OPE.20122003.0587

您当前的位置：

首页 >

文章列表页 >

压电工作台的神经网络建模与控制

微纳技术与精密机械 | 更新时间：2020-08-12

- 压电工作台的神经网络建模与控制
- Modeling and control of piezo-stage using neural networks
- 光学精密工程 2012年20卷第3期页码：587-596
- 作者机构：
  
  1. 青岛理工大学自动化工程学院,山东青岛 266033
  2. 山东大学电气工程学院,山东济南,250061
  3. 山东大学控制科学与工程学院,山东济南,250061
  4. 泰山学院物理与电子工程系, 山东泰安 271021
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No. 61174044)();国家自然科学基金资助项目(No.50877046)();山东省优秀中青年科学家科研奖励基金项目(No.BS20
- DOI：10.3788/OPE.20122003.0587
  中图分类号： TN384;TP183
- 收稿日期：2011-09-01，
  
  修回日期：2011-11-10，
  
  网络出版日期：2012-03-22，
  
  纸质出版日期：2012-03-22
- 稿件说明：
移动端阅览
张栋, 张承进, 魏强, 田艳兵, 赵景波, 李现明. 压电工作台的神经网络建模与控制[J]. 光学精密工程, 2012,(3): 587-596

ZHANG Dong, ZHANG Cheng-jin, WEI Qiang, TIAN Yan-bing, ZHAO Jing-bo, LI Xian-ming. Modeling and control of piezo-stage using neural networks[J]. Editorial Office of Optics and Precision Engineering, 2012,(3): 587-596
张栋, 张承进, 魏强, 田艳兵, 赵景波, 李现明. 压电工作台的神经网络建模与控制[J]. 光学精密工程, 2012,(3): 587-596 DOI： 10.3788/OPE.20122003.0587.

ZHANG Dong, ZHANG Cheng-jin, WEI Qiang, TIAN Yan-bing, ZHAO Jing-bo, LI Xian-ming. Modeling and control of piezo-stage using neural networks[J]. Editorial Office of Optics and Precision Engineering, 2012,(3): 587-596 DOI： 10.3788/OPE.20122003.0587.

摘要

建立了压电工作台的神经网络在线辨识模型并设计了相应的自适应控制器以抑制压电工作台迟滞特性、蠕变特性及动态特性对其微定位精度的影响。采用双Sigmoid激活函数对神经网络激活函数进行了改进

同时分析了改进激活函数的神经网络模型与PI迟滞模型在迟滞建模上的异同。设计了基于改进激活函数的3层BP神经网络作为压电工作台的在线辨识模型

推导了网络权值、阈值及激活函数阈值修正公式。最后

基于神经网络模型设计了压电工作台的自适应控制方案

该控制方案利用另外一个神经网络来完成对PID控制器参数的自适应调整。实验结果表明:提出的神经网络在线辨识模型平均误差为0.095 m

最大误差为0.32 m;自适应控制方案跟踪三角波的平均误差为0.070 m

最大误差为0.100 m;跟踪复频波的平均误差为0.80 m

最大误差为0.105 m。实验数据显示压电工作台的定位精度得到了有效提高。

Abstract

An online identification neural network model and an adaptive controller were designed and verified by simulations to inhibit the influence of hysteresis

creep and dynamic characteristics of a piezo-stage on the positioning accuracy. First

the double Sigmoid activation function was adopted to improve the activation functions of neural networks

and the similarities and differences between improved neural work model and PI hysteresis model were analyzed. Then

a BP neural network with three layers based on the improved activation function was designed as the online identification model of piezo-stage

and the correction formulas for the network weights

thresholds as well as the activation function thresholds were derived. Finally

the adaptive control scheme of the piezo-stage was proposed based on the online identification neural network model

which made use of another neural networks to complete the parameter adjustment of an adaptive PID controller. Experimental results show that the average error and the maximum error are 0.095 m and 0.32 m for the online identification neural network model

0.070 m and 0.100 m for the adaptive control scheme on tracking triangle waves

and 0.080 m and 0.105 m for the tracking multiple frequency wave

respectively. Obtained data prove that positioning accuracy of the piezo-stage is improved effectively.

关键词

Keywords

references

李庆祥,王东生,李玉和. 现代精密仪器设计 [M]. 北京:清华大学出版社,2004. LI Q X, WANG D SH, LI Y H. Design of Modern Precision Instruments[M]. Beijing: Tsinghua University Press, 2004. (in Chinese)[2] LI Y M,XU Q S. A totally decoupled piezo-driven XYZ flexure parallel micropositioning stage for micro/nano manipulation[J]. IEEE Transactions on Automation Science and Engineering, 2011, 8(2): 265-279.[3] 陈立国,张洋,孙立宁,等. 多目标拓扑优化设计在纳米定位平台中的应用 [J]. 压电与声光,2011,33(2):228-231. CHEN L G, ZHANG Y, SUN L N, et al.. Application of multi-objective topology optimization design on the nano-positioning stage[J]. Piezoelectics & Acoustooptics, 2011, 33(2): 228-231. (in Chinese)[4] POLIT S, DONG J Y. Development of a high-bandwidth XY nanopositioning stage for high-rate micro-/nanomanufacturing[J]. IEEE/ASME Transactions on Mechatronics, 2011, 16(4): 724-733.[5] LI Y M,XU Q S. A novel piezoactuated XY stage with parallel decoupled, and stacked flexure structure for micro-/nanopositioning [J]. IEEE Transactions on Industrial Electronics, 2011, 58(8): 3601-3615.[6] 张栋,张承进,魏强. 压电微动工作台的动态迟滞模型 [J]. 光学精密工程,2009,17(3): 549-556. ZHANG D,ZHANG CH J,WEI Q. Dynamical hysteresis model of piezopositioning stage[J]. Opt. Precision Eng., 2009, 17(3): 549-556. (in Chinese)[7] JEDLICSKA I, WEISS R, WEIGEL R. Linearizing the output characteristic of GMR current sensors through hysteresis modeling[J]. IEEE Transactions on Industrial Electronics, 2010, 57(5): 1728-1734.[8] TAN X B, IVER R V. Modeling and control of hysteresis[J]. IEEE Transactions on Control Systems, 2009, 29(1): 26-28.[9] DEVASIA S, ELEFTHERIOU E, MOHEIMANI S O R. A survey of control issues in nanopositioning[J]. IEEE Transactions on Control Systems Technology, 2007, 15(5): 802-823.[10] 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 ZH L, LIU X D, GENG J. et al.. Sliding mode control of hysteresis of piezoceramic actuator based on inverse Preisach compensation[J]. Opt. Precision Eng., 2011, 19(6): 1281-1290. (in Chinese)[11] TAO G, KOKOTOVIC P V. Adaptive Control of Systems with Actuator and Sensor Nonlinearities[M]. New York: Wiley. 1996.[12] GE P, JOUANEH M. Modeling hysteresis in piezoceramic actuators[J]. Precision Engineering, 1995, 17(3):211-221.[13] KRASNOSELSKII M, POKROVSKII A. Systems with Hysteresis[M]. New York: Springer-Verlag, 1994.[14] JANAIDEH M A, RAKHEJA S, SU CH Y. An analytical generalized Prandtl-Ishlinskii model inversion for hysteresis compensation in micropositioning control[J]. IEEE/ASME Transactions on Mechatronics, 2011, 16(4): 734-744.[15] YI J, CHANG S, SHEN Y. Disturbance-observer-based hysteresis compensation for piezoelectric actuators[J]. IEEE/ASME Transactions on Mechatronics, 2009, 14(4): 456-464.[16] 马连伟,谭永红,邹涛. 基于神经网络的迟滞逆模型 [J]. 控制理论与应用,2008,25(5):823-826. MA L W, TAN Y H, ZOU T. A neural-network-based inverse hysteresis model[J]. Control Theory & Application, 2008, 25(5): 823-826. (in Chinese)[17] 张新良,谭永红. 基于输入空间扩张的动态迟滞神经网络模型 [J]. 自动化学报,2009,35(3):319-323. ZHANG X L, TAN Y H. Neural network model for the dynamic hysteresis based on the expanded input space[J]. Acta Automatica Sinica, 2009,35(3): 319-323. (in Chinese)[18] 赵新龙,谭永红,董建萍. 基于扩展输入空间法的压电执行器迟滞特性动态建模 [J]. 机械工程学报,2010,46(20):169-174. ZHAO X L, TAN Y H, DONG J P. Dynamic modeling of rate-dependent hysteresis in piezoelectric actuators based on expanded input space method[J]. Journal of Mechanical Engineering, 2010, 46(20): 169-174. (in Chinese)[19] DONG R L, TAN Y H. A neural networks based model for rate-dependent hysteresis for piezoceramic actuators[J]. Sensors and Actuators, 2008, 143: 370-376.[20] 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 X D, XIU CH B, LI L, et al.. Hysteresis modeling using neural networks[J]. Piezoelectics & Acoustooptics, 2007, 29(1): 106-108. (in Chinese)[21] 耿洁,刘向东,陈振,等. Preisach迟滞逆模型的神经网络分类排序 [J]. 光学精密工程,2010,18(4):855-862. GENG J, LIU X D, CHEN ZH, et al.. Realization of sorting & taxis of Preisach inverse hysteresis model using neural network[J]. Opt. Precision Eng., 2010, 18(4): 855-862. (in Chinese)[22] TANG J, WANG K W. High authority and nonlinearity issues in active passive hybrid piezoelectric networks for structural damping[J]. Journal of Intelligent Material Systems and Structures, 2000, 11(3): 581-591.[23] SU C Y, STEPANENKO Y, SVOBODA J, et al.. Robust adaptive control of a class of nonlinear systems with unkown backlash like hysteresis[J]. IEEE Transactions on Automatic Control, 2000, 45(12): 2427-2432.[24] WEI J D, SUN C T. Constructing hysteresis memory in neural networks[J]. IEEE Transactions on Systems, Man and Cybernetics-Part B: Cybernetics, 2000, 30(4): 601-609.[25] 阎平凡,张长水. 人工神经网络与模拟进化计算 [M]. 2版. 北京:清华大学出版社,2005. YAN P F, ZHANG CH SH. Artificial Neural Network and Simulated Evolutionary Computation [M]. 2 nd ed. Beijing: Tsinghua University Press, 2005. (in Chinese)[26] 袁曾任. 人工神经元网络及其应用 [M]. 北京:清华大学出版社,1999. YUAN Z R. Artificial Neural Networks and Application[M]. Beijing: Tsinghua University Press, 1999. (in Chinese)[27] 张栋,张玉林,李现明,等. 扫描电化学显微镜压电工作台的建模与控制 [J]. 仪器仪表学报,2009,30(12):2669-2675. ZHANG D, ZHANG Y L, LI X M, et al.. Modeling and control of SECM piezo-stage[J]. Chinese Journal of Scientific Instrument, 2009, 30(12): 2669-2675. (in Chinese)

浏览量

358

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

光动力学系统神经网络系统辨识及自适应控制之性能分析

混沌光学系统之快速神经网络自适应控制研究

基于神经网络的全斯托克斯光电探测器

压电平台高精度自适应分数阶滑模跟踪控制

基于圆卷积神经网络的粘连导电粒子检测