基于神经网络的超精密定位控制(英文)

被引:4
作者
张金龙
余玲玲
刘京南
机构
[1] 东南大学自动控制系
关键词
莫尔信号; 超精密定位; 神经网络; 智能控制;
D O I
暂无
中图分类号
TP273 [自动控制、自动控制系统];
学科分类号
080201 ; 0835 ;
摘要
针对精密定位装置存在非线性,精确数学模型难于建立的缺陷,提出了精密定位的神经网络控制方法.将BP神经网络应用于该控制系统中,系统以光栅常数100μm的光栅为定位标记,以激光衍射产生的莫尔光光强及光强的变化率为神经网络的输入变量,利用神经网络的自学习功能进行精密定位控制.建立了精密定位的神经网络控制模型,模型由输入层、隐层和输出层3层神经元组成,通过对光强及光强变化率的映射,得到电机驱动信号.实验结果表明,使用神经网络控制,控制响应快,稳定性好,鲁棒性强,可有效改善控制质量,提高定位速度,系统可获得±0·5μm的定位精度.
引用
收藏
页码:130 / 133
页数:4
相关论文
共 10 条
[1]  
Nanotechnology[P]. COLLI ALAN[GB];WHITE RICHARD[GB].中国专利:US2012038409A1,2012-02-16
[2]  
An alignment tech- nique using diffracted Moir啨signals. Hara K,Nomura T,Kimura S,et al. Journal of Vacu- um Science and Technology . 1989
[3]  
An automatic mask alignment technique using Moir啨interference. Uchida Y,Hattori S,Nomura T. Jour- nal of Vacuum Science and Technology . 1987
[4]  
Tracking and dynamic control of the angular alignment position in a photolitho- graphic mask aligner by Moir啨interference technique. Singh B P,Goto T,Sharma R,et al. The Review of Scientific Instruments . 1995
[5]  
Sensing characteristics of a precision aligner using Moir啨gratings for precisionalignment system. Zhou L Z,Furuhasi H,Uchida Y. Chinese Journal of Lasers B:Eng- lish Edition . 2001
[6]  
Automatic mask alignment without a microscope. Kanjilal A K,Narain R,Sharma R,et al. IEEE Transactions onInstrumentation and Measurement . 1995
[7]  
Artificial neural networks and simulated evolution calculation. Yan Pingfan,Zhang Changshui. . 2000
[8]  
Influences of the inclination of gratings on the alignment accuracies in Moir啨alignment systems. Akihito M,Furuhasi H. Electrical Engineering . 2002
[9]  
Ultra-preci- sion alignment technique based on modified Moir啨signals. Zhang Jinlong,Cheng Congyan,Yu Lingling. Journal of Southeast University:English Edition . 2005
[10]  
Optical heterodyne detection of mask to wafer displacement for fine alignment. Itoh J,Kanayama T. Japanese Journal of Applied Physics . 1986