单频干涉仪瞬时相位计算的神经网络模型

被引:2
作者
李直
Konrad Herrmann
Frank Pohlenz
机构
[1] Physikalisch-TechnischeBundesanstaltDBrauschweig,Physikalisch-TechnischeBundesanstaltDBrauschweig,Physikalisch-TechnischeBundesanstaltDBrauschweigGermany,Germany,Germany
关键词
信息处理技术; 单频干涉仪; 条纹细分; 神经网络; 纳米测量;
D O I
暂无
中图分类号
TP183 [人工神经网络与计算];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
用反三角函数表述的单频干涉仪瞬时相位的解析计算模型通常是分段或不连续的 ,不利于系统性能的综合分析。这里提出了基于神经网络的干涉仪瞬时相位的连续型计算模型 ,给出了网络学习方法。仿真研究结果表明 ,该模型对干涉仪瞬时相位的辨识精度优于 0 5° ,同时对干涉仪的光强波动有良好的鲁棒性 ;实验结果验证了这一点 ,为进一步提高单频干涉仪信号处理精度奠定了基础。此外 ,简要述及了该模型在其他测量领域 ,特别是速度 加速度测量领域的应用前景。
引用
收藏
页码:121 / 124
页数:4
相关论文
共 13 条
[1]  
Nanotechnology[P]. COLLI ALAN[GB];WHITE RICHARD[GB].中国专利:US2012038409A1,2012-02-16
[2]  
New method for absolute shock calibration of accelerometers. Link A,von Martens H J,Wabinski W. Proceedings of SPIE the International Society for Optical Engineering . 1998
[3]  
Theory and applications for the supervised learning method based on gradient algorithms Part Ⅰ: Fundamental algorithm. Si J,Zhou G A,Li H et al. Journal of Tsinghua University . 1997
[4]  
Verification of the sub-nanometric capability of an NPL differential plane mirror interferometer with a capacitance probe. Downs M J,Nunn J W. Measurement Science and Technology . 1998
[5]  
A Double pass attachment for the linear and plane mirror interferometer. Baldwin R R,Siddal G J. Proceedings of SPIE the International Society for Optical Engineering . 1984
[6]  
Recent advances in displacement measuring interferometry. Boroff N. Measurement Science and Technology . 1992
[7]  
MethodsforthecalibrationofvibrationandshocktransducersPart13:Primaryshockcalibrationusinglaserint erferometry. ISO1606313:2001 .
[8]  
Introduction to Duzzy Theory and Neural Networks and their Application. Zhao Z Y,Xu Y M. . 1996
[9]  
Optical fringe subdivision with nanometric accuracy. Birch K P. Precision Engineering . 1990
[10]  
Correction of nonlinearity in one-frequency optical interferometry. Wu C M,Su C S,Peng G S. Measurement Science and Technology . 1996