首页 | 官方网站   微博 | 高级检索  
     

基于模糊神经网络的二维PSD非线性修正算法
引用本文:徐聪,佃松宜,杨杰超.基于模糊神经网络的二维PSD非线性修正算法[J].电子测量技术,2017,40(2):50-54.
作者姓名:徐聪  佃松宜  杨杰超
作者单位:四川大学电气信息学院 成都 610065
摘    要:为了减小二维位置敏感探测器(2D-PSD)的非线性误差,研究了一种基于模糊神经网络的2D-PSD非线性修正算法.基于调制光源法采集到2D-PSD光敏面上可靠的光点位置信号后,采用T-S型模糊神经网络近似表示光点位置信号与光点位置坐标之间的映射,将该映射嵌入到ARM处理器中实现2D-PSD的在线修正计算.采用该模糊神经网络非线性修正算法后,2D-PSD的非线性误差从±0.4 mm减小到±0.15 mm,实验结果表明基于模糊神经网络非线性修正算法对有效性.

关 键 词:模糊神经网络  二维位置敏感探测器  非线性修正算法  调制光源法  ARM处理器

Research and implementation on nonlinear correction for 2D PSD based on fuzzy neural net
Xu Cong,Dian Songyi and Yang Jiechao.Research and implementation on nonlinear correction for 2D PSD based on fuzzy neural net[J].Electronic Measurement Technology,2017,40(2):50-54.
Authors:Xu Cong  Dian Songyi and Yang Jiechao
Affiliation:School of Electrical Engineering and Information, Sichuan University, Chengdu 610065, China,School of Electrical Engineering and Information, Sichuan University, Chengdu 610065, China and School of Electrical Engineering and Information, Sichuan University, Chengdu 610065, China
Abstract:In order to reduce the nonlinear errors for two-dimensional position sensitive detectors (2D-PSD),a novel nonlinear correction algorithm for 2D-PSD based on fuzzy neural network (FNN) was researched and implemented.The method based on modulating light was used to acquire the signal of light source,then T-S type FNN was used to approximate the mapping between the signal of the light-points and the coordinates of the light-points on the photosensitive surface of 2D-PSD.The mapping was embedded into a ARM processor to implement on-line correction calculation.By this nonlinear correction algorithm based on fuzzy neural network,the nonlinear errors are reduced from ±0.4 mm to ±0.15 mm.The experimental results show the efficiency of nonlinear algorithm based on FNN.
Keywords:fuzzy neural network  two-dimensional position sensitive detector  nonlinear correction algorithm  method of modulating light  ARM processor
本文献已被 万方数据 等数据库收录!
点击此处可从《电子测量技术》浏览原始摘要信息
点击此处可从《电子测量技术》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号