首页 | 本学科首页   官方微博 | 高级检索  
     

基于神经网络算法的一维PSD非线性修正
引用本文:莫长涛,陈长征,张黎丽,李刚,孙凤久.基于神经网络算法的一维PSD非线性修正[J].哈尔滨工业大学学报,2004,36(8):1059-1060,1102.
作者姓名:莫长涛  陈长征  张黎丽  李刚  孙凤久
作者单位:哈尔滨商业大学,基础部,黑龙江,哈尔滨,150076;东北大学,理学院,辽宁,沈阳,110004;沈阳工业大学,建筑系,辽宁,沈阳,110023;哈尔滨商业大学,基础部,黑龙江,哈尔滨,150076;东北大学,理学院,辽宁,沈阳,110004
基金项目:国家自然科学基金资助项目(50174020).
摘    要:分析了PSD(position sensitive detetor)的非线性成因,并根据PSD的非线性特点,提出一种基于神经网络的PSD非线性补偿方法,利用神经网络具有逼近任意非线性函数的特点,通过训练使神经网络建立在PSD输出与其理想值之间的非线性映射关系,实现PSD非线性补偿.从而使PSD的非线性区获得了与线性区近似的线性度.实验结果表明,该方法能有效地消除非线性的影响,在神经网络的输出端得到期望的线性输出.

关 键 词:PSD  非线性修正  神经网络  BP算法  补偿
文章编号:0367-6234(2004)08-1059-02
修稿时间:2003年1月10日

Non-linear correction of one-dimension PSD on neural network optimizations
MO Chang-tao.Non-linear correction of one-dimension PSD on neural network optimizations[J].Journal of Harbin Institute of Technology,2004,36(8):1059-1060,1102.
Authors:MO Chang-tao
Affiliation:MO Chang-tao~
Abstract:The causes of non-1inearity of PSD are analyzed in this paper. A method for non-linear compensation of PSD based on artificial neural network is presented. In order to non-linear compensation over a full range, the neural network is trained to properly represent the nonlinear mapping between sensor reading and their represent output accuratelyIt is revealed from the experiment result that not only the influence of non-linear fluctuation can be eliminated effectively, but also a desired linear relationship between the sensor input and the neural network output can be obtained.
Keywords:PSD  correction of non-1inearity  neural network  BP optimizations  compensation
本文献已被 CNKI 维普 万方数据 等数据库收录!
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