首页 | 本学科首页   官方微博 | 高级检索  
     

BP神经网络在测试系统动态补偿中的应用
引用本文:田社平,韦红雨,王志武,颜国正. BP神经网络在测试系统动态补偿中的应用[J]. 测试技术学报, 2005, 19(4): 453-458
作者姓名:田社平  韦红雨  王志武  颜国正
作者单位:上海交通大学,信息检测技术与仪器系,上海,200030;上海交通大学,信息检测技术与仪器系,上海,200030;上海交通大学,信息检测技术与仪器系,上海,200030;上海交通大学,信息检测技术与仪器系,上海,200030
基金项目:国家自然科学基金资助项目(30270382)
摘    要:测试系统的非线性动态补偿是仪器技术的一个重要方面.采用BP神经网络对测试系统进行动态补偿.BP神经网络的结果决定于网络输入、隐层和输出节点.由于其非线性映射特性,BP神经网络完全能够反映测试系统的动态响应特性.采用了收敛速度较快的递推预报误差算法训练神经网络.试验结果表明,BP神经网络的特性完全能够满足测试系统的动态补偿要求.表明本文的方法是有效的.

关 键 词:动态补偿  神经网络  递推预报误差算法
文章编号:1671-7449(2005)04-0453-06
收稿时间:2004-11-19
修稿时间:2004-11-19

Application of Back Propagation Artificial Neural Networks on Dynamic Compensation of Measurement Systems
TIAN She-ping,WEI Hong-yu,WANG Zhi-wu,YAN Guo-zheng. Application of Back Propagation Artificial Neural Networks on Dynamic Compensation of Measurement Systems[J]. Journal of Test and Measurement Techol, 2005, 19(4): 453-458
Authors:TIAN She-ping  WEI Hong-yu  WANG Zhi-wu  YAN Guo-zheng
Affiliation:Dept. of Information Measurement Technology and Instruments,Shanghai Jiaotong University,Shanghai 200030,China
Abstract:Nonlinear dynamic compensation of measurement systems is an important aspect in the field of instrument technique.The back propagation(BP) neural network is proposed for nonlinear dynamic compensation of measurement systems,as its architecture is determined only by the number of nodes in the input,hidden and output layers.With the nonlinear mapping behavior,the BP neural network can catch up with the dynamic response of the system.A recursive prediction error algorithm which converges fast is applied to train the BP neural network.Experimental results show that the performance of the BP neural network model conforms to the measurement system to be compensated,proving the method is not only effective but of high precision.
Keywords:dynamic compensation   neural networks   recursive prediction error algorithm
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