基于Fisher Ratio的RBF网络在涡流定量检测中的应用
The Use of RBF Based on Fisher Ratio for Eddy Current Nondestructive Detecting System
摘 要
采用改进的RBF网络完成涡流定量检测。针对正交最小二乘法不能使网络结构得到最大优化这一缺点，提出应用Fisher Ratio方法选择RBF网络隐层节点数及径向基函数中心，正交变换及前向搜索算法完成结构优化。结果表明，能极大地简化网络结构，提高了分类能力和收敛精度，为神经网络在实时在线检测中的应用提供可能。
改进RBF网络
Fisher Ratio方法
在线检测
Eddy current quantitative testing
Improved RBF neural network
Quantitative detecting
Fisher ratio method
Detecting online
Abstract
Improved RBF neural network is applied on eddy current nondestructive quantitative detecting. Owning to the disadvantages of OLS in network structure optimization, authors put forward using Fisher ratio method to optimize the RBF centers, orthogonal transform and forward selection search method are used to optimize structure. The results show that the neural structure is simplified strongly, the converge precision and class separability is improved, and this method is likely to be used for detecting online.
中图分类号 TG115.28
所属栏目 科研成果与学术交流
基金项目 河北省自然科学基金资助项目(F2007000636)
收稿日期 2008/1/3
修改稿日期
网络出版日期
作者单位点击查看
备注孙晓云(1971-)，女，教授，博士，主要研究方向为无损检测和信号处理。
引用该论文: SUN Xiao-Yun,LIU Dong-Hui,LI Ai-Hua. The Use of RBF Based on Fisher Ratio for Eddy Current Nondestructive Detecting System[J]. Nondestructive Testing, 2008, 30(12): 892～894
孙晓云,刘东辉,李爱华. 基于Fisher Ratio的RBF网络在涡流定量检测中的应用[J]. 无损检测, 2008, 30(12): 892～894
共有人对该论文发表了看法，其中：
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】张友民,李庆国,戴冠中,等.一种RBF网络结构优化方法[J].控制与决策,1996,11(6):667-670.
【2】刘东辉,孙晓云,孙会琴,等.RBF网络在实时在线检测系统中的应用[J].仪器仪表学报,2003,24(5):445-448.
【3】Chen S, Cowan C F N, Grant P M. Orthogonal least squares learning algorithm for Radial Basis Function Networks[J]. IEEE Trans on Neural Networks,1991,2(2):302-309.
【4】Gomm J B, Yu D L. Selecting radial basis function network centers with recursive orthogonal least squares training[J]. IEEE Trans Neural Networks,2000,11(3):306-314.
【5】Uykan Z, Guzelis C, Celebi M E, et al. Analysis of input output clustering for determining centers of RBFN[J]. IEEE Trans Neural Networks,2000,(11):851-858.
【6】Moody J E. The effective number of parameters : an analysis of generalization and regularization in nonlinear learning systems[J]. In Advances in Neural Information Processing Systems, San Mateo, CA,1992,(1):847-854.
【7】Sherstinsky A, Picard R W. On the efficiency of the orthogonal least squares training method for radial basis function networks[J]. IEEE Trans Neural Networks,1996,7(1):195-200.
【8】Mao K Z. RBF neural network center selection based on fisher ratio class separability measure[J]. IEEE Trans Neural Networks,2002,13(5):1211-1217.
【2】刘东辉,孙晓云,孙会琴,等.RBF网络在实时在线检测系统中的应用[J].仪器仪表学报,2003,24(5):445-448.
【3】Chen S, Cowan C F N, Grant P M. Orthogonal least squares learning algorithm for Radial Basis Function Networks[J]. IEEE Trans on Neural Networks,1991,2(2):302-309.
【4】Gomm J B, Yu D L. Selecting radial basis function network centers with recursive orthogonal least squares training[J]. IEEE Trans Neural Networks,2000,11(3):306-314.
【5】Uykan Z, Guzelis C, Celebi M E, et al. Analysis of input output clustering for determining centers of RBFN[J]. IEEE Trans Neural Networks,2000,(11):851-858.
【6】Moody J E. The effective number of parameters : an analysis of generalization and regularization in nonlinear learning systems[J]. In Advances in Neural Information Processing Systems, San Mateo, CA,1992,(1):847-854.
【7】Sherstinsky A, Picard R W. On the efficiency of the orthogonal least squares training method for radial basis function networks[J]. IEEE Trans Neural Networks,1996,7(1):195-200.
【8】Mao K Z. RBF neural network center selection based on fisher ratio class separability measure[J]. IEEE Trans Neural Networks,2002,13(5):1211-1217.
相关信息
