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

作　　者：孙晓云[1] 刘东辉[1] 李爱华[1] 

机构地区：[1]河北科技大学,石家庄050054

出　　处：《无损检测》2008年第12期892-894,905,共4页Nondestructive Testing

基　　金：河北省自然科学基金资助项目(F2007000636)

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。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.

关 键 词：涡流定量检测 改进RBF网络 FISHER Ratio方法 在线检测 

分 类 号：TG115.28[金属学及工艺—物理冶金]