Title :
The Use of RBF Based on Fisher Ratio for Eddy Current Nondestructive Detecting System
Author :
Sun, Xiaoyun ; Liu, Donghui ; Li, Aihua ; Feng, Liqian
Author_Institution :
Hebei Univ. of Sci. & Technol., Shijiazhuang
Abstract :
Improved radial basis function (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 result shows that the neural structure is simplified strongly, the converge precision and class separability is improved, and this method is satisfied to detect online.
Keywords :
condition monitoring; eddy current testing; production engineering computing; radial basis function networks; Fisher ratio method; eddy current nondestructive detecting system; network structure optimization; radial basis function neural network; Algorithm design and analysis; Clustering algorithms; Clustering methods; Eddy currents; Equations; Neural networks; Neurons; Optimization methods; Radial basis function networks; Sun;
Conference_Titel :
Natural Computation, 2007. ICNC 2007. Third International Conference on
Conference_Location :
Haikou
Print_ISBN :
978-0-7695-2875-5
DOI :
10.1109/ICNC.2007.753
