Crack Localization in Hydraulic Turbine Blades Based on Kernel Independent Component Analysis and Wavelet Neural Network

Hydraulic turbine runner has a complex structure, and traditional location methods can’t meet its requirement. This paper describes a source location of cracks in turbine blades by combining kernel independent component analysis (KICA) with wavelet neural network (WNN). The research shows that the l...

Full description

Saved in:

Bibliographic Details
Published in:	International journal of computational intelligence systems Vol. 6; no. 6; pp. 1116 - 1124
Main Authors:	Wang, Xianghong, Mao, Hanling, Hu, Hongwei, Zhang, Zhiyong
Format:	Journal Article
Language:	English
Published:	Dordrecht Springer Netherlands 01.12.2013 Springer
Subjects:	acoustic emission (AE) Crack localization kernel independent component analysis (KICA) Research Article scaled conjugate gradient algorithm wavelet neural network (WNN) wavelet neural network (WNN) scaled conjugate gradient algorithm acoustic emission (AE) kernel independent component analysis (KICA) Crack localization
ISSN:	1875-6891, 1875-6883, 1875-6883
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Hydraulic turbine runner has a complex structure, and traditional location methods can’t meet its requirement. This paper describes a source location of cracks in turbine blades by combining kernel independent component analysis (KICA) with wavelet neural network (WNN). The research shows that the location accuracy of WNN combined with KICA feature extraction is the best comparing with the results of WNN and back propagation neural network (BPNN). The method decreases the dimension of input parameters and improves the accuracy of location as well.
ISSN:	1875-6891 1875-6883 1875-6883
DOI:	10.1080/18756891.2013.817065