International Journal of Computational Intelligence Systems

Volume 6, Issue 6, December 2013, Pages 1116 - 1124

CRACK LOCALIZATION IN HYDRAULIC TURBINE BLADES BASED ON KERNEL INDEPENDENT COMPONENT ANALYSIS AND WAVELET NEURAL NETWORK

Authors
Xianghong Wang, Hanling Mao, Hongwei Hu, Zhiyong Zhang
Corresponding Author
Xianghong Wang
Available Online 9 January 2017.
DOI
https://doi.org/10.1080/18756891.2013.817065How to use a DOI?
Keywords
Crack localization, acoustic emission (AE), kernel independent component analysis (KICA), scaled conjugate gradient algorithm, wavelet neural network (WNN)
Abstract
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.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Journal
International Journal of Computational Intelligence Systems
Volume-Issue
6 - 6
Pages
1116 - 1124
Publication Date
2017/01
ISSN
1875-6883
DOI
https://doi.org/10.1080/18756891.2013.817065How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - JOUR
AU  - Xianghong Wang
AU  - Hanling Mao
AU  - Hongwei Hu
AU  - Zhiyong Zhang
PY  - 2017
DA  - 2017/01
TI  - CRACK LOCALIZATION IN HYDRAULIC TURBINE BLADES BASED ON KERNEL INDEPENDENT COMPONENT ANALYSIS AND WAVELET NEURAL NETWORK
JO  - International Journal of Computational Intelligence Systems
SP  - 1116
EP  - 1124
VL  - 6
IS  - 6
SN  - 1875-6883
UR  - https://doi.org/10.1080/18756891.2013.817065
DO  - https://doi.org/10.1080/18756891.2013.817065
ID  - Wang2017
ER  -