Title :
Application of the B-Spline wavelet in railway catenary intelligent fault diagnosis
Author :
Gao, Yan-ling ; Zhang, De-ying
Author_Institution :
Beijing Inst. of Petro-Chem. Technol., Beijing
Abstract :
A new method based on cubic B-Spline dyadic mother wavelet of centro -symmetric about zero is presented, the principle of singularity detection by using wavelet transform modulus maximum is applied in railway catenary fault feature extraction by using the mother wavelet, at last, the project is concluded by using BP neural network to recognize pattern. The result shows that it can confirm position accurately and identify the fault types effectively.
Keywords :
backpropagation; fault diagnosis; feature extraction; maintenance engineering; railway engineering; railway safety; signal classification; splines (mathematics); wavelet transforms; BP neural network; cubic B-spline dyadic mother wavelet; feature extraction; pattern recognition; railway catenary intelligent fault diagnosis; transient signals; wavelet transform modulus maximum; Fault diagnosis; Feature extraction; Frequency; Pattern recognition; Rail transportation; Spline; Time domain analysis; Wavelet analysis; Wavelet domain; Wavelet transforms; BP neural network; cubic B-Spline; feature extraction; modulus maximum; mother wavelet;
Conference_Titel :
Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-1065-1
Electronic_ISBN :
978-1-4244-1066-8
DOI :
10.1109/ICWAPR.2007.4421756
