Abstracts: NDT of Railway

NDTnet 1998 July, Vol.3 No.7

NDT of Railway

INSPEC Antwortnummer 2 - © 1998 IEE
Title
	Neural pattern identification of railroad wheel-bearing faults from audible acoustic signals: comparison of FFT, CWT, and DWT features.
Author
	Choe, H.C.; Wan, Y.; Chan, A.K. (Dept. of Electr. Eng., Texas A&M Univ., College Station, TX, USA)
Publication Source
	Proceedings of the SPIE - The International Society for Optical Engineering (1997) vol.3078, p.480-96. 40 refs. Published by: SPIE-Int. Soc. Opt. Eng Price: CCCC 0 8194 2493 5/97/$10.00 CODEN: PSISDG ISSN: 0277-786X SICI: 0277-786X(1997)3078L.480:NPIR;1-P Conference: Wavelet Applications OV. Orlando, FL, USA, 22-24 April 1997 Sponsor(s): SPIE
Document Type
	Conference Article; Journal
Treatment Code
	Practical; Theoretical
Country of Publication
	United States
Language
	English
Abstract
	Current railroad wayside hot bearing detector (HBD) systems were developed in the 1960s to identify failing friction bearings. While the electronics used in these systems have been upgraded to microprocessor technology, the basic detection principles have not changed over the last 30 years. In this paper, we present a novel method to detect, recognize, and classify a variety of railroad wheel-bearing defects using audible acoustic signals at several different train speeds (or different angular wheel speeds). Our algorithm consists of a data preprocessor, a feature extractor, and a single multilayer neural network. The feature extractor can use any one of four different transforms to generate feature vectors from input acoustic data: the fast Fourier transform (FFT), the continuous wavelet transform (CWT), the discrete wavelet transform (nonredundant DWT), and the wavelet packet (redundant DWT). The classification performance using each feature vector type is presented. This algorithm can be applied to many kinds of bearings in rotational machinery to perform nondestructive fault detection and identification.
Accession Number
	97:5604869