Classification of ultrasonic shaft inspection data using discrete wavelet transform

Conference Publication ResearchOnline@JCU
Lee, Kyungmi;Estivill-Castro, Vladimir
Abstract

Artificial Neural Networks have been used to process ultrasonic signals for many non-destructive scenarios. However, this scenarios usually involve very shallow surfaces. When testing shafts, the signals are long and the new problem of mode-converted reflections emerges. They are echoes that do not correspond to cracks in the material, neither to characteristics of the shaft. Also, the length of the signals demands the application of feature extraction mechanism to reduce the dimension of the pattern vectors and make classifier training feasible. The results here establish experimentally that DWT provides faster and more reliable feature extraction for ANN in these long signals in shafts. This results match the recent studies for shallow signals where comparisons between FFT and DWT indicate DWT as the preferred feature extraction policy.

Journal

N/A

Publication Name

(AIA 2003) Artificial Intelligence and Applications Conferences

Volume

N/A

ISBN/ISSN

1482-7913

Edition

N/A

Issue

N/A

Pages Count

N/A

Location

Benalmádena, Spain

Publisher

ACTA Press

Publisher Url

N/A

Publisher Location

N/A

Publish Date

N/A

Url

N/A

Date

N/A

EISSN

N/A

DOI

N/A