Research on Automatic Flaw Classification and Feature Extraction of Ultrasonic Testing

Abstract:

Article Preview

In this paper, Lifted Wavelet Transform (LWT) and BP neural network are used for automatic flaw classification of pipeline girth welds. LWT is proposed to extract flaw feature from ultrasonic echo signals, ideally matched local characteristics of original signal and increasing the computational speed and flaw classification efficiency. After extracting features of all flaw echoes, a feature library is constructed. A modified BP neural network is followed as a classifier, trained by the library. When feature of any flaw echo is extracted and sent to BP network, flaw type is the output, realizing automatic flaw classification. Experiment results prove the proposed method, LWT with BP neural network, is more fit for automatic flaw classification than traditional methods.

Info:

Periodical:

Key Engineering Materials (Volumes 381-382)

Edited by:

Wei Gao, Yasuhiro Takaya, Yongsheng Gao and Michael Krystek

Pages:

631-634

DOI:

10.4028/www.scientific.net/KEM.381-382.631

Citation:

J. Li et al., "Research on Automatic Flaw Classification and Feature Extraction of Ultrasonic Testing", Key Engineering Materials, Vols. 381-382, pp. 631-634, 2008

Online since:

June 2008

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.