Research on Automatic Flaw Classification and Feature Extraction of Ultrasonic Testing

Jian Li; X. Zhan; J. Zhuge; Z. Zeng; Shi Jiu Jin

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

Paper Titles

Processing of Complex Modulated Ultrasonic Signals in Gas Flow Metering
p.615

Investigation on the Noise Separation in Watt Balance Experiments
p.619

Advanced Analog-to-Digital Conversion Using Voltage-to-Frequency Converters for Remote Sensors
p.623

Correlation Processing of the Signals of the Single-Fiber Intermode Interferometer with a Small Number of Excited Modes
p.627

Research on Automatic Flaw Classification and Feature Extraction of Ultrasonic Testing
p.631

Simulation of Profiles of Normal Ordinate Distribution
p.635

Processing Speed Acceleration of an Intelligent Communication Instrument
p.639

The Design and Use of F1 Softgauges for Validating Surface Metrology Software
p.643

Instruction Scheduling on a Pipelined Processor for Mechanical Measurements
p.647

HomeKey Engineering MaterialsKey Engineering Materials Vols. 381-382Research on Automatic Flaw Classification and...

Research on Automatic Flaw Classification and Feature Extraction of Ultrasonic Testing

Abstract:

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.

You might also be interested in these eBooks

Measurement Technology and Intelligent Instruments VIII

View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 381-382)

Pages:

631-634

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.381-382.631

Citation:

Cite this paper

Online since:

June 2008

Authors:

Jian Li, X. Zhan, J. Zhuge, Z. Zeng, Shi Jiu Jin

Keywords:

Feature Extraction, Flaw, Nondestructive Testing (NDT), Signal Processing, Ultrasonic

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Wang Likun, Jin Shijiu, Li Jian, et al.: Proc WCICA 2004, Institute of Electrical and Electronics Engineers Inc., Vol. 4 (2004), pp.1675-1679.

Google Scholar

[2] Wu Miao, Zhang Haiyan, Sun Zhi, Liu Xu: Journal of China University of Mining & Technology, Vol. 29 (2000), NO. 3, pp.239-243.

Google Scholar

[3] Feng Lin, Cheng Lu, Wu Zhenyu: Geophysical Prospecting for Petroleum, Vol. 43 (2004), NO. 3, pp.238-241.

Google Scholar

[4] M. Shim, A. Laine : Proc. ICIP 1998, Image Processing, Vol. 2 (1998), pp.242-246.

Google Scholar

[5] I. Daubechies, W. Sweldens: Factoring wavelet transforms into lifting steps, (Bell Laboratories, Lucent Technologies, 1996). Fig. 2 Testing system structure Fig. 3 BP network output result.

DOI: 10.1007/bfb0011095

Google Scholar