Quantitative Ultrasonic Evaluation of Surface-Breaking Crack Height Based on Neural Network

Chang Bo Ke; Bao Zhong Xie

doi:10.4028/www.scientific.net/AMR.468-471.2937

Paper Titles

Recognition and Classification of Human Activity by Posture Sensing and Machine Learning
p.2916

Research of SCARA Robot Based on Fuzzy_PID Hybrid Control
p.2920

Research of High Voltage Transmission Line Monitoring System Based on GPRS and ZIGBEE
p.2926

Separation of Antihypertensive Peptides Derived from Soybean Protein Isolated with Ultrafiltration Technology
p.2931

Quantitative Ultrasonic Evaluation of Surface-Breaking Crack Height Based on Neural Network
p.2937

Pupil Detection in Facial Images with Using Bag of Pixels
p.2941

Research on Development Strategy of Sustainable Utilization of Water Resources in Northwest Hebei – Development Strategy of Sustainable Utilization of Water Resources and Vegetable Industry
p.2951

Water Environmental Quality Evaluation Based on Visualize Classification for Huangbizhuang Reservoir of South-North Water Transfer Project
p.2955

Research on Evaluation System of Urban Ecological Safety
p.2959

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 468-471Quantitative Ultrasonic Evaluation of...

Quantitative Ultrasonic Evaluation of Surface-Breaking Crack Height Based on Neural Network

Abstract:

A three-layer structured Back Propagation (BP) neural network has been proposed to automatically predict the height of surface-breaking crack, 28 group data including different K values of transducers and the beam path distances obtained directly from the tip echo experiment have been taken into consideration as the training samples. It is shown that the predictions of current network are in good consistence with the real crack heights, the robustness testing demonstrates that the current neural network has its feasible expansibility to be utilized in practical engineering applications.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 468-471)

Pages:

2937-2940

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.468-471.2937

Citation:

Cite this paper

Online since:

February 2012

Authors:

Chang Bo Ke, Bao Zhong Xie

Keywords:

BP Neural Network (BPNN), Crack Height, Tip Echo Method, Ultrasonic Test

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] S.W. Liu, J.H. Huang, J.C. Sung and C.C. Lee: Comput. Meth. Appl. Mech. Eng. Vol. 191 (2002), p.2830

Google Scholar

[2] S. Baby, T.Balasubramanian and R.J. Pardikar: Ultrasonic sizing of embedded vertical cracks in ferritic steel welds. Theor. Appl. Fract. Mech. Vol. 40 (2003), p.145

DOI: 10.1016/s0167-8442(03)00042-9

Google Scholar

[3] A. Oishi, K. Yamada, S. Yoshimura and G. Yagawa: Comput. Mech. Vol. 15 (1995), p.521

Google Scholar

[4] F.A. Ravenscroft, K. Newton and C.B. Scruby: Ultrasonics. Vol. 29 (1991), p.29

Google Scholar

[5] P.A. Doyle and C.M. Scala: Ultrasonics. Vol. 28 (1990), p.77

Google Scholar

[6] Z. Chang and A. Mal: Mech. Mater. Vol. 31(1999), p.197

Google Scholar

[7] P. Fromme and M.B. Sayir: Ultrasonics. Vol. 40 (2002), p.199

Google Scholar