SOM and RBF Networks for Eddy Current Nondestructive Testing

Bing Liu; Ai Hua Li; Chang Long Wang; Jian Bin Wang; Ye Teng Ni

doi:10.4028/www.scientific.net/AMR.219-220.1093

Paper Titles

Based on Information Fusion Integrated Wavelet Neural Network Fault Diagnosis
p.1077

Debt Financing, Corporate Governance and Overinvestment
p.1081

The Application of M-Ary Quantum Evolutionary Algorithm in Bit and Power Allocation for OFDM System over the Power Line
p.1085

A New Searching Direction for Linear Complementarity Problems
p.1089

SOM and RBF Networks for Eddy Current Nondestructive Testing
p.1093

Analysis and Application of a Kind of Hierarchical Fuzzy Systems
p.1097

Design of Networked Control Systems Based on Single-Neuron PID
p.1101

Based on Transcad of the Shortest Path Assignment Method
p.1105

Study on Energy Saving and Emission Reduction of EP Low-Voltage Power Supply System in Power Plant
p.1109

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 219-220SOM and RBF Networks for Eddy Current...

SOM and RBF Networks for Eddy Current Nondestructive Testing

Abstract:

Eddy current testing is a popular nondestructive testing (NDT) technology with a solid theoretical foundation. This paper presents a new crack test scheme which uses a self-organizing maps (SOM) network and a radial basis function (RBF) network to process the crack feature signals in eddy current NDT. And Fisher ratio method is adopted to optimize the RBF network centers and simplifies the network structure. The validity of this crack detection algorithm is verified by an experiment in which the wave signals of different crack locations and depths are acquired from the simulations and used as the training and testing samples. Finally, the assessment of the network’s accuracy is performed and the result is satisfactory.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 219-220)

Pages:

1093-1096

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.219-220.1093

Citation:

Cite this paper

Online since:

March 2011

Authors:

Bing Liu, Ai Hua Li, Chang Long Wang, Jian Bin Wang, Ye Teng Ni

Keywords:

Eddy Current NDT, Fisher Ratio, Nondestructive Testing (NDT), RBF Network, SOM Network

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] John Canny: A Computational Approach to Edge Detection. IEEE Trans on PAMI Vol. 86 (1986), pp.679-698.

Google Scholar

[2] Zhang Bin, He Saixian: Improved Edge-detection Method Based on Canny algorithm. Infrared Technology Vol.28 (2006), pp.165-169.

Google Scholar

[3] S. Saravanan, F. Ju and N, Q, Guo: Wave Signal Demodulation and Artificial Neural Networks for Damage Identification. Nondestructive Vol.32 (2010), pp.584-592.

Google Scholar

[4] Von der Malsburg, C.: Self-organization of orientation sensitive cell in the striate cortex. Kybernetik Vol.14 (1973), pp.85-100.

DOI: 10.1007/bf00288907

Google Scholar

[5] Fukushinma, K.: Cognition: A Self-organization Multilayered Neural Network. Biological Cybernetics Vol. 20 (1975), pp.121-136.

Google Scholar

[6] Kohonen, T., in: Self-Organization and Associative Memory, 3rd edn, Springer-Verlag (1989).

Google Scholar

[7] Kohonen, T.: The self-organizing map. Proceeding of the IEEE Vol. 78 (1990), pp.1464-1480.

Google Scholar

[8] Haykin SS, in: Neural networks: a comprehensive foundation, Prentice Hall, (1999).

Google Scholar

[9] Fu, X.J., L.P. Wang: Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance. IEEE Trans. System, Man, Cybern, Part B: Cybernetics Vol.33(2003),pp.399-409.

DOI: 10.1109/tsmcb.2003.810911

Google Scholar

[10] Mao K Z: RBF neural network center selection based on fisher ratio class separability measure. IEEE Trans Neural Networks Vol.13 (2002), pp.1211-1217.

DOI: 10.1109/tnn.2002.1031953

Google Scholar

[11] Sherstinsky A., Picard R. W.: On the efficiency of the orthogonal least squares training method for radial basis function networks. IEEE Trans. Neural Networks Vol.7(1996), pp.195-200.

DOI: 10.1109/72.478404

Google Scholar