2-D Defect Profile Reconstruction from Ultrasonic Guided Wave Signals Based on Radial Wavelet Basis Function Neural Network with ELM

Abstract:

The reconstruction of defect profiles based on ultrasonic guided waves means the acquisition of defect profiles and parameters from ultrasonic guided wave signals. To achieve multi-resolution approximation, this paper proposed a reconstruction approach based on Radial Wavelet Basis Function Neural Network (RWBFNN), which combines wavelet analysis and neural network. Gaussian radial basis functions and Mexican hat wavelet frames are used as scaling functions and wavelet functions respectively. The training and testing samples contain simulation data and experimental data. The input data sets are defect echo signals, and the output data sets are 2-D profile parameters. To reduce the training time and simplify the profile reconstruction procedure without losing accuracy, Extreme Learning Machine (ELM) is adopted simultaneously. The results indicate that significant advantages can be obtained over other defect profile reconstruction schemes, and the accuracy of the predicted defect profile can be controlled by the resolution of the network with the lower computational complexity.

• Periodical: Key Engineering Materials (Volume 693)
• Pages: 1551-1561
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.693.1551
• Online since: May 2016
• Authors: Bing Liu*, Li Wei Tang, Xin Feng Yu, Jian Bin Wang, Ai Hua Li
• Keywords: Extreme Learning Machine, Multi-Resolution Approximation, Neural Network, Profile Reconstruction, Radial Wavelet Basis Function Neural Network, Ultrasonic Guided Wave

References

[1] Igor Lyutak, Wavelet analysis of ultrasonic guided waves in pipeline inspection, Intelligent data acquisition and advanced computing systems: Technology and applications, Sofia, Bulgaria (2005) 517-523.

DOI: 10.1109/idaacs.2005.283037

[2] Y.J. Yang, G. Cascante, M. A. Polak, Depth detection of surface- breaking cracks in concrete plates using fundamental Lamb modes, NDT & E International, 42 (2009) 501-512.

DOI: 10.1016/j.ndteint.2009.02.009

[3] Lee U, Kim S., Identification of multiple directional damages in a thin cylindrical shell, International journal of solids and structures, 43 (2006) 2723-2743.

DOI: 10.1016/j.ijsolstr.2005.03.077

[4] H. -C. fu, L. -Z. hua, Z. -Y. yu, Study on the number and the frequency characteristic of transducers in pipe inspection using guided waves, Journal of Beijing University of Technology, 30 (2004) 394-397.

[5] K. Sun, G. Meng, L. Ye, Damage size identification of thick steel beam based on ultrasonic guided wave, Journal of vibration and shock, 30(2011) 227-231.

[6] Z.H. Song, Z.H. Wang, H.W. Ma, Ultrasonic guided wave-based damage identification with split spectrum processing algorithm, Journal of vibration and shock, 30 (2012) 6-10.

[7] X.S. Zhang, J.B. Wang, J.Z. Wang and F.Z. Ji, 2-D reconstruction of the pipeline defects by means of ultrasonic guided wave based on LS- SVM, Journal of Xi'an Shiyou University ( Natural Science Edition), 27 (2012)87-90.

[8] B. Liu, L.W. Tang, 2-D Defect Profile Reconstruction from Ultrasonic Guided Waves Signals Adopting Fuzzy Wavelet Packet and LS-SVM, 2013 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering (QR2MSE 2013), Emeishan, China (2013).

DOI: 10.1109/qr2mse.2013.6625940

[9] G. -B. Huang, Q. -Y. Zhu, and C. -K. Siew, Extreme Learning Machine: A New Learning Scheme of Feedforward Neural Networks, 2004 International Joint Conference on Neural Networks (IJCNN'2004), Budapest, Hungary, (2004) 25-29.

DOI: 10.1109/ijcnn.2004.1380068

[10] G. -B. Huang, Q. -Y. Zhu, and C. -K. Siew, Extreme learning machine: Theory and applications, Neurocomputing, 70 (2006) 489-501.

DOI: 10.1016/j.neucom.2005.12.126

[11] G. -B. Huang and L. Chen, Convex incremental extreme learning machine, Neurocomputing, 70 (2007) 3056–3062.

DOI: 10.1016/j.neucom.2007.02.009

[12] G. -B. Huang and L. Chen, Enhanced random search based incremental extreme learning machine, Neurocomputing, 71 (2008) 3460–3468.

DOI: 10.1016/j.neucom.2007.10.008

[13] G. -B. Huang, X. Ding, H. Zhou, Optimization method based extreme learning machine for classification, Neurocomputing, 74 (2010) 155-163.

DOI: 10.1016/j.neucom.2010.02.019

[14] G. -B. Huang, H. Zhou, X. Ding, and R. Zhang, Extreme learning machine for regression and multiclass classification, IEEE Transactions on Systems, Man and Cybernetics-Part B: Cybernetics, 42 (2012) 513-529.

DOI: 10.1109/tsmcb.2011.2168604

[15] B. Frénay, M. Verleysen, Parameter-insensitive kernel in extreme learning for non-linear support vector regression, Neurocomputing, 74 (2011) 2526-2531.

DOI: 10.1016/j.neucom.2010.11.037

[16] W. Zong, H. Zhou, G. -B. Huang, and Z. Lin, Face recognition based on kernelized Extreme Learning Machine, AIS2011, Burnaby, Canada (2011) 263-272.

DOI: 10.1007/978-3-642-21538-4_26

[17] I.W. Selesnick, A higher density discrete wavelet transform, IEEE Transactions on Signal Processing, 54 (2006) 3039-3048.

DOI: 10.1109/tsp.2006.875388

[18] G. -B. Huang, Q. -Y. Zhu, K.Z. Mao, C. -K. Siew, P. Saratchandran, and N. Sundararajan, Can Threshold Networks Be Trained Directly? IEEE Trans. Circuits and Systems II, 53 (2006) 187-191.

DOI: 10.1109/tcsii.2005.857540

[19] G. -B. Huang, Q. -Y. Zhu and C. -K. Siew, Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Transactions on Neural Networks, 17 (2006) 879-892.

DOI: 10.1109/tnn.2006.875977

[20] G. -B. Huang, Q. -Y. Zhu and C. -K. Siew, Real-Time Learning Capability of Neural Networks, IEEE Trans. Neural Networks, 17 (2006) 863-878.

DOI: 10.1109/tnn.2006.875974

[21] C.R. Rao, S.K. Mitra. Generalized Inverse of Matrices and its Applications, John Wiley & Sons, Inc., New York (1971).

[22] D. Serre, Matrices: Theory and Applications, Springer, Heidelberg, (2002).