Estimation of Crack Parameters through WFEM and Neural Network

Abstract:

This paper presents the application of the wavelet finite element methods (WFEM) and neural network to crack parameters estimation and discusses the accuracy and efficiency of this method. The crack is presented by a rotational massless spring, and the natural frequencies for various crack parameters (location and depth) are obtained through WFEM. The neural network is then applied to establish the mapping relationship between the natural frequencies and the crack parameters, which uses feed-forward multiplayer neural networks trained by back-propagation, error-driven supervised training. With this trained neural network, the crack location and depth is estimated through using the measured natural frequencies as the input. The results of a cantilever beam experiment indicate that the estimating error of crack location is less than 3%, and the error of crack depth is less than 2%.

• Periodical: Key Engineering Materials (Volumes 413-414)
• Pages: 31-37
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.413-414.31
• Online since: June 2009
• Authors: Bing Li, Jie Zhuo, Zheng Jia He
• Keywords: Crack, Estimation, Neural Network (NN)

References

[1] J.M. Silva, A.J.L. Gomes: Experimental Mechanics Vol. 30 (1992), p.20.

[2] X.F. Yang: Vibration Based Crack Analysis and Detection in Beams Using Energy Method, PhD Thesis, Faculty of Engineering and Applied Science Memorial University of Newfoundland, (2001).

[3] P.F. Rizos, N. Aspragathos, A.D. Dimarogonas: Journal of Sound and Vibration Vol. 138 (1990), p.381.

[4] B.P. Nandwana, S.K. Maiti: Journal of Sound and Vibration Vol. 203 (1997), p.435.

[5] T.D. Chaudhari, S.K. Maiti: International Journal of Solids and Structures Vol. 37 (2000), p.761.

[6] D.K.L. Tsang, S.O. Oyadiji, A.Y.T. Leung: Proceedings of the Fifth International Conference on Vibration, Nanjing, China, September 2002, p.59 Fig. 5. Data processing in neural network T P.

[7] S. Chinchalkar: Journal of Sound and Vibration Vol. 247 (2001), p.417.

[8] W.M. Ostachowicz, M. Krawczuk: Computers and Structures Vol. 77 (1990), p.327.

[9] S.P. Lele, S.K. Maiti: Journal of Sound and Vibration, Vol. 257 (2002), p.559.

[10] C.G. Go, Y.S. Lin: Engineering Fracture Mechanics, Vol. 48(1994), p.475.

[11] W. Dahmen: Journal of Computational Applied Mathematics, Vol. 128 (2001), p.133.

[12] Albert Cohen: �umerical Analysis of Wavelet Methods (North-Holland Press, 2003).

[13] S. Jaffard, P. Laurengot, in: Orthonormal wavelets, analysis of operators, and applications to numerical analysis, edited by C.K. Chui, Wavelets-A Tutorial in Theory and Applications, Academic Press, NewYork(1992), p.543.

DOI: 10.1016/b978-0-12-174590-5.50023-x

[14] J. Ko, A.J. Kurdila, M.S. Pilant: Computational Mechanics, Vol. 16 (1995), p.235.

[15] G. Beylkin, R. Coifman, V. Rokhlin: Communications on Pure and Applied Mathematics, Vol. 44 (1991), p.141.

[16] C. Canuto, A. Tabacco, K. Urban: Applied and Computational Harmonic Analysis, Vol. 6 (1999), p.1.

[17] C. Canuto, A. Tabacco, K. Urban: Applied and Computational Harmonic Analysis, Vol. 8 (2000) , p.123.

[18] J.X. Ma, J.J. Xue, S.J. Yang, Z.J. He: Finite Elements in Analysis and Design, Vol. 39 (2003) p.965.

[19] X.F. Chen, S.J. Yang, J.X. Ma, Z.J. He: Finite Elements in Analysis and Design, Vol. 40 (2004) p.541.

[20] I. Daubechies: Communications on Pure and Applied Mathematics, Vol. 41 (1988), p.909.

[21] P.F. Rizos，N. Aspragathos A.D. Dimarogonas: Journal of Sound and Vibration, Vol. 138 (1990), p.381.

[22] A.D. Dimarogonas: Engineering Fracture Mechanics, Vol. 55(1996), p.831.

[23] Byon, O., Nishi, Y: Key Engineering Materials, Vol. 141 (1998), p.55.

[24] J.N. Reddy: An introduction to the finite element method (McGraw-Hill Inc., New York, 1984).