Inverse Identification of Elastic Constants of Orthotropic Plates Using the Dispersion of Guided Waves and Artical Neural Network

Abstract:

Using guided wave dispersion characteristics, a procedure based on articial neural network (ANN) is presented to inversely determine the elastic constants of orthotropic plate. The Legendre polynomial method is employed as the forward solver to calculate the dispersion curves of SH wave for orthotropic plates. The group velocities of lowest modes at five lower frequencies are used as the inputs for the ANN model. The outputs of the ANN are the elastic constants of orthotropic plates. This procedure is examined for an actual orthotropic plate. The results indicate that the identified elastic constants are sufficiently close to the original one. The developed inverse procedure is concluded to be robust and efficient.

• Periodical: Applied Mechanics and Materials (Volume 163)
• Pages: 151-154
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.163.151
• Online since: April 2012
• Authors: Xiao Ming Zhang, Yu Qing Wang, Jun Cai Ding
• Keywords: Dispersion, Elastic Constants, Legendre Polynomial, Neural Network (NN), Orthotropic Plates

References

[1] X. Han, C. Jiang, G.Y. Li, Z.H. Zhong, and D.B. Hu, An inversion procedure for determination of variable binder force in U-shaped forming, Inverse Prob. Sci. Eng. 14 (2006), p.301–312.

DOI: 10.1080/17415970500485161

[2] L.F. Han, G.Y. Li, X. Han, and Z.H. Zhong, Identification of geometric parameters of drawbead in metal forming processes, Inverse Prob. Sci. Eng. 14 (2006), p.233–244.

DOI: 10.1080/17415970500397101

[3] Han X, Liu GR, Lam KY. A quadratic layer element for analyzing stress waves in FGMs and its application in material characterization. J Sound Vib 2000; 236(2): p.307–321.

DOI: 10.1006/jsvi.2000.2966

[4] Liu GR, Han X, Xu YG, Lam KY. Material characterization of functionally graded material by means of elastic waves and a progressive-learning neural network. Compos Sci Technol 2001; 61(10): p.1401–1411.

DOI: 10.1016/s0266-3538(01)00033-1

[5] Han X, Xu D, Liu GR. A computational inverse technique for material characterization of a functionally graded cylinder using a progressive neural network. Neurocomputing 2003; 51: p.341–360.

DOI: 10.1016/s0925-2312(02)00578-7

[6] Liu GR, Han X, Lam KY. A combined genetic algorithm and nonlinear least square method for material characterization using elastic waves. Comput Methods Appl Mech Eng 2002; 191: p.1909–(1921).

DOI: 10.1016/s0045-7825(01)00359-0

[7] Qian HC, Xia BC, Li SZ, Wang FG. Fuzzy neural network modeling of material properties. J Mater Process Technol 2002; 122(2–3): p.196–200.

[8] B Wu, J.G. Yu and C.F. He. Guided circumferential waves in functionally graded cylinders. Explos Shock Waves 2007; 27(3): p.266–271 (in Chinese).