Artificial neural network based multi-parameter inversion for the characterization of transversely isotropic composite lamina using velocity measurements of Lamb waves
Restricted accessResearch articleFirst published online March, 2012
Artificial neural network based multi-parameter inversion for the characterization of transversely isotropic composite lamina using velocity measurements of Lamb waves
Artificial neural network (ANN) based multi-parameter inversion method is proposed to characterize transversely isotropic composite lamina using Lamb wave group velocity measurements. The ANN is first trained using numerical simulations and known micromechanics based formulae before being deployed on experimental samples. The group velocities obtained from the experiments were fed to the trained network. The network so trained, predicted the elastic properties, fiber volume fraction, and density.
AdamsRD. Damping properties analysis of composites. In: ReinhartTJHalbertHF (eds). Engineered materials hand book1987; Vol 1: Composites. Materials Park, OH: ASM International, 206–217.
2.
Annual Book of ASTM standards 2004, Section 15, General products, chemical specialties and end use products, Volume: 15.03, D 3039/D 3039M, 2004.
3.
ANSYS Inc. User’s manual R11. Pittsburgh, PA: ANSYS Inc 2007.
4.
AutarKK. Mechanics of composite materials, CRC press, 1997.
5.
BalasubramaniamKRaoNS. Inversion of composite materials elastic constants from ultrasonic bulk wave phase velocity data using genetic algorithms. Composites Part B1998; 29: 1710–180.
6.
BalasubramaniamKWhitneySC. Ultrasonic through-transmission characterization of thick fiber-reinforced composites. NDT & E Int1996; 29: 225–236.
7.
BishopC. Neural networks for pattern recognition, Oxford University Press, 1995.
8.
Demuth H and Beale M. Neural network toolbox user’s guide version 4, for use with MATLAB 5.2-5.73.
9.
GibsonRF. Principles of composite materials mechanics, Mc Graw Hill International Edition, 1994.
10.
Halphin JC and Tsai SW. Effect of environment factors on composite materials. Air force technical report, AFML–TR–67–423.
11.
Hashin Z. Experimental data from Hashin Z. NASA technical report contract no. NAS1-8818, 1970.
12.
HenryLeeKrisNeville. Hand book of epoxy resins, McGraw Hill Book Company, 1967.
13.
JonesRM. Mechanics of composite materials, New York: Hemisphere publications, 1975.
14.
KarimMRMalAKBar-CohenY. Inversion of leaky Lamb wave data by simplex algorithm. J. Acoust. Soc. Am1990; 88(1): 482–491.
15.
KesavanADeivasigamaniMJohnSHerszbergI. Damage detection in T – joint composite structures. Compos Struct2006; 75: 313–320.
16.
KimYYKapaniaRK. Neural networks for inverse problems in damage identification and optical imaging. AIAA J2003; 41(4): 732–740.
NayfehAH. Wave propagation in layered anisotropic media with applications to composites. Elsevier publications, Amsterdam, 1995.
20.
Prasad MahadevSBalasubramaniamKKrishnamurthyCV. Structural health monitoring of composite structures using Lamb wave tomography. Smart Mater Struct2004; 13: N73–N79.
21.
RajagopalanJBalasubramaniamKKrishnamurthyCV. A phase reconstruction algorithm for Lamb wave based structural health monitoring of anisotropic multilayered composite plates. J Acoust Soc Am2006; 119: 872–878.
22.
RaoNS. Inverse problems in ultrasonic non-destructive characterization of composite materials using genetic algorithm, MS thesis, Mississippi State University, 1997.
23.
RogersWP. Elastic property measurement using Rayleigh-Lamb waves. J Res Non-destruct Eval1995; 6: 185–208.
24.
RokhlinSIWangW. Double through-transmission bulk wave method for ultrasonic phase velocity measurement and determination of elastic constants of composite materials. J Acoust Soc Am1992; 91: 3303–3312.
25.
RoseJL. Ultrasonic waves in solid media, 1st edition. Cambridge University Press, 1999.
26.
SealeDMSmithTBProsserWHZalamedaNJ. Lamb wave assessment of fiber volume fraction in composites. J Acoust Soc Am1998; 104(3): 1399–1403.
27.
SimonH. Neural networks: a comprehensive foundation, 2nd edition. Pearson Prentice Hall publications, 1998.
VishnuvardhanJKrishnamurthyCVKrishnanB. Genetic algorithm based reconstruction of the elastic moduli of orthotropic plates using an ultrasonic guided wave single-transmitter-multiple-receiver SHM array. Smart Mater Struct2007; 16: 1639–1650.
30.
WuXGhaboussiJGarrettJH. Use of Neural Networks in Detection of Structural Damage. Comput Struct1992; 42(4): 649–659.
