Journal of Failure Analysis and Prevention

, Volume 16, Issue 2, pp 225–234 | Cite as

Predicting Failure Strength of Randomly Oriented Short Glass Fiber-Epoxy Composite Specimen by Artificial Neural Network Using Acoustic Emission Parameters

Technical Article---Peer-Reviewed
  • 100 Downloads

Abstract

Acoustic emission (AE) peak amplitude and cumulative energy emitted during 50% of failure of composite specimen was collected, analyzed, and utilized to predict the ultimate tensile strength (UTS) using artificial neural network (ANN) and the performance of various training algorithm on prediction was analyzed. AE data have been collected from finite numbers of randomly oriented short glass fiber-epoxy tensile specimens, while loading up to failure in a tensile testing machine. AE response from each of the specimen was classified and segregated by understanding the failure mechanism. A feed forward back-propagation type ANN was designed and the segregated data of amplitude hits and cumulative energy was processed using two separate networks to predict the UTS of corresponding specimens using it with appropriate parameters and the results were analyzed.

Keywords

Acoustic emission Prediction Artificial neural network Tensile strength 

References

  1. 1.
    M.E. Fisher, E.K. Hill, Neural network burst pressure prediction in fiber glass epoxy pressure vessels using acoustic emission. Mater. Eval. 56, 1395–1401 (1998)Google Scholar
  2. 2.
    E.K. Hill, J.L. Walker, G.H. Rowell, Burst Pressure prediction in graphite/epoxy pressure vessels using neural networks and acoustics emission amplitude data. Mater. Eval. 54(6), 744–748 (1996)Google Scholar
  3. 3.
    American society for testing materials, ASTM E1316, standard terminology for nondestructive examinations, in Annual book of ASTM standards, nondestructive testing, vol. 03. (ASTM, Philadelphia)Google Scholar
  4. 4.
    N. Ativitavas, T. Pothisiri, T.J. Fowler, Identification of fiber reinforced plastics failure mechanisms from acoustic emission data using neural networks. J. Compos. Mater. 40(3), 193–226 (2006)CrossRefGoogle Scholar
  5. 5.
    E.K. Hill, P.L. Isreal, G.L. Knotts, Neural network prediction of aluminum–lithium weld strength from acoustic emission amplitude data. Mater. Eval. 51(9), 1040–1045 (1993)Google Scholar
  6. 6.
    J.L. Walker, E.K. Hill, Back propagation neural network for predicting ultimate strength of unidirectional graphite/epoxy tensile specimens. Adv. Perform. Mater. 3, 75–83 (1996)CrossRefGoogle Scholar
  7. 7.
    A.N. Kolmogorov. On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition, in D. Akademii, (ed). USSR, 1957, p. 679–81Google Scholar
  8. 8.
    R. Hecht-nielsen. Kolmogorov’s mapping neural network existence theorm, in International Conference on Neural Networks, (IEEE Press, San Diego, 1987), p. 11–14Google Scholar
  9. 9.
    D.A. Spreecher, A universal mapping for Kolmogorov’s superposition therorem. Neural Netw. 6, 1084–1094 (1993)CrossRefGoogle Scholar
  10. 10.
    F. Laurence. Fundamentals of Neural Networks: Architectures, Algorithms and Applications. (Prentice Hall, Inc., Upper Saddle River, 1994), p. 461, 328–30Google Scholar
  11. 11.
    J.R. Wadim, Acoustic Emission Applications (Dunegan, San Juan Capistrano, 1978)Google Scholar
  12. 12.
    O. Ceysson, M. Salvia, L. Vincent, Damage mechanisms characterisation of carbon fibre/epoxy composite laminates by both electrical resistance measurements and acoustic emission analysis. Scripta Mater. 34(8), 1273–1280 (1996)CrossRefGoogle Scholar
  13. 13.
    O. Chen, P. Karandikar, N. Takeda, T. Kishi Rcast, Acoustic emission characterization of a glass-matrix composite. Nondestruct Test Eval. 8(1), 869–878 (1992)CrossRefGoogle Scholar
  14. 14.
    G. Kotsikos, J.T. Evans, A.G. Gibson, J. Hale, Use of acoustic emission to characterize corrosion fatigue damage accumulation in glass fibre reinforced polyester laminates. Polym. Compos. 20(5), 689–696 (1999)CrossRefGoogle Scholar
  15. 15.
    S.T. Kim, Y.T. Lee, Characteristics of damage and fracture process of carbon fiber reinforced plastic under loading-unloading test by using AE method. Mater. Sci. Eng. 234, 322–326 (1997)CrossRefGoogle Scholar
  16. 16.
    X.L. Gong, A. Laksimi, M.L. Benzeghagh, Nouvelle approche de l’émission acoustique et son application à l’identification des mécanismes d’endommagement dans les matériaux composites. Revue des composites et des matériaux avancés 8(1), 179–205 (1998)Google Scholar
  17. 17.
    W.H. Prosser et al., Advanced wave from based A6 detection of matrix crazing in composites. Mater. Eval. 53(9), 1052–1058 (1995)Google Scholar
  18. 18.
    N.F. Hubele, H.B. Hwarng, A neural network model and multiple linear regression, in Intelligent Engineering Systems Through Artificial Neural Networks, vol. 2, ed. by C.H. Dagli, B.R. Fernandez, J. Ghosh, R.T.S. Kumara (ASME, New York, 1994), pp. 199–203Google Scholar

Copyright information

© ASM International 2016

Authors and Affiliations

  1. 1.Department of Mechanical EngineeringAalim Muhammed Salegh College of EngineeringChennaiIndia

Personalised recommendations