The Use of Neural Networks to Detect Damage in Sandwich Composites

  • David SerranoEmail author
  • Frederick A. Just-Agosto
  • Basir Shafiq
  • Andres Cecchini


Composite materials fail in complex failure modes that are difficult to detect. No single NDE technique is capable of detecting all damages. The ability to detect and asses the state of the damage is a key issue in order to improve service life of these materials. A Neural Network (NN) was chosen as a means to interpret and classify the information such that the type of damage, severity and location could be identified. The work describes the implementation of a NN based approach which combines thermal damage detection and vibration signatures in order to detect location and extent of damage in sandwich composites consisting of two carbon fiber/epoxy matrix face sheets laminated onto a urethane foam core. The approach analytically characterized and experimentally validated models for both thermal and vibration response. The numerical models were then used to train the neural networks. This approach is significant as it combines two techniques as opposed to just one as generally performed. Results demonstrated that the multi-component neural network approach successfully detected damage in scenarios in which using just a single method would have failed.


Mode Shape Thermal Image Damage Detection Face Sheet Ship Hull 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors wish to acknowledge the financial support of the ONR-Composites for Marine Structures Division. Special thanks are due to Dr. Yapa Rajapakse, ONR program manager for his guidance and support.


  1. 1.
    Balageas D, Bourasseau S, Dupont M, Bocherens E, Dewynter-Marty V, Ferdinand P (2000) Comparison between non-destructive evaluation techniques and integrated fiber optic health monitoring systems for composite sandwich structures. J Intel Mater Sys Struct 11:426–437.Google Scholar
  2. 2.
    Balageas D, Deom A, Boscher C (1987) Characterization of NDT of carbon epoxy composites by a pulsed photothermal method. Mater Eval 45(4):461–465.Google Scholar
  3. 3.
    Cecchini A (2005) Damage detection and identification in sandwich composites using neural networks. M.S. thesis, University of Puerto Rico, Mayaguez, Puerto Rico.Google Scholar
  4. 4.
    Doebling SW, Farrar CR, Prime MB, Shevitz DW (1996) Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics:a literature review. Los Alamos National Laboratory, LA-13070-MS, UC-900 41–49.Google Scholar
  5. 5.
    Pandey AK, Bisws M, Samman MM (1991) Damage detection from changes in curvature mode shapes. J Sound Vibrat 169(1):3–7.CrossRefGoogle Scholar
  6. 6.
    Plotnikov YA, Winfree William P (1988) Thermographic imaging of defects in anisotropic composites. QNDE 17A:457–464.Google Scholar
  7. 7.
    Ratcliffe CP, Bagaria WJ (1998) A vibration technique for locating delamination in a composite beam. AIAA J 36(6):1074–1077.CrossRefGoogle Scholar
  8. 8.
    Salawu OS, Williams C (1994) Damage location using vibration mode shapes. In:Proceedings of the 12th International Modal Analysis Conference, Honolulu, Hawaii, USA, pp. 933–939.Google Scholar
  9. 9.
    Allen HG (1969) Analysis and design of structural sandwich panels. Pergamon, Oxford/ New York.Google Scholar
  10. 10.
    Just F, Shafiq B, Jairo J, Serrano D (2004) Damage detection using transient temperature response. Int J Nat Disasters, Accidents, Civil Struct 3(3):129–141.Google Scholar
  11. 11.
    Kessler SS, Spearing SM, Atalla MJ, Cesnik CE (2001) Damage detection in composite materials using frequency response methods. Department of Aeronautics and Aeronautics, Massachusetts Institute of Technology, Cambridge, MA.Google Scholar
  12. 12.
    Kondo I, Hamamoto T (1994) Local damage detection of flexible offshore platforms using ambient vibrations measurements. In:Proceedings of the 4th International Offshore and Polar Engineering Conference, Osaka, Japan, vol. 4, pp. 400–407.Google Scholar
  13. 13.
    Maldague X (2000) Applications of infrared thermography and nondestructive evaluation. In:Rastogi P and Inaudi D (eds.), Trends in optical nondestructive testing, Elsevier Science Amsterdam, pp. 591–601.Google Scholar
  14. 14.
    Maldague X (2002) Introduction to NDT by active infrared thermography. Mater Eval 6(9):1060–1073.Google Scholar
  15. 15.
    Plotnikov YA, Winfree WP (1988) Advanced image processing for defect visualization in infrared thermography. NASA Langley Research Center, M.S. 231, Hamplton, VA 23681-0001.Google Scholar
  16. 16.
    Shilbayeh N, Iskandarani MZ (2004) Application of new feature extraction technique to PVT images of composite structures. Inform Technol J 3(3):332–336.CrossRefGoogle Scholar
  17. 17.
    Toro C, Shafiq B, Serrano D, Just F (2003) Application of neural networks to eigen-parameter based damage detection in multi-component sandwich ship hull structures. In:Sixth International Conference on Sandwich Structures, Fort.Lauderdale, FL, pp. 25–29.Google Scholar
  18. 18.
    Versteeg H, Malalasekera W (1995) An introduction to computational fluid dynamics the finite volume method. Pearson Prentice Hall, Malaysia.Google Scholar
  19. 19.
    Oosthuizen PH, Naylor D (1999) Introduction to convective heat transfer analysis. McGraw Hill, New York.Google Scholar
  20. 20.
    Quarteroni A, Sacco R, Saleri F (2000) Numerical mathematics. Texts in applied mathematics 37, Springer, New York.Google Scholar
  21. 21.
    Hou Z, Noori M, Amand RS (2000) Wavelet based approach for structural damage detection. J Eng Mech 126(7):677–683.CrossRefGoogle Scholar
  22. 22.
    Wu S, Ghaboussi J, Garret Jr JH (1992) Use of neural networks in detection of structural damage. Compos Struct 42(4):649–659.CrossRefGoogle Scholar
  23. 23.
    Zang C, Imregun M (2000) Combined neural network and reduced FRF techniques for slight damage detection using measured response data. Arch Appl Mech 71:525–536.CrossRefGoogle Scholar
  24. 24.
    Spanos PD, Rao VRS (2001) Random field representation in a biorthogonal wavelet basis. J Eng Mech ASCE 127(2):194–205.CrossRefGoogle Scholar
  25. 25.
    Liao SH (2004) Expert systems methodologies and applications, a decade review from 1995 to 2004. Expert Syst Appl 28:93–103.Google Scholar
  26. 26.
    Sawyer JP, Rao SS (2000) Structural damage detection and identification using fuzzy logic. AIAA J 38(12):2328–2335.CrossRefGoogle Scholar
  27. 27.
    Bishop CM (2004) Neural Networks for Pattern Recognition, Oxford University Press, New York.Google Scholar
  28. 28.
    Byon O, Ben G, Nishi Y (1988) Damage identification of CFRP laminated cantilever beam by using neural network. Key Eng Mater 141–143:55–64.Google Scholar
  29. 29.
    Masri SF, Chassiakos AG, Caughey TK (1992) Identification of nonlinear dynamic systems using neural networks. J Appl Mech Trans ASME 60:123–133.CrossRefGoogle Scholar
  30. 30.
    Sahin M, Shenoi RA (2003) Quantification and localization of damage in beam like structures by using artificial neural networks with experimental validation. Eng Struct 25:1785–1802.CrossRefGoogle Scholar
  31. 31.
    Sahin M, Shenoi RA (2003) Vibration based damage identification in beam like composite laminates by using artificial neural networks. J Mech Eng Sci 217 Part C:661–676.CrossRefGoogle Scholar
  32. 32.
    Zhao J, Ivan JN, DeWolf JT (1998) Structural damage detection using artificial neural networks. J Infr Syst 4(3):93–101.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2009

Authors and Affiliations

  • David Serrano
    • 1
    Email author
  • Frederick A. Just-Agosto
    • 1
  • Basir Shafiq
    • 1
  • Andres Cecchini
    • 1
  1. 1.College of EngineeringUniversity of Puerto RicoMayaguezUSA

Personalised recommendations