Multilayer Perceptron Training Optimization for High Speed Impacts Classification

  • Angel Garcia-Crespo
  • Belen Ruiz-Mezcua
  • Israel Gonzalez-Carrasco
  • Jose Luis Lopez-Cuadrado
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 39)

The construction of structures subjected to impact was traditionally carried out empirically, relying on real impact tests. The need for design tools to simulate this process triggered the development in recent years of a large number of models of different types. Taking into account the difficulties of these methods, poor precision and high computational cost, a neural network for the classification of the result of impacts on steel armours was designed. Furthermore, the numerical simulation method was used to obtain a set of input patterns to probe the capacity of themodel development. In the problem tackled with, the available data for the network designed include, the geometrical parameters of the solids involved — radius and length of the projectile, thickness of the steel armour — and the impact velocity, while the response of the system is the prediction about the plate perforation.

Keywords

Impacts Classification Multilayer Perceptron Optimization neural network simulation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    K. Swingler. Applying Neural Networks: A Practical Guide. Morgan Kaufmann, San Francisco, CA 1996.Google Scholar
  2. 2.
    Z. Waszczyszyn and L. Ziemianski. Neural networks in mechanics of structures and materials. New results and prospects of applications. Computers & Structures, 79 IS-22-25:2261 EP-2276, 2001.Google Scholar
  3. 3.
    R. Ince. Prediction of fracture parameters of concrete by artificial neural networks. Engineering Fracture Mechanics, 71(15):2143–2159, 2004.CrossRefGoogle Scholar
  4. 4.
    S.W. Liu, J.H. Huang, J.C. Sung, and C.C. Lee. Detection of cracks using neural networks and computational mechanics. Computer methods in applied mechanics and engineering (Comput. methods appl. mech. eng.), 191(25–26):2831–2845, 2002.MATHCrossRefGoogle Scholar
  5. 5.
    W. Carpenter and J. Barthelemy. A comparison of polynomial approximations and artificial neural nets as response surfaces. Structural and multidisciplinary optimization, 5(3):166, 1993.Google Scholar
  6. 6.
    P. Hajela and E. Lee. Topological optimization of rotorcraft subfloor structures for crash worthiness consideration. Computers and Structures, 64:65–76, 1997.MATHCrossRefGoogle Scholar
  7. 7.
    L. Lanzi, C. Bisagni, and S. Ricci. Neural network systems to reproduce crash behavior of structural components. Computers structures, 82(1):93, 2004.CrossRefGoogle Scholar
  8. 8.
    A. Garcia, B. Ruiz, D. Fernandez, and R. Zaera. Prediction of the response under impact of steel armours using a multilayer perceptron. Neural Computing & Applications, 2006.Google Scholar
  9. 9.
    C. Bishop. Neural Networks for Pattern Recognition. Oxford University Press, USA, 1996.MATHGoogle Scholar
  10. 10.
    G. Cybenko. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, 2:303–314, 1989.MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    K. Hornik and M. Stinchcombe. Multilayer feedforward networks are universal approxima-tors. Neural Networks, 2(5):359–366, 1989.CrossRefGoogle Scholar
  12. 12.
    R. Lippmann. An introduction to computing with neural nets. ASSP Magazine, IEEE [see also IEEE Signal Processing Magazine], 4(2):4–22, 1987.Google Scholar
  13. 13.
    P. Isasi and I. Galvan. Redes de neuronas artificiales: un enfoque practico. Pearson Prentice Hall, Madrid, 2004.Google Scholar
  14. 14.
    L. Tarassenko. A guide to neural computing applications. Arnol/NCAF, 1998.Google Scholar
  15. 15.
    B. Widrow. 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proceedings of the IEEE 78, 9:1415–1442, 1990.CrossRefGoogle Scholar
  16. 16.
    USA. ABAQUS Inc., Richmond. Abaqus/explicit v6.4 users manual, 2003.Google Scholar
  17. 17.
    M. Gevrey, I. Dimopoulos, and S. Lek. Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecological Modelling, 160(16):249–264, 2003.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V 2009

Authors and Affiliations

  • Angel Garcia-Crespo
    • 1
  • Belen Ruiz-Mezcua
    • 1
  • Israel Gonzalez-Carrasco
    • 1
  • Jose Luis Lopez-Cuadrado
    • 1
  1. 1.Department of Computer ScienceUniversidad Carlos IIILeganesSpain

Personalised recommendations