Journal of Optimization Theory and Applications

, Volume 76, Issue 2, pp 207–223 | Cite as

Associative memory approach to the identification of structural and mechanical systems

  • R. E. Kalaba
  • F. E. Udwadia
Contributed Papers


This paper presents a new method for identification of parameters in nonlinear structural and mechanical systems in which the initial guesses of the unknown parameter vectors may be far from their true values. The method uses notions from the field of artificial neural nets and, using an initial set of training parameter vectors, generates in an adaptive fashion other relevant training vectors to yield identification of the parameter vector in a recursive fashion. The simplicity and power of the technique are illustrated by considering three highly nonlinear systems. It is shown that the technique presented here yields excellent estimates with only a limited amount of response data, even when each element of the set comprising the initial training parameter vectors is far from its true value—in fact, sufficiently far that the usual recursive identification schemes fail to converge.

Key Words

Parameter identification nonlinear mechanical and structural systems associative memory adaptive training recursive memory matrix 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rodriguez, G., Editor,Proceedings of the Workshop on Identification and Control of Flexible Structures, Vols. 1 and 2, Publication 85-29, Jet Propulsion Laboratory, 1985.Google Scholar
  2. 2.
    Kalaba, R. E., andSpringarn, K.,Control, Identification, and Input Optimization, Plenum, New York, New York, 1982.Google Scholar
  3. 3.
    Ljung, L.,System Identification: Theory for the User, McGraw Hill, New York, New York, 1988.Google Scholar
  4. 4.
    Ljung, L., andSoderstrom, T.,Theory and Practice of Recursive Identification, MIT Press, Cambridge, Massachusetts, 1983.Google Scholar
  5. 5.
    Udwadia, F. E., Garba, J., andGhodsi, A.,Parameter Identification Problems in Structural and Geotechnical Engineering, Journal of Engineering Mechanics, Vol. 110, pp. 1409–1432, 1984.Google Scholar
  6. 6.
    Udwadia, F. E., andSharma, D. K.,Some Uniqueness Problems in the Identification of Building Structural Systems, SIAM Journal on Applied Mathematics, Vol. 34, pp. 104–118, 1978.Google Scholar
  7. 7.
    Kosko, B.,Bidirectional Associative Memories, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 18, pp. 49–60, 1988.Google Scholar
  8. 8.
    Kohonen, T.,Self-Organization and Associative Memory, Springer-Verlag, New York, New York, 1988.Google Scholar
  9. 9.
    Rumelhart, D., andMcClelland, J., Editors,Parallel Distributed Processing: Exploration in the Microstructure of Cognition, Vols. 1 and 2, MIT Press, Cambridge, Massachusetts, 1988.Google Scholar
  10. 10.
    Rehak, D., Thewalt, C. R., andDoo, L. B.,Neutral Network Approaches in Structural Mechanics Confrontations, Proceedings of ASCE Structures Congress, pp. 168–176, 1989.Google Scholar
  11. 11.
    Kalaba, R. E., andUdwadia, F. E.,An Adaptive Learning Approach to the Identification of Structural and Mechanical Systems, International Journal of Computers and Mathematics with Applications, Vol. 22, pp. 67–75, 1990.Google Scholar

Copyright information

© Plenum Publishing Corporation 1993

Authors and Affiliations

  • R. E. Kalaba
    • 1
  • F. E. Udwadia
    • 2
  1. 1.Economics, and Electrical EngineeringUniversity of Southern CaliforniaLos Angeles
  2. 2.Decision Systems, and Mechanical EngineeringUniversity of Southern CaliforniaLos Angeles

Personalised recommendations