L' application des reseaux neuronaux artificiels pour I 'identification et Ia detection de I' endommagement dans les ponts
Keywords:
back propagation, dynamic, finite elements, identification, neural networks, structuralAbstract
This paper presents the development of an automatic monitoring method for the detection of structural damage. In this f easibility study, we have explored the use of selforganisation of artificial neural networks in strucwral damage assessment combined with the finite element method. The basic strategy is to train the network to recognise the behaviour of the structure with various possible damage states. When the trained network is subjected to the measurements of the structural response, it should be able to detect any existing damage. Three examples are examined and the results are promising.
Downloads
References
[AKO 97] AKOUSSAH E., FAFARD M., TALBOT M., BEAULIEU D. (1997). "Etude parametrique
du facteur d'amplification dynamique des charges pour les ponts a travce simple en beton
anne". Revue canadienne de genie civil, Vol. 24(2), pp.313-322.
(BAR 95) BARAt S. V., PANDEY P. C. (1995). "Vibration Signature Analysis Using Artificicl
Neural Networks", ASCE, J. ofComp. Civil Engng. 9, 259-265.
[BOU 96] BOUDJELAL M.T., FAFARD M. & GAKWAYA A. (1996). "Modelling of Damping
and its Applications to Dynamic Bridge-Vehicle Interaction", Proceedings of 3rd
-uropean Conference on Structural Dynamics (EURODYN), Ed. by G. Augusti et al.
(Publi hed by Balkema, Rotterdam), Florence, Italic, 5-8 Juin, pp 767-774.
[BOU 97] BOUDJELAL M.T., FAFARD M., GAKWAYA A. (1997). "Modclisation de
l'amortissement par une approche thcrmodynamique et son application a !'interaction
dynamique pont-vehicules", Rapport GCS-97-10, GIREF ct Dcp. de Genie civi l,
Univcrsite Laval, Quebec.
[FAF 97] FAFARD M., BOUDJELAL M.T. ( 1997). "Modelisation de l'amortissement dans les
structures". Actes du troisieme colloque national en calcul des structures, 20-23 mai,
Giens, France, Pres es Academiqucs de !'ouest, Vol. I, pp. 11 3- 11 8.
[FAF 98) FAFARD M., LAFLAMME M., SAVARD M., BENNUR M. ( 1998). "Dynamic analysis of
an existing continuous bridge", ASCE, J. of Bridge Eng. (in press).
(IIAJ 91 J HAJELA P., BERKE L. ( 1991 ). "Neurobiological Computational Models in Structural
Analysis and Design", omp. & Slru cl., Vol. 41(4), 657-667.
[liEN 95] II ENCHI K. (1995). "Analyse dynamique des ponts par elements finis sous Ia
sollicitation des vehicules mobiles", These de doctoral, Universitc de Technologic de
ompiegne, France.
[liEN 96] HENCIIt K., FAFARD M. (1996). "Identification parametrique des ponts en
comportements statique et dynamique avec !'utili ation des rcseaux ncuronaux artificiels",
Rapport GCS-96-07, Dcp. de Genie civi l. Universite Laval, Quebec.
[HEN 97a] HENCHI K., DHATT G., TALBOT M., FAFARD M. (1997). "Dynamic Behaviour of
Multi-span Beams Under Moving Loads", Journal of Sound and Vibralion., Vol. 199( I),
pp. 33-50.-
-IEN 97b) HENCH! K., FAFARD M., TALBOT M., LANGIS D. (1997). "L'application des
rcseaux neuronaux artificiels pour !'identification et Ia detection de l'endommagement
dans les ponts" . Actes du troisieme colloque national en calcul des structures, 20-23 mai,
Giens, France, Presses Academiques de !'Ouest, Vol. II, pp. 831-836.
[LAN 97) LANGIS D., FAFARD M., HENCHI K. (1997).':1dentification structural et reseaux
neuromimetiques : calibration de modeles elements finis", Rapport GCS-97-09, G1REF et
Dcp. de Genie civil, Universitc Laval, Quebec.
[LIP 87] LIPPMANN R. P. (1987). "An introduction to computing with neural nets", IEEE
ASSP Magazine, 4-22, avril.
