An advanced recurrent artificial neural network (ANN) is used to store the nonlinear dynamic characteristics of the vehicle structure. Hundreds of impact scenarios can be performed quickly with much less cost by using the trained networks. A finite element model for a simple box beam with rigid mass attached to it was developed to represent a general crushable object. The simulation results were performed by impacting this model into a rigid wall with different initial velocities. The results indicated that the recurrent ANN can accurately capture the frontal crash characteristics of any impacting structure, and predict the crash performance of the same structure for any other crash scenario within the training limits.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen


    Exportieren, teilen und zitieren



    Titel :

    Recurrent artificial neural networks for crashworthiness analysis


    Beteiligte:
    Omar, T.A. (Autor:in) / Bedewi, N.E. (Autor:in) / Eskandarian, A. (Autor:in)


    Erscheinungsdatum :

    1997


    Format / Umfang :

    10 Seiten, 9 Quellen


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Recurrent Artificial Neural Networks for Crashworthiness Analysis

    Omar, T. A. / Bedewi, N. E. / Eskandarian, A. et al. | British Library Conference Proceedings | 1997


    Modeling Vehicles' Offset Impacts Using Recurrent Artificial Neural Networks

    Omar, T. A. / Eskandarian, A. / Bedewi, N. E. et al. | British Library Conference Proceedings | 2000


    Crashworthiness

    Online Contents | 1999



    Crashworthiness

    Giavotto, V. / Dan Knassim | British Library Conference Proceedings | 1999