IDENTIFICATION OF STRUCTURAL SYSTEMS BY NEURAL NETWORKS

A method based on the use of neural networks is developed for the iden tification of systems encountered in the field of structural dynamics. The methodology is applied to the identification of linear and nonlin ear dynamic systems such as the damped Duffing oscillator and the Van der Pol equation. The ''generalization'' ability of the neural network s is used to predict the response of the identified systems under dete rministic and stochastic excitations. It is shown that neural networks provide high fidelity models of unknown structural dynamic systems, w hich are used in applications such as structural control, health monit oring of structures, earthquake engineering, etc.