Abstract
The artificial neural network is a newly developed technique for the identification and modeling of linear and nonlinear dynamic systems through the use of measured experimental data. In this paper, a neural network approach for the structural dynamic response prediction is presented and applied to an elastic and perfectly elasto-plastic system with a single degree of freedom. A three-layer backpropagation neural network is chosen as the neural network to predict the response at the next time step as an output with the input earthquake records and the corresponding responses at the past few time steps as inputs to the neural network. The application examples show the great promise of using the neural network in structural dynamic response prediction.
