Vehicle crash modelling using recurrent neural networks

The initial velocity and structural characteristics of any vehicle are the main factors affecting the vehicle response in case of frontal impact. Fini te Element (FE) simulations are essential tools for crashworthiness analysi s, however, the FE models are getting bigger, which increases the simulatio n time and cost. In the current research, an advanced Artificial Neural Net work (ANN) was used to store the nonlinear dynamic characteristics of the v ehicle structure. Therefore, several impact scenarios can be analyzed quick ly with much less computational cost by using the trained networks. The equ ation of motion of the dynamic system was used to define the inputs and out puts of the ANN. The system dynamics was included in the network performanc e and the recurrent back-propagation learning rule was adapted in training the network. The results of the numerical examples indicated that the recurrent ANN can accurately capture the frontal crash characteristics of the impacting struc tures, and predict the crash performance of the same structures for any oth er crash scenario within the training limits. (C) 1998 Elsevier Science Ltd . All rights reserved.