The prediction of vibration and noise for the high-speed train based on neural network and boundary element method

The vibration acceleration of the high-speed train is an important parameter reflecting the state of track irregularities and the quality of contact between wheel and rail. A model for predicting vibration acceleration of the high-speed train based on nonlinear auto-associative neural network (NARX NN) and multi-body dynamics model is built. In order to improve the prediction precision, the parameters such as the order of time-delay and hidden nodes are determined by traversal method. The vibration acceleration computed by the NN model is then compared with that computed by SIMPACK model. The corresponding results show that the output of NARX NN is highly consistent with those of the multi-body dynamics model. Then, the vibration acceleration computed by NN model is used to compute the low frequency noise of the high-speed train. The computational results are also compared with those of the experimental values, and they are consistent with each other. It shows that the computational noises are reliable, and it also indirectly indicates that the vibration acceleration predicted by NN model is credible. Otherwise, the computational results will deviate far away from the experimental value.