This paper investigates the variation of vertical vibrations of vehicles using a neural network (NN). The NN is a back propagation\r\nNN, which is employed to predict the amplitude of acceleration for different road conditions such as concrete, waved stone block\r\npaved, and country roads. In this paper, four supervised functions, namely, newff, newcf, newelm, and newfftd, have been used for\r\nmodeling the vehicle vibrations.Thenetworks have four inputs of velocity (V), damping ratio (?),natural frequency of vehicle shock\r\nabsorber (Wn), and road condition (R.C) as the independent variables and one output of acceleration amplitude (AA). Numerical\r\ndata, employed for training the networks and capabilities of the models in predicting the vehicle vibrations, have been verified.\r\nSome training algorithms are used for creating the network. The results show that the Levenberg-Marquardt training algorithm\r\nand newelm function are better than other training algorithms and functions. This method is conceptually straightforward, and it\r\nis also applicable to other type vehicles for practical purposes.
Loading....