Authors: Wan-Suk Yoo, Woon-Kyung Baek, Jeong-Hyun Sohn
Addresses: School of Mechanical Engineering, Pusan National University, Pusan, 609-735, South Korea. ' School of Mechanical Engineering, Pukyong National University, Pusan, 608-739, South Korea. ' School of Mechanical Engineering, Pukyong National University, Pusan, 608-739, South Korea
Abstract: In this article, a practical model for automotive bushing components is developed to improve the accuracy of the vehicle dynamic analysis. Bushing components of a vehicle suspension system are tested to capture the nonlinear and hysteretic behaviour of typical rubber bushing elements and the test results are used to develop a practical bushing model using an artificial neural network. A back propagation algorithm is then used to obtain the weighting factor of the neural network. Since the output for a dynamic system depends on the past histories of inputs and outputs, Narendra|s algorithm of ||NARMAX|| form is employed to consider these effects. A numerical example is carried out to demonstrate the developed bushing model.
Keywords: artificial neural networks; rubber bushing; suspension systems; vehicle dynamic analysis; automotive bushing components; bushing modelling.
International Journal of Vehicle Design, 2004 Vol.36 No.4, pp.345 - 364
Available online: 07 Dec 2004 *Full-text access for editors Access for subscribers Purchase this article Comment on this article