Multi-Body Model Identification of Vehicle Semi-Active Suspension Based on Genetic Neural Network

Abstract:

Article Preview

A multi-body vehicle dynamics model was established using ADAMS and a multilayer feed forward neural network of series parallel structure was built by Matlab in this study. The weights and threshold of neural networks which has built was optimizes by GA. This method was used in identifying multi-body vehicle dynamics model. The results show that the maximum error of identification is less than 0.05% and the network convergence rapidly. The designed genetic neural network could replace the vehicle semi-active suspension systems using in neural network adaptive control which can avoid the difficulty of establishing accurately mathematical model and the poor effective of traditional identification methods for the vehicle semi-active suspension.

Info:

Periodical:

Edited by:

Dongye Sun, Wen-Pei Sung and Ran Chen

Pages:

4069-4073

DOI:

10.4028/www.scientific.net/AMM.121-126.4069

Citation:

J. J. Zhang et al., "Multi-Body Model Identification of Vehicle Semi-Active Suspension Based on Genetic Neural Network", Applied Mechanics and Materials, Vols. 121-126, pp. 4069-4073, 2012

Online since:

October 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.