Multi-body Model Identification of Vehicle Semi-active Suspension Based on Genetic Neural Network

摘要：

　　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.

关键词： genetic neural networks identification semi-active suspension

作者: Jingjun Zhang Bingan Han RuiZen Gao

作者单位: Hebei University of Engineering, Handan, Hebei, 056038, China

会议类型: 国际会议

会议名称: the Second International Conference on Frontiers of Manufacturing and Design Science(第二届制造与设计科学国际会议(ICFMD 2011))

会议地点: 台湾

会议语种:英文

页码: 4069-4073

在线出版日期: 2011-12-11（万方平台首次上网日期，不代表论文的发表时间）