Abstract: Two important problems in the control of semi-active suspension which are the establishing of system model and the determination of control strategy are studied. The multi-body dynamic equations of the automobiles are deduced. After the study of applying fuzzy neural network method to the suspension control, the controller is designed. The GA algorithm is used to optimize the parameters and structure of the controller, and the DFGS algorithm is used to optimize weights of the network. Based on the simulation, the experiment is carried out. Both the simulation and experimental results show that the model and control strategy put forward can improve the performance of suspension noticeably.

Key words: Multibody dynamics, Control, Fuzzy neural network, Semi-active suspension