Research on adaptive control for automotive semi-active suspensions based on nonlinear neural networks

Based on the analysis of nonlinear characteristics of automotive suspension, the suspension model is built, the adaptive control strategy based on neural networks is put forward and the neural identifier and controller are designed. In order to improve the control effects, a compensating network is added to the control system. It can be used for the preview control of the rear suspension according to the road disturbances experienced by the front wheels. Simulation results show that adaptively controlled semi-active suspensions with nonlinear neural networks can achieve obvious vibration reducing effects, and the effects are even better for those with preview control of rear suspension. In order to check the simulation results, experiments are carried out on the test rig. The results of different road surfaces and vehicle speeds coincide with those of simulation quite well.