원문정보
초록
영어
This paper is concerned with full vehicle nonlinear active suspension systems, in which each suspension unit consists of three components: a nonlinear spring, a nonlinear damper and a nonlinear hydraulic actuator. An artificial intelligence Neural Control technique has been presented in this paper to design a robust controller for full vehicle nonlinear active suspension systems. The advantage of this controller is that it can handle the nonlinearities faster than other conventional controllers. Neural controller are devised to adjust the hydraulic actuators forces to minimize the vertical displacement at each suspension point when travelling on rough roads and to reduce the inclination of the vehicle during sudden manoeuvres such as sharp bending and braking. The robustness of the proposed controller is being assessed by comparing with Fractional Order PIiDd (FOPID) controller. To validate the robustness of the proposed approach, the cases with six types of disturbances will be investigated. The results show that intelligent neural controller have improved dynamic response measured by a decreased cost function.
목차
1. Introduction
2. Mathematical Model of the Controlled System
I. Vertical motion
II. Pitching motion
III. Rolling motion
3. The structure of Neural Network:
4. Levenberg-Marquardt Training Algorithm
5. Design of the Neural Controller
6. Simulation and Results:
7. Conclusion
References