车辆悬架系统的神经网络控制算法

Neural Network Control Algorithm of Vehicle Suspension System

搭建了车辆的主动悬架系统再生网络模型,基于多层神经网络提出一种神经模糊适应性控制算法。在此基础上,使用一套模糊规则调节控制器参数,借助神经网络建模确定车辆悬架的动态参数向控制器提供学习信号。在一辆装有磁流变液减震器和基于处理器模糊神经控制系统的车辆上进行不同速度的实验,并把控制效果与开环被动悬架系统进行比较。实验结果证明,所提出的神经控制算法能够有效减轻汽车的振动。

The model of vehicle active suspension system was established,and a kind of neural fuzzy adaptive control algorithm was proposed.Based on the algorithm,a set of fuzzy rules was used to adjust the controller parameters,and the dynamic parameters of the suspension were determined through the neural network modeling,and the learning signals were provided to the controller.Finally,an experiment was carried out on a vehicle equipped with shock absorber and based on the fuzzy neural control system,and the control effect was compared with that of the open-loop passive suspension system.The results show that the neural control algorithm proposed in this paper can effectively reduce the vibration of the vehicle.