基于RBF神经网络滑模控制的车辆横向控制研究

Vehicle Lateral Control Based on RBF Neural Networks Sliding Mode Control

针对车辆横向控制系统中滑模控制器存在的抖振现象对转向机械结构带来的损耗问题,提出了一种基于RBF神经网络的滑模控制算法。利用RBF神经网络较强的自学习能力实时在线调节滑模控制器的切换项增益参数,增强系统的抗干扰能力与动态性能。将车辆实际参数代入仿真数学模型中,在Simulink仿真环境中进行对比仿真实验,仿真结果表明:该控制算法跟踪性能好,能够有效降低滑模控制器的抖振,满足车辆横向控制要求。

In order to solve the problem of the loss of the steering mechanism caused by the chattering phenomenon of the sliding mode controller in the vehicle lateral control system,a sliding mode control algorithm based on RBF neural network is proposed.By utilizing the strong self-learning ability of the RBF neural network,the switching term gain parameters of the sliding mode controller are adjusted online in real time,and the anti-interference ability and dynamic performance of the system are enhanced.The actual parameters of the vehicle are substituted into the simulation mathematical model,and the comparative simulation experiment is carried out in the simulink simulation environment.The simulation results show that the tracking performance of the control algorithm is good,which can effectively reduce the chattering of the sliding mode controller,and meet the requirements of vehicle lateral control.