采用改进神经网络PID控制的车辆悬架振动仿真研究

为了研究车辆悬架振动模型,创建了车辆悬架平面简图,并根据牛顿定律推导出车辆悬架振动微分方程式。引用BP神经网络PID控制器,对传统粒子群算法进行改进,将改进粒子群算法用于优化BP神经网络PID可知结构。通过MATLAB软件中对车辆悬架位移、速度和加速度进行仿真验证;同时,与BP神经网络PID控制器仿真结果进行比较和分析。结果表明,车辆悬架采用BP神经网络PID控制器,悬架行程、轮胎位移和车身加速度均方根值较大,车辆整体振动幅度较大;而采用改进BP神经网络PID控制器,悬架行程、轮胎位移和车身加速度均方根值较小,车辆整体振动幅度较小。采用改进神经网络PID控制车辆悬架,能够抑制路面噪声激励对车辆振动幅度的影响,提高车辆行驶的安全性。

RESEARCH ON VEHICLE SUSPENSION VIBRATION SIMULATION USING IMPROVED NEURAL NETWORK PID CONTROL

In order to study the vibration model of vehicle suspension, the plane diagram of vehicle suspension was created, and the differential equation of vehicle suspension vibration was derived according to Newton''s law. BP neural network PID controller was used to improve the traditional particle swarm optimization algorithm. The improved particle swarm optimization algorithm was used to optimize the BP neural network PID knowable structure. The displacement, speed and acceleration of vehicle suspension were simulated and verified by MATLAB software. At the same time, the simulation results of the BP neural network PID controller were compared and analyzed. The results showed that the average square root of suspension travel, tire displacement and body acceleration were larger and the overall vibration amplitude of vehicle is larger when the BP neural network PID controller was used for vehicle suspension, while the average square root of suspension travel, tire displacement and body acceleration were smaller when the improved BP neural network PID controller was used, and the overall vibration amplitude of vehicle was smaller. Using improved neural network PID to control vehicle suspension can restrain the influence of road noise excitation on vehicle vibration amplitude and improve vehicle driving safety.