馈能悬架BP神经网络PID控制研究

BP neural network PID control of energy-regenerative suspension

为使主动悬架能回收振动能量,建立了二自由度电磁式馈能悬架系统模型,设计了基于BP神经网络算法的PID控制器,对电路执行PI控制,以调节主动控制力的实际输出,以悬架的车身加速度、悬架动行程和轮胎动位移作为车辆动力学性能的评价指标,以自供能效率、馈能效率分别作为悬架能量利用与回收的评价指标,利用MATLAB/Simulink软件进行仿真分析。结果表明,通过PI控制电路输出的主动控制力的实际值与理想值基本一致;基于BP神经网络PID控制的馈能悬架在不同输入条件下均能有效改善车辆性能;并且该系统能回收部分悬架振动能量,其中自供能效率稳定在约55%,馈能效率稳定在约16%。

In order to enable active suspension to recover vibration energy,a 2-DOF electromagnetic energy-regenerative suspension system model was established,a PID controller based on BP neural network algorithm was designed,and a PI control was performed on the circuit to adjust the actual output of the active control force.The body acceleration,the suspension working space and the tire dynamic deflection were used as the evaluation indexes of the vehicle dynamic performance.The self-supply energy efficiency and the energy-regenerative efficiency were respectively used as the evaluation indexes of the energy utilization and energy recovery of the suspension.The simulation analysis was carried out by using MATLAB/Simulink.The results show that the actual value of the active control force output by the PI control circuit is basically the same as the ideal value;the energy-regenerative suspension based on BP neural network PID control can effectively improve vehicle performance under different input conditions;and the system can recover part of the suspension vibration energy,where the self-supply energy efficiency is stable at about 55%and the energy-regenerative efficiency is stable at about 16%.