基于动态规划与RBF神经网络的PHEV能量管理策略

PHEV Energy Management Strategy Based on Dynamic Programming and RBF Neural Network

为提高插电式混合动力汽车燃油经济性,设计了一种基于动态规划和径向基函数(RBF)神经网络的插电式混合动力汽车能量管理策略。首先,建立了插电式混合汽车数学模型;其次,以发动机油耗最小为目标函数,采用动态规划求解全局最优的离线优化结果;最后,采用RBF神经网络对离线最优控制结果进行学习,建立了发动机输出转矩与车辆状态参数之间的非线性映射关系,得到了基于动态规划和RBF神经网络的能量管理策略。仿真结果表明,文章所提策略油耗较之于电量消耗-维持策略降低了2.92%,验证了该策略的有效性。

To improve the fuel economy of plug-in hybrid electric vehicles,an energy management strategy for plug-in hybrid electric vehicles based on dynamic programming and radial basis function(RBF)neural network is designed.First,a mathematical model of a plug-in hybrid vehicle is established.Secondly,with the minimum engine fuel consumption as the objective function,dynamic programming is used to solve the global optimal offline optimization results.Finally,RBF neural network is used to learn the offline optimal control results,and a nonlinear mapping relationship between engine output torque and vehicle state parameters is established,and an energy management strategy based on dynamic programming and RBF neural network is obtained.The simulation results show that the fuel consumption of the energy management strategy proposed in this article is reduced by 2.92%compared with the power consumption-power maintenance strategy,which verifies the effectiveness of the strategy.