混合动力重卡自适应等效燃油消耗最小化能量管理策略

Adaptive Equivalent Consumption Minimization Energy Management Strategy for Hybrid Heavy Trucks

为解决等效燃油消耗最小化策略的关键参数在不同工况下的动态调整,提出一种适用于混合动力重型汽车的自适应等效燃油消耗最小化策略(adaptive equivalent consumption minimization strategy,A-ECMS)。该策略以层次聚类算法得到的6种典型行驶工况为例,提出了一种基于神经网络工况识别算法。应用改进的混沌粒子群优化(chaosparticle swarm optimization,CPSO)算法优化特定驾驶循环下等效燃油消耗最小化策略(equivalent consumption minimization strategy,ECMS)的3个关键参数:等效因子、惩罚函数的比例因子和发动机起动车速阈值。提出了一种基于工况识别的新型自适应能量管理策略对关键参数进行优化,根据该重型卡车的传动系统构型,建立了车辆的纵向动力学模型,并通过仿真进行了验证。仿真结果表明复合工况驱动循环下的CPSO-ECMS和A-ECMS控制策略与传统等效燃油消耗策略相比,油耗分别降低了5.9%和8.9%。

In order to solve the dynamic adjustment of key parameters of equivalent fuel consumption minimization strategy under different working conditions,an adaptive equivalent consumption minimization strategy(A-ECMS)suitable for hybrid heavy vehicles was proposed.Taking six typical driving conditions obtained by hierarchical clustering algorithm as an example,a condition recognition algorithm based on neural network was proposed.The improved chaos particle swarm optimization(CPSO)was applied to optimize three key parameters of equivalent consumption minimization strategy(ECMS),the scale factor of penalty function and the threshold of engine starting speed under a specific driving cycle.Based on the above two aspects,a new adaptive energy management strategy based on condition identification was proposed to optimize the key parameters.According to the transmission system configuration of the heavy truck,the longitudinal dynamics model of the vehicle was established and verified by simulation.The simulation results show that compared with the traditional equivalent fuel consumption strategy,the fuel consumption of CPSO-ECMS and A-ECMS control strategies under composite driving cycles was reduced by 5.9%and 8.9%respectively.