基于强化学习的混合动力汽车能量管理策略  

Energy Management Strategies for Hybrid Vehicles Based on Intensive Learning

作　　者：孔泽慧 刘港[1] 吴慧 Kong Zehui;Liu Gang;Wu Hui

机构地区：[1]广西机电职业技术学院,广西南宁市530000

出　　处：《时代汽车》2024年第3期19-21,共3页Auto Time

基　　金：广西高校中青年教师(科研)基础能力提升项目——基于机器学习的混合动力汽车预测能量管理策略研究项目资助(项目编号:2022KY1073)。

摘　　要：文章针对一串联式混合动力汽车,提出了一种基于强化学习的能量管理策略。首先为了便于分析,对该串联式混合动力汽车动力学模型进行简化,包括汽车功率需求模型、电池模型和发动机-发电机模型等。其次,基于强化学习算法,建立串联式混合动力汽车能量管理策略优化模型。最后,基于目标工况进行仿真分析,求解控制策略,获得燃油消耗。结果表明,基于强化学习的能量管理策略相比于基于规则的能量管理策略,其燃油经济性提升了12%。This paper proposes an energy management strategy based on intensive learning for a series hybrid electric vehicle.Firstly,to facilitate the analysis,the dynamics model of the series hybrid vehicle is simplified,including the vehicle power demand model,the battery model and the engine-generator model.Secondly,based on the strong intensive learning algorithm,an optimization model of energy management strategy for series hybrid vehicles was established.Finally,the simulation analysis is carried out based on the target working conditions,the control strategy is solved,and the fuel consumption is obtained.The results show that the fuel economy of the energy management strategy based on intensive learning is improved by 12%compared with the rule-based energy management strategy.

关 键 词：混合动力车辆 能量管理策略 强化学习 

分 类 号：U46[机械工程—车辆工程]