双行星排混合动力客车动态规划能量管理策略研究  

Research on Energy Management Strategy for Dual-Planetary Hybrid Electric Bus Based on Dynamic Programming

作　　者：王坤羽 杨蓉[1] 张松[2] 黄伟[1] WANG Kun-yu;YANG Rong;ZHANG Song;HANG Wei(School of Mechanical Engineering,Guangxi University,Guangxi Nanning 530004,China;Guangxi Yuchai Machinery Co.,Ltd.,Guangxi Yulin 537005,China)

机构地区：[1]广西大学机械工程学院,广西南宁530004 [2]广西玉柴机器股份有限公司,广西玉林537005

出　　处：《机械设计与制造》2024年第7期167-172,共6页Machinery Design & Manufacture

基　　金：国家重点研发计划(2017YFE0102800);广西科技基地和人才专项项目(AD19110019);广西创新驱动发展专项(AA18242045-3)。

摘　　要：为解决混合动力系统传统动态规划(Dynamic Programming,DP)策略成本函数值受罚函数影响较大、平衡电量调试时间较长的问题,针对某款双行星排混合动力客车提出了变惩罚系数DP(Variable Penalty Coefficient DP,DP-VAR)策略和边界迭代DP(Boundary Iterative DP,DP-ITE)策略。同时,还提出了基于XGBoost算法的动态规划策略模式切换规则提取方法,并对自适应等效燃油消耗最小策略(Adaptive Equivalent Fuel Consumption Minimization Strategy,A-ECMS)进行了改进,建立了具有模式切换规则的A-ECMS策略。基于C-WTVC工况的仿真结果表明:(1)相比于DP策略,DPVAR和DP-ITE策略的控制规则更为明确且百公里油耗分别降低了1.18%和4.31%;(2)DP-ITE策略在取消罚函数的前提下具有终止SOC绝对收敛性;(3)优化后的A-ECMS策略较优化前的百公里油耗降低了1.17%。In order to solve the problem that the cost function value of the traditional Dynamic Programming(DP)strategy of the hybrid power system is greatly affected by the penalty function and the balance electric power debugging time is too long,the variable penalty coefficient Dynamic Programming(DP-VAR)strategy and the boundary iterative Dynamic Programming(DP-ITE)strategy are proposed for a dual-planetary hybrid electric bus.At the same time,a dynamic programming mode switching rule extraction method based on XGBoost algorithm is proposed,and the Adaptive Equivalent Fuel Consumption Minimization Strategy(A-ECMS)is improved,and an A-ECMS with mode switching rules is established.The simulation results based on C-WTVC cycle show that:(1)Compared with DP strategy,the control rules of DP-VAR and DP-ITE strategies are clearer,and the fuel consumption is reduced by 1.18%and 4.31%respectively;(2)DP-ITE strategy has absolute convergence of termination SOC on the premise of canceling penalty function;(3)The optimized A-ECMS strategy reduces fuel consumption by 1.17%compared with that before optimization.

关 键 词：双行星排 混合动力 能量管理 动态规划 规则提取 

分 类 号：TH16[机械工程—机械制造及自动化] U469.7[机械工程—车辆工程]