基于工况识别的PHEB能量管理策略研究  

Study of energy management strategy for plug-in hybrid electric bus based on driving cycle recognition

作　　者：尹安东 张黎明 YIN Andong;ZHANG Liming(School of Automobile and Traffic Engineering,Hefei University of Technology,Hefei 230009,China)

机构地区：[1]合肥工业大学汽车与交通工程学院

出　　处：《合肥工业大学学报（自然科学版）》2020年第2期145-150,共6页Journal of Hefei University of Technology：Natural Science

基　　金：国家科技支撑计划资助项目(2013BAG08B01);国家新能源汽车产业技术创新工程整车资助项目(财建[2012]1095号)

摘　　要：为提高插电式混合动力客车(plug-in hybrid electric bus,PHEB)的燃油经济性,文章提出了一种基于工况识别的PHEB能量管理策略。首先运用主成分分析(principal component analysis,PCA)和模糊C均值聚类法构建代表性城市工况;然后基于学习向量量化(learning vector quantization,LVQ)神经网络进行工况识别,并根据改进动态规划(dynamic programming,DP)算法提炼出全局最优能量分配规则,对能量管理策略进行优化;最后基于AMESim和Simulink建立PHEB整车和能量管理策略仿真模型,并在构建的合肥市代表性城市工况下进行仿真分析。仿真结果表明,该文提出的能量管理策略比电量消耗-电量维持(CD-CS)能量管理策略的燃油经济性提高了5.2%。To improve the fuel economy of plug-in hybrid electric bus(PHEB), an energy management strategy for PHEB based on driving cycle recognition was proposed. Firstly, the principal component analysis(PCA) and fuzzy C-means clustering algorithm were used to construct the typical urban driving cycle. Then the learning vector quantization(LVQ) neural network was used to identify the driving cycles, and the global optimal energy allocation rules were extracted according to the improved dynamic programming(DP) algorithm to optimize the energy management control strategy. Finally, the simulation model of PHEB and control strategy were established based on AMESim and Simulink to validate the control strategy under the typical urban driving cycle of Hefei. The simulation results show that the fuel economy of the proposed control strategy is 5.2% higher than that of the charge depletion-charge sustaining(CD-CS) control strategy.

关 键 词：插电式混合动力客车(PHEB) 能量管理策略 行驶工况 学习向量量化(LVQ)神经网络 动态规划(DP)算法 

分 类 号：U469.72[机械工程—车辆工程]