汽车工程 ›› 2023, Vol. 45 ›› Issue (12): 2357-2365.doi: 10.19562/j.chinasae.qcgc.2023.12.018

所属专题: 新能源汽车技术-动力电池&燃料电池2023年

• • 上一篇    下一篇

基于能耗加权策略的燃料电池汽车续驶里程预测

姜俊昭1,杨文豪1(),彭彬1,郭婷2,徐业凯1,王国卓2   

  1. 1.合肥工业大学汽车与交通工程学院,合肥 230009
    2.中国汽车技术研究中心有限公司,天津 300300
  • 收稿日期:2023-04-18 修回日期:2023-05-29 出版日期:2023-12-25 发布日期:2023-12-21
  • 通讯作者: 杨文豪 E-mail:yangwenhao20210609@163.com
  • 基金资助:
    国家重点研发计划新能源汽车重点专项(2018YFB0105300);安徽省新能源汽车暨智能网联汽车创新工程项目(JZ2021AFKJ0002)

Driving Range Prediction of Fuel Cell Vehicles Based on Energy Consumption Weighting Strategy

Junzhao Jiang1,Wenhao Yang1(),Bin Peng1,Ting Guo2,Yekai Xu1,Guozhuo Wang2   

  1. 1.School of Transportation and Automobile Engineering,Hefei University of Technology,Hefei  230009
    2.China Automotive Technology and Research Center Co. ,Ltd. ,Tianjin  300300
  • Received:2023-04-18 Revised:2023-05-29 Online:2023-12-25 Published:2023-12-21
  • Contact: Wenhao Yang E-mail:yangwenhao20210609@163.com

摘要:

燃料电池汽车能量消耗量及续驶里程是评价其性能的关键指标。以电电混合燃料电池汽车为例,利用数据驱动方法,综合考虑集成学习模型预测的实时能耗值与模糊C均值聚类工况计算的片段能耗值,设计搭建燃料电池汽车多模型协同能耗预测算法,得到修正能耗值。基于此,构建历史-实时能耗加权的续驶里程预测算法,解决片段内极端工况变化导致的续驶里程预测偏离大的问题,实现燃料电池汽车续驶里程有效预测。最后进行了燃料电池汽车室内转鼓实验以及开放道路实验,预测结果与实验结果吻合度较高,验证了算法的准确性。

关键词: 燃料电池汽车, 能耗预测, 续驶里程预测, 机器学习, 工况聚类, 能耗加权

Abstract:

Energy consumption and driving range of fuel cell vehicle are the key indexes to evaluate its performance. Taking electric hybrid fuel cell vehicle as an example, a data-driven method is used to design and build a multi-model collaborative energy consumption prediction algorithm for fuel cell vehicle, taking into account of real-time energy consumption predicted by integrated learning model and fragment energy consumption calculated by fuzzy C-means clustering conditions, so as to get the corrected energy consumption value. Based on this, a driving range prediction algorithm weighted by historical and real-time energy consumption is constructed to solve the problem of large deviation in driving range prediction caused by changes in extreme operating conditions within segments, to achieve effective driving range prediction for fuel cell vehicles. Finally, the indoor drum experiment and open road experiment of fuel cell vehicle are carried out, and the predicted results are in good agreement with the experimental results, which verifies the accuracy of the algorithm.

Key words: fuel cell vehicle, energy consumption prediction, driving range prediction, machine learning, working condition clustering, energy consumption weighting