Development of Battery Electric Vehicle's Driving Cycle in the Mountain Environment Based on Big Data
ZHU Shu-jiang1, XU Ting-ting2, LONG Fang-jia2, HU Xiao-rui2
1. China Automotive Engineering Research Institute Co., Ltd., Chongqing 401122, China; 2. State Grid Chongqing Electric Power Company, Chongqing 400015, China
Development of Battery Electric Vehicle's Driving Cycle in the Mountain Environment Based on Big Data
ZHU Shu-jiang1, XU Ting-ting2, LONG Fang-jia2, HU Xiao-rui2
1. China Automotive Engineering Research Institute Co., Ltd., Chongqing 401122, China; 2. State Grid Chongqing Electric Power Company, Chongqing 400015, China
摘要With the increasing trend of battery electric vehicles, it is no longer appropriate to use the traditional fuel vehicle’s driving cycle for battery electric vehicle driving cycle research. In order to obtain the driving cycle of the battery electric vehicle and compare it with the traditional driving cycle from a data perspective, the driving data of the battery electric vehicle in the Chongqing area was analyzed. The proprietary big data platform provided whole vehicle and battery data, and the short-stroke method was used to identify the kinematic fragments. Then, the kinematic fragments’ feature is constructed using the correlation method of feature engineering. The dimension of high-dimensional feature data is reduced through principal component analysis, and the feature weight is calculated to eliminate the influence of feature correlation. Next, the K-means++ clustering method is used to partition the structure of the driving speed and battery current curves, and thus to construct four types of working conditions: low speed, medium speed, medium-high speed, and high speed. Moreover, the most suitable short-time working conditions are selected by sorting the distance of each working condition from the cluster center as the origin. The weight of the data set is determined by the ratio of the total duration of the data set to the total duration of the data set. Through error analysis, the characteristic deviation error of the smallest curve is selected as a representative of the working condition to determine the representative of the vehicle and battery working conditions. Finally, the reliability of the battery electric vehicle operating curve in a mountainous environment is demonstrated by comparing international and domestic typical operating conditions. The results indicate that in mountainous environments, pure electric vehicles exhibit shorter constant speed driving times, longer idling times, greater deceleration, and a smaller proportion of deceleration time compared to non-mountainous environments. Additionally, battery discharge efficiency is higher, and the vehicle speed is maintained at a moderate level.
Abstract：With the increasing trend of battery electric vehicles, it is no longer appropriate to use the traditional fuel vehicle’s driving cycle for battery electric vehicle driving cycle research. In order to obtain the driving cycle of the battery electric vehicle and compare it with the traditional driving cycle from a data perspective, the driving data of the battery electric vehicle in the Chongqing area was analyzed. The proprietary big data platform provided whole vehicle and battery data, and the short-stroke method was used to identify the kinematic fragments. Then, the kinematic fragments’ feature is constructed using the correlation method of feature engineering. The dimension of high-dimensional feature data is reduced through principal component analysis, and the feature weight is calculated to eliminate the influence of feature correlation. Next, the K-means++ clustering method is used to partition the structure of the driving speed and battery current curves, and thus to construct four types of working conditions: low speed, medium speed, medium-high speed, and high speed. Moreover, the most suitable short-time working conditions are selected by sorting the distance of each working condition from the cluster center as the origin. The weight of the data set is determined by the ratio of the total duration of the data set to the total duration of the data set. Through error analysis, the characteristic deviation error of the smallest curve is selected as a representative of the working condition to determine the representative of the vehicle and battery working conditions. Finally, the reliability of the battery electric vehicle operating curve in a mountainous environment is demonstrated by comparing international and domestic typical operating conditions. The results indicate that in mountainous environments, pure electric vehicles exhibit shorter constant speed driving times, longer idling times, greater deceleration, and a smaller proportion of deceleration time compared to non-mountainous environments. Additionally, battery discharge efficiency is higher, and the vehicle speed is maintained at a moderate level.
ZHU Shu-jiang, XU Ting-ting, LONG Fang-jia, HU Xiao-rui. Development of Battery Electric Vehicle's Driving Cycle in the Mountain Environment Based on Big Data[J]. Journal of Highway and Transportation Research and Development, 2024, 18(1): 27-37.
ZHU Shu-jiang, XU Ting-ting, LONG Fang-jia, HU Xiao-rui. Development of Battery Electric Vehicle's Driving Cycle in the Mountain Environment Based on Big Data. Journal of Highway and Transportation Research and Development, 2024, 18(1): 27-37.
[1] HUERTAS J I, DÍAZ J, CORDERO D, et al. A New Methodology to Determine Typical Driving Cycles for The Design of Vehicles Power Trains[J]. Springer Paris, 2018, 12(1):319-326. [2] ZHANG Jian-wei, LI Meng-liang, AI Guo-he, et al. A Study on the Features of Existing Typical Vehicle Driving Cycles[J]. Automotive Engineering, 2005(2):220-224, 245.(in Chinese) [3] CAI E, LI Yang-yang, LI Chun-ming, et al. Research on Synthetic Technique of Driving Cycle in Xi'an Based on K-means Clustering[J]. Automobile Technology, 2015(8):33-36.(in Chinese) [4] XU Ting, CUI Shi-chao, LIU Ming, et al. Study on Construction Method of Driving Cycle of Passenger Vehicle in Plateau Mountainous Area[J]. Journal of Highway and Transportation Research and Development, 2021, 38(2):117-124.(in Chinese) [5] SUN Jun, FANG Tao, ZHANG Bing-li, et al. Construction of Hefei Electric Buses Driving Cycle Based on Improved K-Means Clustering[J]. Automobile Technology, 2020(8):56-62.(in Chinese) [6] LIU Yu, WU Zhi-xin, LI Meng-liang, et al. Development of China Light-duty Passenger Car Test Cycle[J].Journal of Transportation Systems Engineering and Information Technology, 2020, 20(3):233-240.(in Chinese) [7] GB/T 38146.1-2019, China Automotive Test Cycle-Part 1:Light-duty Vehicles[S].(in Chinese) [8] TONG H Y. Development of a Driving Cycle for a Super Capacitor Electric Bus Route in Hong Kong[J]. Sustainable Cities and Society, 2019, 48(7):233-240. [9] HU Zheng-yun. Study on Construction Method of Urban Driving Cycle of Passenger Vehicles[J]. Journal of Highway and Transportation Research and Development, 2019, 36(11):142-150.(in Chinese)[ZK)] [10] WANG WEN-qi, GAO Guang-kuo, WANG Zi-jian, et al. A Method for Constructing Automobile Operation Condition[J].Journal of Highway and Transportation Research and Development, 2020, 37(9):128-138.(in Chinese) [11] HU Zhi-yuan, QIN Yan, TAN Pei-qiang, et al. Large-sampled-based Car-driving Cycle in Shanghai City[J]. Journal of Tongji University (Natural Science), 2015, 43(10):1523-1527.(in Chinese) [12] GAO Chi. Grasp the Situation, Focus on Transformation, Lead Innovation, Recording the 2020 China Electric Vehicle Hundreds Conference Forum[J]. Automobile&Parts, 2020(3):26-29.(in Chinese) [13] YU Man, ZHAO Wei-hua, WU Ling, et al. Working Condition of Electric Vehicle Based on K-Mean Clustering and Support Vector Machine[J]. Journal of Chongqing Jiaotong University (Natural Science), 2021, 40(5):129-139.(in Chinese) [14] KUI Hai-xia, SONG Ruo-yang, LAN Hai-chao, et al. Research on Construction Method of Electric Vehicle Urban Driving Conditions[J]. Automobile Applied Technology, 2020, 45(22):10-13.(in Chinese) [15] LI Yao-hua, LIU Peng, YANG Wei, et al. Research on Xi'an Pure Electric Bus Driving Cycle[J]. China Sciencepaper, 2016, 11(7):754-759.(in Chinese) [16] XU Xiao-jun, LI Jun, LIU Yu, et al. The Development of Electric Vehicles Urban Driving Cycle[J]. Science Technology and Engineering, 2017, 17(35):330-336.(in Chinese) [17] PAN Deng. Study on Urban Driving Cycle Construction and Its Multi-scale Prediction for Hybrid Electric Vehicles[D]. Beijing:Beijing Institute of Technology, 2015.(in Chinese) [18] MA Zhi-xiong, LI Meng-liang, ZHU Xi-chan, et al. Study of the Methodology for Car Driving Cycle Development[J]. Journal of Wuhan University of Technology (Information&Management Engineering), 2004(3):182-184, 188.(in Chinese)
2024, Vol. 18 
