To achieve the accurate prediction of the driving range of electric vehicles, a driving range prediction method based on the combination of the Variational Mode Decomposition (VMD) algorithm and Deep Extreme Learning Machine (DELM) model after optimizing the parameters by the Dung Beetle Optimizer (DBO) algorithm is proposed by comprehensively considering the battery performance and driving parameters in this paper. Firstly, by exploring the effects of vehicle operating status, driving behavior and external environment on the driving range of electric vehicles, six characteristic indicators including 100 km energy consumption, driving behavior and ambient temperature are constructed. Secondly, the VMD algorithm is used to reduce the nonlinearity and non-stationarity of the raw data, and the DBO algorithm is employed to optimize the parameters of the DELM model, establishing the electric vehicle driving mileage prediction model based on the integrated VMD-DBO-DELM algorithm. Finally, the prediction results of the constructed prediction model were compared and analyzed with the prediction results of other existing models. The results indicate that the VMD-DBO-DELM model significantly outperforms the different models in prediction performance, showing the highest prediction accuracy under both conditions and accurately fitting the variation trend of the driving range.
BiJun, ZhangJia-wei, ZhangDong, et al. A correlation analysis and modeling for battery soc and driving mileage of electric vehicle[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(1): 49-54.
LiuGuang-ming, OuyangMing-gao, LuLan-guang, et al. Driving range estimation for electric vehicles based on battery energy state estimation and vehicle energy consumption prediction[J]. Chinese Journal of Automotive Engineering, 2014, 36(11): 1302-1309.
LuoHong-mei, ZhouYi-fan. Research on the prediction method of electric vehicle mileage based on big data analysis[J]. Automobile Applied Technology, 2020(13): 1-4.
ChenDe-hai, RenYong-chang, HuangYan-guo, et al. Real time prediction for remaining mileage of battery electric vehicle based on modified pso-rbf algorithm[J]. Chinese Journal of Automotive Engineering, 2018, 40(7): 764-769.
SongYuan-yuan. Energy consumption modeling and cruising range estimation based on driving cycle for electric vehicles[D]. Beijing: School of Traffic and Transportation, Beijing Jiaotong University, 2014.
SuSu, YangTian-tian, LiYu-jing, et al. Charging route planning for electric vehicles considering rear-time dynamic energy consumption[j]. Automation of Electric Power Systems, 2019, 43(7): 136-143.
[13]
YavasogluH A, TetikY E, GokceK. Implementation of machine learning based real time range estimation method without destination knowledge for BEVs[J]. Energy, 2019, 172: 1179-1186.
HuJie, WengLing-long, QinXiong-zhen, et al. Mileage prediction of electric vehicle based on multi model fusion[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(5): 100-106.
TianHui-xin, LiXiao-yu, LiuFang. Prediction of continued driving range of battery electric vehicle based on map information and cyclic svr model[J]. Chinese Journal of Automotive Engineering, 2020, 42(9): 1174-1182.
RanYong-chuan, ZengJun, ZhangYi. Research on SVM model prediction method of pure electric vehicle cruising range under urban operating conditions[J]. Mechanical Science and Technology for Aerospace Engineering, 2025, 44(8): 1442-1450.
LiFang-zhou, ZhongYong, QiuHuang-le, et al. Estimation of remaining mileage for pure electrie vehicle based on condition identification and prediction[J]. Vehicle Engine, 2024(5): 86-92.
[22]
DragomiretskiyK, ZossoD. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
LiBo, LiXin, RuiHong, et al. Displacement prediction of tunnel entrance slope based on variational modal decomposition and grey wolf optimized extreme learning machine[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(6): 1853-1860.
[25]
XueJ, ShenB. Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. Journal of Supercomputing, 2023, 79(7): 7305-7336.
GuPing-wei, DuanBin, KangYong-zhe, et al. Online lithium-ion battery capacity estimation based on random charging data[J]. Journal of Mechanical Engineering, 2023, 59(22): 100-110.
ZhangHui, LiShao-peng, DingNai-kan. Research on the association characteristics between battery temperature consistency and driving behavior of electric vehicles[J]. China Journal of Highway and Transport, 2024, 37(3): 216-230.
LiangHai-qiang, HeHong-wen, DaiKang-wei, et al. Analysis on the effects of user behavior on battery aging of electric vehicles based on big data[J]. Chinese Journal of Automotive Engineering, 2022, 44(8): 1212-1217.
[32]
FebbaroA D, SaccoN, SaeedniaM. One-way car-sharing profit maximization by means of user-based vehicle relocation[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 20(2): 628-641.
[33]
KasunL, ZhouH M, HuangG B, et al. Representational learning with ELMs for big data[J]. IEEE Intelligent Systems, 2013, 28: 31-34.
QinYong-feng, LiGang, QiJin-ping, et al. Fault diagnosis of transverse damper for high-speed trains based on RIME-VMD[J]. Journal of Railway Science and Engineering, 2025, 22(3): 942-953.
LuoYi-yong, YaoYi-bin, HuangCheng, et al. Deformation feature extraction and analysis based on improved variational mode decomposition[J]. Geomatics and Information Science of Wuhan University, 2020, 45(4): 612-619.