Electric vehicle range prediction considering real-time driving factors and battery capacity index

Accurate prediction of the Remaining Driving Range (RDR) of Electric Vehicles (EVs) is crucial for alleviating range anxiety. However, most current studies predict RDR based solely on the current state, failing to capture the impact of real-time driving behaviors and battery aging on RDR. This study uses a dataset from 100 EVs in Tianjin, China, collected every 10 s from March 30 to April 7, 2024, encompassing detailed driving behavior and battery status. A new metric, the Battery Capacity Index (BCI), is introduced to quantify battery health and aging, reflecting the charge retained per unit of State of Charge (SOC). Novel Kolmogorov-Arnold Networks (KAN)-integrated time series models are applied, with the BiLSTM-KAN model demonstrating superior prediction accuracy. SHapley Additive exPlanations (SHAP) analysis identifies observed SOC, BCI, and driving behavior as key factors influencing RDR. These findings contribute to EV technology and support sustainable transportation development.

• Record URL:
  • https://doi.org/10.1016/j.trd.2025.104795
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S1361920925002056
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/13619209
• Supplemental Notes:
  • © 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. Abstract reprinted with permission of Elsevier.
• Authors:
  • Ma, Xinwei
  • Li, Jiaao
  • Cui, Hongjun
  • Cheng, Long
  • Ji, Yanjie
  • Wang, Jianbiao
• Publication Date: 2025-7

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: 104795
• Serial:
  • Transportation Research Part D: Transport and Environment
  • Volume: 144
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 1361-9209
  • Serial URL: http://www.sciencedirect.com/science/journal/13619209

Subject/Index Terms

• TRT Terms: Aging (Materials); Electric batteries; Electric vehicles; Vehicle range
• Geographic Terms: Tianjin (China)
• Subject Areas: Energy; Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01956091
• Record Type: Publication
• Files: TRIS
• Created Date: May 27 2025 9:33AM