Trans Motauto World
Vol. 10 (2025), Issue 1, pg(s) 12-15

TRANSPORT TECHNICS. INVESTIGATION OF ELEMENTS. RELIABILITY

Multi-Method Statistical Analysis of Factors Influencing Predictive Maintenance of Electric Vehicle Fleets

  • 1 Transilvania University of Brasov, Romania

Abstract

Accurate estimation of predictive maintenance is important for effective electric vehicle fleet management. Existing approaches often fail to account for the complex relationships between diverse influencing factors. In this study, we propose a multi-method statistical analysis framework that integrates Spearman correlation, Mutual Information, and ElasticNet regression to quantify these relationships. The findings show that charge cycles and load weight exhibit the strongest positive correlations with Remaining Useful Life (RUL), while route roughness and battery temperature demonstrate significant negative impacts. Additionally, the Mutual Information analysis identified battery temperature as having the strongest non-linear relationship with RUL, underscoring its unique predictive relevance. Interestingly, maintenance records were found to have small predictive value across all analytical methods. The ElasticNet regression also refined the analysis by identifying 11 critical predictive factors, successfully eliminating redundant variables, and showing how corresponding statistical methods can improve predictive maintenance. These results can help the fleet operators to prioritize monitoring efforts on the most impactful factors and develop more precise RUL prediction models.

Keywords

References

  1. R. S. Nuvvula, P.P. Kumar , A. Siddiqui, S. Thamizharasan, C. C. Tan , R. Alubady , B. Khan, 12th International Conference on Smart Grid (icSmartGrid) (IEEE, 309-311, 2024)
  2. P. Aqueveque, L. Radrigan, F. Pastene, A. S. Morales, E. Guerra, IEEE Access, 9, 17365-17381 (2021)
  3. J. Hu, L. Weng, Z. Gao, B. Yang, IEEE Trans. Veh. Technol, 72, 1 (2022)
  4. S. Bharathi, S. Tenali, R. Maddula, J. Kavitha, M. Ponnusamy, 9th International Conference on Communication and Electronics Systems (ICCES), (IEEE, 1049, 2024)
  5. B. Acharjee, R.R. Ghosh, T. Dey, S. Das, D. Nandan, TENCON 2024-2024 IEEE Region 10 Conference (TENCON), (IEEE, 197, 2024)
  6. S. Gupta, P.K. Mishra, 5th International Conference on Energy, Power and Environment: Towards Flexible Green Energy Technologies (ICEPE), (IEEE, 1, 2023)
  7. A. Dineva, Batteries, 10, 10 (2024)
  8. S.B. Sarmah, P. Kalita, A. Garg, X. Niu, X.W. Zhang, X. Peng, D. Bhattacharjee, J. Electrochem. Energy Convers. Storage, 16, 4 (2019)
  9. J. Zhou, J. Yang, Q. Qian, Y. Qin, Measurement Science and Technology, 35, 6 (2024)
  10. K. L. Tsui, N. Chen, Q. Zhou, Y. Hai, W. Wang, Mathematical Problems in Engineering, 2015, 1 (2015)
  11. C. Ren, H. Li, Z. Zhang, X Si, 12th Data Driven Control and Learning Systems Conference (DDCLS), (IEEE, 172, 2023)
  12. D. Geerts, R. Medina, W. van Sark, S. Wilkins, Batteries, 10, 2 (2024)
  13. J. John, G. Kudva, N.S. Jayalakshmi, IEEE Access, (2024)
  14. P. E . I. Hong, J. Mech. Eng, 55,8 (2019)
  15. Y. Jiang, Y. Lyu, Y. Wang, P. Wan, 12th International Conference on Advanced Computational Intelligence (ICACI), (IEEE, 620, 2020)
  16. B. Zraibi, C. Okar, H. Chaoui, M. Mansouri, IEEE Trans. Veh. Technol, 70, 5 (2021)
  17. Y. Fan, Z. Lin, F. Wang, J. Zhang, Scientific Reports, 15, 1 (2025)
  18. H. Wu, C. Ye, Y. Zhang, J. Nie, Y. Kuang, Z. Li, Symmetry, 12, 8 (2020)
  19. EVIOT Dataset, Kaggle. Retrieved April 4, 2025, from https://www.kaggle.com/datasets/datasetengineer/eviot-predictivemaint-dataset.
  20. C. Xiao, J. Ye, R.M. Esteves, C. Rong, CCPE, 28, 14 (2016)
  21. A Kraskov, H Stögbauer, P Grassberger, Physical Review E, 69, 6 (2004)
  22. Q. Li, N. Lin, The Bayesian elastic net, (2010)

Article full text

Download PDF