Battery retirement state prediction method based on real-world data and the TabNet model

Zhaosheng Zhang, Shoukun Sun, Zhenpo Wang and Ni Lin

Energy, 2025, vol. 334, issue C

Abstract: Accurately predicting the retirement state of power batteries is essential for estimating their remaining useful life, optimizing resource recycling, and promoting sustainable development. This paper proposes a novel method for predicting the retirement state of battery based on multidimensional retirement feature fusion and the TabNet model. First, static data from 23,741 retired vehicles and dynamic operational data from 720 electric vehicles over three years were collected. After preprocessing, the retirement state of the battery was labeled. Next, a retirement-related feature extraction method was developed, integrating vehicle dimension, health dimension, and usage dimension to enrich the decision-making dimensions for battery retirement. Finally, a retirement state prediction model based on Bayesian optimization and TabNet was developed, and its performance was compared with other models. The experimental results show that the proposed method achieves an F1 score of 0.850 and an AUC of 0.977 on the test set, demonstrating its effectiveness in predicting battery retirement state based on real-world data.

Keywords: Electric vehicles; Battery retirement; Real-world data; End of life; Machine learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225034371
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:334:y:2025:i:c:s0360544225034371

DOI: 10.1016/j.energy.2025.137795

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().