Fault cause inferences of onboard lithium-ion battery thermal runaway using convolutional neural network

Wang Shuhui, Wang Zhenpo, Zhang Zhaosheng and Cheng Ximing

Energy, 2025, vol. 320, issue C

Abstract: Lithium battery thermal runaway fires are the most common and alarming type of electric vehicle accident. While pre-accident lithium battery fault diagnosis is well-studied, post-accident analysis for identifying causes and determining liability remains limited. This paper categorizes such accidents into "latent" and "sudden" failures, introducing a novel feature indicator and a convolutional neural network (CNN) for automatic classification. The method explores data characteristics linked to different accident causes and their correlation with thermal runaway mechanisms. Based on this, a data-driven framework is proposed for identifying causes and determining liability, aiding on-site investigations. The study analyzes 41 electric vehicles with actual thermal runaway incidents, achieving 100 % precision and 75 % recall, validating the approach's effectiveness. Compared to existing research, this work enables more precise cause identification through classification based on diverse, coupled features rather than broad assumptions. The data-driven, principled framework also offers generalizability, extending its applicability to accident analyses beyond the current dataset.

Keywords: Electric vehicles; Lithium battery thermal-runaway; Latent-failure accidents; Sudden-failure accidents; Data-driven cause inferences (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225009703
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:320:y:2025:i:c:s0360544225009703

DOI: 10.1016/j.energy.2025.135328

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 ().