A dual-stage thermal runaway early warning strategy for lithium-ion batteries based on multi-domain acoustic signal fusion

Hankun Liu, Yue Wang, Teng Wang, Yichang Gong and Yunlong Shang

Energy, 2025, vol. 322, issue C

Abstract: Effective thermal runaway prediction is essential for the safe use of lithium-ion batteries (LIBs). However, the early stages of thermal runaway are so covert that it is difficult for classical warning methods to provide timely warnings based on characteristics like temperature and current. To address this issue, a dual-stage thermal runaway early warning strategy for LIBs based on multi-domain acoustic signal fusion is proposed. Firstly, sound signals during the battery thermal runaway experiment are collected. In the first stage, outliers are detected using isolated forests, followed by time-frequency multi-domain analysis. The results are then processed with an Entropy-Pruned and Cluster-Optimized KNN Classification (EPCOKC) to provide the second-level warning. Finally, the experimental results demonstrate that the proposed early warning method is effective, general and robust, with 98.08 % accuracy of the recognition system. This sound-based early warning method issues alerts on average at 9352s, much earlier than the temperature and pressure-based warning methods.

Keywords: Fault diagnosis; Lithium-ion battery; Multi-domain analysis; Voice recognition (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225013908
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:322:y:2025:i:c:s0360544225013908

DOI: 10.1016/j.energy.2025.135748

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 ().