Thermal runaway detection method of SiO₂ aerogel battery pack based on mixed Gaussian hidden Markov model
by Mingzheng Jia; Yanfen Li
International Journal of Microstructure and Materials Properties (IJMMP), Vol. 17, No. 2/3, 2024

Abstract: Thermal runaway has become one of the key factors leading to battery pack failure. Therefore, this paper proposes a detection method based on the mixed Gaussian hidden Markov model to detect the thermal runaway phenomenon of SiO₂ aerogel battery pack. Firstly, by analysing the dynamic characteristics of thermal runaway of SiO₂ aerogel battery pack, the mechanism of thermal runaway was clarified, and the diffusion behaviour characteristics of thermal runaway were explored. Subsequently, a calculation formula for thermal diffusion coefficient was constructed and feature parameters of thermal runaway were extracted. On this basis, a detection model for thermal runaway of battery packs was constructed using a mixed Gaussian hidden Markov model. The output result obtained by inputting the determined parameters into the model is the detection result of thermal runaway of the battery pack. The experimental data shows that the minimum detection time of 1 second can be obtained by using the method proposed in this paper to detect the thermal runaway of SiO₂ aerogel battery pack, and the accuracy of the detection results can reach 96%.

Online publication date: Mon, 15-Apr-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Microstructure and Materials Properties (IJMMP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com