Accurate battery temperature prediction using self-training neural networks within embedded system

Xinyuan Fan, Weige Zhang, Hongfeng Qi and Xingzhen Zhou

Energy, 2024, vol. 313, issue C

Abstract: The temperature of lithium-ion batteries is an essential factor in the performance and safety of the battery pack. By predicting batteries’ temperature, the battery management system (BMS) can optimize the strategy in advance, improve the precision of temperature control, and enhance the battery pack’s performance. A self-training feedforward neural network is proposed as a means of predicting the battery surface temperature 300 s later. By extracting knowledge-driven features from current and voltage data, the structure of the proposed method is greatly simplified, facilitating implementation in a real BMS. The model is capable of self-training and parameter updating at the edge side, addressing the issue of poor generalizability associated with pre-trained models. The proposed method was validated under a variety of temperatures and operating conditions. The root-mean-square error (RMSE) of battery temperature prediction is 0.55 °C for constant ambient temperature and 0.64 °C for varying ambient temperature. Predicting 100 battery temperatures takes only 94 ms, enabling the BMS of electric vehicles to realize real-time temperature prediction.

Keywords: Battery temperature; Temperature prediction; Neural network; Embedded system; Self-training (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S036054422403809X
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:313:y:2024:i:c:s036054422403809x

DOI: 10.1016/j.energy.2024.134031

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 ().