Transformer autoencoder framework for estimating core temperature of lithium-ion battery from pulse discharge dynamics

Beg, Mustehsan, Alcock, Keith M. ORCID: https://orcid.org/0000-0003-0958-9141, Sam, Vishnu, Rakshit, Sanjay, Paul, Sambit, Yu, Hongnian and Goh, Keng (2026) Transformer autoencoder framework for estimating core temperature of lithium-ion battery from pulse discharge dynamics. Applied Thermal Engineering, 288. ISSN 1359-4311

Preview

PDF (1-s2.0-S1359431125041444-main) - Published Version Available under License Creative Commons Attribution. Download (7MB) | Preview

Abstract

This study presents a non-invasive, data-driven approach for estimating the core temperature of lithium-ion batteries using a transformer-based autoencoder model. Pulse discharge data were collected from a Panasonic NCR18650B cell at three different C-rates (0.5C, 1C, and 2C) to train and evaluate the model. The transformer autoencoder leverages its ability to capture long-range temporal dependencies, efficiently reconstructing multivariate battery signals while compressing them into latent representations that serve as proxies for core temperature. Additionally, two-dimensional visualisation using Principal Component Analysis and t-distributed Stochastic neighbour embedding of the latent space revealed well-separated and structured clusters, further confirming the model’s ability to encode relevant thermal dynamics effectively. These latent features were used as inputs to a random forest regressor, which was trained to predict temperature and validated against a physicalbased thermal model. The proposed method achieved high accuracy across all discharge rates, physics-based model, and drive cycle analysis, with R2 scores of >0.99 outperforming previously reported studies. These re-sults demonstrate the transformer autoencoder’s superior ability to extract meaningful temporally structured representation and its robustness in dynamic operating conditions.

Item Type:	Article
Uncontrolled Keywords:	data-driven,transformer autoencoder,lithium-ion,core temperature,thermal,pulse discharge,sdg 7 - affordable and clean energy ,/dk/atira/pure/sustainabledevelopmentgoals/affordable_and_clean_energy
Faculty \ School:	Faculty of Science > School of Engineering, Mathematics and Physics
Depositing User:	LivePure Connector
Date Deposited:	26 Jun 2026 14:56
Last Modified:	28 Jun 2026 05:37
URI:	https://ueaeprints.uea.ac.uk/id/eprint/103514
DOI:	10.1016/j.applthermaleng.2025.129552

Downloads

Actions (login required)

View Item