journal article·2026-04Open access

Real-time spatiotemporal temperature gradient estimation based on a graph convolutional neural network for battery cells

Saulius Pakštys, Fabio Boscarino, Marco Maritano, Angelo Bonfitto

Abstract

Monitoring the temperature distribution of cells in large-scale battery packs can be a costly endeavour. This paper proposes a spatiotemporal model based on a graph convolutional neural network for the estimation of the axial surface temperature distribution of 21 700 cylindrical cells in a small-scale battery pack. The model is developed on the basis of experimental results obtained from the studied pack subject to various immersion thermal management conditions. The pack is charged and discharged at current rates of 0.5C and 1C at four immersion ratios: 25%, 50%, 75% and 100% with respect to the total cell height. A cross-fold training methodology is employed to train the model making use of thermally dynamic input data. The results show that a root mean square error of less than 1.1 °C can be achieved for the fold displaying the poorest performance. Finally, this paper includes a processor-in-the-loop analysis, indicating the feasibility of the model to run on embedded hardware. It is shown that up to 50 cells may be monitored in real-time. The model offers the possibility to expand the safety and health monitoring in battery management systems for not only battery packs with novel thermal management solutions, but conventional solutions as well.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Battery Technologies Research · Machine Learning and ELM · Neural Networks and Applications

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (43)

Show source-provided references
1. Recent advances in lithium-ion battery materials for improved electrochemical performance: A review10.1016/j.rineng.2022.100472 ↗
2. 2021
3. Surface cooling causes accelerated degradation compared to tab cooling for lithium-ion pouch cells10.1149/2.0361609jes ↗
4. The effect of cell-to-cell variations and thermal gradients on the performance and degradation of lithium-ion battery packs10.1016/j.apenergy.2019.04.108 ↗
5. A critical review of thermal issues in lithium-ion batteries10.1149/1.3515880 ↗
6. Comparison of different cooling methods for lithium ion battery cells10.1016/j.applthermaleng.2015.10.015 ↗
7. Temperature effect and thermal impact in lithium-ion batteries: A review10.1016/j.pnsc.2018.11.002 ↗
8. xEV Li-ion battery low-temperature effects—Review10.1109/TVT.2019.2906487 ↗
9. A study on parameter variation effects on battery packs for electric vehicles10.1016/j.jpowsour.2017.08.033 ↗
10. Effect of different cooling configurations on thermal gradients inside cylindrical battery cells10.1016/j.est.2018.11.030 ↗
11. Improved thermal performance of a li-ion cell through heat pipe insertion10.1149/2.0191706jes ↗
12. Non-invasive measurement of internal temperature of a cylindrical li-ion cell during high-rate discharge10.1016/j.ijheatmasstransfer.2017.03.095 ↗
13. Immersion cooling for lithium-ion batteries – A review10.1016/j.jpowsour.2022.231094 ↗
14. Three-dimensional thermal modeling of li-ion battery cell and 50 V li-ion battery pack cooled by mini-channel cold plate10.1016/j.applthermaleng.2018.11.009 ↗
15. Sensorless state of temperature estimation for smart battery based on electrochemical impedance
16. Real-time sensorless temperature estimation of lithium-ion batteries based on online operando impedance acquisition10.1109/TPEL.2024.3424267 ↗
17. A review of modeling, acquisition, and application of lithium-ion battery impedance for onboard battery management10.1016/j.etran.2020.100093 ↗
18. An electrical equivalent circuit model of a lithium titanate oxide battery10.3390/batteries5010031 ↗
19. A method for the lifetime sensorless estimation of surface and core temperature in lithium-ion batteries via online updating of electrical parameters10.1016/j.est.2022.106260 ↗
20. Numerical analysis of single-phase liquid immersion cooling for lithium-ion battery thermal management using different dielectric fluids10.1016/j.ijheatmasstransfer.2022.122608 ↗
21. Potential and current distribution in electrochemical cells: Interpretation of the half-cell voltage measurements as a function of reference-electrode location10.1149/1.2220746 ↗
22. Effect of electrode configuration on the thermal behavior of a lithium-polymer battery10.1016/j.jpowsour.2007.09.054 ↗
23. A novel dielectric fluid immersion cooling technology for Li-ion battery thermal management10.1016/j.enconman.2020.113715 ↗
24. Transient thermal analysis of a li-ion battery module for electric cars based on various cooling fan arrangements10.3390/en13092387 ↗
25. Conjugate heat transfer analysis of thermal management of a li-ion battery pack
26. An electrochemical-thermal multiphysics model for lithium polymer battery
27. Robust estimation of battery system temperature distribution under sparse sensing and uncertainty10.1109/TCST.2019.2892019 ↗
28. A comprehensive review of lithium-ion cell temperature estimation techniques applicable to health-conscious fast charging and smart battery management systems10.3390/en14185960 ↗
29. A lumped thermal model of lithium-ion battery cells considering radiative heat transfer10.1016/j.applthermaleng.2018.07.105 ↗
30. Adaptive prognosis of lithium-ion batteries based on the combination of particle filters and radial basis function neural networks10.1016/j.jpowsour.2017.01.105 ↗
31. A spatiotemporal estimation method for temperature distribution in lithium-ion batteries10.1109/TII.2014.2341955 ↗
32. Data-driven hybrid internal temperature estimation approach for battery thermal management
33. Co-estimation of lithium-ion battery state of charge and state of temperature based on a hybrid electrochemical-thermal-neural-network model10.1016/j.jpowsour.2020.227935 ↗
34. The graph neural network model10.1109/TNN.2008.2005605 ↗
35. Real-time temperature prediction for large-scale multi-core chips based on graph convolutional neural networks
36. Multivariate multi-step time series prediction of induction motor situation based on fused temporal-spatial features10.1016/j.ijhydene.2023.11.047 ↗
37. Temperature prediction by graph convolutional network with transformer for lithium-ion battery to improve the thermal management system10.1016/j.est.2025.118537 ↗
38. Temperature field spatiotemporal modeling of lithium-ion battery pack configured sparse temperature sensors10.1016/j.est.2024.113005 ↗
39. Capacity estimation of lithium-ion batteries based on data aggregation and feature fusion via graph neural network10.1016/j.apenergy.2023.120808 ↗
40. Aging-aware capacity prediction for lithium-ion batteries: A dynamic graph networks framework with spatiotemporal feature fusion10.1016/j.measurement.2025.119005 ↗
41. Impact of busbar-induced joule heating on battery temperature rise in electric vehicle batteries
42. A gentle introduction to graph neural networks10.23915/distill.00033 ↗
43. Fukumoto · 2025