Key points are not available for this paper at this time.
In this comprehensive review, we meticulously examine the role of Artificial Neural Networks (ANN) in predicting and understanding the thermal behavior of Lithium-ion batteries (LIBs), with a focus on battery temperature and thermal runaway (TR) prediction. Throughout this review, A bibliometric analysis of over 200 publications between 2010 and 2024 revealed a more than 5 × growth in ANN-based thermal modeling studies in the last five years. We quantitatively compare recent models including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Feedforward Neural Networks (FFNN), with reported root mean square errors (RMSE) ranging from as low as 0.055 °C (LSTM) to 1.3 °C (FFNN) in surface temperature prediction tasks. Moreover, we have identified an emerging trend in the design of hybrid models such as LSTM-CNN, which achieves TR detection of up to 27 min in advance. Therefore, emphasizing the advantage of hybrid modeling in battery thermal safety. In parallel, this review highlights the current state-of-the-art of Physics informed Machine Learning (PIML) that integrates domain knowledge and governing physical laws with neural networks and achieves average RMSE as low as 0.12 ° C in temperature prediction. Furthermore, PIML models reduce drift error by up to 40% under dynamic conditions, while reducing computation time by up to 250 times less than purely ML data-driven models. This highlights the transformative role PIML can provide in onboard and real-time BTMS. Despite this progress, a critical research gap remains, such as the underutilization of GRU based models, limited core temperature prediction, and a shortage in publicly available battery datasets with internal thermal measurement. This review concludes by providing a curated summary of benchmark datasets and model evaluation to serve as a valuable reference for researchers in the domain of next-generation BTMS.
Tahhan et al. (Tue,) studied this question.