Recent advancements in Artificial Neural Network-based temperature prediction and management of lithium-ion batteries: A comprehensive review
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it