Integrating Physics-Informed Neural Networks and GRU for SciML-based Surface Temperature Prediction Li-ion Battery
Bibliographic record
Abstract
Optimal temperature conditions are critical for maintaining the performance, lifespan, and safety of lithiumion batteries (LIBs). Deviations from these conditions can lead to severe degradation, performance losses, or even catastrophic failure. Therefore, accurate and reliable surface temperature estimation is essential for effective thermal management and the safe operation of these batteries. This study proposes a novel approach for estimating the surface temperature of LIBs by integrating a gated recurrent unit (GRU) network with physics-informed neural networks (PINNs). The GRU network enables precise handling of sequential data, capturing temporal dependencies effectively and providing structured input that aligns with the data requirements of the PINN model. In turn, the physics-informed neural network utilizes this sequence to model the thermal behavior of the lithium-ion cells while embedding the underlying physics of heat transfer within the battery. By combining GRU and PINN, the proposed approach achieved the surface temperature prediction error as low as $\mathbf{0. 3 6}^{\circ} \mathbf{C}$, offering a practical tool for predictive thermal management of LIBs. This method not only enhances prediction accuracy but also provides insights into the fundamental thermal dynamics, paving the way for safer and more efficient battery operation.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".