Introducing Time-lag and Bi-LSTM Neural Network for In-Operando Surface Temperature Estimation in Lithium-ion Batteries
Bibliographic record
Abstract
Automotive lithium-ion battery (LIB) packs comprise hundreds to thousands of individual cells to achieve the required DC bus voltage for the powertrain. The operating temperature of LIBs significantly influences performance and serves as a key indicator of potential thermal runaway and catastrophic failure. However, monitoring the temperature of individual cells remains challenging due to the cost, complexity, and wiring demands of conventional battery management systems (BMS). This paper proposes a bidirectional long short-term memory (Bi-LSTM) neural network that utilizes commonly available BMS parameters voltage, current, and ambient temperature along with a time-lag feature to accurately estimate surface temperature. The model is experimentally validated on a 14 -cell LIB module equipped with an automotive-grade BMS from NXP®. Results show that the proposed algorithm estimates surface temperature with the mean absolute error as low as $0.151^{\circ} \mathrm{C}$ and a root mean square error as low as $0.171^{\circ} \mathrm{C}$, when compared to actual measurements during constant-current constant-voltage (CC-CV) charging and constant-current (CC) discharging across a wide operating temperature range ($0^{\circ} \mathrm{C}$ to $40^{\circ} \mathrm{C}$) and C -rate. This study demonstrates the practical feasibility of the approach, which relies solely on existing BMS data eliminating the need for direct surface temperature measurements, reducing system cost and complexity, while maintaining high accuracy under diverse thermal conditions.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| 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".