Physics-Informed NN for Improving Electric Vehicles Lithium-Ion Battery State-of-Charge Estimation Robustness
Bibliographic record
Abstract
Electric vehicles (EVs) are often powered by lithium-ion batteries. To ensure the reliability of EVs, it is essential to model and predict the remaining useful life of these batteries. Accurate estimation of the state of charge (SoC) is a critical aspect for effectively managing and ensuring operational reliability of battery systems. Building principled accurate models is challenging due to the complex electrochemistry that governs battery operation. This research paper presents a novel approach that utilizes Physics-Informed Neural Networks (PINNs) to enhance the accuracy of SoC estimation. PINNs combine the data-driven learning capabilities of neural networks with the fundamental physical laws that govern battery dynamics. By incorporating both aspects, PINNs offer a novel way to improve the accuracy of SoC estimation in lithium-ion batteries and enable better management of battery systems in the context of electric vehicles. We demonstrate how incorporating physical constraints into the learning process enhances model prediction performance and ensures physically plausible solutions. The approach is validated using data publicly available through the Mendeley Data website by McMaster University in Hamilton, Ontario, Canada. Results showed that our proposed robust approach can successfully overcome the measurement's errors and noise. Moreover, the model can obtain an SoC estimation accuracy of less than 2.85% root mean squared error (RMSE).
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".