State of Charge Estimation of Lithium-Ion Batteries Using Convolutional Neural Networks in Electric Vehicle Applications
Bibliographic record
Abstract
The emergence of Electric Vehicles (EVs) has introduced new issues and complexities, particularly in accurately gauging the remaining battery capacity or the distance an EV can travel before needing a recharge, known as the State of Charge (SoC) estimation problem. This study aims to develop an innovative solution to this problem while considering the usual computational complexity requirements. It emphasizes maintaining low memory and computational demands for practical implementation within a Battery Management System (BMS). By leveraging contemporary tools from artificial intelligence, especially Machine Learning (ML) models, the findings indicate that accurate SoC prediction can be achieved with simple ML models, given a well-curated dataset. Specifically, a Convolutional Neural Network (CNN) with two hidden layers and a limited number of hidden neurons shows promising results in estimating the SoC for a lithium-ion battery cell while maintaining low computational complexity. At 25°C, the CNN model reports a mean absolute error (MAE) of 0.97 and a root mean squared error (RMSE) of 1.71. This research offers significant potential for future advancements in SoC estimation, providing a solid foundation for addressing the issue and suggesting an optimal ML architecture for future BMSs to improve the SoC prediction accuracy.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".