Deep Learning-Based Estimation of Li-Ion Battery State of Charge: Comparative Analysis of CNN, LSTM, and GRU Approaches
Bibliographic record
Abstract
The growing demand for accurate battery state monitoring in electric vehicles has driven significant advancements in data-driven estimation methods. In recent years, deep learning-based approaches have emerged as powerful alternatives to traditional model-based techniques for State of Charge (SoC) prediction. This study systematically evaluates three neural network architectures : Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) for lithium-ion battery SoC estimation under varying temperature conditions using the LG 18650HG2 dataset. The normalized input features (voltage, current, and temperature) are directly fed into each model, and their performance is assessed using standard regression metrics. The experimental results show that all models achieve high estimation accuracy, with the GRU model demonstrating superior robustness and precision. Notably, at 40°C, the GRU achieves an RMSE of 0.4%, MAE of 0.7%, and an R2score of 99.8%, outperforming the CNN and LSTM. These findings confirm the effectiveness of recurrent models in capturing the temporal dependencies inherent in battery data. The GRU architecture, in particular, it effectively navigates the trade-off between prediction precision and computational load, which renders it appropriate for deployment in real-time battery management systems.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".