A self-attention-based CNN-Bi-LSTM model for accurate state-of-charge estimation of lithium-ion batteries
Bibliographic record
Abstract
In the quest for clean and efficient energy solutions, lithium-ion batteries have emerged at the forefront of technological innovation. Accurate state-of-charge (SOC) estimation across a broad temperature range is essential for extending battery longevity, and enduring effective management of overcharge and over-discharge conditions. However, prevailing challenges persist in achieving precise SOC estimates and generalizing across a wide temperature range, particularly at lower temperatures. Our comparative analysis reveals that, while a single-layer bidirectional LSTM model with a self-attention mechanism achieves remarkable SOC estimation accuracy at room temperature, the intricacies of SOC estimation at lower temperatures necessitate the incorporation of more hidden layers and more complex network architecture to capture intricate features influencing battery dynamics. Hence, we propose a deep learning model, based on convolutional neural networks integrating bidirectional long short-term memory and self-attention mechanism (CNN-Bi-LSTM-AM), specifically designed to tackle the challenges of achieving accurate SOC estimations across a wide temperature range. The proposed model demonstrates proficiency in capturing both spatial and temporal dependencies critical for lithium-ion battery SOC estimation. Furthermore, the integration of a self-attention mechanism enhances the model’s adeptness to discern pertinent features and patterns within the dataset, thereby improving its overall performance and robustness, even in sub-room temperature environments.
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 | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".