Correlation-aware kernel selection for multi-scale feature fusion of convolutional neural networks in multivariate and multi-step time series forecasting: Application to Li-ion battery state of health forecasting
Bibliographic record
Abstract
Proper forecasting of the State of Health (SOH) of lithium-ion batteries is crucial for enhancing performance, ensuring safety, and prolonging the lifespan of energy storage systems, particularly in electric vehicles and renewable energy applications. This study develops a Convolutional Neural Network (CNN) that incorporates multi-scale feature fusion to extract multi-resolution patterns through a correlation-aware, multi-scale kernel selection mechanism for multivariate and multi-step time series forecasting of battery SOH. The system includes two main parts: Preprocessing and modeling. The preprocessing of the raw battery data includes time series features extraction across statistical, temporal, and frequency domains; normalizing the data; and employing hybrid feature selection that utilizes both filter-based and wrapper-based methods. In the modeling part, the proposed CNN architecture is developed. This model includes a novel approach of determining adaptive kernel sizes that are established through cross-correlation of the input features, enabling the model to identify short-, medium-, and long-term patterns. Extensive experiments carried out on benchmark datasets provided by NASA and a commercial battery testing facility showcase the model's advantages compared to conventional CNNs, Long Short-Term Memory (LSTM) networks, fully connected neural networks (LNNs), and two combinations of LSTM and CNN. The suggested approach consistently results in notably reduced prediction errors and demonstrates greater robustness throughout repeated trials, affirming its promise as a dependable solution for practical battery prognostics.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".