PFFN: A Parallel Feature Fusion Network for Remaining Useful Life Early Prediction of Lithium-Ion Battery
Bibliographic record
Abstract
Remaining useful life (RUL) early prediction of lithium-ion battery (LIB) is crucial to develop advanced battery health management and complete security assessment. However, most of the existing methods still suffer from two limitations, i.e., the inadaptability to the different data distribution and the inability to capture the relationship between input series and RUL, which always make the RUL early prediction difficult and challengeable. To address these issues, this article proposes a parallel feature fusion network (PFFN) for RUL early prediction of LIB. First, a feature selection strategy is designed to filter the optimal feature sets (containing cycle statistical features and domain knowledge-based features) that are most related to RUL of LIB. Second, two specific transformer encoders connected in parallel configuration are developed to integrate the cycle statistical features and domain knowledge-based features, respectively, achieving original RUL early prediction results. Furthermore, Bayesian optimization is applied for global iterative optimization, aiming to enhance the prediction accuracy and generalization capability. A series of experiments are conducted with different data distributions. Experimental results demonstrate that the proposed PFFN outperforms the state-of-the-art (SOTA) methods, achieving 6.00%~27.61%, 0.58%~6.49%, and 5.95%~7.03% reduction in root mean square error (RMSE), mean absolute percentage error (MAPE), and score, respectively.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".