Online Fault Tolerant RUL Prediction Strategy for Lithium-Ion Batteries Using Machine Learning
Bibliographic record
Abstract
The deterioration of lithium-ion batteries can lead to electrical system failures and potentially catastrophic consequences. Consequently, predicting the remaining useful life (RUL) of batteries is essential to prevent such failures and related issues. Reliable, accurate, and straightforward RUL prediction is crucial for effective power management in electric vehicles and to mitigate the risk of battery failure. This study introduces a highly available fault-tolerant prediction framework designed to forecast the RUL of lithium-ion batteries in challenging scenarios where key features such as voltage, current, and temperature are unavailable. The framework utilizes an Improved Convolutional Long Short-Term Memory Deep Network (Imp-CLD), a hybrid machine learning algorithm integrating Deep Neural Networks, Convolutional Neural Networks, and Long Short-Term Memory networks. Performance metrics including Mean Absolute Error, Absolute Error, Relative Error, and Root Mean Square Error are used to assess the accuracy of RUL predictions. The model’s ability to maintain accuracy is influenced by the point at which predictions begin, as earlier predictions introduce higher levels of uncertainty due to accumulating errors over time. The proposed method is experimentally validated using datasets from the Massachusetts Institute of Technology and the Center for Advanced Life Cycle Engineering. The results indicate that this approach demonstrates greater resilience in predicting RUL, thereby enhancing lifetime control strategies and the safety monitoring function of the battery. This framework maintains prediction accuracy even when all features are missing at the prediction time, potentially preventing short-term catastrophes.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 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".