Fault Tolerant, Adversarial and Highly Available Lithium Batteries Health Monitoring Framework
Bibliographic record
Abstract
Lithium batteries are becoming highly popular and used as a viable renewable energy source to compensate the shortage of other energy sources such as fossil fuels. Batteries are subject to external events such as collisions, shocks and vibrations and internal events such as overcharging, excessive discharging that can cause batteries to malfunction. One of the main external events that cause direct failure of lithium batteries are failure related to sensors, knowingly: Temperature, Voltage and Current. Batteries failures, especially at the sensors level represent a major challenge for battery health monitoring frameworks. Wireless BHM frameworks are becoming more popular which exposes them to malicious cyber attacks threatening the reporting accuracy of underlying BHM frameworks which can cause life threatening harm especially in systems such as aircrafts or medical implantable cardioverter defibrillator. It becomes crucial to implement BHM frameworks that relies on sensor readings to accurately predict batteries metrics such as state of charge (SOC), state of health (SOH) and remaining useful life (RUL) while been fault tolerant to any sensor failure, highly available by keeping sensor readings available even if sensors are deemed nonoperational, finally, adversarial to any potential cyber attacks especially in the era of wireless BHM frameworks. Our main contribution in this thesis is to offer a BHM framework that is equipped with a fault detection and isolation module that reports any sensor malfunction to a prognostic accurate, fault tolerant, adversarial and highly available module. The four key attributes, knowingly, accuracy, fault tolerance, adversariality and highly availability makes the proposed BHM framework robust, agile and more reliable to work in extreme conditions where battery sensors are subject to external hazards. The proposed prediction models’ effectiveness was evaluated using two batteries datasets, the first one is developed by NASA and the second one is developed by Toyota research institute. Testing the proposed predictive models against large datasets prove that the models are robust and their prediction accuracy does not decrease with data volume. The performance of the suggested prognostic frameworks was evaluated using the error indicators Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and the R square (R2).
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 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".