Diagnosis and Prognosis of Lithium-Ion Batteries State Using Machine Learning
Bibliographic record
Abstract
Lithium-ion batteries (LIBs) have recently emerged as the dominant energy storage solution for electric vehicles (EVs) and stationary energy storage systems.However, safety and reliability concerns continue to impede their widespread adoption, particularly in the EV market.As battery aging leads to capacity and power decline, it directly impacts the range and safety of EVs, emphasizing the urgent need for sustainable energy solutions.Battery management systems (BMS) have been developed to control battery operations by measuring variables such as voltage, current, and temperature of the battery, enabling the estimation of various critical states within the battery.Among these states, precise health estimation and temperature monitoring are crucial for extending battery life and mitigating potential risks.This doctoral thesis explores novel methodologies aimed at enhancing the longevity and performance of LIBs through precise health and temperature estimation.Initially, the research introduces a meticulous long-term estimation of the state of health (SOH) and prediction of remaining useful life (RUL) utilizing nonlinear autoregressive with exogenous input (NARX) recurrent neural networks (RNN).Given the dependency of battery health estimation accuracy on the quality and quantity of available data, the study emphasizes the critical need for establishing reliable battery health prognosis methods, especially in industries where sensor data may be intermittently inaccessible.Subsequently, this thesis presents further research introducing an accurate model for estimating LIBs' SOH utilizing NARX recurrent neural networks, even in scenarios where certain features are subject to random missing measurements.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 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".