Battery state of charge prediction using deep neural networks and longshort term memory networks
Bibliographic record
Abstract
Accurate estimation of the State of Charge (SOC) of a battery is non-trivial given its non-linear and time varying electrochemical properties. It plays a major role in determining the overall state of health (SOH) of a battery and in electric vehicles (EVs) where range anxiety is a concern. Traditional methods to estimate SOC, which include Coulomb Counting and Extended Kalman Filter (EKF), come with several disadvantages in real-world applications such as complexity to setup. This paper uses a publicly available battery dataset with drive cycle tests between -20ºC and 40ºC to train a machine learning (ML) model to predict the battery’s SOC. Neural network architectures such as deep neural networks (DNNs) and long short-term memory networks (LSTMs) are experimented with. Best in class prediction results with each of these architectures show prediction errors comparable to or better than those in EKF literature. Results also show that for DNNs, larger models do not necessarily mean better prediction outcomes. For the LSTM models, however, more data combined with extended training is critical for good results. DNN models take significantly less time to train than LSTM, but they get comparable SOC prediction results with a mean average error (MAE) between 1 and 3%.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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 | 0.001 |
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".