Two-Stage Genetic Algorithm Offline Parameter Optimization of Adaptive Extended Kalman Filter for Robust Battery State-Of-Charge Estimation
Bibliographic record
Abstract
Accurately estimating battery state of charge (SOC) in electric vehicle applications (EVs) is crucial to ensure a safe and reliable vehicle operation. However, robust SOC estimation under all possible operating conditions is challenging due to varying load conditions, varying and non-linear battery impedance, sensor inaccuracies, among others. Meanwhile, battery management systems (BMS) are trending toward more compact designs to enhance reliability by reducing wiring and boosting energy density. Hence, minimizing the memory footprint of SOC estimation algorithms is a key challenge, as their design and tuning remain a time-consuming and costly process for the industry. This paper introduces an Adaptive Extended Kalman Filter (AEKF) algorithm with a two-stage genetic algorithm (GA) for parameter optimization. The first stage role is to find the equivalent circuit parameters’ optimal values in a non-SOC-dependent manner. The second GA optimizes the initial AEKF model tuning parameters. To mitigate the randomness of the GA, an algorithm is designed to automatically determine the optimum set of parameters with minimal user intervention. Finally, to avoid calibrating the AEKF to a Coulomb counter, the obtained parameters were tested locally and using an online tool to ensure the robustness of the estimator. The described algorithm achieves a low root mean square error (RMSE) of 0.7% to 2% across various positive and negative temperatures under several drive conditions. With this tool, the AEKF can be rapidly tuned with minimal user effort, providing fast and robust SOC estimation suitable for automotive applications.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".