Enchancing SOC Estimation Hybrid RNN Models for Li-Ion Batteries Under Various Temperatures
Bibliographic record
Abstract
Accurate estimation of State of Charge (SOC) across different temperatures is essential for ensuring the optimal performance and dependability of electrical systems, particularly in electric vehicles, Electrical Vertical Take-Off and Landing aircraft (eVTOLs), and smart devices. In this study, both hybrid and non-hybrid models are evaluated through a dynamically structured neural network to identify the most efficient approach for SOC prediction. The model architecture, which includes layer types, neuron counts, activation functions, and batch normalization, is optimized to enhance performance. A comparative analysis demonstrates that hybrid models achieve superior efficiency in SOC estimation, with lower Mean Absolute Error (MAE) values and enhanced generalization across varying temperature conditions. The findings indicate that combining various recurrent architectures enhances both adaptability and precision, making hybrid models a more effective and reliable option for SOC estimation. To further explore model performance, a dynamic model generation strategy was employed, enabling the construction of diverse architectures using real-world battery data collected under various driving cycles and temperature conditions. Among the evaluated models, the GRU-LSTM hybrid architectures achieved the lowest MAE values, demonstrating their improved generalization capability across diverse thermal and operational conditions.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".