Energy & materialsResearch findings
Dynamic Fusion of Multi-Source Data for Accurate Battery Lifespan Prediction
Original published 2025.04.25 19:24 KSTAdded to Blackdeck 2026.11.09 05:26 KST
What has changed?
A dynamic weighting mechanism fuses heterogeneous datasets to improve prediction accuracy
Key points
- Integrates NASA, CALCE, MIT-Stanford-Toyota data to enhance lifespan prediction accuracy
- Stacked ensemble model combining Ridge regression, LSTM, and XGBoost captures temporal and nonlinear degradation patterns
- Achieves MAE of 0.0058, RMSE of 0.0092, and R² of 0.9839, outperforming baseline models
Connect it to your work
Entropy-based weighting reduces variability across diverse data sources
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.