Data Augmentation for Lithium-Ion Battery State-of-Charge Estimation Across Methods and Models

Accurate state-of-charge (SoC) estimation from voltage, current, and temperature is required for lithium-ion pack energy management. Learning-based estimators need labeled field traces that are costly on a deployed sensing chain, and data augmentation is used to enlarge those sets. Published studies almost always train one synthesizer for one learner, so it remains unknown which operators help which estimator classes, at what intensity, and after how much real labeled volume. In this paper, a factorial of classical, physics-informed, and generative operators is evaluated on twelve SoC estimators (dose L=1–10, labeled volume n=1–5; >5000 configurations) using dual stand–logger unmanned aerial vehicle (UAV) pack flights as the labeled corpus, with root-mean-square error (RMSE) scored on a locked acceptance trajectory. RMSE change versus the matched unaugmented baseline is class-conditional: sequential and convolutional estimators improve by +18% to +32%, LightGBM and XGBoost average ≈−2.4% and −4.9%, and a physics-informed network degrades by ≈22%. Labeled volume accounts for ≈53% of logRMSE variance versus ≈2% for synthesizer identity. Operators that preserve the empirical training distribution (thermo-voltage coupling and point shuffle) outrank mean-shift and TimeGAN. Dose L is a process parameter: thermo-voltage is optimal at L=8 for all eleven classical estimators, and selecting L on the acceptance set inflates reported gain by a factor of ≈2.5 relative to averaging over L. Admissible operators therefore depend on estimator class and on labeled volume n.