XGBoost–random forest stacking with dual-state Kalman filtering for real-time battery SOC estimation

Accurate real-time state-of-charge estimation remains a bottleneck for e-bike battery management because firmware must deliver sub-[Figure presented] updates while drawing less than [Figure presented]. Classical observers drift under sensor bias, and purely data-driven models exceed the timing and memory ceilings of low-cost microcontrollers. This study therefore proposes the Hybrid Ensemble Dual-State Kalman Filter (HEAD-KF), which fuses Extreme Gradient Boosting and Random-Forest regressors through non-negative ridge stacking and smooths the fused output with a dual-state Kalman filter whose noise covariances are tuned online from residual statistics. The pipeline runs end-to-end on a Raspberry Pi 4 and is validated on a 20S Samsung INR18650-25R pack that uses NCA chemistry and is cycled between [Figure presented] and [Figure presented]. HEAD-KF yields a global mean-absolute error of [Figure presented] SOC, keeps dynamic-discharge error to [Figure presented], and updates in [Figure presented] while consuming [Figure presented] per prediction. Covariance-perturbation and sensor-noise injections hold the estimator inside the ISO-12405 [Figure presented] band, and ablation tests show that removing either the ensemble fusion or the adaptive Kalman loop doubles the error. These results indicate that HEAD-KF satisfies the accuracy, timing, and energy constraints of embedded battery-management systems on commodity hardware, and they motivate future work on cross-chemistry retraining, aggressive model compression for sub-[Figure presented] targets, and on-device drift detection to preserve accuracy as packs age.