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

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-Image 1 updates while drawing less than Image 2. Classical observers drift under sensor bias, and purely data-driven models exceed the timing and memory ceilings of low-...

Full description

Saved in:
Bibliographic Details
Main Authors: Robin K.E. Tau, Abid Yahya, Mmoloki Mangwala, Nonofo M.J. Ditshego
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Machine learning
Battery management systems (BMS)
Lithium-ion batteries
SOC estimation
Edge AI
Embedded systems
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025024971
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate real-time state-of-charge estimation remains a bottleneck for e-bike battery management because firmware must deliver sub-Image 1 updates while drawing less than Image 2. 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 Image 3 and Image 4. HEAD-KF yields a global mean-absolute error of Image 5 SOC, keeps dynamic-discharge error to Image 6, and updates in Image 7 while consuming Image 8 per prediction. Covariance-perturbation and sensor-noise injections hold the estimator inside the ISO-12405 Image 9 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-Image 10 targets, and on-device drift detection to preserve accuracy as packs age.
ISSN:2590-1230

Similar Items