Battery state of charge estimation using kalman filter in Matlab

Neural ODE-based State of Charge (SOC) estimation for Li-ion batteries using the NASA Battery Dataset. Built as a weekend project to explore learned dynamics for battery modeling, with visualizations designed for engineering audiences.

Sandbox to develop, test and compare neural network-enabled estimation techniques for state of charge of a sample lithium-ion battery using deep learning methodologies, utilizing transient signals to predict state across points in time.

MATLAB implementation of VBMCCKF for Li-ion battery SOC estimation.

Prior-based patch-level representation learning for electric vehicle battery state-of-charge estimation across a wide temperature scope

Battery SOC estimation using equivalent circuit models, EKF, embedded-oriented implementation, and C firmware-style code

Research-grade, AI-augmented Battery Management System (BMS) digital twin for a multi-cell Li-ion pack: ECM, thermal, balancing, SOC estimation (EKF/UKF/LSTM), hybrid fault detection, FMEA/RUL, EV range prediction, plus a Streamlit dashboard. 155 tests passing.

Battery Management System (BMS) State of Charge (SoC) estimator for Lithium-Ion batteries using an Extended Kalman Filter (EKF). Features a realistic simulation environment with sensor fusion, noise compensation, and voltage relaxation dynamics modeling.

MATLAB/Simulink battery SOC estimation project comparing Coulomb Counting, EKF, and UKF using a 1-RC lithium-ion battery model.

Self-calibrating Dual Extended Kalman Filter (DEKF) state-of-charge estimator for LFP home batteries — AppDaemon apps for Home Assistant

Simulation and Data Science Project: Model-based State-of-Charge estimation with a Kalman filter (MATLAB/Simulink) and data-driven Remaining-Useful-Life prediction using a Long Short-Term Memory Recurrent Neural Network (PyTorch).