State of health (SOH) prediction for Lithium-ion batteries using regression and LSTM

Sunwoda Electronic Co., Ltd, and Tsinghua Berkeley Shenzhen Institute (TBSI) generate the TBSI Sunwoda Battery Dataset. We open-source this dataset to inspire more data-driven novel material verification, battery management research and applications.

An awesome list of papers on remaining useful life (RUL) prediction from arXiv

The project analyzes battery cycling data to predict degradation patterns and performance metrics using both deep learning (LSTM) and traditional machine learning (XGBoost) approaches. The implementation enables accurate estimation of battery health, which is crucial for battery management systems in various applications.

A comprehensive simulation platform integrating vehicle dynamics, environment emulation, body controls, and battery management for holistic testing and validation of automated vehicles.

A reproducible battery prognostics repository with a three-layer physics defense, bounded real-data reporting, and uncertainty-aware evaluation.

Sandbox to develop, test and compare Kalman Fitler-enabled estimation techniques for state of charge of a sample lithium-ion battery, utilizing transient signals to predict state across points in time.

Repository of my master’s thesis "Development and evaluation of a model for predicting the state of health of traction batteries based on artificial neural networks"

translation for paper Machine learning pipeline for battery state-of-health estimation

Code and models for estimating the State of Charge (SoC) and of battery cells. Utilizing advanced deep learning techniques.

ML + multi-criteria decision framework for EV-battery end-of-life routing under EU, GBA, and India regulatory regimes. Live Streamlit demo with model weights hosted on the Hugging Face Hub.

Evidence-first long-horizon SOH digital twin for LFP energy storage

A modular Python-based Electric Vehicle (EV) powertrain R&D simulator. High-fidelity modeling of longitudinal dynamics, battery behavior (SOC, SOH, and Thermal), and motor efficiency maps. Includes an interactive Streamlit dashboard and a sensitivity analysis suite for parametric optimization and benchmarking against industry-standard drive cycles

LSTM-based prediction of lithium-ion battery State of Health (SOH) and Remaining Useful Life (RUL) using cycle-level degradation data in PyTorch.

Bayesian hierarchical inference for Li-ion battery State-of-Health prediction | PyMC + NumPyro

Research-style project documentation for EV Li-ion battery State of Health estimation using XGBoost and LightGBM.

Repository for "Volt-Guardian XAI" (Accepted at ICAIA 2026). A hybrid GA-XGBoost and SHAP framework for predicting and explaining Electric Vehicle (EV) battery State of Health (SoH).

End-to-end ML & DL pipeline for battery State of Health (SOH) estimation with transfer learning and domain adaptation

苏州科技大学《人工智能开发实训 II》（2026.05）。实践二：MSTAR SAR半监督学习（FixMatch完整网格搜索+报告分节素材）；实践三：锂离子电池SOH预测（三种划分+20次独立实验+消融）；ResNet32 GA+PSO通道宽度搜索（H100/L40S）。附完整工具链、实验结果与答辩素材。