RUL and battery-rul-prediction
These are **competitors** — both implement neural network approaches (Transformer and LSTM/Transformer respectively) to predict remaining useful life of lithium-ion batteries, targeting the same problem domain with overlapping technical solutions.
About RUL
XiuzeZhou/RUL
Transformer Network for Remaining Useful Life Prediction of Lithium-Ion Batteries
Implements attention-based and mixture-of-experts variants (AttMoE) for cycle-level degradation modeling, evaluated on NASA and CALCE benchmark datasets. Built with PyTorch, the architecture incorporates tunable dropout and noise injection parameters to improve robustness during training. Supports end-to-end RUL forecasting from electrochemical time-series data with configurable sequence encoding strategies.
About battery-rul-prediction
MystiFoe/battery-rul-prediction
Professional Battery RUL Prediction System with Advanced Machine Learning - Predicting Remaining Useful Life (RUL) and State of Performance (SOP) of lithium-ion batteries using LSTM, Transformer, and Ensemble models with 95%+ accuracy. Features real-time analytics dashboard, REST API, and production-ready deployment.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work