remaining-useful-life

Tag

Cards List
#remaining-useful-life

Physics-Guided Masked Multi-Task Network for Edge-Friendly Battery Health Diagnostics from Sto-chastically Fragmented Charging Profiles

arXiv cs.LG · 6d ago Cached

Proposes RoSIP-Batt, a physics-guided multi-task transformer for joint estimation of battery State of Health and Remaining Useful Life, achieving state-of-the-art accuracy on NASA, MIT-Stanford, and HUST datasets.

0 favorites 0 likes
#remaining-useful-life

Leakage-Robust Evaluation and Data-Scale Sensitivity of Attention-Enhanced Multi-Task Learning for Joint Fault Diagnosis and Remaining Useful Life Estimation

arXiv cs.LG · 2026-07-21 Cached

This paper demonstrates that naive train/test splitting on sliding-window sequences can severely inflate or deflate performance metrics in multi-task learning for predictive maintenance, and proposes a leakage-robust evaluation protocol.

0 favorites 0 likes
#remaining-useful-life

Quantum Annealing Enhanced Reinforcement Learning for Accurate Remaining Useful Lifetime Prediction

arXiv cs.LG · 2026-06-18 Cached

This paper proposes a quantum annealing enhanced Q-learning framework for remaining useful life prediction, using the D-Wave system to solve QUBO formulations for action selection. It outperforms classical and quantum baselines on NASA C-MAPSS and predictive maintenance datasets.

0 favorites 0 likes
#remaining-useful-life

Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation

Hugging Face Daily Papers · 2026-06-10 Cached

This paper introduces a lightweight approach for remaining useful life estimation using frozen embeddings from the Chronos-2 time-series foundation model combined with a simple regression head, achieving superior performance on industrial sensor data compared to baseline methods.

0 favorites 0 likes
#remaining-useful-life

Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction

arXiv cs.LG · 2026-06-01 Cached

This paper presents a multi-task scientific machine learning framework for turbine prognostics that jointly predicts engine health metrics and remaining useful life with quantified uncertainty, using a shared sequence encoder and task-specific heads.

0 favorites 0 likes
← Back to home

Submit Feedback