Tag
FedCMAPSS introduces a benchmark for federated learning in remaining useful life estimation based on the NASA C-MAPSS dataset, with standardized tasks to evaluate federated optimization algorithms across neural architectures.
This paper presents a controlled study of federated learning for aircraft-engine remaining-useful-life prediction under both benign and adversarial client heterogeneity, evaluating personalization and Byzantine-robust aggregation methods. It finds that shared-representation personalization closes much of the local-central accuracy gap, robust aggregation with Krum effectively mitigates backdoor attacks, and combining both yields a composed defense with low attack success at a modest accuracy cost.
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.
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.
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.
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.
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.