← Back to all news
arXiv AI By Zhuojun Xie, Adam Abdin, Yiping Fang

Data-Driven Maintenance Optimization: Aligning Prognostic Learning with Decision Objective

Read the original on arXiv AI →

The paper investigates data‑driven predictive maintenance where health‑condition estimation is coupled with an ordering‑replacement decision model. It shows that the traditional Estimate‑Then‑Optimize (ETO) approach can lead to inconsistent, suboptimal decisions and introduces an Integrated Estimate‑Optimize (IEO) framework that directly optimizes maintenance cost, bypassing conventional accuracy metrics. Experiments on CMAPSS data demonstrate that IEO reduces mean maintenance cost by 14.8–22.7% versus ETO and 7.2–11.8% versus a decision‑oriented baseline, while also lowering failure rates and cost variability, even when prediction errors are higher.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Aug 28

FedCMAPSS: A Benchmark for Federated Learning in Remaining Useful Life Estimation

FedCMAPSS is a new benchmark for federated learning applied to remaining useful life (RUL) estimation, built on the NASA C‑MAPSS dataset. It defines five standardized tasks that mimic real‑world industrial scenarios, from ideal IID conditions to highly heterogeneous data distributions. The paper evaluates state‑of‑the‑art federated optimization algorithms across multiple neural architectures, providing reproducible baselines and publicly available code and data splits.

By Amelia Sorrenti, Matteo Pennisi, Concetto Spampinato, Simone Palazzo
benchmarks
More like this →
arXiv Machine Learning
Sep 22

Uncertainty and Business-Aware Remaining Useful Life Estimation for Semiconductor Manufacturing

The paper presents a predictive maintenance framework for semiconductor manufacturing that combines deep learning sequence models with simultaneous quantile regression to provide uncertainty‑aware remaining useful life (RUL) estimates. It evaluates several architectures—including state‑space models—on ion‑milling data from the 2018 PHM Data Challenge, showing that the Diagonal State Space (S4D) model delivers the most accurate RUL predictions across quantiles. Compared to preventive maintenance baselines, the S4D approach significantly reduces business costs by avoiding unnecessarily early interventions.

By Davide Frizzo, Francesco Borsatti, Gian Antonio Susto
More like this →