Metraipolis › archive › dc_ea0976d593ad

Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data — arXiv:2611.06194

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06194
License (as archived): CC0-1.0
Archived: 2026-11-05T18:22:12.094Z
SHA-256 of the archived text: 450c83ec9ffd51e5c5c700390b89ce4291260260c7d877be70a1352eaaa10eee
Stable URL of this page: https://metraipolis.com/documento/dc_ea0976d593ad

How to cite

Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data — arXiv:2611.06194 — arXiv (en), https://arxiv.org/abs/2611.06194 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea0976d593ad (Metraipolis archive dc_ea0976d593ad, sha256 450c83ec9ffd51e5c5c700390b89ce4291260260c7d877be70a1352eaaa10eee)

BibTeX

@misc{dcea0976d593ad,
  title = {Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data — arXiv:2611.06194},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06194},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea0976d593ad; sha256 450c83ec9ffd51e5c5c700390b89ce4291260260c7d877be70a1352eaaa10eee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06194. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliability management of industrial fleets depends on early fault warnings, yet lifecycle data across similar assets are highly imbalanced. A few assets accumulate run-to-failure histories, while newly installed or rarely failing assets provide only normal-condition data. This paper asks how diagnostic knowledge can be transferred from a data-rich source asset to a data-scarce target asset when no fault data have been observed on the target. We formulate cross-asset early fault detection as a zero-shot domain adaptation problem, in which zero-shot refers to the absence of target fault samples, and propose a framework that requires only normal data from the target. The framework comprises (1) a statistical process control step that labels the source asset run-to-failure data with an exponentially weighted moving average chart, reducing manual annotation to verifying flagged segments, (2) an Adapted Domain-Adversarial Neural Network (ADANN) that combines domain-adversarial training and a Maximum Mean Discrepancy penalty with an Adapted Classification-Domain (ACD) loss, which anchors the classifier normal region to the target own normal data, and (3) an ahead-of-time labeling scheme with a prediction horizon that targets incipient faults. Under an exact-classification assumption, a theoretical analysis characterizes the domain-adversarial term for a normal-only target and the alignment state in which source fault features remain separated from target normal features. On a public run-to-failure bearing dataset, ADANN attains the highest mean F1-score among four transfer baselines, with a nominally significant precision gain over the strongest baseline, and its robustness is examined under synthetic noise.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.06194 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:15:49.013Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).