Metraipolis › archive › dc_f1725fa46049

What Streaming Anomaly Detection Finds (and Misses) in Industrial Time Series — arXiv:2609.39232

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39232
License (as archived)
CC0-1.0
Archived
2026-10-07T12:45:05.362Z
SHA-256 of the archived text
f3eb9a109c27d2a60a53a6b7e9ca405625e5d93ac2f5ce2601f92d2559723160
Stable URL of this page
https://metraipolis.com/documento/dc_f1725fa46049

How to cite

What Streaming Anomaly Detection Finds (and Misses) in Industrial Time Series — arXiv:2609.39232 — arXiv (en), https://arxiv.org/abs/2609.39232 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1725fa46049 (Metraipolis archive dc_f1725fa46049, sha256 f3eb9a109c27d2a60a53a6b7e9ca405625e5d93ac2f5ce2601f92d2559723160)
BibTeX
@misc{dcf1725fa46049,
  title = {What Streaming Anomaly Detection Finds (and Misses) in Industrial Time Series — arXiv:2609.39232},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39232},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1725fa46049; sha256 f3eb9a109c27d2a60a53a6b7e9ca405625e5d93ac2f5ce2601f92d2559723160},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39232. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

EDF relies on continuous monitoring of its power plants to detect anomalies as soon as they occur. Given the absence of a universally optimal streaming method in unsupervised settings, we compare streaming methods with state-of-the-art TSAD models deployed online on a real nuclear power plant dataset. This work also evaluates Automated Anomaly Detection in a streaming context. Results show higher consistency for online TSAD and strong robustness from ensembling strategies.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.39232 — 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 2026-10-07T12:14:14.039Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).