Metraipolis › archive › dc_187eb65a59bc

Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance — arXiv:2609.04840

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04840
License (as archived)
CC0-1.0
Archived
2026-10-16T22:20:57.790Z
SHA-256 of the archived text
a392420b85e1e24a6d8237a59f2f23836372a54b2b38f13c86076215bf6276c0
Stable URL of this page
https://metraipolis.com/documento/dc_187eb65a59bc

How to cite

Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance — arXiv:2609.04840 — arXiv (en), https://arxiv.org/abs/2609.04840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_187eb65a59bc (Metraipolis archive dc_187eb65a59bc, sha256 a392420b85e1e24a6d8237a59f2f23836372a54b2b38f13c86076215bf6276c0)
BibTeX
@misc{dc187eb65a59bc,
  title = {Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance — arXiv:2609.04840},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04840},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_187eb65a59bc; sha256 a392420b85e1e24a6d8237a59f2f23836372a54b2b38f13c86076215bf6276c0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon predictive maintenance requires models to distinguish slowly evolving degradation from normal operating-regime variation over planning windows measured in days rather than hours. This paper evaluates whether an explicit conditional-quantile representation provides an informative classifier interface for this problem. The proposed TQRNN30d framework combines a dual-stage quantile regression neural network (QRNN) feature extractor with a multi-stream temporal fusion classifier. Each hourly word of 81-channel machine behaviour is mapped to a 324-dimensional quantile-state representation, and 720 ordered hourly words form the 30-day document supplied to the long-horizon model. The classifier fuses quantile states with dynamic covariates, channel-level static metadata, and a 168-hour latent-history stream using gated residual processing, causal recurrent encoding, and metadata-conditioned cross-modal attention. A bounded instability-aware signal derived from sustained one-word-ahead prediction-error divergence provides auxiliary memory modulation at the longest horizon. Evaluation uses a machine-disjoint 43/14/15 train/validation/test allocation across 72 machines in nine manufacturing facilities. At 30 days, TQRNN30d achieves 79.97% F1, 80.18% recall, 81.82% precision, 82.39% accuracy, and 0.820 ROC-AUC. It leads all 18 evaluated baselines at the 7-, 14-, and 30-day fixed-threshold comparisons, with the largest F1 advantage at 14 days. The results support held-out-machine performance within the observed homogeneous nine-facility fleet, but do not establish unseen-site, cross-equipment, or cross-sector generalisation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.04840 — 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 2026-10-16T22:18:11.399Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).