Metraipolis › archive › dc_dbab03f5fbb4

Cross-Domain Joint-Embedding Pretraining For Heterogeneous Industrial Time Series — arXiv:2611.02489

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02489
License (as archived)
CC0-1.0
Archived
2026-11-03T10:48:22.304Z
SHA-256 of the archived text
bc273dc5a182a3a3cfef4c2b39c5c3dee14105c12cd7d85ac3cc3d80c455a3b7
Stable URL of this page
https://metraipolis.com/documento/dc_dbab03f5fbb4

How to cite

Cross-Domain Joint-Embedding Pretraining For Heterogeneous Industrial Time Series — arXiv:2611.02489 — arXiv (en), https://arxiv.org/abs/2611.02489 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbab03f5fbb4 (Metraipolis archive dc_dbab03f5fbb4, sha256 bc273dc5a182a3a3cfef4c2b39c5c3dee14105c12cd7d85ac3cc3d80c455a3b7)
BibTeX
@misc{dcdbab03f5fbb4,
  title = {Cross-Domain Joint-Embedding Pretraining For Heterogeneous Industrial Time Series — arXiv:2611.02489},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02489},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbab03f5fbb4; sha256 bc273dc5a182a3a3cfef4c2b39c5c3dee14105c12cd7d85ac3cc3d80c455a3b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02489. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial predictive maintenance and manufacturing tasks frequently contain abundant sensor measurements, but with limited labeled data. We investigate cross-domain self-supervised pretraining using joint-embedding predictive architecture for heterogeneous industrial time series (JEPA-HITS), which learns one encoder from various domains such as battery, semiconductor chemical mechanical planarization (CMP), computer numerical control (CNC) machining, and bearing while preserving dataset-specific temporal scales. We evaluate representation reuse on regression and classification problems under reduced-label downstream training, and leave-one-domain-out (LODO) pretraining. Compared with the same architecture initialized randomly, LODO pretraining reduces RMSE from 10.72 to 7.95 on battery remaining useful life (RUL), 4.34 to 3.89 on CMP, and 13.53 to 11.72 on tool wear regression, while improving bearing fault diagnosis macro-F1 from 0.547 to 0.737. Overall results suggest that unlabeled time series measurements from heterogeneous industrial processes can provide reusable representations for downstream learning with limited labeled data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02489 — 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 2026-11-03T10:39:50.575Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).