EUVIMEDEUVIMED entdecken
Crossref

Bidirectional gated feature pyramid network‐decoupled variational autoencoder for robust soft sensing in multi‐rate industrial processes

Jingyun Xu, Kexin Fang, Chenghui Mo, Peiliang Wang

The Canadian Journal of Chemical Engineering · 12.11.2026

DOI: 10.1002/cjce.70647 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Canadian Journal of Chemical Engineering, online erschienen am 12.11.2026. Verfasst von Jingyun Xu und 3 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi‐rate data are common in industrial processes and pose significant challenges for robust soft sensing. Although the multi‐rate pyramid variational autoencoder regression model has been developed to handle such data, it still suffers from latent variable feature entanglement and noise‐sensitive information propagation. To address these issues, this paper proposes a bidirectional gated feature pyramid network‐decoupled variational autoencoder for robust soft sensing in multi‐rate industrial processes. The proposed model decouples process data into quality‐relevant and quality‐irrelevant latent variables across multiple time scales. A mutual information maximization term is introduced to preserve key quality‐related information, thereby mitigating feature entanglement. In addition, a bidirectional gated fusion pyramid network is designed, which integrates top‐down semantic and bottom‐up detail streams and employs learnable gates to enable adaptive cross‐resolution fusion and effective noise suppression. Experimental results on numerical and industrial benchmark datasets demonstrate that the proposed method achieves superior prediction accuracy and robustness over mainstream approaches, offering an effective solution for multi‐rate soft sensing applications.

Zitieren

APA

Xu, J., Fang, K., Mo, C., & Wang, P. (2026). Bidirectional gated feature pyramid network‐decoupled variational autoencoder for robust soft sensing in multi‐rate industrial processes. The Canadian Journal of Chemical Engineering. https://doi.org/10.1002/cjce.70647

Vancouver

Xu J, Fang K, Mo C, Wang P. Bidirectional gated feature pyramid network‐decoupled variational autoencoder for robust soft sensing in multi‐rate industrial processes. The Canadian Journal of Chemical Engineering. 2026. doi:10.1002/cjce.70647

BibTeX
@article{Xu2026,
  author = {Xu, Jingyun and Fang, Kexin and Mo, Chenghui and Wang, Peiliang},
  title = {Bidirectional gated feature pyramid network‐decoupled variational autoencoder for robust soft sensing in multi‐rate industrial processes},
  journal = {The Canadian Journal of Chemical Engineering},
  year = {2026},
  doi = {10.1002/cjce.70647}
}
Kostenlos starten →