An industrial process monitoring method based on fusion of multi-scale sparse autoencoder and dual-branch slow feature architecture

•MSAE-DSFA merges multi-scale sparse AEs and dual slow feature for monitoring.•Tackles info redundancy, nonlinearity and slow faults in industrial processes.•Enhances fault detection and outperforms similar methods in two industrial cases.•Delivers solutions and support for process safety and optimi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Chemical engineering science Jg. 321; S. 122924
Hauptverfasser:	Ling, Guobi, Wang, Zhiwen, Wang, Jieying, Shi, Yaoke, Li, Long, Zeng, Jingxiao
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.02.2026
Schlagworte:	Dual-branch slow feature structure Feature extraction Multi-scale sparse autoencoder Process monitoring Whitening operation Process monitoring Whitening operation Feature extraction Dual-branch slow feature structure Multi-scale sparse autoencoder
ISSN:	0009-2509
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!