Dynamic historical information incorporated attention deep learning model for industrial soft sensor modeling

Due to the limitations of sampling conditions and sampling techniques in many real industrial processes, the process data under different sampling conditions subject to different sampling frequencies, which leads to irregular interval sampling characteristics of the entire process data. The dynamic...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Advanced engineering informatics Jg. 52; S. 101590
Hauptverfasser:	Wang, Yalin, Liu, Diju, Liu, Chenliang, Yuan, Xiaofeng, Wang, Kai, Yang, Chunhua
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.04.2022
Schlagworte:	AD-SAE Attention mechanism Deep learning Soft sensor Stacked autoencoder Deep learning Stacked autoencoder Attention mechanism Soft sensor AD-SAE
ISSN:	1474-0346, 1873-5320
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!