Semisupervised dynamic soft sensor based on complementary ensemble empirical mode decomposition and deep learning

•CEEMD and Isomap are combined to eliminate noise and redundancy in the data.•A new semisupervised dynamic soft sensor model named SSDGRU-CNN is proposed.•The soft sensor methodology has good dynamic performance and prediction accuracy.•The effectiveness is proven by measuring the rotor deformation...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Measurement : journal of the International Measurement Confederation 2021-10, Vol.183, p.109788, Article 109788
Hauptverfasser:	Guo, Runyuan, Liu, Han
Format:	Artikel
Sprache:	eng
Schlagworte:	Complementary ensemble empirical mode decomposition Correlation coefficients Deep learning Dynamic characteristics Gated recurrent unit Heating equipment Measurement Noise Redundancy Rotor thermal deformation Semisupervised dynamic modeling Sensors Soft sensor
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!