Deep Learning for Data Modeling of Multirate Quality Variables in Industrial Processes

Recently, deep-learning (DL)-based soft sensor has been widely applied to industrial processes, which plays a vital role for process monitoring, control, and optimization. However, most existing soft sensor models are established for only one quality variable or multiple quality variables with the s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on instrumentation and measurement Jg. 70; S. 1 - 11
Hauptverfasser: Yuan, Xiaofeng, Feng, Lu, Wang, Kai, Wang, Yalin, Ye, Lingjian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Belief networks
Biological system modeling
Boiling points
Data models
Deep learning
Deep learning (DL)
Hexadecane
multirate sampling
Oils
Optimization
Predictive models
Process control
quality variables
Sensors
soft sensor
stacked autoencoder (SAE)
Training
Variables
ISSN:0018-9456, 1557-9662
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recently, deep-learning (DL)-based soft sensor has been widely applied to industrial processes, which plays a vital role for process monitoring, control, and optimization. However, most existing soft sensor models are established for only one quality variable or multiple quality variables with the same sampling rate. There are very few models focusing on prediction for multirate quality variables, especially with DL networks. To handle this problem, a novel DL strategy based on multirate stacked autoencoder (MR-SAE) is proposed. In MR-SAE, the network is composed of two parts: the cascade shared network for joint feature representations and the parallel quality-specific network for individual feature learning and quality prediction. The training procedure consists of three steps for MR-SAE. First, the available input data are used to pretrain the shared network. Then, all the multirate data are used to fine-tune the whole network. Finally, individual fine-tuning is further carried out for quality-specific subnetworks. The proposed MR-SAE method is used to build a unified soft sensor model for predicting both the 50% boiling point and cetane content of diesel oil. The results show that the performance of MR-SAE-based model is superior to SAE and deep belief networks. Moreover, the parameters and training time of MR-SAE model are less than the other two methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2021.3075754