Prediction of Multiple Molten Iron Quality Indices in the Blast Furnace Ironmaking Process Based on Attention-wise Deep Transfer Network

Molten iron quality (MIQ) indices prediction based on data-driven models is an important way to monitor product quality and smelting status in the blast furnace ironmaking process. However, some challenges still place in the MIQ prediction: 1) limited nonlinear and dynamic description capabilities a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on instrumentation and measurement Jg. 71; S. 1
Hauptverfasser: Jiang, Ke, Jiang, Zhaohui, Xie, Yongfang, Pan, Dong, Gui, Weihua
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Attention-wise deep network
Blast furnace
Computational modeling
Denoising autoencoder (DAE)
Heuristic algorithms
Iron
Ironmaking
Modules
Molten iron quality
Multitask transfer learning
Prediction
Predictive models
Process variables
Silicon
Smelting
Task analysis
ISSN:0018-9456, 1557-9662
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Molten iron quality (MIQ) indices prediction based on data-driven models is an important way to monitor product quality and smelting status in the blast furnace ironmaking process. However, some challenges still place in the MIQ prediction: 1) limited nonlinear and dynamic description capabilities and interpretability of data-driven models; 2) high demand on the number of the labeled samples; 3) insufficient exploration of the underlying relationship between MIQ indices. In this case, we propose a novel data-driven deep model for the online prediction of MIQ indices. First, we design an attention-wise module to self-learn the nonlinear and dynamic relationship between process variables and prediction targets and enhance interpretability. Then, the minute-level molten iron temperature data detected by our previously developed equipment is used to pre-train the attention-wise deep network to obtain the improved weights and reduce dependence on labeled samples. Finally, the pre-trained model is extended to a structure with a weight-shared attention-wise module and task-separated prediction networks to explore the relationship between multiple prediction tasks. The effectiveness of the proposed attention-wise deep network is verified in an industrial ironmaking plant, which shows a significant improvement in performance, i.e., high accuracy and interpretability.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2022.3185325