LAPSE:2020.0543
Published Article
LAPSE:2020.0543
Fault Detection and Identification of Blast Furnace Ironmaking Process Using the Gated Recurrent Unit Network
June 3, 2020
It is of critical importance to keep a steady operation in the blast furnace to facilitate the production of high quality hot metal. In order to monitor the state of blast furnace, this article proposes a fault detection and identification method based on the multidimensional Gated Recurrent Unit (GRU) network, which is a kind of recurrent neural network and is highly effective in handling process dynamics. Comparing to conventional recurrent neural networks, GRU has a simpler structure and involves fewer parameters. In fault detection, a moving window approach is applied and a GRU model is constructed for each process variable to generate a series of residuals, which is further monitored using the support vector data description (SVDD) method. Once a fault is detected, fault identification is performed using the contribution analysis. Application to a real blast furnace fault shows that the proposed method is effective.
Record ID
Keywords
fault detection and identification, gated recurrent unit, support vector data description, time sequence prediction
Subject
Suggested Citation
Ouyang H, Zeng J, Li Y, Luo S. Fault Detection and Identification of Blast Furnace Ironmaking Process Using the Gated Recurrent Unit Network. (2020). LAPSE:2020.0543
Author Affiliations
Ouyang H: College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou 310018, China
Zeng J: College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou 310018, China
Li Y: College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou 310018, China
Luo S: School of Statistics, Jiangxi University of Finance and Economics, Nanchang 330013, China
Zeng J: College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou 310018, China
Li Y: College of Metrology and Measurement Engineering, China Jiliang University, Hangzhou 310018, China
Luo S: School of Statistics, Jiangxi University of Finance and Economics, Nanchang 330013, China
Journal Name
Processes
Volume
8
Issue
4
Article Number
E391
Year
2020
Publication Date
2020-03-27
Published Version
ISSN
2227-9717
Version Comments
Original Submission
Other Meta
PII: pr8040391, Publication Type: Journal Article
Record Map
Published Article
LAPSE:2020.0543
This Record
External Link
doi:10.3390/pr8040391
Publisher Version
Download
Meta
Record Statistics
Record Views
422
Version History
[v1] (Original Submission)
Jun 3, 2020
Verified by curator on
Jun 3, 2020
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2020.0543
Original Submitter
Calvin Tsay
Links to Related Works