Fault Detection and Identification of Blast Furnace Ironmaking Process Using the Gated Recurrent Unit Network
Open Access
- 27 March 2020
- Vol. 8 (4), 391
- https://doi.org/10.3390/pr8040391
Abstract
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.Keywords
Funding Information
- Ministry of Science and Technology of the People's Republic of China (2018YFF0214700)
- National Natural Science Foundation of China (61673358; 61973145)
This publication has 22 references indexed in Scilit:
- Fault Diagnosis for Blast Furnace Ironmaking Process Based on Two-stage Principal Component AnalysisISIJ International, 2014
- Survey on data-driven industrial process monitoring and diagnosisAnnual Reviews in Control, 2012
- A State Space Model for Monitoring of the Dynamic Blast Furnace SystemISIJ International, 2012
- Multi-Class Classification Methods of Cost-Conscious LS-SVM for Fault Diagnosis of Blast FurnaceJournal of Iron and Steel Research International, 2011
- Multivariate process monitoring of an experimental blast furnaceQuality and Reliability Engineering International, 2010
- A Novel Fault Diagnosis System for Blast Furnace Based on Support Vector Machine EnsembleISIJ International, 2010
- Expert system methodologies and applications—a decade review from 1995 to 2004Expert Systems with Applications, 2005
- Long Short-Term MemoryNeural Computation, 1997
- Approximation of dynamical systems by continuous time recurrent neural networksNeural Networks, 1993
- Expert system for blast furnace operation at Kimitsu works.ISIJ International, 1990