Machine Learning-Based Regression Models for Ironmaking Blast Furnace Automation

Calix, Ricardo A.; Ugarte, Orlando; Okosun, Tyamo; Wang, Hong

doi:10.3390/dynamics3040034

Machine Learning-Based Regression Models for Ironmaking Blast Furnace Automation

Journal Article · Sun Oct 08 00:00:00 EDT 2023 · Dynamics

DOI:https://doi.org/10.3390/dynamics3040034· OSTI ID:2076187

Calix, Ricardo A. ^[1]; Ugarte, Orlando ^[1]; Okosun, Tyamo ^[1]; Wang, Hong ^[2]

Purdue University Northwest, Hammond, IN (United States)
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Computational fluid dynamics (CFD)-based simulation has been the traditional way to model complex industrial systems and processes. One very large and complex industrial system that has benefited from CFD-based simulations is the steel blast furnace system. The problem with the CFD-based simulation approach is that it tends to be very slow for generating data. The CFD-only approach may not be fast enough for use in real-time decisionmaking. To address this issue, in this work, the authors propose the use of machine learning techniques to train and test models based on data generated via CFD simulation. Regression models based on neural networks are compared with tree-boosting models. In particular, several areas (tuyere, raceway, and shaft) of the blast furnace are modeled using these approaches. The results of the model training and testing are presented and discussed. The obtained R² metrics are, in general, very high. The results appear promising and may help to improve the efficiency of operator and process engineer decisionmaking when running a blast furnace.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Industrial Efficiency & Decarbonization Office (IEDO)

Grant/Contract Number:: AC05-00OR22725; EE0009390

OSTI ID:: 2076187

Journal Information:: Dynamics, Journal Name: Dynamics Journal Issue: 4 Vol. 3; ISSN 2673-8716

Publisher:: MDPICopyright Statement

Country of Publication:: United States

Language:: English

References (23)

Survey on stochastic distribution systems: A full probability density function control theory with potential applications Wang, Aiping; Wang, Hong Optimal Control Applications and Methods, Vol. 42, Issue 6 https://doi.org/10.1002/oca.2755	journal	July 2021
Review on Computational Modeling and Visualization of the Ironmaking Blast Furnace at Purdue University Northwest Okosun, Tyamo; Silaen, Armin K.; Zhou, Chenn Q. steel research international, Vol. 90, Issue 4 https://doi.org/10.1002/srin.201900046	journal	March 2019
A desicion-theoretic generalization of on-line learning and an application to boosting Freund, Yoav; Schapire, Robert E. Lecture Notes in Computer Science https://doi.org/10.1007/3-540-59119-2_166	book	January 1995
A dual graphic representation of the blast-furnace mass and heat balances Rist, A.; Meysson, N. JOM, Vol. 19, Issue 4 https://doi.org/10.1007/BF03378564	journal	April 1967
Key issues and progress of industrial big data-based intelligent blast furnace ironmaking technology Shi, Quan; Tang, Jue; Chu, Mansheng International Journal of Minerals, Metallurgy and Materials, Vol. 30, Issue 9 https://doi.org/10.1007/s12613-023-2636-3	journal	August 2023
Numerical analysis of flow and combustion behavior in tuyere and raceway of blast furnace fueled with pulverized coal and recycled top gas Yeh, Cheng-Peng; Du, Shan-Wen; Tsai, Chien-Hsiung Energy, Vol. 42, Issue 1 https://doi.org/10.1016/j.energy.2012.03.065	journal	June 2012
CFD study of bio-syngas and coal co-injection in a blast furnace with double lance Wang, Qi; Wang, Enlu; An, Qi Energy, Vol. 263 https://doi.org/10.1016/j.energy.2022.125906	journal	January 2023
Transient 3D CFD study of pulverised coal combustion and coke combustion in a blast furnace: Effect of blast conditions Zhuo, Yuting; Shen, Yansong Fuel, Vol. 340 https://doi.org/10.1016/j.fuel.2023.127468	journal	May 2023
Fast flow field prediction over airfoils using deep learning approach Sekar, Vinothkumar; Khoo, Boo Cheong Physics of Fluids, Vol. 31, Issue 5 https://doi.org/10.1063/1.5094943	journal	May 2019
Machine learning–accelerated computational fluid dynamics Kochkov, Dmitrii; Smith, Jamie A.; Alieva, Ayya Proceedings of the National Academy of Sciences, Vol. 118, Issue 21 https://doi.org/10.1073/pnas.2101784118	journal	May 2021
Machine Learning Computational Fluid Dynamics Usman, Ali; Rafiq, Muhammad; Saeed, Muhammad 2021 Swedish Artificial Intelligence Society Workshop (SAIS) https://doi.org/10.1109/SAIS53221.2021.9483997	conference	June 2021
Data-Driven Time Discrete Models for Dynamic Prediction of the Hot Metal Silicon Content in the Blast Furnace—A Review Saxen, Henrik; Gao, Chuanhou; Gao, Zhiwei IEEE Transactions on Industrial Informatics, Vol. 9, Issue 4 https://doi.org/10.1109/TII.2012.2226897	journal	November 2013
Co-Optimization Scheme for the Powertrain and Exhaust Emission Control System of Hybrid Electric Vehicles Using Future Speed Prediction Hong, Wanshi; Chakraborty, Indrasis; Wang, Hong IEEE Transactions on Intelligent Vehicles, Vol. 6, Issue 3 https://doi.org/10.1109/TIV.2021.3049296	journal	September 2021
XGBoost: A Scalable Tree Boosting System Chen, Tianqi; Guestrin, Carlos Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16 https://doi.org/10.1145/2939672.2939785	conference	January 2016
Neural Networks and the Bias/Variance Dilemma Geman, Stuart; Bienenstock, Elie; Doursat, René Neural Computation, Vol. 4, Issue 1 https://doi.org/10.1162/neco.1992.4.1.1	journal	January 1992
machine. Friedman, Jerome H. The Annals of Statistics, Vol. 29, Issue 5 https://doi.org/10.1214/aos/1013203451	journal	October 2001
Comparison of data-driven prediction methods for comprehensive coke ratio of blast furnace Zhai, Xiuyun; Chen, Mingtong High Temperature Materials and Processes, Vol. 42, Issue 1 https://doi.org/10.1515/htmp-2022-0261	journal	January 2023
A Mathematical Model of Four Phase Motion and Heat Transfer in the Blast Furnace. Austin, Peter Richard; Nogami, Hiroshi; Yagi, Jun-ichiro ISIJ International, Vol. 37, Issue 5 https://doi.org/10.2355/isijinternational.37.458	journal	January 1997
A Mathematical Model for Blast Furnace Reaction Analysis Based on the Four Fluid Model. Austin, Peter Richard; Nogami, Hiroshi; Yagi, Jun-ichiro ISIJ International, Vol. 37, Issue 8 https://doi.org/10.2355/isijinternational.37.748	journal	January 1997
Predictive Modeling of Blast Furnace Gas Utilization Rate Using Different Data Pre-Processing Methods Jiang, Dewen; Wang, Zhenyang; Li, Kejiang Metals, Vol. 12, Issue 4 https://doi.org/10.3390/met12040535	journal	March 2022
Analysis of Particle Size Distribution of Coke on Blast Furnace Belt Using Object Detection Li, Meng; Wang, Xu; Yao, Hao Processes, Vol. 10, Issue 10 https://doi.org/10.3390/pr10101902	journal	September 2022
Machine Learning-Based Prediction of a BOS Reactor Performance from Operating Parameters Rahnama, Alireza; Li, Zushu; Sridhar, Seetharaman Processes, Vol. 8, Issue 3 https://doi.org/10.3390/pr8030371	journal	March 2020
Applied Regression: An Introduction Lewis-Beck, Colin; Lewis-Beck, Michael SAGE Publications https://doi.org/10.4135/9781483396774	journal	January 2016

Similar Records

Coal and oil mixture injection into blast furnace

Conference · Wed Dec 31 23:00:00 EST 1980 · Proc., Ironmaking Conf.; (United States) · OSTI ID:6289131

Minimization of Blast furnace Fuel Rate by Optimizing Burden and Gas Distribution

Technical Report · Wed Aug 15 00:00:00 EDT 2012 · OSTI ID:1053052

Raceway behaviors in blast furnace with pulverized coal injection

Book · Thu Nov 30 23:00:00 EST 1995 · OSTI ID:129059

Related Subjects

97 MATHEMATICS AND COMPUTING
XGBoost
computational fluid dynamics
machine learning
regression
steel blast furnace

Machine Learning-Based Regression Models for Ironmaking Blast Furnace Automation

Citation Formats

References (23)

Similar Records

Related Subjects