Artificial Neural Network-Based Non-Linear Modeling and Simulation of CaO-SiO2-Al2O3-MgO Blast Furnace Slag Viscosity

被引:0
作者
dos Anjos, Patrick [1 ]
Coleti, Jorge Luis [1 ]
Junca, Eduardo [2 ]
Grillo, Felipe Fardin [3 ]
Machado, Marcelo Lucas Pereira [3 ]
机构
[1] Fed Ctr Technol Educ Minas Gerais, Dept Met & Chem, Rua 19 Novembro,121 Ctr Norte, BR-35180008 Timoteo, MG, Brazil
[2] Univ Extremo Sul Catarinense, Postgrad Program Mat Sci & Engn, Lab Met & Ind Waste Treatment LAMETRI, Ave Univ 1105,Bairro Univ, BR-88806000 Criciuma, SC, Brazil
[3] Inst Fed Educ Ciencia & Tecnol Espirito Santo, Ave Vitoria 1729 Jucutuquara, BR-29040780 Vitoria, ES, Brazil
关键词
blast furnace slag; slag viscosity; artificial neural networks; numerical simulation; critical temperature; ternary diagrams; iso-viscosity curves; RHEOLOGICAL PROPERTIES; FEEDFORWARD NETWORKS; TEMPERATURES; TRANSITION; PREDICTION; CRYSTALS;
D O I
10.3390/min14111160
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Blast furnace slags are formed by CaO-SiO2-Al2O3-MgO systems and have several physical characteristics, one of which is viscosity. Viscosity is an important variable for the operation and blast furnace performance. This work aimed to model viscosity through linear and non-linear models in order to obtain a model with precision and accuracy. The best model constructed was a non-linear model by artificial neural networks that presented 23 nodes in the first hidden layer and 24 nodes in the second hidden layer with 6 input variables and 1 output variable named ANN 23-24. ANN 23-24 obtained better statistical evaluations in relation to 11 different literature equations for predicting viscosity in CaO-SiO2-Al2O3-MgO systems. ANN 23-24 was also subjected to numerical simulations in order to demonstrate the validation of the non-linear model and presented applications such as viscosity prediction, calculation of the inflection point in the viscosity curve by temperature, the construction of ternary diagrams with viscosity data, and the construction of iso-viscosity curves.
引用
收藏
页数:17
相关论文
共 64 条
[1]   RELAXATION IN LIQUIDS, POLYMERS AND PLASTIC CRYSTALS - STRONG FRAGILE PATTERNS AND PROBLEMS [J].
ANGELL, CA .
JOURNAL OF NON-CRYSTALLINE SOLIDS, 1991, 131 :13-31
[2]  
Ba J, 2014, ACS SYM SER
[3]  
Bai YB, 2021, Arxiv, DOI arXiv:2106.15853
[4]   FactSage thermochemical software and databases, 2010-2016 [J].
Bale, C. W. ;
Belisle, E. ;
Chartrand, P. ;
Decterov, S. A. ;
Eriksson, G. ;
Gheribi, A. E. ;
Hack, K. ;
Jung, I. -H. ;
Kang, Y. -B. ;
Melancon, J. ;
Pelton, A. D. ;
Petersen, S. ;
Robelin, C. ;
Sangster, J. ;
Spencer, P. ;
Van Ende, M-A. .
CALPHAD-COMPUTER COUPLING OF PHASE DIAGRAMS AND THERMOCHEMISTRY, 2016, 54 :35-53
[5]   Development of structure-informed artificial neural network for accurately modeling viscosity of multicomponent molten slags [J].
Chen, Ziwei ;
Wang, Minghao ;
Meng, Zhao ;
Wang, Hao ;
Liu, Lili ;
Wang, Xidong .
CERAMICS INTERNATIONAL, 2021, 47 (21) :30691-30701
[6]   Effect of MgO/Al2O3 on Viscosity and Thermodynamic Properties of High-Titanium Slag Containing Chlorine [J].
Cheng, Qinyu ;
Zhang, Zhaohui ;
Xing, Xiangdong ;
Zheng, Jianlu ;
She, Yuan .
MINERALS, 2023, 13 (03)
[7]   Real-time prediction of grid voltage and frequency using artificial neural networks: An experimental validation [J].
Chettibi, N. ;
Pavan, A. Massi ;
Mellit, A. ;
Forsyth, A. J. ;
Todd, R. .
SUSTAINABLE ENERGY GRIDS & NETWORKS, 2021, 27
[8]   Machine Learning Enhanced by Feature Engineering for Estimating Snow Water Equivalent [J].
Cisty, Milan ;
Danko, Michal ;
Kohnova, Silvia ;
Povazanova, Barbora ;
Trizna, Andrej .
WATER, 2024, 16 (16)
[9]   Prediction on crystallization behaviors of blast furnace slag in a phase change cooling process with corrected optical basicity [J].
Ding, Bin ;
Wang, Hong ;
Zhu, Xun ;
He, Xian-Yan ;
Tan, Yu ;
Liao, Qiang .
FUEL, 2018, 223 :360-365
[10]  
Ding T, 2020, Arxiv, DOI arXiv:1911.01413