This study presents a hybrid optimisation approach to enhance electric arc furnace (EAF) operations by minimising arcing time through the integration of machine learning models and genetic algorithm (GA) optimisation. The goal is to improve productivity, reduce energy consumption and lower operational costs. A comprehensive historical dataset of EAF operations was utilised to develop predictive models, including Gaussian process regression (GPR), decision trees, support vector regression, and artificial neural networks for predicting optimal arcing time. Key input parameters such as raw material quality, direct reduced iron composition, power input, oxygen and natural gas usage, carbon, flux additions and furnace temperature were considered. Feature engineering technique R-Relief was used to identify significant variables, and hyperparameter tuning improved model performance. The exponential GPR model achieved coefficient of determination (R²) of 0.93 and root mean square error of 0.75. GA optimisation reduced arcing time by 5%, increasing steel production from 216.6 to 223 tons per hour.
Banerjee R, Cong Y, Gielen D, et al. Energy end-use: Industry. In: Johansson TB, Nakicenovic N, Patwardhan A, et al. (eds) Gobal energy assessment - Toward a sustainable future. Cambridge: Cambridge University Press, pp.513–573.
2.
International Energy Agency. World Energy Outlook 2021, www.iea.org/weo (2021).
3.
JungHAl-LbrahimNAl-SayeghA,et al.Hadeed-concept and latest results of the world’s largest EAF plant for long products on DRI-basis*. Rev Metall1994; 91: 1123–1130.
4.
KirschenMHayTEchterhofT. Process improvements for direct reduced iron melting in the electric arc furnace with emphasis on slag operation. Processes2021; 9: 402.
5.
MapelliCBaragiolaS. Evaluation of energy and exergy performances in EAF during melting and refining period. Ironmaking Steelmaking2006; 33: 379–388.
6.
PfeifferAErnstDZhengH, et al.The behavior of direct reduced iron in the electric arc furnace hotspot. Metals2023; 13: 978.
7.
JinBXuX. Carbon emission allowance price forecasting for China Guangdong carbon emission exchange via the neural network. Global Finance Rev2024; 6: 3491.
8.
JinBXuX. Wholesale price forecasts of green grams using the neural network. Asian J Econ Banking2024. DOI: 10.1108/AJEB-01-2024-0007.
9.
JinBXuX. Price forecasting through neural networks for crude oil, heating oil, and natural gas. Meas Energy2024; 1: 100001.
10.
JinBXuX. Forecasts of thermal coal prices through Gaussian process regressions. Ironmaking Steelmaking2024; 51: 819–834. Epub ahead of print 23 October 2024.
11.
JinBXuX. Forecasting wholesale prices of yellow corn through the Gaussian process regression. Neural Comput Appl2024; 36: 8693–8710.
12.
JinBXuX. Pre-owned housing price index forecasts using Gaussian process regressions. J Modell Manage2024; 19: 1927–1958.
13.
AladeIOZhangYXuX. Modeling and prediction of lattice parameters of binary spinel compounds (AM2X4) using support vector regression with Bayesian optimization. New J Chem2021; 45: 15255–15266.
14.
YuZLiXWangB, et al. A hybrid prediction model of blast furnace permeability index combining least square support vector machine and artificial neural network. Ironmaking Steelmaking2024 Oct 14.
15.
BotoFMuruaMGutierrezT, et al.Data driven performance prediction in steel making. Metals2022; 12: 172.
16.
ChoiS-WSeoB-GLeeE-B. Machine learning-based tap temperature prediction and control for optimized power consumption in stainless electric arc furnaces (EAF) of steel plants. Sustainability2023; 15: 6393.
17.
FernándezJMMCabalVÁMontequinVR, et al.Online estimation of electric arc furnace tap temperature by using fuzzy neural networks. Eng Appl Artif Intell2008; 21: 1001–1012.
18.
CarlssonL. Applied Machine Learning in Steel Process Engineering Using Supervised Machine Learning Models to Predict the Electrical Energy Consumption of Electric Arc Furnaces. Dissertation, KTH Royal Institute of Technology, 2021.
19.
LeeJKimSYooB, et al.Power consumption optimization for electric arc furnace with time series prediction. In: PHM society Asia-Pacific conference, 4 September 2023, Vol. 4, No. 1.
20.
JinBXuX. Machine learning predictions of regional steel price indices for East China. Ironmaking Steelmaking2024: 03019233241254891.
21.
YuSZhangZLiangX, et al. A matlab toolbox for feature importance ranking. In: 2019 International Conference on Medical Imaging Physics and Engineering (ICMIPE), 2019, pp. 1–6. IEEE.
22.
ShanthiDMadhuravaniBKumarA. Handbook of artificial intelligence. Sharjah: Bentham Science Publishers, 2023.
23.
MuntinAVZhikharev PYZiniaginAG, et al.Artificial intelligence and machine learning in metallurgy. Part 1. methods and algorithms. Metallurgist2023; 67: 886–894.
24.
Al TobiMASBevanG. Genetic algorithm. In: Artificial intelligence methods for fault diagnosis in centrifugal pumps. New York: AIP Publishing LLCMelville, 2022, pp.4–1–4–8.
25.
WorapradyaKThanakijkasemP. Optimising steel production schedules via A hierarchical genetic algorithm. S Afr J Ind Eng2014; 25: 209–221.
26.
AlbadrMATiunSAyobM, et al.Genetic algorithm based on natural selection theory for optimization problems. Symmetry2020; 12: 1–31.
27.
CarreónCAHTolamaJEMValdezGC, et al.Multi-objective optimization of the hot rolling scheduling of steel using a genetic algorithm. MRS Adv2019; 4: 3373–3380.
28.
YunlianLTiebinWXiaC, et al.A novel whale optimization algorithm and its application in metallurgical process. In: 2020 7th International Conference on Information Science and Control Engineering (ICISCE), 2020, pp.101–105: IEEE.
29.
MengLMDingJGDuH, et al.Stacking ensemble learning fused with whale optimisation algorithm based method for crown prediction of hot-rolled strip. Ironmaking Steelmaking2024; 51: 281–296.
30.
ShadravanSNajiHRBardsiriVK. The sailfish optimizer: a novel nature-inspired metaheuristic algorithm for solving constrained engineering optimization problems. Eng Appl Artif Intell2019; 80: 20–34.
31.
ZhangYMoY. Dynamic optimization of chemical processes based on modified sailfish optimizer combined with an equal division method. Processes2021; 9: 1806.
32.
ShiJYinDYangG. Particle swarm optimization based steel rolling parameter optimization. In: 2014 10th International Conference on Natural Computation (ICNC), 2014, pp.632–636: IEEE.
33.
LinFZhizhongMYuanP, et al.An improved multi-objective particle swarm optimization algorithm and its application in EAF steelmaking process. In: 2012 24th Chinese Control and Decision Conference (CCDC), 2012, pp.867–871: IEEE.
34.
XueYYangQJianW. Improved particle swarm optimization algorithm for optimum charge plan for steelmaking-continuous casting production scheduling. In: INDIN ‘05. 2005 3rd IEEE International Conference on Industrial Informatics, 2005, pp.558–561: IEEE.
35.
RawatDSinghP. An effective algorithm using moth flame optimization (MFO) for numerical expression solutions. IJFMR 2024; 6.
36.
WangHWangJLiZ. Research on optimization of grey wolf algorithm with multiple improved strategies. In: 2023 4th International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), 2023, pp.70–75: IEEE.
37.
HattaNMZainAMSallehuddinR, et al.Recent studies on optimisation method of grey wolf optimiser (GWO): a review (2014–2017). Artif Intell Rev2019; 52: 2651–2683.
38.
MengLDingJLiX, et al.Novel shape control system of hot-rolled strip based on machine learning fused mechanism model. Expert Syst Appl2024; 255: 124789.
39.
MengLDingJDongZ, et al.Prediction of roll wear and thermal expansion based on informer network in hot rolling process and application in the control of crown and thickness. J Manuf Process2023; 103: 248–260.
40.
XuXZhangY. House price forecasting with neural networks. Intell Syst Appl2021; 12: 200052.
41.
XuXZhangY. Commodity price forecasting via neural networks for coffee, corn, cotton, oats, soybeans, soybean oil, sugar, and wheat. Intell Syst Acc Finance Manag2022; 29: 169–181.
