Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II

Combining classical technologies with modern intelligent algorithms, this paper introduces a new approach for the optimisation and modelling of the EAF-based steel-making process based on a multi-objective optimisation using evolutionary computing and machine learning. Using a large amount of real-w...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Matheus F. Torquato, German Martinez-Ayuso, Ashraf A. Fahmy, Johann Sienz
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Electric arc furnace genetic algorithms multi-objective optimisation NSGA-II optimisation steel-making Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/41aff34d029947d8b8d4d0fe34e3b586
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:41aff34d029947d8b8d4d0fe34e3b586
record_format	dspace
spelling	oai:doaj.org-article:41aff34d029947d8b8d4d0fe34e3b5862021-11-18T00:02:20ZMulti-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II2169-353610.1109/ACCESS.2021.3125519https://doaj.org/article/41aff34d029947d8b8d4d0fe34e3b5862021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9600818/https://doaj.org/toc/2169-3536Combining classical technologies with modern intelligent algorithms, this paper introduces a new approach for the optimisation and modelling of the EAF-based steel-making process based on a multi-objective optimisation using evolutionary computing and machine learning. Using a large amount of real-world historical data containing 6423 consecutive EAF heats collected from a melt shop in an established steel plant this work not only creates machine learning models for both EAF and ladle furnaces but also simultaneously minimises the total scrap cost and EAF energy consumption per ton of scrap. In the modelling process, several algorithms are tested, tuned, evaluated and compared before selecting Gradient Boosting as the best option to model the data analysed. A similar approach is followed for the selection of the multi-objective optimisation algorithm. For this task, six techniques are tested and compared based on the hypervolume performance indicator to just then select the Non-dominated Sorting Genetic <xref ref-type="algorithm" rid="alg2">Algorithm II</xref> (<italic>NSGA-II</italic>) as the best option. Given this applied research focus on a real manufacturing process, real-world constraints and variables such as individual scrap price, scrap availability, tap additives and ambient temperature are used in the models developed here. A comparison with an equivalent EAF model from the literature showed a 13% improvement using the mean absolute error in the EAF energy usage prediction as a comparative metric. The multi-objective optimisation resulted in reductions in the energy consumption costs that ranged from 1.87% up to 8.20% among different steel grades and scrap cost reductions ranging from 1.15% up to 5.2%. The machine learning models and the optimiser were ultimately deployed with a graphical user interface allowing the melt-shop staff members to make informed decisions while controlling the EAF operation.Matheus F. TorquatoGerman Martinez-AyusoAshraf A. FahmyJohann SienzIEEEarticleElectric arc furnacegenetic algorithmsmulti-objective optimisationNSGA-IIoptimisationsteel-makingElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149715-149731 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electric arc furnace genetic algorithms multi-objective optimisation NSGA-II optimisation steel-making Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Electric arc furnace genetic algorithms multi-objective optimisation NSGA-II optimisation steel-making Electrical engineering. Electronics. Nuclear engineering TK1-9971 Matheus F. Torquato German Martinez-Ayuso Ashraf A. Fahmy Johann Sienz Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II
description	Combining classical technologies with modern intelligent algorithms, this paper introduces a new approach for the optimisation and modelling of the EAF-based steel-making process based on a multi-objective optimisation using evolutionary computing and machine learning. Using a large amount of real-world historical data containing 6423 consecutive EAF heats collected from a melt shop in an established steel plant this work not only creates machine learning models for both EAF and ladle furnaces but also simultaneously minimises the total scrap cost and EAF energy consumption per ton of scrap. In the modelling process, several algorithms are tested, tuned, evaluated and compared before selecting Gradient Boosting as the best option to model the data analysed. A similar approach is followed for the selection of the multi-objective optimisation algorithm. For this task, six techniques are tested and compared based on the hypervolume performance indicator to just then select the Non-dominated Sorting Genetic <xref ref-type="algorithm" rid="alg2">Algorithm II</xref> (<italic>NSGA-II</italic>) as the best option. Given this applied research focus on a real manufacturing process, real-world constraints and variables such as individual scrap price, scrap availability, tap additives and ambient temperature are used in the models developed here. A comparison with an equivalent EAF model from the literature showed a 13% improvement using the mean absolute error in the EAF energy usage prediction as a comparative metric. The multi-objective optimisation resulted in reductions in the energy consumption costs that ranged from 1.87% up to 8.20% among different steel grades and scrap cost reductions ranging from 1.15% up to 5.2%. The machine learning models and the optimiser were ultimately deployed with a graphical user interface allowing the melt-shop staff members to make informed decisions while controlling the EAF operation.
format	article
author	Matheus F. Torquato German Martinez-Ayuso Ashraf A. Fahmy Johann Sienz
author_facet	Matheus F. Torquato German Martinez-Ayuso Ashraf A. Fahmy Johann Sienz
author_sort	Matheus F. Torquato
title	Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II
title_short	Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II
title_full	Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II
title_fullStr	Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II
title_full_unstemmed	Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II
title_sort	multi-objective optimization of electric arc furnace using the non-dominated sorting genetic algorithm ii
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/41aff34d029947d8b8d4d0fe34e3b586
work_keys_str_mv	AT matheusftorquato multiobjectiveoptimizationofelectricarcfurnaceusingthenondominatedsortinggeneticalgorithmii AT germanmartinezayuso multiobjectiveoptimizationofelectricarcfurnaceusingthenondominatedsortinggeneticalgorithmii AT ashrafafahmy multiobjectiveoptimizationofelectricarcfurnaceusingthenondominatedsortinggeneticalgorithmii AT johannsienz multiobjectiveoptimizationofelectricarcfurnaceusingthenondominatedsortinggeneticalgorithmii
_version_	1718425220718526464

Multi-Objective Optimization of Electric Arc Furnace Using the Non-Dominated Sorting Genetic Algorithm II

Ejemplares similares