Genetic programming in the steelmaking industry

Kovačić, Miha; Župerl, Uroš

doi:10.1007/s10710-020-09382-5

Cited by 17 publications

(8 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Genetic Programming, the structures undergoing simulated evolution are computer programs the content of which depends on the problem we are solving. For example, if the goal of research is modeling based on experimental/numerical data, the individual computer program (organism) has the form of a prediction model which consists of function genes and terminal genes [33][34][35][36]. Function genes are most often the basic analytical operations, such as the operation of addition, subtraction, multiplication, division.…”

Section: Modeling Of Tensile Strengthmentioning

confidence: 99%

“…We developed the Genetic Programming System (University of Maribor, Faculty of Mechanical Engineering, Slovenia; Štore Steel Ltd., Štore, Slovenia) in the AutoLISP computer language inside the AutoCAD CAD/CAM systems [34][35][36]. The following evolutionary settings were used; population size: 1000; maximum number of generations: 1000; probability of reproduction: 0.4, probability of crossover: 0.6; maximum depth of organisms in the initial generation: 30; maximum permissible depth of offspring after the performing of crossover: 30; smallest permissible depth of organisms in the initial generation: 2; tournament size for selection operation: 7; number of independent runs: 100.…”

Section: Modeling Of Tensile Strength Using Genetic Programmingmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of the Continuous Casting Process of Hypoeutectoid Steel Grades Using Multiple Linear Regression and Genetic Programming—An Industrial Study

Brezočnik

Župerl

2021

Metals

Self Cite

View full text Add to dashboard Cite

Štore Steel Ltd. is one of the major flat spring steel producers in Europe. Until 2016 the company used a three-strand continuous casting machine with 6 m radius, when it was replaced by a completely new two-strand continuous caster with 9 m radius. For the comparison of the tensile strength of 41 hypoeutectoid steel grades, we conducted 1847 tensile strength tests during the first period of testing using the old continuous caster, and 713 tensile strength tests during the second period of testing using the new continuous caster. It was found that for 11 steel grades the tensile strength of the rolled material was statistically significantly lower (t-test method) in the period of using the new continuous caster, whereas all other steel grades remained the same. To improve the new continuous casting process, we decided to study the process in more detail using the Multiple Linear Regression method and the Genetic Programming approach based on 713 items of empirical data obtained on the new continuous casting machine. Based on the obtained models of the new continuous casting process, we determined the most influential parameters on the tensile strength of a product. According to the model’s analysis, the secondary cooling at the new continuous caster was improved with the installation of a self-cleaning filter in 2019. After implementing this modification, we performed an additional 794 tensile tests during the third period of testing. It was found out that, after installation of the self-cleaning filter, in 6 steel grades out of 19, the tensile strength in rolled condition improved statistically significantly, whereas all the other steel grades remained the same.

show abstract

Section: Modeling Of Tensile Strengthmentioning

confidence: 99%

Section: Modeling Of Tensile Strength Using Genetic Programmingmentioning

confidence: 99%

Optimization of the Continuous Casting Process of Hypoeutectoid Steel Grades Using Multiple Linear Regression and Genetic Programming—An Industrial Study

Brezočnik

Župerl

2021

Metals

Self Cite

View full text Add to dashboard Cite

show abstract

“…To fulfill demand, steel’s strength, ductility, durability, and corrosion resistance have all increased over time. A variety of processes, strongly influenced by the equipment, modify the final product’s shape, appearance, and properties [ 1 ]. Due to its superior features, steel has been widely used for various applications since it was commercialized at the beginning of the 1900s.…”

Section: Introductionmentioning

confidence: 99%

“…Inclusions distributed in liquid steel are sometimes engulfed in the solidification interface in the mold and become defects in steel products. Inclusions entrapped by the solidifying front during continuous casting will adversely affect the properties of the final steel products [ 1 , 12 , 13 , 14 ]. Therefore, the behavior of inclusions at the interface should be investigated in detail.…”

Section: Introductionmentioning

confidence: 99%

Simulation of Inclusion Particle Motion Behavior under Interfacial Tension in Continuous Casting Mold

Siddiqui

Albaqami²,

Arifudin³

et al. 2022

Materials

View full text Add to dashboard Cite

Inclusions entrapped by the solidifying front during continuous casting adversely affect the properties of the final steel products. In this study, we investigated the effect of the interfacial tension due to surfactant concentration, particularly sulfur, on alumina inclusion motion behavior during molten steel solidification in a continuous casting mold. A two-dimensional numerical model was developed in Ansys Fluent software to simulate the inclusion motion in a continuous casting mold. Further, the impacts of different values of the alumina inclusion diameter, sulfur concentration, and melt temperature were studied to understand the inclusion motion behavior. The inclusion diameter affected the inclusion distribution throughout the domain. The alumina inclusion entrapment percentage varied in the case of sulfur mixing (using an empirical relationship for modeling). It was found that the removal percentage varied according to the sulfur concentration. The addition of sulfur at concentrations from 10 ppm to 70 ppm resulted in a 4% increase in the removal of alumina inclusions (trapped in the solidifying shell), except for the 100-ppm case. Smaller-sized inclusion particles had a 25% higher chance of entrapment at the top level of the mold. Under the effect of a higher surface tension gradient between inclusions and the melt, the predicted findings show that inclusions were vulnerable to engulfment by the solidification front.

show abstract

“…The output of the last layer (output) predicts target variables, in our case, the surface roughness. -Genetic programming (GP) is one of the most efficient and universal methods for solving problems developers use to face [14][15][16], such as symbolic regression, data mining, design optimization [17], and research of the behavior of developing populations (emergent behavior) in biological communities. GP belongs to a class of methods known as evolutionary algorithms since they are based on the concepts of natural selection and evolution (as evident in [18]).…”

Section: Introductionmentioning

confidence: 99%

Modelling the surface roughness of steel after laser hardening by using 2D visibility network, convolutional neural networks and genetic programming

Babič¹,

Wangyao²,

Šter³

et al. 2022

FME Transactions

View full text Add to dashboard Cite

The surface characterization of materials after Robot Laser Hardening (RLH) is a technically demanding procedure. RLH is commonly used to harden parts, especially when subject to wear. By changing their surface properties, this treatment can offer several benefits such as lower costs for additional machining, no use of cooling agents or chemicals, high flexibility, local hardening, minimal deformation, high accuracy, and automated and integrated process in the production process. However, the surface roughness strongly depends on the heat treatment and parameters used in the process. This article used a network theory approach (i.e., the visibility network in 2D space) to analyze the surface roughness of tool steel EN100083-1 upon RLH. Specifically, two intelligent methods were merged in this investigation. Firstly, a genetic algorithm was applied to derive a relationship between the parameters of the robot laser cell and topological surface properties. Furthermore, convolutional neural networks allowed the assessment of surface roughness based on 2D photographic images.

show abstract

Genetic programming in the steelmaking industry

Cited by 17 publications

References 124 publications

Optimization of the Continuous Casting Process of Hypoeutectoid Steel Grades Using Multiple Linear Regression and Genetic Programming—An Industrial Study

Optimization of the Continuous Casting Process of Hypoeutectoid Steel Grades Using Multiple Linear Regression and Genetic Programming—An Industrial Study

Simulation of Inclusion Particle Motion Behavior under Interfacial Tension in Continuous Casting Mold

Modelling the surface roughness of steel after laser hardening by using 2D visibility network, convolutional neural networks and genetic programming

Contact Info

Product

Resources

About