Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning Procedures

This study is focused on the implementation of statistical learning methods for the prediction of the mechanical properties of steel products from the chemical profile of the raw material and the process parameters. The integration of this model into the production process allows a large-scale steel...

Full description

Saved in:
Bibliographic Details
Main Authors: Valerio Zippo, Elisa Robotti, Daniele Maestri, Pietro Fossati, David Valenza, Stefano Maggi, Gennaro Papallo, Masho Hilawie Belay, Simone Cerruti, Giorgio Porcu, Emilio Marengo
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Technologies
Subjects:
Online Access:https://www.mdpi.com/2227-7080/13/2/75
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078557757243392
author Valerio Zippo
Elisa Robotti
Daniele Maestri
Pietro Fossati
David Valenza
Stefano Maggi
Gennaro Papallo
Masho Hilawie Belay
Simone Cerruti
Giorgio Porcu
Emilio Marengo
author_facet Valerio Zippo
Elisa Robotti
Daniele Maestri
Pietro Fossati
David Valenza
Stefano Maggi
Gennaro Papallo
Masho Hilawie Belay
Simone Cerruti
Giorgio Porcu
Emilio Marengo
author_sort Valerio Zippo
collection DOAJ
description This study is focused on the implementation of statistical learning methods for the prediction of the mechanical properties of steel products from the chemical profile of the raw material and the process parameters. The integration of this model into the production process allows a large-scale steel industry to predict steel properties with heightened accuracy, optimizing the manufacturing process for minimal waste and improved consistency. A workflow for process data analysis has been developed, based on the use of machine learning algorithms to build an interface for data treatment to be directly used online. The proposed approach has a comprehensive connotation, starting from data pre-treatment and cleaning, to model building and prediction. Different machine learning algorithms are compared (Polynomial Regression, LASSO, Random Forests and Gradient Boosting, ANN, SVM, and k-NN), to provide the best predictive ability, also exploiting human reinforcement. The results proved to be very promising for all the types of steel investigated, with very good RMSE and R<sup>2</sup> values both in fitting and in prediction. The application here presented is being integrated into Total Quality Tutor (TQT) software, developed in-house in C# language, for predicting the mechanical properties of steel.
format Article
id doaj-art-0c83166119e641bfb0e797fbfc0e8fef
institution DOAJ
issn 2227-7080
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Technologies
spelling doaj-art-0c83166119e641bfb0e797fbfc0e8fef2025-08-20T02:45:31ZengMDPI AGTechnologies2227-70802025-02-011327510.3390/technologies13020075Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning ProceduresValerio Zippo0Elisa Robotti1Daniele Maestri2Pietro Fossati3David Valenza4Stefano Maggi5Gennaro Papallo6Masho Hilawie Belay7Simone Cerruti8Giorgio Porcu9Emilio Marengo10Acciaierie d’Italia S.p.A., Strada Boscomarengo 1, 15067 Novi Ligure, ItalyDepartment of Sciences and Technological Innovation, University of Piemonte Orientale, Viale Michel 11, 15121 Alessandria, ItalyAcciaierie d’Italia S.p.A., Strada Boscomarengo 1, 15067 Novi Ligure, ItalyAcciaierie d’Italia S.p.A., Strada Boscomarengo 1, 15067 Novi Ligure, ItalyAcciaierie d’Italia S.p.A., Strada Boscomarengo 1, 15067 Novi Ligure, ItalyAcciaierie d’Italia S.p.A., Strada Boscomarengo 1, 15067 Novi Ligure, ItalyAcciaierie d’Italia S.p.A., Strada Boscomarengo 1, 15067 Novi Ligure, ItalyDepartment of Sciences and Technological Innovation, University of Piemonte Orientale, Viale Michel 11, 15121 Alessandria, ItalyDepartment of Sciences and Technological Innovation, University of Piemonte Orientale, Viale Michel 11, 15121 Alessandria, ItalyAcciaierie d’Italia S.p.A., Strada Boscomarengo 1, 15067 Novi Ligure, ItalyDepartment of Sciences and Technological Innovation, University of Piemonte Orientale, Viale Michel 11, 15121 Alessandria, ItalyThis study is focused on the implementation of statistical learning methods for the prediction of the mechanical properties of steel products from the chemical profile of the raw material and the process parameters. The integration of this model into the production process allows a large-scale steel industry to predict steel properties with heightened accuracy, optimizing the manufacturing process for minimal waste and improved consistency. A workflow for process data analysis has been developed, based on the use of machine learning algorithms to build an interface for data treatment to be directly used online. The proposed approach has a comprehensive connotation, starting from data pre-treatment and cleaning, to model building and prediction. Different machine learning algorithms are compared (Polynomial Regression, LASSO, Random Forests and Gradient Boosting, ANN, SVM, and k-NN), to provide the best predictive ability, also exploiting human reinforcement. The results proved to be very promising for all the types of steel investigated, with very good RMSE and R<sup>2</sup> values both in fitting and in prediction. The application here presented is being integrated into Total Quality Tutor (TQT) software, developed in-house in C# language, for predicting the mechanical properties of steel.https://www.mdpi.com/2227-7080/13/2/75process optimizationsteelmechanical propertiesmachine learninggenetic algorithmartificial neural networks
spellingShingle Valerio Zippo
Elisa Robotti
Daniele Maestri
Pietro Fossati
David Valenza
Stefano Maggi
Gennaro Papallo
Masho Hilawie Belay
Simone Cerruti
Giorgio Porcu
Emilio Marengo
Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning Procedures
Technologies
process optimization
steel
mechanical properties
machine learning
genetic algorithm
artificial neural networks
title Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning Procedures
title_full Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning Procedures
title_fullStr Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning Procedures
title_full_unstemmed Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning Procedures
title_short Development of a Self-Updating System for the Prediction of Steel Mechanical Properties in a Steel Company by Machine Learning Procedures
title_sort development of a self updating system for the prediction of steel mechanical properties in a steel company by machine learning procedures
topic process optimization
steel
mechanical properties
machine learning
genetic algorithm
artificial neural networks
url https://www.mdpi.com/2227-7080/13/2/75
work_keys_str_mv AT valeriozippo developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT elisarobotti developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT danielemaestri developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT pietrofossati developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT davidvalenza developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT stefanomaggi developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT gennaropapallo developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT mashohilawiebelay developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT simonecerruti developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT giorgioporcu developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures
AT emiliomarengo developmentofaselfupdatingsystemforthepredictionofsteelmechanicalpropertiesinasteelcompanybymachinelearningprocedures