Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learning

Solid solution strengthening theory is essential for designing steel with high microhardness. Experimental determination is quite time consuming and costly. It is necessary to develop an alternate approach to rapidly and accurately predict new solid solution strengthening theory for steel. In this s...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Wu, Jianyuan Zhang, Jintao Zhang, Chengjie Ge, Lu Ren, Xinkun Suo
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Materials & Design
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0264127524008487
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850122000541941760
author Hao Wu
Jianyuan Zhang
Jintao Zhang
Chengjie Ge
Lu Ren
Xinkun Suo
author_facet Hao Wu
Jianyuan Zhang
Jintao Zhang
Chengjie Ge
Lu Ren
Xinkun Suo
author_sort Hao Wu
collection DOAJ
description Solid solution strengthening theory is essential for designing steel with high microhardness. Experimental determination is quite time consuming and costly. It is necessary to develop an alternate approach to rapidly and accurately predict new solid solution strengthening theory for steel. In this study, a data-driven model combining machine learning (ML), firefly optimization algorithm (FA) and conditional generative adversarial networks (CGANs) were proposed to predict solid solution strengthening theory of Fe-C-Cr-Mn-Si steel. Three alloys were fabricated using cladding to validate the predict accuracy of the models. The results show that the trained support vector regression (SVR) model demonstrated the highest prediction precision for microhardness. The coefficient of determination (R2) value increased from 0.85 to 0.89 and root mean square error (RMSE) decreased from 0.39 to 0.31 after introducing the modified solid solution strengthening theory. The experimental validation revealed a minimum error of 1.17% between the predicted value and the experimental value. The investigation provides a valuable method to expedite design of Fe-C-Cr-Mn-Si steel with extreme high accuracy.
format Article
id doaj-art-87fd69e0b978445fb80182df2fb44a47
institution OA Journals
issn 0264-1275
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Materials & Design
spelling doaj-art-87fd69e0b978445fb80182df2fb44a472025-08-20T02:34:56ZengElsevierMaterials & Design0264-12752024-12-0124811347310.1016/j.matdes.2024.113473Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learningHao Wu0Jianyuan Zhang1Jintao Zhang2Chengjie Ge3Lu Ren4Xinkun Suo5Multidimensional Additive Manufacturing Institute, Faculty of Mechanical Engineering and Mechanics, Ningbo University, 315211 Ningbo, PR ChinaMultidimensional Additive Manufacturing Institute, Faculty of Mechanical Engineering and Mechanics, Ningbo University, 315211 Ningbo, PR ChinaMultidimensional Additive Manufacturing Institute, Faculty of Mechanical Engineering and Mechanics, Ningbo University, 315211 Ningbo, PR ChinaMultidimensional Additive Manufacturing Institute, Faculty of Mechanical Engineering and Mechanics, Ningbo University, 315211 Ningbo, PR ChinaMultidimensional Additive Manufacturing Institute, Faculty of Mechanical Engineering and Mechanics, Ningbo University, 315211 Ningbo, PR ChinaCorresponding author.; Multidimensional Additive Manufacturing Institute, Faculty of Mechanical Engineering and Mechanics, Ningbo University, 315211 Ningbo, PR ChinaSolid solution strengthening theory is essential for designing steel with high microhardness. Experimental determination is quite time consuming and costly. It is necessary to develop an alternate approach to rapidly and accurately predict new solid solution strengthening theory for steel. In this study, a data-driven model combining machine learning (ML), firefly optimization algorithm (FA) and conditional generative adversarial networks (CGANs) were proposed to predict solid solution strengthening theory of Fe-C-Cr-Mn-Si steel. Three alloys were fabricated using cladding to validate the predict accuracy of the models. The results show that the trained support vector regression (SVR) model demonstrated the highest prediction precision for microhardness. The coefficient of determination (R2) value increased from 0.85 to 0.89 and root mean square error (RMSE) decreased from 0.39 to 0.31 after introducing the modified solid solution strengthening theory. The experimental validation revealed a minimum error of 1.17% between the predicted value and the experimental value. The investigation provides a valuable method to expedite design of Fe-C-Cr-Mn-Si steel with extreme high accuracy.http://www.sciencedirect.com/science/article/pii/S0264127524008487Fe-C-Cr-Mn-Si steelMachine learningConditional generative adversarial networksSolid solution strengtheningFirefly optimization algorithm
spellingShingle Hao Wu
Jianyuan Zhang
Jintao Zhang
Chengjie Ge
Lu Ren
Xinkun Suo
Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learning
Materials & Design
Fe-C-Cr-Mn-Si steel
Machine learning
Conditional generative adversarial networks
Solid solution strengthening
Firefly optimization algorithm
title Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learning
title_full Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learning
title_fullStr Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learning
title_full_unstemmed Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learning
title_short Extreme high accuracy prediction and design of Fe-C-Cr-Mn-Si steel using machine learning
title_sort extreme high accuracy prediction and design of fe c cr mn si steel using machine learning
topic Fe-C-Cr-Mn-Si steel
Machine learning
Conditional generative adversarial networks
Solid solution strengthening
Firefly optimization algorithm
url http://www.sciencedirect.com/science/article/pii/S0264127524008487
work_keys_str_mv AT haowu extremehighaccuracypredictionanddesignoffeccrmnsisteelusingmachinelearning
AT jianyuanzhang extremehighaccuracypredictionanddesignoffeccrmnsisteelusingmachinelearning
AT jintaozhang extremehighaccuracypredictionanddesignoffeccrmnsisteelusingmachinelearning
AT chengjiege extremehighaccuracypredictionanddesignoffeccrmnsisteelusingmachinelearning
AT luren extremehighaccuracypredictionanddesignoffeccrmnsisteelusingmachinelearning
AT xinkunsuo extremehighaccuracypredictionanddesignoffeccrmnsisteelusingmachinelearning