Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model

Abstract A high-performance, low-cost weathering steel was developed using a deep learning-based interpretable Attention mechanism, which identifies key compositional factors and captures complex feature interactions. By revealing the intrinsic drivers of strength, ductility, and corrosion resistanc...

Full description

Saved in:
Bibliographic Details
Main Authors: Bingxiao Shi, Xin Guo, Luntao Wang, Wenbo Huang, Hong Luo, Lizhi Qin, Guowei Yang, Xuequn Cheng, Xiaogang Li
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Materials Degradation
Online Access:https://doi.org/10.1038/s41529-025-00654-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849764489455468544
author Bingxiao Shi
Xin Guo
Luntao Wang
Wenbo Huang
Hong Luo
Lizhi Qin
Guowei Yang
Xuequn Cheng
Xiaogang Li
author_facet Bingxiao Shi
Xin Guo
Luntao Wang
Wenbo Huang
Hong Luo
Lizhi Qin
Guowei Yang
Xuequn Cheng
Xiaogang Li
author_sort Bingxiao Shi
collection DOAJ
description Abstract A high-performance, low-cost weathering steel was developed using a deep learning-based interpretable Attention mechanism, which identifies key compositional factors and captures complex feature interactions. By revealing the intrinsic drivers of strength, ductility, and corrosion resistance, and introducing a utility function to balance performance and cost, the newly designed steel achieved a UTS of 837 MPa, 20% elongation, and a corrosion rate of 0.54 g/(m2·h) after 576 hours in a simulated marine environment, demonstrating excellent overall properties.
format Article
id doaj-art-2881e8c2a0ee42a284a58df27e56ea69
institution DOAJ
issn 2397-2106
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Materials Degradation
spelling doaj-art-2881e8c2a0ee42a284a58df27e56ea692025-08-20T03:05:07ZengNature Portfolionpj Materials Degradation2397-21062025-08-019111610.1038/s41529-025-00654-yMulti-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning modelBingxiao Shi0Xin Guo1Luntao Wang2Wenbo Huang3Hong Luo4Lizhi Qin5Guowei Yang6Xuequn Cheng7Xiaogang Li8Institute for Advanced Materials and Technology, University of Science and Technology BeijingInstitute for Advanced Materials and Technology, University of Science and Technology BeijingInstitute for Advanced Materials and Technology, University of Science and Technology BeijingSchool of Computer Science and Engineering, Southeast UniversityInstitute for Advanced Materials and Technology, University of Science and Technology BeijingInstitute for Advanced Materials and Technology, University of Science and Technology BeijingInstitute for Advanced Materials and Technology, University of Science and Technology BeijingInstitute for Advanced Materials and Technology, University of Science and Technology BeijingInstitute for Advanced Materials and Technology, University of Science and Technology BeijingAbstract A high-performance, low-cost weathering steel was developed using a deep learning-based interpretable Attention mechanism, which identifies key compositional factors and captures complex feature interactions. By revealing the intrinsic drivers of strength, ductility, and corrosion resistance, and introducing a utility function to balance performance and cost, the newly designed steel achieved a UTS of 837 MPa, 20% elongation, and a corrosion rate of 0.54 g/(m2·h) after 576 hours in a simulated marine environment, demonstrating excellent overall properties.https://doi.org/10.1038/s41529-025-00654-y
spellingShingle Bingxiao Shi
Xin Guo
Luntao Wang
Wenbo Huang
Hong Luo
Lizhi Qin
Guowei Yang
Xuequn Cheng
Xiaogang Li
Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model
npj Materials Degradation
title Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model
title_full Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model
title_fullStr Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model
title_full_unstemmed Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model
title_short Multi-objective optimization of corrosion resistance, strength, ductility properties of weathering steel utilizing interpretable attention-based deep learning model
title_sort multi objective optimization of corrosion resistance strength ductility properties of weathering steel utilizing interpretable attention based deep learning model
url https://doi.org/10.1038/s41529-025-00654-y
work_keys_str_mv AT bingxiaoshi multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT xinguo multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT luntaowang multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT wenbohuang multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT hongluo multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT lizhiqin multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT guoweiyang multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT xuequncheng multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel
AT xiaogangli multiobjectiveoptimizationofcorrosionresistancestrengthductilitypropertiesofweatheringsteelutilizinginterpretableattentionbaseddeeplearningmodel