Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learning

This study proposes an interpretable chain-based machine learning (ICML) strategy for designing ultra-high strength aluminum alloys with high damage tolerance. Firstly, by integrating a gradient boosting regression model linking alloy composition (AC) and solution-aging processes (SAP) to tensile me...

Full description

Saved in:
Bibliographic Details
Main Authors: Lei Jiang, Xinbiao Zhang, Wentao Zhoutai, Zhilin Han, Minghong Mao, Wenli Xue, Jianxin Xie
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Materials & Design
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0264127525007099
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849424598267854848
author Lei Jiang
Xinbiao Zhang
Wentao Zhoutai
Zhilin Han
Minghong Mao
Wenli Xue
Jianxin Xie
author_facet Lei Jiang
Xinbiao Zhang
Wentao Zhoutai
Zhilin Han
Minghong Mao
Wenli Xue
Jianxin Xie
author_sort Lei Jiang
collection DOAJ
description This study proposes an interpretable chain-based machine learning (ICML) strategy for designing ultra-high strength aluminum alloys with high damage tolerance. Firstly, by integrating a gradient boosting regression model linking alloy composition (AC) and solution-aging processes (SAP) to tensile mechanical properties (TMP), including ultimate tensile strength σb, yield strength σy, and elongation A, with an explicit quantitative relationship between TMP and fatigue strength (FS), expressed as FS = ασbA1/4, a multi-scale interpretable prediction model was constructed to AC + SAP → TMP → FS. Subsequently, combining SHAP analysis, multi-objective optimization, and thermodynamic calculations, the study achieves the integrated optimization design of AC and SAP. The newly developed ultra-high strength aluminum alloy with high damage tolerance Al-10.5Zn-2.34 Mg-1.28Cu-0.11Zr-0.1Cr demonstrates outstanding mechanical properties, with a measured σb = 794 ± 2 MPa, σy = 765 ± 3 MPa, A = 11.9 ± 0.4 %, FS = 376 ± 14 MPa. Compared to commercial AA7050 and AA7055 alloys, the novel alloy demonstrated over 20 % enhancements in σb, σy, and FS, while maintaining equivalent or superior A. Furthermore, the FS = ασbA1/4 model reveals the influence of strength and plasticity on fatigue strength, enabling accurate fatigue strength predictions and excellent generalization capability, which can be extended to various metallic materials. This work provides a novel approach for efficiently designing high damage tolerance alloys.
format Article
id doaj-art-46196b87f0ed498ca992df3cc89e92b1
institution Kabale University
issn 0264-1275
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Materials & Design
spelling doaj-art-46196b87f0ed498ca992df3cc89e92b12025-08-20T03:30:05ZengElsevierMaterials & Design0264-12752025-08-0125611428910.1016/j.matdes.2025.114289Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learningLei Jiang0Xinbiao Zhang1Wentao Zhoutai2Zhilin Han3Minghong Mao4Wenli Xue5Jianxin Xie6Beijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology Beijing, Beijing 100083, ChinaKey Laboratory for Advanced Materials Processing (MOE), University of Science and Technology Beijing, Beijing 100083, ChinaKey Laboratory for Advanced Materials Processing (MOE), University of Science and Technology Beijing, Beijing 100083, ChinaKey Laboratory for Advanced Materials Processing (MOE), University of Science and Technology Beijing, Beijing 100083, ChinaKey Laboratory for Advanced Materials Processing (MOE), University of Science and Technology Beijing, Beijing 100083, ChinaKey Laboratory for Advanced Materials Processing (MOE), University of Science and Technology Beijing, Beijing 100083, ChinaBeijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology Beijing, Beijing 100083, China; Beijing Laboratory of Metallic Materials and Processing for Modern Transportation, Institute for Advanced Materials and Technology, University of Science and Technology Beijing, Beijing 100083, China; Key Laboratory for Advanced Materials Processing (MOE), University of Science and Technology Beijing, Beijing 100083, China; Institute of Materials Intelligent Technology, Liaoning Academy of Materials, Shenyang 110004, China; Corresponding author at: Beijing Advanced Innovation Center for Materials Genome Engineering, University of Science and Technology Beijing, Beijing 100083, China.This study proposes an interpretable chain-based machine learning (ICML) strategy for designing ultra-high strength aluminum alloys with high damage tolerance. Firstly, by integrating a gradient boosting regression model linking alloy composition (AC) and solution-aging processes (SAP) to tensile mechanical properties (TMP), including ultimate tensile strength σb, yield strength σy, and elongation A, with an explicit quantitative relationship between TMP and fatigue strength (FS), expressed as FS = ασbA1/4, a multi-scale interpretable prediction model was constructed to AC + SAP → TMP → FS. Subsequently, combining SHAP analysis, multi-objective optimization, and thermodynamic calculations, the study achieves the integrated optimization design of AC and SAP. The newly developed ultra-high strength aluminum alloy with high damage tolerance Al-10.5Zn-2.34 Mg-1.28Cu-0.11Zr-0.1Cr demonstrates outstanding mechanical properties, with a measured σb = 794 ± 2 MPa, σy = 765 ± 3 MPa, A = 11.9 ± 0.4 %, FS = 376 ± 14 MPa. Compared to commercial AA7050 and AA7055 alloys, the novel alloy demonstrated over 20 % enhancements in σb, σy, and FS, while maintaining equivalent or superior A. Furthermore, the FS = ασbA1/4 model reveals the influence of strength and plasticity on fatigue strength, enabling accurate fatigue strength predictions and excellent generalization capability, which can be extended to various metallic materials. This work provides a novel approach for efficiently designing high damage tolerance alloys.http://www.sciencedirect.com/science/article/pii/S0264127525007099Machine learningSymbolic regressionTensile mechanical propertiesFatigue strengthAlloy design
spellingShingle Lei Jiang
Xinbiao Zhang
Wentao Zhoutai
Zhilin Han
Minghong Mao
Wenli Xue
Jianxin Xie
Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learning
Materials & Design
Machine learning
Symbolic regression
Tensile mechanical properties
Fatigue strength
Alloy design
title Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learning
title_full Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learning
title_fullStr Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learning
title_full_unstemmed Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learning
title_short Discovery of ultra-high strength aluminum alloys with high damage tolerance via interpretable chain-based machine learning
title_sort discovery of ultra high strength aluminum alloys with high damage tolerance via interpretable chain based machine learning
topic Machine learning
Symbolic regression
Tensile mechanical properties
Fatigue strength
Alloy design
url http://www.sciencedirect.com/science/article/pii/S0264127525007099
work_keys_str_mv AT leijiang discoveryofultrahighstrengthaluminumalloyswithhighdamagetoleranceviainterpretablechainbasedmachinelearning
AT xinbiaozhang discoveryofultrahighstrengthaluminumalloyswithhighdamagetoleranceviainterpretablechainbasedmachinelearning
AT wentaozhoutai discoveryofultrahighstrengthaluminumalloyswithhighdamagetoleranceviainterpretablechainbasedmachinelearning
AT zhilinhan discoveryofultrahighstrengthaluminumalloyswithhighdamagetoleranceviainterpretablechainbasedmachinelearning
AT minghongmao discoveryofultrahighstrengthaluminumalloyswithhighdamagetoleranceviainterpretablechainbasedmachinelearning
AT wenlixue discoveryofultrahighstrengthaluminumalloyswithhighdamagetoleranceviainterpretablechainbasedmachinelearning
AT jianxinxie discoveryofultrahighstrengthaluminumalloyswithhighdamagetoleranceviainterpretablechainbasedmachinelearning