Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learning

Abstract Exploring the “composition‐microstructure‐property” relationship is a long‐standing theme in materials science. However, complex interactions make this area of research challenging. Based on the image processing and machine learning techniques, this paper proposes a multimodal fusion learni...

Full description

Saved in:
Bibliographic Details
Main Authors: Longfei Zhu, Qun Luo, Qiaochuan Chen, Yu Zhang, Lijun Zhang, Bin Hu, Yuexing Han, Qian Li
Format: Article
Language:English
Published: Wiley-VCH 2024-03-01
Series:Materials Genome Engineering Advances
Subjects:
Online Access:https://doi.org/10.1002/mgea.26
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203220281917440
author Longfei Zhu
Qun Luo
Qiaochuan Chen
Yu Zhang
Lijun Zhang
Bin Hu
Yuexing Han
Qian Li
author_facet Longfei Zhu
Qun Luo
Qiaochuan Chen
Yu Zhang
Lijun Zhang
Bin Hu
Yuexing Han
Qian Li
author_sort Longfei Zhu
collection DOAJ
description Abstract Exploring the “composition‐microstructure‐property” relationship is a long‐standing theme in materials science. However, complex interactions make this area of research challenging. Based on the image processing and machine learning techniques, this paper proposes a multimodal fusion learning framework that comprehensively considers both composition and microstructure in prediction of the ultimate tensile strength (UTS) of Al‐Si alloys. Firstly, the composition and image information are collected from the literature and supplementary experiments, followed by the image segmentation and quantitative analysis of eutectic Si images. Subsequently, the quantitative analysis results are combined with other features for three‐step feature screening, and 12 key features are obtained. Finally, four machine‐learning models (i.e., decision tree, random forest, adaptive boosting, and extreme gradient boosting [XGBoost]) are used to predict the UTS of Al‐Si alloys. The results show that the quantitative analysis method proposed in this paper is superior to Image‐Pro Plus (IPP) software in some aspects. The XGBoost model has the best prediction performance with R2 = 0.94. Furthermore, five mixed features and their critical values that significantly affect UTS are identified. Our study provides enlightenment for the prediction of UTS of Al‐Si alloys from composition and microstructure, and would be applicable to other alloys.
format Article
id doaj-art-765670d8139346c0aa4d8fe6a5f98cfd
institution OA Journals
issn 2940-9489
2940-9497
language English
publishDate 2024-03-01
publisher Wiley-VCH
record_format Article
series Materials Genome Engineering Advances
spelling doaj-art-765670d8139346c0aa4d8fe6a5f98cfd2025-08-20T02:11:34ZengWiley-VCHMaterials Genome Engineering Advances2940-94892940-94972024-03-0121n/an/a10.1002/mgea.26Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learningLongfei Zhu0Qun Luo1Qiaochuan Chen2Yu Zhang3Lijun Zhang4Bin Hu5Yuexing Han6Qian Li7State Key Laboratory of Advanced Special Steels & Shanghai Key Laboratory of Advanced Ferrometallurgy & School of Materials Science and Engineering Shanghai University Shanghai ChinaState Key Laboratory of Advanced Special Steels & Shanghai Key Laboratory of Advanced Ferrometallurgy & School of Materials Science and Engineering Shanghai University Shanghai ChinaSchool of Computer Engineering and Science Shanghai University Shanghai ChinaCollege of Materials Science and Engineering Chongqing University Chongqing ChinaState Key Laboratory of Powder Metallurgy Central South University Changsha ChinaCollege of Materials Science and Engineering Chongqing University Chongqing ChinaSchool of Computer Engineering and Science Shanghai University Shanghai ChinaState Key Laboratory of Advanced Special Steels & Shanghai Key Laboratory of Advanced Ferrometallurgy & School of Materials Science and Engineering Shanghai University Shanghai ChinaAbstract Exploring the “composition‐microstructure‐property” relationship is a long‐standing theme in materials science. However, complex interactions make this area of research challenging. Based on the image processing and machine learning techniques, this paper proposes a multimodal fusion learning framework that comprehensively considers both composition and microstructure in prediction of the ultimate tensile strength (UTS) of Al‐Si alloys. Firstly, the composition and image information are collected from the literature and supplementary experiments, followed by the image segmentation and quantitative analysis of eutectic Si images. Subsequently, the quantitative analysis results are combined with other features for three‐step feature screening, and 12 key features are obtained. Finally, four machine‐learning models (i.e., decision tree, random forest, adaptive boosting, and extreme gradient boosting [XGBoost]) are used to predict the UTS of Al‐Si alloys. The results show that the quantitative analysis method proposed in this paper is superior to Image‐Pro Plus (IPP) software in some aspects. The XGBoost model has the best prediction performance with R2 = 0.94. Furthermore, five mixed features and their critical values that significantly affect UTS are identified. Our study provides enlightenment for the prediction of UTS of Al‐Si alloys from composition and microstructure, and would be applicable to other alloys.https://doi.org/10.1002/mgea.26Al‐Si alloysimage processingmachine learningmultimodalproperty prediction
spellingShingle Longfei Zhu
Qun Luo
Qiaochuan Chen
Yu Zhang
Lijun Zhang
Bin Hu
Yuexing Han
Qian Li
Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learning
Materials Genome Engineering Advances
Al‐Si alloys
image processing
machine learning
multimodal
property prediction
title Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learning
title_full Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learning
title_fullStr Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learning
title_full_unstemmed Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learning
title_short Prediction of ultimate tensile strength of Al‐Si alloys based on multimodal fusion learning
title_sort prediction of ultimate tensile strength of al si alloys based on multimodal fusion learning
topic Al‐Si alloys
image processing
machine learning
multimodal
property prediction
url https://doi.org/10.1002/mgea.26
work_keys_str_mv AT longfeizhu predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning
AT qunluo predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning
AT qiaochuanchen predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning
AT yuzhang predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning
AT lijunzhang predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning
AT binhu predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning
AT yuexinghan predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning
AT qianli predictionofultimatetensilestrengthofalsialloysbasedonmultimodalfusionlearning