Al-Si alloys have excellent corrosion resistance,low thermal expansion coefficient,and high strength-to-weight ratio,which make them widely used in structural components in the automotive and aerospace industries[1,2]...Al-Si alloys have excellent corrosion resistance,low thermal expansion coefficient,and high strength-to-weight ratio,which make them widely used in structural components in the automotive and aerospace industries[1,2].However,the coarseα-Al dendrites result in poor mechanical properties[3,4],and the widely used Al-5Ti-B(all compositions are in wt.%unless otherwise specified)refiner fails in as-cast aluminum alloys with high silicon content(≥5 wt.%)due to the Si-poisoning effect[5,6].Fortunately,in order to overcome Si-poisoning,a series of refiners have been developed.Al-B refiner is effective for refining aluminum alloys with high silicon content,but it is easy to be poisoned by Ti/Zr[7,8].Al-Nb-B[9–11]and Al-V-B[12]refiners have a certain ability to overcome Si-poisoning,while the nucleating particles have a large density and are easy to agglomerate and settle,leading to the grain refinement fading phenomenon.Al-Ti-C-B refiner realizes the anti-Si/Zrpoisoning ofα-Al grain refinement based on the evolving effect of a doped TCB complex[13,14].Al-Ti-Nb-B refiner prepared with Nb partially substituted Ti can improve the refinement level of Al-10Si alloy to 109–125μm[15,16].However,the existing preparation method of the refiner uses pure Nb powder as raw material,resulting in high preparation costs,which limits its application in industry to a certain extent.展开更多
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 mach...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 experi-ments,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 R^(2)=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.展开更多
基金supported by the National Natural Science Foundation of China(No.U2102212)and the Shanghai Rising-Star Program(No.21QA1403200).
文摘Al-Si alloys have excellent corrosion resistance,low thermal expansion coefficient,and high strength-to-weight ratio,which make them widely used in structural components in the automotive and aerospace industries[1,2].However,the coarseα-Al dendrites result in poor mechanical properties[3,4],and the widely used Al-5Ti-B(all compositions are in wt.%unless otherwise specified)refiner fails in as-cast aluminum alloys with high silicon content(≥5 wt.%)due to the Si-poisoning effect[5,6].Fortunately,in order to overcome Si-poisoning,a series of refiners have been developed.Al-B refiner is effective for refining aluminum alloys with high silicon content,but it is easy to be poisoned by Ti/Zr[7,8].Al-Nb-B[9–11]and Al-V-B[12]refiners have a certain ability to overcome Si-poisoning,while the nucleating particles have a large density and are easy to agglomerate and settle,leading to the grain refinement fading phenomenon.Al-Ti-C-B refiner realizes the anti-Si/Zrpoisoning ofα-Al grain refinement based on the evolving effect of a doped TCB complex[13,14].Al-Ti-Nb-B refiner prepared with Nb partially substituted Ti can improve the refinement level of Al-10Si alloy to 109–125μm[15,16].However,the existing preparation method of the refiner uses pure Nb powder as raw material,resulting in high preparation costs,which limits its application in industry to a certain extent.
基金supported by the National Natural Science Foundation of China(U2102212)the National Natural Science Foundation of China(52273228)+2 种基金the Shanghai Rising-Star Program(21QA1403200)the Key Research Project of Zhejiang Laboratory(2021PE0AC02)the Shanghai Science and Technology Young Talents Sailing Program(23YF1412900).
文摘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 experi-ments,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 R^(2)=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.
