Yong-fei JUAN , Guo-shuai NIU , Yang YANG , Zi-han XU , Jian YANG , Wen-qi TANG , Hai-tao JIANG , Yan-feng HAN , Yong-bing DAI , Jiao ZHANG , Bao-de SUN
{"title":"Accelerated design of Al−Zn−Mg−Cu alloys via machine learning","authors":"Yong-fei JUAN , Guo-shuai NIU , Yang YANG , Zi-han XU , Jian YANG , Wen-qi TANG , Hai-tao JIANG , Yan-feng HAN , Yong-bing DAI , Jiao ZHANG , Bao-de SUN","doi":"10.1016/S1003-6326(23)66429-5","DOIUrl":null,"url":null,"abstract":"<div><p>A machine learning-based alloy rapid design system (ARDS) was proposed to customize the preparation strategies for the desired properties or predict the alloy properties following the preparation strategies. For achieving this, three regression algorithms: linear regression (LR), support vector regression (SVR), and back propagation neural network (BPNN), were employed separately to train the multi-property prediction model, in which the machine learning (ML) model built using SVR was proved to be the best. Then, inspired by the generative adversarial network (GAN) algorithm, the ARDS was constructed. The predictive reliability of ARDS was examined, and for the accurate prediction of the preparation strategies, the upper limits of ultimate tensile strength (UTS), yield strength (YS), and elongation (EL) are about 790 MPa, 730 MPa, and 28%, respectively. Moreover, an ARDS-designed aluminum alloy with superior mechanical properties (764 MPa for UTS, 732 MPa for YS, and 10.1% for EL) was experimentally fabricated, further verifying the reliability of ARDS.</p></div>","PeriodicalId":23191,"journal":{"name":"Transactions of Nonferrous Metals Society of China","volume":null,"pages":null},"PeriodicalIF":4.7000,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1003632623664295/pdf?md5=9a6a58ab27c88c90757f91b6a0b66562&pid=1-s2.0-S1003632623664295-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transactions of Nonferrous Metals Society of China","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1003632623664295","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
A machine learning-based alloy rapid design system (ARDS) was proposed to customize the preparation strategies for the desired properties or predict the alloy properties following the preparation strategies. For achieving this, three regression algorithms: linear regression (LR), support vector regression (SVR), and back propagation neural network (BPNN), were employed separately to train the multi-property prediction model, in which the machine learning (ML) model built using SVR was proved to be the best. Then, inspired by the generative adversarial network (GAN) algorithm, the ARDS was constructed. The predictive reliability of ARDS was examined, and for the accurate prediction of the preparation strategies, the upper limits of ultimate tensile strength (UTS), yield strength (YS), and elongation (EL) are about 790 MPa, 730 MPa, and 28%, respectively. Moreover, an ARDS-designed aluminum alloy with superior mechanical properties (764 MPa for UTS, 732 MPa for YS, and 10.1% for EL) was experimentally fabricated, further verifying the reliability of ARDS.
期刊介绍:
The Transactions of Nonferrous Metals Society of China (Trans. Nonferrous Met. Soc. China), founded in 1991 and sponsored by The Nonferrous Metals Society of China, is published monthly now and mainly contains reports of original research which reflect the new progresses in the field of nonferrous metals science and technology, including mineral processing, extraction metallurgy, metallic materials and heat treatments, metal working, physical metallurgy, powder metallurgy, with the emphasis on fundamental science. It is the unique preeminent publication in English for scientists, engineers, under/post-graduates on the field of nonferrous metals industry. This journal is covered by many famous abstract/index systems and databases such as SCI Expanded, Ei Compendex Plus, INSPEC, CA, METADEX, AJ and JICST.