Understanding the creep behaviors and mechanisms of Mg-Gd-Zn alloys via machine learning

作     者：Shuxia Ouyang Xiaobing Hu Qingfeng Wu Jeong Ah Lee Jae Heung Lee Chenjin Zhang Chunhui Wang Hyoung Seop Kim Guangyu Yang Wanqi Jie Shuxia Ouyang;Xiaobing Hu;Qingfeng Wu;Jeong Ah Lee;Jae Heung Lee;Chenjin Zhang;Chunhui Wang;Hyoung Seop Kim;Guangyu Yang;Wanqi Jie

作者机构：Graduate Institute of Ferrous and Eco Materials Technology(GIFT)Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea State Key Laboratory of Solidification ProcessingNorthwestern Polytechnical UniversityXi’an 710072China Xi’an Rare Metal Materials lnstitute Co.LtdXi’an 710016China Department of Materials Science and EngineeringPohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea DepartmentAdvanced Institute for Materials Research(WPI-AIMR)Tohoku UniversitySendai 980-8577Japan Institute for Convergence Research and Education in Advanced TechnologyYonsei UniversitySeoul 03722South Korea 

出 版 物：《Journal of Magnesium and Alloys》 (镁合金学报（英文）)

年 卷 期：2024年第12卷第8期

页      面：3281-3291页

核心收录：

学科分类：08[工学] 080502[工学-材料学] 0805[工学-材料科学与工程（可授工学、理学学位）] 

基　　金：supported by the National Science and Technology Major Project(Grant number J2019-VI-0004-0118) the National Natural Science Foundation of China(Grant number 51771152) the National Key R&D Program of China(Grant number 2018YFB1106800) supported by the Brain Pool Program through the National Research Foundation of Korea(NRF)(Grant No.RS-2023-00304296) supported by the Brain Pool Program through National Research Foundation of Korea(NRF)(Grant No.RS-2023-00222130) 

主　　题：Mg-Gd-Zn based alloys Machine learning Creep rate Creep mechanism Constitutive equation 

摘      要：Mg-Gd-Zn based alloys have better creep resistance than other Mg alloys and attract more attention at elevated ***,the multiple alloying elements and various heat treatment conditions,combined with complex microstructural evolution during creep tests,bring great challenges in understanding and predicting creep *** this study,we proposed to predict the creep properties and reveal the creep mechanisms of Mg-Gd-Zn based alloys by machine *** the one hand,the minimum creep rates were effectively predicted by using a support vector regression *** complex and nonmonotonic effects of test temperature,test stress,alloying elements,and heat treatment conditions on the creep properties were *** the other hand,the creep stress exponents and creep activation energies were calculated by machine learning to analyze the variation of creep mechanisms,based on which the constitutive equations of Mg-Gd-Zn based alloys were *** study introduces an efficient method to comprehend creep behaviors through machine learning,offering valuable insights for the future design and selection of Mg alloys.