Distilling physical origins of hardness in multi-principal element alloys directly from ensemble neural network models

作     者：D.Beniwal P.Singh S.Gupta M.J.Kramer D.D.Johnson P.K.Ray 

作者机构：Metallurgical&Materials EngineeringIndian Institute of Technology RoparRupnagar140001PunjabIndia Ames LaboratoryUS Department of EnergyAmesIA50011USA Materials Science&EngineeringIowa State UniversityAmesIA50011USA 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2022年第8卷第1期

页      面：1450-1460页

核心收录：

学科分类：08[工学] 081104[工学-模式识别与智能系统] 0806[工学-冶金工程] 0805[工学-材料科学与工程（可授工学、理学学位）] 080502[工学-材料学] 0811[工学-控制科学与工程] 0702[理学-物理学] 

基　　金：The machine-learning studies were supported by ISIRD Phase-I grant(9-405/2019/IITRPR/3480)from IIT Ropar The work at Ames Laboratory,including theory developments for MPEAs,was supported by U.S.DOE Office of Science,Basic Energy Sciences,Materials Science&Engineering Division.Ames Laboratory is operated by ISU for the U.S.DOE under contract DE-AC02-07CH11358 Experimental work and application of theory to this system was supported by the U.S.Department of Energy(DOE),Office of Fossil Energy,Crosscutting Research Program.The Advanced Photon Source use was supported by U.S.DOE,Office of Science,Office of Basic Energy Sciences under Contract No.DE-AC02-06CH11357. 

主　　题：alloys alloy element 

摘      要：Despite a plethora of data being generated on the mechanical behavior of multi-principal element alloys,a systematic assessment remains inaccessible via Edisonian approaches.We approach this challenge by considering the specific case of alloy hardness,and present a machine-learning framework that captures the essential physical features contributing to hardness and allows high-throughput exploration of multi-dimensional compositional space.The model,tested on diverse datasets,was used to explore and successfully predict hardness in Al_(x)Ti_(y)(CrFeNi)_(1-x-y),Hf_(x)Co_(y)(CrFeNi)_(1-x-y)and Al_(x)(TiZrHf)_(1-x)systems supported by data from density-functional theory predicted phase stability and ordering behavior.The experimental validation of hardness was done on TiZrHfAlx.The selected systems pose diverse challenges due to the presence of ordering and clustering pairs,as well as vacancy-stabilized novel structures.We also present a detailed model analysis that integrates local partial-dependencies with a compositional-stimulus and model-response study to derive material-specific insights from the decision-making process.