Machine learning of phases and mechanical properties in complex concentrated alloys

来源 :材料科学技术(英文版) | 被引量 : 0次 | 上传用户:zhulimin520
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
The mechanical properties of complex concentrated alloys (CCAs) depend on their formed phases and corresponding microstructures.The data-driven prediction of the phase formation and associated mechanical properties is essential to discovering novel CCAs.The present work collects 557 samples of various chemical compositions,comprising 61 amorphous,167 single-phase crystalline,and 329 multi-phases crystalline CCAs.Three classification models are developed with high accuracies to category and understand the formed phases of CCAs.Also,two regression models are constructed to predict the hard-ness and ultimate tensile strength of CCAs,and the correlation coefficient of the random forest regression model is greater than 0.9 for both of two targeted properties.Furthermore,the Shapley additive expla-nation (SHAP) values are calculated,and accordingly four most important features are identified.A significant finding in the SHAP values is that there exists a critical value in each of the top four fea-tures,which provides an easy and fast assessment in the design of improved mechanical properties of CCAs.The present work demonstrates the great potential of machine learning in the design of advanced CCAs.
其他文献
1.IntroductionrnHigh strength steels continue to be developed for automotive applications to increase safety and reduce lightweight by down-gauging[1,2].In addition,reducing density is another solution for the lightweight of automotive components[3,4].Alu
期刊
The microstructure and room-temperature tensile deformation behavior of the cast CrFeCoNiAl0.7 high-entropy alloy (HEA) were studied in details.The cast HEA consisted of a dual-phase structure of 77.3 vol.% face-centered-cubic (FCC) phase plus 22.7 vol.%
The top-down method was used to fabricate the TiNi1+xSn half-Heusler alloy.Several knotty problems have been solved using the top-down method,including the generation of impurity phases,the visi-ble discrepancy in the grain size of the TiNi2Sn second phas
The influence of different precipitate-dislocation interactions,namely dislocation shearing and bypass-ing mechanisms,on PLC bands and the resultant surface roughness in AlMgScZr alloy was investigated.Three-dimensional surface roughness was quantitativel
Low photothermal conversion efficiency restricts the antibacterial application of photothermal materials.In this work,two-dimensional carbon nanosheets (2D C) were prepared and decorated with Cu nanopar-ticles (2D C/Cu) by using a simple soluble salt temp
The electrochemical properties of a friction stir processed (FSPed) equiatomic CrMnFeCoNi high-entropy alloy (HEA) was investigated in an aerated 0.5 M Na2SO4 electrolyte solution at room temperature.The microstructural analysis reveals a highly refined s
The chain-like prior particle boundaries (PPBs) as a kind of stubborn harmful precipitate will hinder atomic diffusion and particle connection.They can only be broken into nanoscale through thermal defor-mation (1160-1200 ℃).Here,treated by the pulsed ele
The effect of surface gradient nanostructure on the fatigue life of commercial pure (CP) Zr was inves-tigated.Four point bending fatigue tests indicated that the fatigue limit of CP Zr with surface gradient nanostructure was increased by about 28.3 % comp
The microstructural evolution of purity Pd under 30 keV He+ irradiation at 573 K was investigated by in-situ transmission electron microscopy.The nucleation,growth,merging,annihilation,size change,number density variation,and types of dislocation loops we
The reasonable design of the composition of the composite materials is of great significance to optimized the electromagnetic (EM) wave absorption performance.Herein,the Ni/NiO@C hybrid composites with tunable Ni proportion were successfully synthesized t