Machine Learning and Data Analytics for Design and Manufacturing of High-Entropy Materials Exhibiting Mechanical or Fatigue Properties of Interest.

Published on Dec 5, 2020in arXiv: Materials Science
Steingrimsson Baldur Andrew , Xuesong Fan4
Estimated H-index: 4
+ 2 AuthorsPeter K. Liaw94
Estimated H-index: 94
This chapter presents an innovative framework for the application of machine learning and data analytics for the identification of alloys or composites exhibiting certain desired properties of interest. The main focus is on alloys and composites with large composition spaces for structural materials. Such alloys or composites are referred to as high-entropy materials (HEMs) and are here presented primarily in context of structural applications. For each output property of interest, the corresponding driving (input) factors are identified. These input factors may include the material composition, heat treatment, manufacturing process, microstructure, temperature, strain rate, environment, or testing mode. The framework assumes the selection of an optimization technique suitable for the application at hand and the data available. Physics-based models are presented, such as for predicting the ultimate tensile strength (UTS) or fatigue resistance. We devise models capable of accounting for physics-based dependencies. We factor such dependencies into the models as a priori information. In case that an artificial neural network (ANN) is deemed suitable for the applications at hand, it is suggested to employ custom kernel functions consistent with the underlying physics, for the purpose of attaining tighter coupling, better prediction, and for extracting the most out of the - usually limited - input data available.
#1Kai Suzuki (Kyushu University)H-Index: 2
#2Motomochi Koyama (Tohoku University)H-Index: 1
Last. Hiroshi Noguchi (Kyushu University)H-Index: 58
view all 5 authors...
Abstract High-cycle fatigue crack initiation and propagation in an equiatomic CrMnFeCoNi high-entropy alloy were investigated using smooth specimens. The microstructural deformation characteristics, i.e., planar dislocation slip, significantly affected the fatigue crack initiation and small fatigue crack propagation. The deformation localization associated with dislocation planarity led to multiple crack initiation on the slip planes. The crack propagation mechanism comprised crack formation on ...
20 CitationsSource
#1Michael Moorehead (UW: University of Wisconsin-Madison)H-Index: 4
#2Kaila Bertsch (UW: University of Wisconsin-Madison)H-Index: 1
Last. Adrien Couet (UW: University of Wisconsin-Madison)H-Index: 13
view all 9 authors...
Abstract High-entropy alloys (HEAs) are a class of alloys that can exhibit promising properties including enhanced irradiation resistance, high-temperature strength, and corrosion resistance. However, they exist in a relatively unexplored region of quasi-limitless composition space. Thus, to enable the development of promising compositionally complex alloys, such as HEAs, high-throughput methods are needed. Such high-throughput capabilities are developed and presented in this work. In situ alloy...
38 CitationsSource
#1Zhang Xin (Chongqing University)H-Index: 3
#2Weiguo Li (Chongqing University)H-Index: 21
Last. Jianzuo Ma (Chongqing University)H-Index: 11
view all 11 authors...
Abstract In this study, considering the combined effects of the load carrying capacity of broken fibers and its evolution with temperature, a theoretical model for characterizing ultimate tensile strength of unidirectional ceramic-fiber reinforced ceramic composites (UCFRCCs) as a function of temperature is established. The model is verified by comparison with measurements available of temperature dependent ultimate tensile strength of UCFRCCs. Besides, on the basis of the established model, the...
4 CitationsSource
#1Jie Qi (UVA: University of Virginia)H-Index: 1
#2Andrew M. Cheung (UVA: University of Virginia)H-Index: 5
Last. S. Joseph Poon (UVA: University of Virginia)H-Index: 23
view all 3 authors...
High entropy alloys (HEA) are a new type of high-performance structural material. Their vast degrees of compositional freedom provide for extensive opportunities to design alloys with tailored properties. However, compositional complexities present challenges for alloy design. Current approaches have shown limited reliability in accounting for the compositional regions of single solid solution and composite phases. For the first time, a phenomenological method analysing binary phase diagrams to ...
21 CitationsSource
Abstract Laser beam welding was used to produce butt joints from the CoCrFeNiMn-type high entropy alloy. The alloy in the initial condition had an fcc single-phase coarse-grained structure. Laser welding resulted in the M7C3-type carbides precipitation in the fcc matrix. The carbide particles precipitation resulted in a considerable increase in microhardness from 150 HV 0.5 for the as-sintered condition to 205 HV 0.5 in the fusion zone. Laser beam welding had a negligible effect on both static m...
24 CitationsSource
#1Zdeněk ChlupH-Index: 16
#2Stanislava FintováH-Index: 12
Last. Jiří MatějíčekH-Index: 15
view all 6 authors...
9 CitationsSource
#1Yao-Jen Chang (NTHU: National Tsing Hua University)H-Index: 10
#2Chia-Yung JuiH-Index: 1
Last. An-Chou Yeh (NTHU: National Tsing Hua University)H-Index: 22
view all 4 authors...
Machine learning with artificial neural network (ANN)-based methods is a powerful tool for the prediction and exploitation of the subtle relationships between the composition and properties of materials. This work utilizes an ANN to predict the composition of high-entropy alloys (HEAs) based on non-equimolar AlCoCrFeMnNi in order to achieve the highest hardness in the system. A simulated annealing algorithm is integrated with the ANN to optimize the composition. A bootstrap approach is adopted t...
28 CitationsSource
#1Luke Johnson (A&M: Texas A&M University)H-Index: 8
#2Mohamad Mahmoudi (A&M: Texas A&M University)H-Index: 8
Last. Raymundo Arroyave (A&M: Texas A&M University)H-Index: 33
view all 10 authors...
Abstract We propose a methodology for predicting the printability of an alloy, subject to laser powder bed fusion additive manufacturing. Regions in the process space associated with keyhole formation, balling, and lack of fusion are assumed to be strong functions of the geometry of the melt pool, which in turn is calculated for various combinations of laser power and scan speed via a Finite Element thermal model that incorporates a novel vaporization-based transition from surface to volumetric ...
55 CitationsSource
#1Young-Kyun Kim (Inha University)H-Index: 10
#2Gi-Su Ham (Inha University)H-Index: 3
Last. Kee-Ahn Lee (Inha University)H-Index: 17
view all 4 authors...
Abstract High entropy alloy (HEA), a new class of materials, has received attention as a substance that can potentially replace conventional alloys. Equiatomic CoCrFeMnNi HEA is an attractive material with excellent strength-ductility combination and corrosion resistance, and it achieves greater performance in low temperatures. This study investigated the HCF and tensile deformation behavior of equiatomic CoCrFeMnNi HEA. In order to suggest the possibility of the material's application in an as-...
30 CitationsSource
#1K. LiuH-Index: 16
#2Bharat Gwalani (UNT: University of North Texas)H-Index: 25
Last. Rajiv S. Mishra (UNT: University of North Texas)H-Index: 73
view all 6 authors...
Abstract Fatigue damage is inevitable and destructive for in-service structural materials and hence warrants a detailed examination of the fatigue behavior of potential structural materials such as high entropy alloys (HEAs). This study focused on investigation of the mechanical properties of Al 0.7 CoCrFeNi HEA with two microstructural conditions; i.e., a lamellar structure consisting of FCC + B2 phases (a) without precipitates and (b) with nano-sized L1 2 precipitates in the FCC phase. Nano-si...
8 CitationsSource
Cited By0