Data-driven analysis of process,structure,and properties of additively manufactured Inconel 718 thin walls

作     者：Lichao Fang Lin Cheng Jennifer A.Glerum Jennifer Bennett Jian Cao Gregory J.Wagner 

作者机构：Department of Mechanical EngineeringNorthwestern UniversityEvanstonIL60208USA Department of Materials Science and EngineeringNorthwestern UniversityEvanstonIL60208USA DMG MORIHoffman EstatesIL60192USA Department of Mechanical and Materials EngineeringWorcester Polytechnic InstituteWorcesterMA01609USA Department of Civil and Mechanical EngineeringUS Military Acadeemy at West PointWest PointNY10996USA 

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：1168-1182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：This work was supported by the National Science Foundation(NSF)under Grant No.CMMI-1934367 the Beijing Institute of Collaborative Innovation under Award No.20183405 J.A.G.and J.B.acknowledge support by the US Army Research Laboratory under Grant No.W911NF-19-2-0092 The SEM analysis work made use of the EPIC facility of NUANCE Center and the MatCI Facility of the Materials Research Center at Northwestern University,which was supported by NSF under Grant No.ECCS-1542205 and DMR-1720139,the International Institute for Nanotechnology(IIN),the Keck Foundation,and the State of Illinois through the IIN 

主　　题：Inconel process additive 

摘      要：In additive manufacturing of metal parts,the ability to accurately predict the extremely variable temperature field in detail,and relate it quantitatively to structure and properties,is a key step in predicting part performance and optimizing process *** this work,a finite element simulation of the directed energy deposition(DED)process is used to predict the space-and time-dependent temperature field during the multi-layer build process for Inconel 718 *** thermal model results show good agreement with dynamic infrared images captured in situ during the DED *** relationship between predicted cooling rate,microstructural features,and mechanical properties is examined,and cooling rate alone is found to be insufficient in giving quantitative property *** machine learning offers an efficient way to identify important features from series data,we apply a 1D convolutional neural network data-driven framework to automatically extract the dominant predictive features from simulated temperature *** good predictions of material properties,especially ultimate tensile strength,are obtained using simulated thermal history *** further interpret the convolutional neural network predictions,we visualize the extracted features produced on each convolutional layer and compare the convolutional neural network detected features of thermal histories for high and low ultimate tensile strength cases.A key result is the determination that thermal histories in both high and moderate temperature regimes affect material properties.