Additive manufacturing features rapid production of complicated shapes and has been widely employed in biomedical,aeronautical and aerospace applications.However,additive manufactured parts generally exhibit deteriora...Additive manufacturing features rapid production of complicated shapes and has been widely employed in biomedical,aeronautical and aerospace applications.However,additive manufactured parts generally exhibit deteriorated fatigue resistance due to the presence of random defects and anisotropy,and the prediction of fatigue properties remains challenging.In this paper,recent advances in fatigue life prediction of additive manufactured metallic alloys via machine learning models are reviewed.Based on artificial neural network,support vector machine,random forest,etc.,a number of models on various systems were proposed to reveal the relationships between fatigue life/strength and defect/microstructure/parameters.Despite the success,the predictability of the models is limited by the amount and quality of data.Moreover,the supervision of physical models is pivotal,and machine learning models can be well enhanced with appropriate physical knowledge.Lastly,future challenges and directions for the fatigue property prediction of additive manufactured parts are discussed.展开更多
As one of the fundamental outcomes of dislocation self-interaction,dislocation dipoles have an important influence on the plastic deformation of materials,especially on fatigue and creep.In this work,superdislocation ...As one of the fundamental outcomes of dislocation self-interaction,dislocation dipoles have an important influence on the plastic deformation of materials,especially on fatigue and creep.In this work,superdislocation dipoles inγ-TiAl andα_(2)-Ti_(3)Al were systematically investigated by atomistic simulations,with a variety of dipole heights,orientations and annealing tempe ratures.The results indicate that non-screw super-dipoles transform into locally stable dipolar or reconstructed cores at low temperature,while into isolated or interconnected point defect clusters and stacking fault tetrahedra at high temperature via short-range diffu sion.Non-screw super-dipoles inγ-TiAl andα_(2)-Ti_(3)Al exhibit similar features as fcc and hcp metals,respectively.Generally,over long-term annealing where diffusion is significant,60°superdipoles inγ-TiAl are stable,whereas the stability of super-dipoles inα2-Ti3 Al increases with dipole height and orientation angle.The influence on mechanical properties can be well evaluated by integrating these results into mesoscale or constitutive models.展开更多
基金support of National Natural Science Foundation of China(No.U2241245)support of National Natural Science Foundation of China(No.91960202)+4 种基金National Key Laboratory Foundation of Science and Technology on Materials under Shock and Impact(No.6142902220301)Natural Science Foundation of Shenyang(No.23-503-6-05)support of Opening Project of National Key Laboratory of Shock Wave and Detonation Physics(No.2022JCJQLB05702)Aeronautical Science Foundation of China(No.2022Z053092001)support of Shanghai Engineering Research Center of High-Performance Medical Device Materials(No.20DZ2255500).
文摘Additive manufacturing features rapid production of complicated shapes and has been widely employed in biomedical,aeronautical and aerospace applications.However,additive manufactured parts generally exhibit deteriorated fatigue resistance due to the presence of random defects and anisotropy,and the prediction of fatigue properties remains challenging.In this paper,recent advances in fatigue life prediction of additive manufactured metallic alloys via machine learning models are reviewed.Based on artificial neural network,support vector machine,random forest,etc.,a number of models on various systems were proposed to reveal the relationships between fatigue life/strength and defect/microstructure/parameters.Despite the success,the predictability of the models is limited by the amount and quality of data.Moreover,the supervision of physical models is pivotal,and machine learning models can be well enhanced with appropriate physical knowledge.Lastly,future challenges and directions for the fatigue property prediction of additive manufactured parts are discussed.
基金the National Key Research and Development Program of China(No.2016YFB0701304 and 2017YFB0306201)the Natural Science Foundation of China(Nos.51671195 and 91960202)+4 种基金the Frontier and Key Projects of the Chinese Academy of Sciences(Nos.QYZDJ-SSW-JSC031-01 and XXH13506-304)the Natural Science Foundation of Liaoning(No.20180510032)the Aeronautical Science Foundation of China(No.20160292002)the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDC01000000)The Project is sponsored by the“Liaoning BaiQianWan”Talents Program。
文摘As one of the fundamental outcomes of dislocation self-interaction,dislocation dipoles have an important influence on the plastic deformation of materials,especially on fatigue and creep.In this work,superdislocation dipoles inγ-TiAl andα_(2)-Ti_(3)Al were systematically investigated by atomistic simulations,with a variety of dipole heights,orientations and annealing tempe ratures.The results indicate that non-screw super-dipoles transform into locally stable dipolar or reconstructed cores at low temperature,while into isolated or interconnected point defect clusters and stacking fault tetrahedra at high temperature via short-range diffu sion.Non-screw super-dipoles inγ-TiAl andα_(2)-Ti_(3)Al exhibit similar features as fcc and hcp metals,respectively.Generally,over long-term annealing where diffusion is significant,60°superdipoles inγ-TiAl are stable,whereas the stability of super-dipoles inα2-Ti3 Al increases with dipole height and orientation angle.The influence on mechanical properties can be well evaluated by integrating these results into mesoscale or constitutive models.
