To leverage advancements in machine learning for metallic materials design and property prediction,it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of curr...To leverage advancements in machine learning for metallic materials design and property prediction,it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of current physics-based discrete microstructure descriptors.This need is particularly relevant for metallic materials processed through additive manufacturing,which exhibit complex hierarchical microstructures that cannot be adequately described using the conventional metrics typically applied to wrought materials.Furthermore,capturing the spatial heterogeneity of microstructures at the different scales is necessary within such framework to accurately predict their properties.To address these challenges,we propose the physical spatial mapping of metal diffraction latent space features.This approach integrates(i)point diffraction data encoding via variational autoencoders or contrastive learning and(ii)the physical mapping of the encoded values.Together,these steps offer a method to comprehensively describe metal microstructures.We demonstrate this approach on a wrought and additively manufactured alloy,showing that it effectively encodes microstructural information and enables direct identification of microstructural heterogeneity not directly possible by physics-based models.This data-reduced microstructure representation opens the application of machine learning models in accelerating metallic material design and accurately predicting their properties.展开更多
A high-entropy metal disilicide,(Mo_(0.2)Nb_(0.2)Ta_(0.2)Ti_(0.2)W_(0.2))Si_(2),has been successfully synthesized.X-ray diffraction(XRD),energy dispersive X-ray spectroscopy(EDX),and electron backscatter diffraction(E...A high-entropy metal disilicide,(Mo_(0.2)Nb_(0.2)Ta_(0.2)Ti_(0.2)W_(0.2))Si_(2),has been successfully synthesized.X-ray diffraction(XRD),energy dispersive X-ray spectroscopy(EDX),and electron backscatter diffraction(EBSD)collectively show the formation of a single high-entropy silicide phase.This high-entropy(Mo_(0.2)Nb_(0.2)Ta_(0.2)Ti_(0.2)W_(0.2))Si_(2) possesses a hexagonal C40 crystal structure with ABC stacking sequence and a space group of P6222.This discovery expands the known families of high-entropy materials from metals,oxides,borides,carbides,and nitrides to a silicide,for the first time to our knowledge,as well as demonstrating that a new,non-cubic,crystal structure(with lower symmetry)can be made into highentropy phase.This(Mo_(0.2)Nb_(0.2)Ta_(0.2)Ti_(0.2)W_(0.2))Si_(2) exhibits high nanohardness of 16.7±1.9 GPa and Vickers hardness of 11.6±0.5 GPa.Moreover,it has a low thermal conductivity of 6.9±1.1Wm^(-1) K^(-1),which is approximately one order of magnitude lower than that of the widely-used tetragonal MoSi_(2) and ~1/3 of those reported values for the hexagonal NbSi_(2) and TaSi_(2) with the same crystal structure.展开更多
基金support from DARPAC.B., D.A., H.P. and J.C.S. acknowledge the NSF (award #2338346) for financial support.This work was carried out in the Materials Research Laboratory Central Research Facilities, University of Illinois. Carpenter Technology is acknowledged for providing the 718 material. Morad Behandish and Adrian Lew are acknowledged for their support and leadership. Tresa Pollock, McLean Echlin and James Lamb are acknowledged for their support on the EBSD sharpness calculations. Marat Latypov, Marie Charpagne, and Florian Strub are gratefully acknowledged for their support and insightful discussions.
文摘To leverage advancements in machine learning for metallic materials design and property prediction,it is crucial to develop a data-reduced representation of metal microstructures that surpasses the limitations of current physics-based discrete microstructure descriptors.This need is particularly relevant for metallic materials processed through additive manufacturing,which exhibit complex hierarchical microstructures that cannot be adequately described using the conventional metrics typically applied to wrought materials.Furthermore,capturing the spatial heterogeneity of microstructures at the different scales is necessary within such framework to accurately predict their properties.To address these challenges,we propose the physical spatial mapping of metal diffraction latent space features.This approach integrates(i)point diffraction data encoding via variational autoencoders or contrastive learning and(ii)the physical mapping of the encoded values.Together,these steps offer a method to comprehensively describe metal microstructures.We demonstrate this approach on a wrought and additively manufactured alloy,showing that it effectively encodes microstructural information and enables direct identification of microstructural heterogeneity not directly possible by physics-based models.This data-reduced microstructure representation opens the application of machine learning models in accelerating metallic material design and accurately predicting their properties.
基金the partial financial support from an Office of Naval Research MURI program(grant no.N00014-15-1-2863,Program Mangers:Dr.Kenny Lipkowitz and Dr.Eric Wuchina)funding from the National Science Foundation,Grant No.CBET-1706388supported by the Deparment of Defense(DoD)through the National Defense Science and Engineering Graduate Fellowship(NDSEG)program as well as the ARCS foundation.
文摘A high-entropy metal disilicide,(Mo_(0.2)Nb_(0.2)Ta_(0.2)Ti_(0.2)W_(0.2))Si_(2),has been successfully synthesized.X-ray diffraction(XRD),energy dispersive X-ray spectroscopy(EDX),and electron backscatter diffraction(EBSD)collectively show the formation of a single high-entropy silicide phase.This high-entropy(Mo_(0.2)Nb_(0.2)Ta_(0.2)Ti_(0.2)W_(0.2))Si_(2) possesses a hexagonal C40 crystal structure with ABC stacking sequence and a space group of P6222.This discovery expands the known families of high-entropy materials from metals,oxides,borides,carbides,and nitrides to a silicide,for the first time to our knowledge,as well as demonstrating that a new,non-cubic,crystal structure(with lower symmetry)can be made into highentropy phase.This(Mo_(0.2)Nb_(0.2)Ta_(0.2)Ti_(0.2)W_(0.2))Si_(2) exhibits high nanohardness of 16.7±1.9 GPa and Vickers hardness of 11.6±0.5 GPa.Moreover,it has a low thermal conductivity of 6.9±1.1Wm^(-1) K^(-1),which is approximately one order of magnitude lower than that of the widely-used tetragonal MoSi_(2) and ~1/3 of those reported values for the hexagonal NbSi_(2) and TaSi_(2) with the same crystal structure.
