Metal additive manufacturing provides remarkable flexibility in geometry and component design,but localized heating/cooling heterogeneity leads to spatial variations of as-built mechanical properties,significantly com...Metal additive manufacturing provides remarkable flexibility in geometry and component design,but localized heating/cooling heterogeneity leads to spatial variations of as-built mechanical properties,significantly complicating the materials design process.To this end,we develop a mechanistic data-driven framework integrating wavelet transforms and convolutional neural networks to predict location-dependent mechanical properties over fabricated parts based on process-induced temperature sequences,i.e.,thermal histories.The framework enables multiresolution analysis and importance analysis to reveal dominant mechanistic features underlying the additive manufacturing process,such as critical temperature ranges and fundamental thermal frequencies.We systematically compare the developed approach with other machine learning methods.The results demonstrate that the developed approach achieves reasonably good predictive capability using a small amount of noisy experimental data.It provides a concrete foundation for a revolutionary methodology that predicts spatial and temporal evolution of mechanical properties leveraging domain-specific knowledge and cutting-edge machine and deep learning technologies.展开更多
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 p...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 design.In 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 walls.The thermal model results show good agreement with dynamic infrared images captured in situ during the DED builds.The 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 predictions.Because 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 history.Very good predictions of material properties,especially ultimate tensile strength,are obtained using simulated thermal history data.To 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.展开更多
基金This study was supported by the National Science Foundation(NSF)through grants CMMI-1934367We thank Jennifer Glerum for performing the SEM imaging and Mark Fleming for his detailed review and helpful suggestions.J.Bennett and J.Cao would like to acknowledge the support from the Army Research Laboratory(ARL W911NF-18-2-0275)J.Bennet acknowledeg the ARL Oak Ridge Associated Universities(ORAU)Journeyman Fellowship.
文摘Metal additive manufacturing provides remarkable flexibility in geometry and component design,but localized heating/cooling heterogeneity leads to spatial variations of as-built mechanical properties,significantly complicating the materials design process.To this end,we develop a mechanistic data-driven framework integrating wavelet transforms and convolutional neural networks to predict location-dependent mechanical properties over fabricated parts based on process-induced temperature sequences,i.e.,thermal histories.The framework enables multiresolution analysis and importance analysis to reveal dominant mechanistic features underlying the additive manufacturing process,such as critical temperature ranges and fundamental thermal frequencies.We systematically compare the developed approach with other machine learning methods.The results demonstrate that the developed approach achieves reasonably good predictive capability using a small amount of noisy experimental data.It provides a concrete foundation for a revolutionary methodology that predicts spatial and temporal evolution of mechanical properties leveraging domain-specific knowledge and cutting-edge machine and deep learning technologies.
基金This work was supported by the National Science Foundation(NSF)under Grant No.CMMI-1934367the Beijing Institute of Collaborative Innovation under Award No.20183405+1 种基金J.A.G.and J.B.acknowledge support by the US Army Research Laboratory under Grant No.W911NF-19-2-0092The 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.
文摘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 design.In 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 walls.The thermal model results show good agreement with dynamic infrared images captured in situ during the DED builds.The 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 predictions.Because 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 history.Very good predictions of material properties,especially ultimate tensile strength,are obtained using simulated thermal history data.To 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.