Abstract
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.
Highlights
Additive manufacturing (AM), sometimes called three-dimensional (3D) printing, is a rapidly growing advanced manufacturing paradigm that promises unparalleled flexibility in the production of metal or non-metal parts with complex geometries
The nature of the process creates position-dependent microstructures, residual stresses, and mechanical properties that complicate printing process design, part qualification, and manufacturing certification. Metal additive manufacturing, such as laser powder bed fusion (L-PBF) and directed energy deposition (DED), have most of the relevant physical processes occurring in the vicinity of the melt pool
Dendritic growth with micro-segregation of the alloy constituents can produce non-equilibrium phases and anisotropic grain morphologies that strongly affect the local component properties and performances. These multiscale and multiphysics phenomena involve interactions and dependencies of a large number of process parameters and material properties leading to complex process-structure-properties (PSP) relationships[2]
Summary
Additive manufacturing (AM), sometimes called three-dimensional (3D) printing, is a rapidly growing advanced manufacturing paradigm that promises unparalleled flexibility in the production of metal or non-metal parts with complex geometries. The nature of the process creates position-dependent microstructures, residual stresses, and mechanical properties that complicate printing process design, part qualification, and manufacturing certification Metal additive manufacturing, such as laser powder bed fusion (L-PBF) and directed energy deposition (DED), have most of the relevant physical processes occurring in the vicinity of the melt pool. Dendritic growth with micro-segregation of the alloy constituents can produce non-equilibrium phases and anisotropic grain morphologies that strongly affect the local component properties and performances These multiscale and multiphysics phenomena involve interactions and dependencies of a large number of process parameters and material properties leading to complex process-structure-properties (PSP) relationships[2]. Wang et al.[28] proposed a data-driven framework based on high-throughput AM simulations and AM benchmark experiments[10] They developed a Bayesian calibration approach to calibrate experimental parameters and correct the model, which improves the validity of the surrogate model. Zhang et al.[30,31] designed a convolutional neural network (CNN) model to recognize patterns in melt pool images to predict porosity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
