Search for: All records

Abstract 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. 

The phase-field (PF) method is a physics-based computational approach for simulating interfacial morphology. It has been used to model powder melting, rapid solidification, and grain structure evolution in metal additive manufacturing (AM). However, traditional direct numerical simulation (DNS) of the PF method is computationally expensive due to sufficiently small mesh size. Here, a physics-embedded graph network (PEGN) is proposed to leverage an elegant graph representation of the grain structure and embed the classic PF theory into the graph network. By reformulating the classic PF problem as an unsupervised machine learning task on a graph network, PEGN efficiently solves temperature field, liquid/solid phase fraction, and grain orientation variables to minimize a physics-based loss/energy function. The approach is at least 50 times faster than DNS in both CPU and GPU implementation while still capturing key physical features. Hence, PEGN allows to simulate large-scale multi-layer and multi-track AM build effectively.