A multi-fidelity (MF) surrogate involving Gaussian processes (GPs) is used for designing temporal process maps in laser directed energy deposition (L-DED) additive manufacturing (AM). Process maps are used to establish relationships between the melt pool properties (e.g., melt pool depth) and process parameters (e.g., laser power and scan velocity). The MFGP surrogate involves a high-fidelity (HF) and a low-fidelity (LF) model. The Autodesk Netfabb${}^{\circledR }$ finite element model (FEM) is selected as the HF model, while an analytical model developed by Eagar-Tsai is chosen as the LF one. The results show that the MFGP surrogate is capable of successfully blending the information present in different fidelity models for designing the temporal forward process maps (e.g., given a set of process parameters for which the true depth is not known, what would be the melt pool depth?). To expand the newly-developed formulation for establishing the temporal inverse process maps (e.g., to achieve the desired melt pool depth for which the true process parameters are not known, what would be the optimal prediction of the process parameters as a function of time?), a case study is performed by coupling the MFGP surrogate with Bayesian Optimization (BO) under computational budget constraints. The results demonstrate that MFGP-BO can significantly improve the optimization solution quality compared to the single-fidelity (SF) GP-BO, along with incurring a lower computational budget. As opposed to the existing methods that are limited to developing steady-state forward process maps, the current work successfully demonstrates the realization of temporal forward and inverse process maps in L-DED incorporating uncertainty quantification (UQ).

The objective of this work is to compare the microstructure and microhardness properties of IN718 deposited by both powder- and wire-fed laser-directed energy deposition (L-DED) processes. The powder-fed L-DED is carried out on an Optomec LENS^® system while the wire-fed L-DED is performed in an in-house custom-built system. Several single-layer single-track specimens are fabricated using different combinations of process parameters to down-select the optimal process parameters for both systems. The finalized parameters are, thereafter, used to build thin-wall specimens having identical designs. The specimens are characterized using optical and electron microscopy as well as microhardness measurements. The results demonstrate that the powder-fed specimen, built using optimal process parameters, does not exhibit any distortion. On the contrary, the wire-fed specimen, built with optimal process parameters, show lesser porosity. Differences in elemental segregation are also detected in the two specimens. For example, nitrides and carbides are observed in the wire-fed specimen but not in the powder-fed specimen. The microhardness measurements reveal the powder-fed specimen has higher microhardness values compared to the wire-fed specimen. These results can be used to fabricate parts with sequential powder and wire deposition to achieve biomimetic structures of varying microstructure and microhardness properties.