Metal additive manufacturing (AM) works on the principle of consolidating feedstock material in layers towards the fabrication of complex objects through localized melting and resolidification using high-power energy sources. Powder bed fusion and directed energy deposition are two widespread metal AM processes that are currently in use. During layer-by-layer fabrication, as the components continue to gain thermal energy, the melt pool geometry undergoes substantial changes if the process parameters are not appropriately adjusted on-the-fly. Although control of melt pool geometry via feedback or feedforward methods is a possibility, the time needed for changes in process parameters to translate into adjustments in melt pool geometry is of critical concern. A second option is to implement multi-physics simulation models that can provide estimates of temporal process parameter evolution. However, such models are computationally near intractable when they are coupled with an optimization framework for finding process parameters that can retain the desired melt pool geometry as a function of time. To address these challenges, a hybrid framework involving machine learning-assisted process modeling and optimization for controlling the melt pool geometry during the build process is developed and validated using experimental observations. A widely used 3D analytical model capable of predicting the thermal distribution in a moving melt pool is implemented and, thereafter, a nonparametric Bayesian, namely, Gaussian Process (GP), model is used for the prediction of time-dependent melt pool geometry (e.g., dimensions) at different values of the process parameters with excellent accuracy along with uncertainty quantification at the prediction points. Finally, a surrogate-assisted statistical learning and optimization architecture involving GP-based modeling and Bayesian Optimization (BO) is employed for predicting the optimal set of process parameters as the scan progresses to keep the melt pool dimensions at desired values. The results demonstrate that a model-based optimization can be significantly accelerated using tools of machine learning in a data-driven setting and reliable a priori estimates of process parameter evolution can be generated to obtain desired melt pool dimensions for the entire build process.

The turbine section of aircraft engines (both commercial and military) is an example of one of the most hostile environments as the components in this section typically operate at upwards of 1650 °C in the presence of corrosive and oxidative gases. The blades are at the heart of the turbine section as they extract energy from the hot gases to generate work. The turbine blades are typically fabricated using investment casting, and depending on the casting complexity, they generally display one of the three common microstructures (i.e., equiaxed or polycrystalline, directionally solidified, and single crystal). Single crystal casting is exotic as several steps of the casting process are traditionally hands-on. Due to the complex production process involving several prototyping iterations, the blade castings have a significant cost associated with them. For example, a set of 40 single crystal turbine blades costs above USD 600,000 and requires 60–90 weeks for production. Additionally, if the components suffer from material loss due to prolonged service or manufacturing defects, the traditional manufacturing methods cannot restore the parent metallurgy at the damage locations. Hence, there is a significant interest in developing additive manufacturing (AM) technologies that can repair the single crystal turbine blades. Despite the blades’ criticality in aircraft propulsion, there is currently no review article that summarizes the metallurgy, production process, failure mechanisms, and AM-based repair methods of the single crystal turbine blades. To address this existing gap, this review paper starts with a discussion on the composition of the single crystal superalloys, describes the traditional fabrication methods for the metallic single crystal turbine blades, estimates the material and energy loss when the blades are scrapped or reverted, and provides a summary of the AM technologies that are currently being investigated for their repair potential. In conclusion, based on the literature reviewed, this paper identifies new avenues for research and development approaches for advancing the fabrication and repair of single crystal turbine blades.

Additive manufacturing (AM) of metals can be broadly accomplished via two defined technologies: powder bed fusion and directed energy deposition. During AM fabrication, the melted feedstock material experiences fast thermal cycling due to the layer-by-layer deposition process resulting in microstructures and properties that are drastically different from the traditionally manufactured parts. For AM to become a viable process for fabricating critical components made of high-performance structural alloys, such as AlSi10Mg, a comprehensive understanding is required toward developing the process-structure-property relationships prevalent in AM. AlSi10Mg, with its good castability, strength, hardness, and dynamic properties, is typically used to fabricate structural components that are required to withstand high loads. This alloy has been consolidated predominantly by the laser powder bed fusion (L-PBF) method and several critical mechanical properties, such as fatigue, have been reported to date. This article, first, summarizes the as-deposited and heat-treated microstructures of AlSi10Mg specimens fabricated by L-PBF. Then, the article discusses the linkages among the feedstock properties, printing parameters, specimen geometry, post-processing techniques, and fatigue properties. This discussion is followed by a section on the fatigue life prediction of AlSi10Mg specimens using computational modeling. Finally, the article identifies critical research gaps and pinpoints future research opportunities.

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).