Metal additive manufacturing (AM) holds immense potential for developing advanced structural alloys. However, the complex, heterogeneous nature of AM-produced materials presents significant challenges to traditional material characterization and optimization methods. This review explores the integration of artificial intelligence (AI) and machine learning (ML) with high-throughput material characterization protocols to rapidly establish the process–structure–property (PSP) relationships critically needed to dramatically accelerate the development of metal AM processes. Combinatorial high-throughput evaluations, including rapid material synthesis and nonstandard high-throughput testing protocols, such as spherical indentation and small punch tests, are discussed for their capability to rapidly assess mechanical properties and establish PSP linkages. Furthermore, the review examines the role of AI and ML in optimizing AM processes, particularly through Bayesian optimization, which offers new avenues for efficient exploration of high-dimensional design spaces. The review envisions a future where AI- and ML-driven, autonomous AM development cycles significantly enhance material and process optimization.

As multiple macro scale directed energy deposition (DED) processes begin to be industrially adopted for large scale component manufacture, it is imperative that interface strategies between the processes are fully understood. The present work investigates the asynchronous deposition of a wire component (DED-arc), followed by a powder-based deposition (DED-LP) with varying surface treatments which were evaluated for flatness, porosity, hardness, and Charpy impact energy. The self-regulation effect of DED-LP was fully realized with up to 55% reduction in surface variation relative to the DED-arc surface. Contrarily, as surface contaminants were not removed between each process, the resultant DED-LP porosity was significantly reduced from 99.5% to 92.4%. Albeit the reduction in density did not negatively impact the impact toughness as evidenced by a low correlation coefficient of −0.46. As such, the overall manufacturing costs and application space must be considered for selection of the different interface strategies presented in the current work.

Metal additive manufacturing has been an area of significant growth over the past decade resulting in the need to rapidly optimize additive manufacturing processes and materials so they may be qualified for industrial applications. The additive manufacturing development pipeline currently relies on Edisonian trial-and-error methodologies that come at a high expense and delay potential game-changing advancements. High-throughput testing in conjunction with machine learning can upset this current paradigm by decreasing the time and cost associated with obtaining experimental data and by creating methods to derive the greatest value from that experimental data. This study demonstrates how Small Punch Test, a high-throughput mechanical testing method, and a machine learning framework ideally suited for small datasets, namely Gaussian Process Regression, can be applied to a set of seven additive manufactured Inconel 625 samples to extract useful Process-Structure-Property linkages. Models are built with and without the inclusion of microstructure information, namely δ phase precipitates, so we may assess the value of this information that accounts for a significant portion of the data collection expenses.

Cracking during directed energy deposition limits the processability of components fabricated from high γ′ Ni-based superalloys and demands prediction tools that are both accurate and transparent while computationally efficient. This work develops a lightweight, data-driven framework that correlates in-situ infrared (IR) thermal histories to crack susceptibility in IN625–IN100 graded alloy mixtures spanning compositions with varying γ′-forming precursors (Al, Ti). Thirty-three thin walls were deposited across a range of compositions and process parameters, generating diverse thermal histories for analysis. The pipeline comprises four modules: (i) extraction and alignment of pixel-level IR thermal histories (9 × 27 grid) from identical locations of each deposit, (ii) PCA-based compression of 891 layer-level profiles into low-dimensional thermal-history descriptors (first ten PCs explain > 90% variance), (iii) crack-susceptibility classification using composition/process inputs with and without PC scores (CP-P, CPS-P, and CS-P), and (iv) crack-probability mapping over the composition–parameter space. Using standardized inputs, the best-performing configuration (composition + process + PC scores) with a Gaussian Process classifier (ARDSE kernel) achieved accuracy = 0.96 (F1 = 0.92; recall = 0.92), while composition + PC scores performed comparably, indicating that thermal histories largely subsume nominal process metadata. Feature-relevance analyses (Random-Forest importances and ARDSE per-feature length-scales) consistently ranked low-order PC scores and composition as most influential. The resulting maps reveal sharp susceptibility transitions near ~ 87.5 wt% IN100 under no-dwell and strong mitigation with a 10 s dwell, highlighting the utility of compact thermal descriptors for process planning and in-situ quality assurance in metal additive manufacturing.

The present study examines the effect of varying laser incidence angles on textural, microstructural, and geometric characteristics of directed energy deposition (DED) processed materials, providing a more comprehensive outlook on participating laser-matter interaction phenomena and ultimately devise strategies to ameliorate print performance. In this study, single-layer, single-/multi-track specimens were processed to examine the effect of non-orthogonal angular configurations on bead morphology, microstructure, phase composition and textural representation of DED-processed 316L stainless steel materials. It was observed that bead size decreased at increasing lead and lean angles. Asymmetry in the distribution of the bead morphology as a function of lead angle indicates better catchment for acute lead angle configurations over obtuse configurations. No significant differences in phase composition, texture, and microstructure were observed in moderate off-axis configurations. When penetration depth for the deposits was below 20 µm, columnar structures dominated the microstructure of the deposited material. At deeper penetration depths, columnar and equiaxed structures were observed at the bead-substrate interface and center of the bead, respectively. Compared to powder-blown DED, wire-DED dilution profiles were found to be asymmetric in both orthogonal and non-orthogonal wire DED samples.