Additive Friction-Stir Deposition is a form of solid-state additive manufacturing that has shown potential for producing large-scale components. Often, AFSD utilized a graphite lubricant during the manufacture of components from 7xxx-series aluminum alloys. In this work, AFSD was utilized without lubricant to print high-strength AA7075 aluminum alloy, which will reduce the risk of contamination to the feed material, ensuring that the deposited material retains mechanical properties akin to wrought or forged AA7075 aluminum alloy. The fabricated material underwent mechanical testing and characterization to better understand the mechanical properties and microstructure associated with AFSD-printed AA7075 alloy when graphite is removed. Optical imagery showed that the as-deposited material exhibited a fully dense and crack-free build. The microstructure was found to be heavily refined and equiaxed, which is consistent with most AFSD results, although different grain orientations were observed in each plane. The mechanical properties of the as-deposited material were not homogeneous, and mechanical properties were found to vary with height. T6 heat treatment resulted in significant grain growth, along with grain elongation. Remarkably, the heat treatment significantly minimized the anisotropic mechanical properties of the samples, enhancing them to reach 95% of the performance typically seen in wrought AA7075-T6 alloy, with yield strength and ultimate tensile strength averaging 480 MPa and 533 MPa respectively, and elongation averaging 9%. Post heat treatment, hardness also exhibited a significant increase, even for thicker samples, with average values of at least 169.9 HV.

Electron beam powder bed fusion (E-PBF) requires reliable in situ process monitoring, and electron emission signals offer a promising avenue for this purpose. Most prior studies have relied on dedicated beam scans performed before or after melting, leaving open the question of whether the signal acquired during the melt itself can directly indicate geometric and topographical features of the fabricated part. In this work, the in-operando electron emission signal was recorded during spot-melting of a Ti-6Al-4V spur gear and evaluated for its ability to reconstruct geometric features and surface topography, with optical microscopy and profilometry serving as ground truth. A melt-pool dilation correction was applied to compensate for the geometric expansion of individual melt spots. After correction, the in-operando reconstruction reached agreement deviation values below 2.2% across the tooth tips, tooth bases, and chord widths, which are comparable to or better than those obtained from post-melt ELO imaging. Comparison with profilometer height profiles confirmed strong correlation with surface topography (Pearson 0.67–0.87 across all four profiles, p < 0.05 for all), indicating that the signal captures meaningful surface-topography variation in addition to geometric boundaries. The results demonstrate that the in-operando electron emission signal shows strong potential for in situ geometric and topographical assessment of complex parts in E-PBF, supporting its future integration into closed-loop process monitoring.

Reliable pore detection in in situ monitoring is essential for quality control in additive manufacturing, particularly in safety-critical applications. However, existing automated approaches often struggle with low-quality images, computational inefficiency, and the lack of reliable uncertainty estimates to identify the pores accurately. To address these limitations, this paper proposes U-SAMNet, an Uncertainty-Aware Self-Attention Multi-Task Network. The model jointly performs pore segmentation, image-level classification, and denoising on in situ monitoring images, while deriving epistemic uncertainty via Monte Carlo dropout variance to dynamically suppress unreliable attention features. This study uses electron-optical (ELO) images from the E-PBF process. A novel Uncertainty Guidance Attention (UGA) block is introduced. It suppresses channel attention weights using inverted uncertainty estimates. Unlike prior methods that modulate classification weights, U-SAMNet operates on pixel-wise feature maps. The model has only 1.69 M parameters. A single forward pass takes 17.46 ms per image, while uncertainty estimation is performed through multiple Monte Carlo dropout passes. The model was evaluated on real E-PBF images and achieved 99.42% pixel accuracy, 85.31% F1-score, and 74.38% IoU on a held-out test set of 43 real images. It also generalizes to other industrial defect detection benchmarks, reaching 85.09% F1-score on DAGM 2007 and 82.32% on DeepCrack. GAN-synthesized training data improves the F1-score by 21.34 percentage points over rotation augmentation alone. Ablation studies confirm that each component contributes meaningfully to the final performance.