Process control and quality assurance of wire + arc additive manufacturing (WAAM) and automated welding rely heavily on in-process monitoring videos to quantify variables such as melt pool geometry, location and size of droplet transfer, arc characteristics, etc. To enable feedback control based upon this information, an automatic and robust segmentation method for monitoring of videos and images is required. However, video segmentation in WAAM and welding is challenging due to constantly fluctuating arc brightness, which varies with deposition and welding configurations. Additionally, conventional computer vision algorithms based on greyscale value and gradient lack flexibility and robustness in this scenario. Deep learning offers a promising approach to WAAM video segmentation; however, the prohibitive time and cost associated with creating a well-labelled, suitably sized dataset have hindered its widespread adoption. The emergence of large computer vision models, however, has provided new solutions. In this study a semi-automatic annotation tool for WAAM videos was developed based upon the computer vision foundation model SAM and the video object tracking model XMem. The tool can enable annotation of the video frames hundreds of times faster than traditional manual annotation methods, thus making it possible to achieve rapid quantitative analysis of WAAM and welding videos with minimal user intervention. To demonstrate the effectiveness of the tool, three cases are demonstrated: online wire position closed-loop control, droplet transfer behaviour analysis, and assembling a dataset for dedicated deep learning segmentation models. This work provides a broader perspective on how to exploit large models in WAAM and weld deposits.

Wire-based directed energy deposition (WDED) of Invar alloys is prone to cracking due to high thermal stresses and microstructural anisotropy. In this study, in-process machine hammer peening (MHP) was integrated into WDED to mitigate cracking and control the microstructure of Invar alloy. The as-deposited material exhibited millimetre-scale columnar grains with strong build-directional alignment and severe solidification cracking along grain boundaries, indicating a dominant role of deposition-induced thermal stresses. Interlayer MHP promoted a transition from epitaxial growth to heterogeneous nucleation, producing a refined and more equiaxed grain structure with improved tolerance to thermal straining. Deformation-related FCC texture components and an increased fraction of low-energy Σ3 coincidence site lattice boundaries were observed in the MHP-treated material, contributing to enhanced grain-boundary-mediated plasticity and cracking resistance. Mechanical characterisation further revealed increased hardness and elastic modulus achieved by interlayer MHP, together with progressive build-height-dependent strengthening. In general, in-process MHP offers an effective and cost-efficient thermo-mechanical strategy for crack mitigation and is expected to contribute to microstructure-property optimisation in additively manufactured Invar alloys.