300 M ultra-high-strength steel (UHSS) is widely used to produce landing gear components for aircraft. The conventional manufacturing route for these components involves extensive machining and significant material wastage. Here, the application of wire-based gas metal arc additive manufacturing to produce 300 M UHSS parts was investigated. In particular, the influence of torch shielding atmosphere on the process stability and material performance of 300 M UHSS was investigated. The shielding gases used for comparison are pure Ar, Ar with 2.5% CO₂, Ar with 8% CO₂, Ar with 20% CO₂, and Ar with 2% CO₂ and 38% He. It was found that the arc length decreased, the transfer mode changed from spray to droplet mode, and spattering became more severe as the CO₂ proportion increased. Additionally, replacing Ar with He led to a broader arc core, and a slightly shorter arc length and maintained a spray transfer, which decreased spatter. The wall surface roughness followed the trend in spatter, becoming worse with the increasing CO₂ proportion, and better with He addition. Adding CO₂ and He in pure Ar significantly increased the bead and wall width. The microstructure and mechanical properties exhibited a strong location dependence in the as-built state, with fresh martensite and higher strength in the top region, and tempered martensite and better ductility in the reheated bulk. Generally, torch shielding gas composition appeared to have no significant effect on the microstructure evolution. This study provides a reference for the subsequent application of gas metal arc additive manufacturing to aircraft landing gear mass production to achieve a high deposition rate and process stability simultaneously.

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.