In the production of titanium alloy, the electron beam cold hearth melting (EBCHM) process is commonly used due to its effectiveness and the high quality of the end product. However, its main drawback is the significant loss of elements such as aluminum (Al) due to evaporation under the vacuum environment. Numerical coupled thermal-flow models were here developed to investigate the effects of scanning strategies on Al loss in a titanium alloy during EBCHM. The validation model was successful in comparison with previously published experimental data. The Al mass fraction results at the outlet of the water-cooled hearth were strongly influenced by changes in the applied scanning strategies. The results indicated that the Al mass fraction loss could be reduced by using the full-hearth scanning strategies.

Detecting parcels accurately and efficiently has always been a challenging task when unloading from trucks onto conveyor belts because of the diverse and complex ways in which parcels are stacked. Conventional methods struggle to quickly and accurately classify the various shapes and surface patterns of unordered parcels. In this paper, we propose a parcel-picking surface detection method based on deep learning and image processing for the efficient unloading of diverse and unordered parcels. Our goal is to develop a systematic image processing algorithm that emphasises the boundaries of parcels regardless of their shape, pattern, or layout. The core of the algorithm is the utilisation of RGB-D technology for detecting the primary boundary lines regardless of obstacles such as adhesive labels, tapes, or parcel surface patterns. For cases where detecting the boundary lines is difficult owing to narrow gaps between parcels, we propose using deep learning-based boundary line detection through the You Only Look at Coefficients (YOLACT) model. Using image segmentation techniques, the algorithm efficiently predicts boundary lines, enabling the accurate detection of irregularly sized parcels with complex surface patterns. Furthermore, even for rotated parcels, we can extract their edges through complex mathematical operations using the depth values of the specified position, enabling the detection of the wider surfaces of the rotated parcels. Finally, we validate the accuracy and real-time performance of our proposed method through various case studies, achieving mAP (50) values of 93.8% and 90.8% for randomly sized and rotationally covered boxes with diverse colours and patterns, respectively.

This study investigated the influence of circumferential welding position and process parameters on bead geometry during multi-pass orbital gas tungsten arc welding (GTAW) of SUS304 stainless-steel pipes. Three-dimensional surface profiles were measured using a laser line scanner at the top (12H, −45° to 45°) and bottom (6H, 135° to 225°) circumferential regions. The incremental bead height and width of Passes 1 and 2 were quantitatively evaluated after excluding the first and last 10% of the measured region to minimize edge effects. Under identical root-pass conditions, the average Pass 1 bead height at 6H was 9.6% greater than that at 12H, whereas the bead width was 3.3% smaller. After Pass 2, the height difference increased to 12.0%, while the width difference remained small at 2.4%. Primary current, wire feed speed, and travel speed exhibited position-dependent effects on bead formation. Primary current affected the balance between vertical buildup and lateral spreading, wire feed speed consistently influenced bead width, and travel speed strongly affected bead buildup through changes in heat input, filler deposition per unit length, and molten-pool residence time. The greater reinforcement at 6H was attributed to gravity-dependent molten-metal accumulation during successive deposition. Interpolation of the primary-current experiments predicted that approximately 173 A at 12H and 175.5 A at 6H would produce comparable Pass 2 geometries of approximately 1.62 mm in height and 6.57 mm in width. These results demonstrate that circumferential bead uniformity can be improved through position-dependent parameter adjustment rather than identical welding conditions around the pipe circumference.