Internal flow behaviour during melt-pool-based metal manufacturing remains unclear and hinders progression to process optimisation. In this contribution, we present direct time-resolved imaging of melt pool flow dynamics from a high-energy synchrotron radiation experiment. We track internal flow streams during arc welding of steel and measure instantaneous flow velocities ranging from 0.1 m s⁻¹ to 0.5 m s⁻¹. When the temperature-dependent surface tension coefficient is negative, bulk turbulence is the main flow mechanism and the critical velocity for surface turbulence is below the limits identified in previous theoretical studies. When the alloy exhibits a positive temperature-dependent surface tension coefficient, surface turbulence occurs and derisory oxides can be entrapped within the subsequent solid as result of higher flow velocities. The widely used arc welding and the emerging arc additive manufacturing routes can be optimised by controlling internal melt flow through adjusting surface active elements.

Machine learning has been widely exploited in developing new materials. However, challenges still exist: small dataset is common for most tasks; new datasets, special descriptors and specific models need to be built from scratch when facing a new task; knowledge cannot be readily transferred between independent models. In this paper we propose a general and transferable deep learning (GTDL) framework for predicting phase formation in materials. The proposed GTDL framework maps raw data to pseudo-images with some special 2-D structure, e.g., periodic table, automatically extracts features and gains knowledge through convolutional neural network, and then transfers knowledge by sharing features extractors between models. Application of the GTDL framework in case studies on glass-forming ability and high-entropy alloys show that the GTDL framework for glass-forming ability outperformed previous models and can correctly predicted the newly reported amorphous alloy systems; for high-entropy alloys the GTDL framework can discriminate five types phases (BCC, FCC, HCP, amorphous, mixture) with accuracy and recall above 94% in fivefold cross-validation. In addition, periodic table knowledge embedded in data representations and knowledge shared between models is beneficial for tasks with small dataset. This method can be easily applied to new materials development with small dataset by reusing well-trained models for related materials.

Vaporization and its associated surface defect formation have become one of the most important challenges in manufacturing single-crystal components. During the kinetic-influenced casting and solution heat treatment of Ni-base superalloys, elements undergo processes of vaporization and deposition causing unpredictable defects. To quantitatively examine the vaporization phenomenon, partial vapor pressures of Ni, Al and Cr in Ni-base alloys were measured in the γ phase over the temperature range of 1473 K to 1650 K using Knudsen effusion mass spectrometry. Experimental results showed that the partial pressure of Al is about two orders of magnitude lower than that of Ni and five times lower than that of Cr, revealing that the vaporization of Al is almost negligible compared with those of Ni and Cr at solution heat treatment temperatures. Variation of partial pressures during homogenization of the as-cast Ni-base alloys was measured in long-term isothermal experiments at 1573 K. It was found that Cr vapor pressure decreases by a factor of two in the first 20 hours whereas the Ni and Al remain nearly constant.

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.