Refractory high-entropy alloys (RHEAs) typically exhibit a body-centered cubic (BCC) structure with excellent strength but poor ductility, which limits their practical applications. In this study, we designed BCC/FCC dual-phase RHEAs through phase diagram calculations and neural network modeling. The analysis of the binary phase formation relationships among alloying elements enabled the preliminary screening and inclusion of 13 liquid-phase-separated BCC/FCC dual-phase RHEAs in the training dataset for the machine learning model. Two strategic binary classifications of this dataset were conducted on HEAs to identify their “multiphase” and “solid solution” structures. Consequently, two neural network models were trained, achieving accuracies of 89.52% and 89.83%, respectively. These models predicted 51 BCC/FCC dual-phase RHEAs among 504 novel RHEAs, representing the first successful compositional design of metastable BCC/FCC dual-phase RHEAs. The arc-melted alloys exhibited refined dendritic structure. This study provides valuable insights for the tailored design of novel multi-phase RHEAs to achieve specific targeted properties.

Because the laser powder bed fusion process is generally completed in a confined space and in a very short time, it is difficult to study material oxidation during this process using traditional methods. To address this knowledge gap, in this work, we used molecular dynamics (MDs) based on a reaction force field (ReaxFF) to clarify the atomic-level interaction mechanism between metal atoms and oxygen molecules during laser powder bed fusion. The ReaxFF potential energy model has variable charges that can dynamically handle charge changes between atoms and the breaking and formation of chemical bonds that occur during oxidation reactions. We investigated the effects of laser power, scanning speed, region position, and oxygen concentration on powder oxidation. The results show that the laser power and scanning speed affected the oxidation degree by changing the energy input density, and the oxidation degree increased with the energy input density. Different forms of oxidation occurred near the melt channel due to the existence of a temperature gradient, and the degree of oxidation increased with the temperature. Atoms in the metal powder model underwent selective oxidation, which was related to the potential energy of their atomic position. A larger potential energy made it easier for iron atoms to overcome the energy barrier during the initial stage of oxidation, making them easier to oxidize.

In this research, the Eulerian method was used to simulate the relationship between the preheating temperature and the critical velocity. The size and shape of the void (no-material-existence zone) and the thickness of the model were investigated. Various preheating temperatures were used throughout the whole model. The critical velocity was determined with jet's appearance. The simulation results demonstrated the void size and shape influenced the results, although the thickness did not. The critical velocity decreased as the preheating temperature rose. The relationship between critical velocity and minimum preheating temperature when the jet formed appeared to be a linear relationship. The experimental results confirmed the simulation results. The linear equation could be used to predict the preheating temperature at a certain velocity below the critical value. The corresponding steady maximum PEEQ (equivalent plastic strain) value at the minimum preheating temperature could be divided into a stable type and a fluctuation type.