Grain size is one of the most important parameters for metallographic microstructure analysis, which can partly determine the material performance. The measurement of grain size is based on accurate image segmentation methods, which include traditional image processing methods and emerging machine-learning-based methods. Unfortunately, traditional image processing methods can hardly segment grains correctly from metallographic images with low contrast and blurry boundaries. Moreover, the proposed machine-learning-based methods need a large dataset to train the model and can hardly deal with the segmentation challenge of complex images with fuzzy boundaries and complex structure. In this paper, an improved U-Net model is proposed to automatically accomplish image segmentation of complex metallographic images with only a small training set. The experiments on metallographic images show the significant advantage of the method, especially for the metallographic images with low contrast, a fuzzy boundary and complex structure. Compared with other deep learning methods, the improved U-Net scored higher in ACC, MIoU, Precision, and F1 indexes, among which ACC was 0.97, MIoU was 0.752, Precision was 0.98, and F1 was 0.96. The grain size was calculated based on the segmentation according to the American Society for Testing Material (ASTM) standards, producing a satisfactory result.

This study investigated the effects of microwave sintering on the microstructures and properties of copper-rGO composites. Graphene oxide was coated onto copper particles by wet ball milling, and copper-rGO composites were formed upon microwave sintering in an argon atmosphere. Scanning electron microscopy was then used to observe the mixing in the ball-milled composite powder, and the morphology of the bulk composite after microwave sintering. Raman spectra revealed how graphene oxide changed with ball milling and with microwave sintering. The microhardness, electrical conductivity, and thermal conductivity of the composite were also measured. The results showed that graphene oxide and copper particles were well combined and uniformly distributed after wet ball milling. The overall microhardness of microwave-sintered samples was 81.1 HV, which was 14.2% greater than that of pure copper (71 HV). After microwave sintering, the microhardness of the samples in areas showing copper oxide precipitates with eutectic structures was 89.5 HV, whereas the microhardness of the precipitate-free areas was 70.6 HV. The electrical conductivity of the samples was 87.10 IACS%, and their thermal conductivity was 391.62 W·m⁻¹·K⁻¹.

Ni₃Al-based single crystal alloy IC6SX was prepared by seed crystal method. The effect of different stress conditions on creep behavior of this alloy at 980°C was investigated. The results showed that the creep life of this alloy at 980°C decreased significantly with the increase of stress. When the stress increased from 180 MPa to 230 MPa, the creep life dropped from 245.5 h to 69.3 h, and the steady-state creep rate increased slightly but not significantly. Meanwhile, the morphology of γ phase and dislocation after creep were studied. The results showed that with the increase of stress, the density of dislocations in the γ phase increased gradually, the strength of this alloy decreased gradually, so the creep life decreased significantly. The Y-NiMo phase resolved from the γ phase decreased gradually as the creep life decreased. The creep experiment of the alloy was carried out at 980°C. Due to the higher temperature, the diffusion of atoms in this alloy became faster. Deformation was not only caused by the slippage of dislocations in the crystal but also by the diffusion of atoms. Therefore, the creep mechanism of single crystal alloy IC6SX at this temperature is a mixed mechanism of dislocation glide and diffusion.

Y ₂ O ₃ is widely utilized as a coating material to prevent hydrogen permeation in alloys.