Since Ti alloys are difficult-to-machine materials, the application of powder metallurgy such as metal injection molding (MIM) is desired. Although injection molded Ti-6Al-4V alloys showed sufficient tensile properties, their fatigue strength was significantly lower than that of the wrought material. In this study, various approaches were applied to improve the fatigue strength through MIM processing parameters such as raw material powders, addition of 4th and 5th elements such as Mo and B, sintering techniques, and heat treatment conditions. Eventually, we obtained the fatigue strength as same as wrought materials. We also investigated the factors, which control the fatigue strength of injection molded Ti alloys. Regarding the relationship between the pore size and grain size on the fatigue strength, it was found that the crack initiation occurred from the largest pore when the ratio of the pore size to the grain size was large, and simultaneously the fatigue strength was significantly decreased.
The mechanical properties, such as Vickers hardness and crack length, of various WC-FeAl hard materials were predicted using deep learning via a convolutional neural network (CNN) trained on microstructures. The accuracy of the predictions was verified using gradient-weighted class activation mapping (Grad-CAM), which is a kind of image visualization technology that identifies important structural features for AI classification based on mechanical properties. The accuracies, expressed as coefficients of determination for unknown samples (test data), were found to be 0.89 and 0.75 at most for Vickers hardness and crack length, respectively. The AI correctly recognized microstructural quality and determined classes that represented differences in mechanical properties as evidenced by the feature maps obtained, indicating that CNN prediction was a powerful tool for analyzing WC-FeAl hard materials.