Metallographic image segmentation of GCr15 bearing steel based on CGAN

A novel deep learning segmentation method based on Conditional Generative Adversarial Nets (CGAN) is proposed, being U-GAN in this paper to overtake shortcomings of the metallographic images of GCr15 bearing steel, such as multi-noise, low contrast and difficult to segment. The results of experiment indicate that the proposed model is the most accurate comparing with the digital image processing methods and deep learning methods on carbide particle segmentation. The average Dice’s coefficient of similarity measure function is 0.9158, which is the state-of-the-art performance on dataset.

An analytical model for force prediction in micromilling silicon carbide particle–reinforced aluminum matrix composites

In micromilling the silicon carbide particle–reinforced aluminum matrix composites, cutting forces can provide a better insight of the cutting mechanism. In this article, an analytical model for force prediction in micromilling composites is developed considering the size effect of the matrix. In modeling, for the matrix, the cutting area is divided into shearing area and plowing area and the removal forces are established considering chip formation and edge forces; for the particle, the removal forces are established based on Griffith fracture theory. The model is verified by micromilling experiments. The influences of the process parameters (milling width, milling depth, and feed per tooth) on the milling force were studied. It shows that the maximum milling force increased with the increase in the feed per tooth and the milling depth and increases first and then stabilizes with the increase in milling width; the average milling force increases with the increase in the three parameters. In addition, the contribution of the particle fracture force is analyzed, and it is found that the contribution of the particle fracture force is affected by the feed per tooth, which basically accounts for about 23% of the maximum milling force and accounts for 23%–30% of the average milling force.