When sapphire crystal is prepared with Kyropoulos method, the necking-down growth process is a key stage. Sapphire growth defect is a big problem in this stage. However, diagnosing growth defects is subject to the interference of workers subjectivity and accuracy always goes down. To address the problem, a novel defect diagnosis method is proposed for necking-down growth process in this paper. Industrial CCD sensors replace eyes of skilled workers to observe in this method. A new Defect-Diagnosing Siamese network (DDSN) is used in this method. We use Siamese architecture to learn similarity through pairs of images. We use the deep separable convolution (DSC) into the DDSN to optimize running speed and model size. In experiment, dataset is acquired by industrial CCD sensors in the necking-down growth process. The accuracy of defect diagnosis can reach up to 94.5%. The method significantly improves the traditional way.@en

The seeding technique is critical to the quality of the sapphire single crystal. The core of the seeding technique is the identification of seeding state. The MIVD method is proposed in the paper to detect the optimal seeding state. Compared with the OCS method, the MIVD method detects the characteristics of spoke pattern before a single point is formed on melt surface. Based on the similarity and periodicity of the melt motion, the optimal seeding state is detected by Fréchet distance. In the experiment, the MIVD method was compared with the OCS method and the artificial seeding method in terms of seeding efficiency and crystal quality. The MIVD method improves the quality of the sapphire crystal, at same time, it ensures seeding efficiency. The MIVD method is more suitable for practical production.@en