Search

The experimental and numerical simulation analysis of a TiAl alloy by laser metal deposition technology is presented in this paper. The research examines the macroscopic morphology, microstructure, and mechanical properties of samples as laser power varies. It also delves into how the temperature field and residual stress evolve under different laser powers. The results reveal that the microstructure of samples is mainly composed of α2-Ti3Al phase and a γ-TiAl phase and that the details of the microstructure are significantly affected by laser power. As laser power increases, coarse lamellar structure content increases, corresponding to a decrease in α2 phase content. The deposited layer hardness ranges from 550 HV to 600 HV, and the average deposition layer hardness decreases with increased laser power. Simulation results predict the molten pool’s size, temperature, and residual stresses. A significant increase in the molten pool size is observed when the laser power exceeds 1000 W, and the measured molten pool depths correspond closely to simulation predictions. However, significant tensile stresses are generated in the deposition layer due to high cooling rates, mainly in the x direction. Cracks are observed on the surface of the deposition layer at all laser powers.

Thermal damage to diamonds is a major limitation in laser powder bed fusion (LPBF) processing of metal matrix diamond composites. In this paper, a numerical simulation model was established to describe the thermal effect of the Diamond-CuSn10 composite on the LPBF process. The simulation results show that the temperature of the diamond presents a double-peak structure, and the double-peak temperature curve shape can be modulated by modifying the laser scanning offset and the size of the diamond powder. And it suggests that the heat of the diamond mainly comes from the transfer of the molten pool. Then, combined with the experimental phenomenon, the mechanism of diamond graphitization in the LPBF process is analyzed. It indicates that since the surface defects of the diamond inhibit the heat conduction of the diamond, the temperature accumulates on the surface, leading to the graphitization of the diamond. Finally, based on this model, the potential of Ti-coated diamonds to prevent and reduce thermal damage in the LPBF process has been extensively studied. It is found that a Ti coating with low thermal conductivity can effectively reduce diamond temperature and improve diamond graphitization resistance. This study can provide a good method and basis for the preliminary selection of LPBF process parameters and the understanding of the graphitization mechanism of diamond tools.

Image classification is widely used in industrial defect detection, medical diagnosis, social welfare, and other fields, in which privacy and security of models and data must be involved. For example, in diamond synthesis, the diamond substrate image annotation data and the defect detection model are of value for conservation. Based on ensuring inference efficiency and the security of these private data intellectual property, the 3-party secure inference based on secure multi-party computation (MPC) can be adopted. MPC allows parties to use neural networks while preserving their input privacy for collaborative computing, but it will lead to huge communication and memory consumption. This paper propose PriRepVGG, a lightweight privacy-preserving image-based defect detection framework for 3-party. In this work, firstly, This work optimized the division and added an AdaptiveAvgpool layer in MPC framework FALCON; then, This work ported the inference architecture of the RegVGG network into FALCON creatively. Our work applied PriRepVGG to the secure inference of the diamond substrates defect detection under the data server, model server, and compute server settings, which can be carried out in batches with a low misjudgment rate and verify the feasibility of image-based secure inference with a lightweight network in an industrial case under MPC.