Search for: All records

Ti6Al4V has been recognized as an attractive material, due to its combination of low density and favorable mechanical properties. However, its insufficient oxidation resistance has limited the high-temperature application. In this work, an AlCoCrFeNiTi0.5 high-entropy alloy (HEA) coating was fabricated on a Ti6Al4V substrate using laser metal deposition (LMD). The microstructure and isothermal oxidation behaviors were investigated. The microstructure of as-deposited HEA exhibited a Fe, Cr-rich A2 phase and an Al, Ni, Ti-enriched B2 phase. Its hardness was approximately 2.1 times higher than that of the substrate. The oxidation testing at 700 °C and 800 °C suggested that the HEA coating has better oxidation resistance than the Ti6Al4V substrate. The oxide scales of the Ti6Al4V substrate were mainly composed of TiO2, while continuous Al2O3 and Cr2O3 were formed in the HEA coatings and could be attributed to oxidation resistance improvement. This work provides an approach to mitigate the oxidation resistance of Ti6Al4V and explore the applicability of the HEA in a high-temperature environment. 

Metal additive manufacturing (AM) is gaining increasing attention from academia and industry due to its unique advantages compared to the traditional manufacturing process. Parts quality inspection is playing a crucial role in the AM industry, which can be adopted for product improvement. However, the traditional inspection process has relied on manual recognition, which could suffer from low efficiency and potential bias. This study presented a convolutional neural network (CNN) approach toward robust AM quality inspection, such as good quality, crack, gas porosity, and lack of fusion. To obtain the appropriate model, experiments were performed on a series of architectures. Moreover, data augmentation was adopted to deal with data scarcity. L2 regularization (weight decay) and dropout were applied to avoid overfitting. The impact of each strategy was evaluated. The final CNN model achieved an accuracy of 92.1%, and it took 8.01 milliseconds to recognize one image. The CNN model presented here can help in automatic defect recognition in the AM industry.