Due to its advantages of high customization and rapid production, metal laser melting manufacturing (MAM) has been widely applied in the medical industry, manufacturing, aerospace and boutique industries in recent years. However, defects during the selective laser melting (SLM) manufacturing process can result from thermal stress or hardware failure during the selective laser melting (SLM) manufacturing process. To improve the product’s quality, the use of defect detection during manufacturing is necessary. This study uses the process images recorded by powder bed fusion equipment to develop a detection method, which is based on the convolutional neural network. This uses three powder-spreading defect types: powder uneven, powder uncovered and recoater scratches. This study uses a two-stage convolutional neural network (CNN) model to finish the detection and segmentation of defects. The first stage uses the EfficientNet B7 to classify the images with/without defects, and then to locate the defects by evaluating three different instance segmentation networks in second stage. Experimental results show that the accuracy and Dice measurement of Mask-R-CNN network with ResNet 152 backbone can reach 0.9272 and 0.9438. The computational time of an image only takes approximately 0.2197 sec. The used CNN model meets the requirements of the early detected defects, regarding the SLM manufacturing process.

This article aims to implement an axial flux variable reluctance (VR) resolver design with a three-dimensional unequal air gap rotor via the newly developed magnetic metal additive manufacturing method, also known as Selective Laser Melting (SLM). Under the same eccentricity, the proposed axial flux VR possesses a smaller sensing angle error, having an improved eccentric fault tolerance higher than that of the radial type. Consequently, the proposed axial flux VR can greatly reduce the process precision requirement and benefit mass production. In this work, finite element analysis was utilized to simulate and verify the resolver. SLM technology was combined with oxygen control technology to reduce the eddy current loss of the resolver, which can quickly and accurately fabricate the three-dimensional parts of the resolver stator and rotor without mold-making. Finally, the experimental results with the axial flux VR resolver prototype are presented to verify the designed performance and compared with the commercial radial flux variable reluctance resolver.

Photo-assisted one-step electrodeposition has been applied to help in forming smooth and dense CuInSe2 films. The difference in surface morphology and crystalline quality between CuInSe2 films with various photo-assistance has been investigated. In the photo-assisted electrodeposition process, the many kinds of lamps providing maximum light intensity at about 380 to 620 nm were used as light source to be irradiated onto the surface of Mo-coated soda-lime glass substrates. The results suggested effects of photo-assistance including activating surface diffusion and growing high-crystalline quality films with reduced defects during electrodeposition.

Stainless steel grade 430 is a type of soft magnetic electromagnetic material with rapid magnetization and demagnetization properties. Considering the delay phenomenon during operation, this study selected 430 stainless steel as the material and explored various metallurgical methods such as magnetic annealing and the addition of Mo as well as increasing the Si content to investigate the microstructure, mechanical behavior, and magnetic properties of each material, aiming to improve the magnetic properties of 430 stainless steel. Experimental results showed that the four electromagnetic steel materials (430F, 430F-MA, 434, and KM31) had equiaxed grain matrix structures, and excellent tensile and elongation properties were observed for each specimen. Additionally, the magnetic properties of the 430F specimen were similar under the DC and AC-10 Hz conditions. According to the hysteresis curves under different AC frequencies (10, 100, 1000 Hz), both magnetic annealing and the addition of Mo could reduce the Bm, Br, and Hc values of the raw 430F material. Increasing the Si content resulted in a decrease in Hc values and an increase in Bm and Br values.