Defect detection is an important part of the manufacturing process of mechanical products. In order to detect the appearance defects quickly and accurately, a method of defect detection for the metal base of TO-can packaged laser diode (metal TO-base) based on the improved You Only Look Once (YOLO) algorithm named YOLO-SO is proposed in this study. Firstly, convolutional block attention mechanism (CBAM) module was added to the convolutional layer of the backbone network. Then, a random-paste-mosaic (RPM) small object data augmentation module was proposed on the basis of Mosaic algorithm in YOLO-V5. Finally, the K-means++ clustering algorithm was applied to reduce the sensitivity to the initial clustering center, making the positioning more accurate and reducing the network loss. The proposed YOLO-SO model was compared with other object detection algorithms such as YOLO-V3, YOLO-V4, and Faster R-CNN. Experimental results demonstrated that the YOLO-SO model reaches 84.0% mAP, 5.5% higher than the original YOLO-V5 algorithm. Moreover, the YOLO-SO model had clear advantages in terms of the smallest weight size and detection speed of 25 FPS. These advantages make the YOLO-SO model more suitable for the real-time detection of metal TO-base appearance defects.

A group of Ti-10Nb-xSn alloys with Sn content varying from 0 to 8 wt.% were fabricated from blended elemental powders using powder metallurgy processing. The effects of the Sn content on the microstructure, mechanical performance, and tribological behavior were investigated. The results showed that Ti-10Nb-xSn alloys with high density could be fabricated using powder metallurgy. When the Sn content increased from 0 to 8 wt.%, the density increased slightly from 96.76% to 98.35%. The alloys exhibited a typical α + β microstructure. As the Sn content increased, the dendritic β grains gradually converted into a laminar α + β structure, accompanied by intergranular α and a small number of micropores. The elastic modulus of the alloys decreased with increasing Sn content but not significantly (73–76 GPa). The addition of Sn initially reduced the Vickers hardness, compressive strength, and maximum strain. When Sn was added up to 5 wt.%, these properties tended to increase slowly in the ranges 310–390 HV, 1100–1370 MPa, and 15.44–23.72%, respectively. With increasing Sn content, the friction coefficient of the alloys increased from 0.41 to 0.50. Without Sn, Ti-10Nb was dominated by abrasive wear. The wear mechanism of Ti-10Nb-3Sn and Ti-10Nb-5Sn changed to adhesive wear together with abrasive wear with increasing Sn content, while Ti-10Nb-8Sn predominately exhibited adhesive wear. Compared with Ti-10Nb alloy, an appropriate amount of Sn could achieve a lower elastic modulus, while Vickers hardness and compressive strengths were little changed. Moreover, it had a minor influence on the friction coefficient. The good mechanical performance and wear resistance make the powder-metallurgy-fabricated Ti-10Nb-xSn alloys attractive candidates for biomedical materials.