Search

Surfactants are always added to coating formulations to ensure good adhesion of edible coatings to a product’s surface and to maintain freshness. In this study, the effects of the mix surfactants Tween 20 and Span 80 with different hydrophile–lipophile balance (HLB) values on the film-forming ability, wettability, and preservation capacity of blueberry sodium alginate coating were investigated. The results indicated that Tween 20 obviously ensured favorable wettability and improved the uniformity and mechanical properties of the resulting film. While the addition of Span 80 reduced the mean particle size of the coating, enhanced the water resistance of the film, and helped to reduce blueberry weight loss. A sodium alginate coating with low viscosity and medium HLB could better inhibit the galactose, sucrose, and linoleic acid metabolism of blueberries, reduce the consumption of phenols, promote the accumulation of flavonoids, and thus display superior coating performance. In summary, sodium alginate coating with medium HLB had comprehensive advantages in film-forming ability and wettability and was conducive to the fresh-keeping role.

Surface defect detection for printed circuit board (PCB) is indispensable for managing PCB production quality. However, automatic detection of PCB surface defects is still a challenging task because, even within the same category of surface defect, defects present great differences in morphology and pattern. Although many computer vision-based detectors have been established to handle these problems, current detectors struggle to achieve high detection accuracy, fast detection speed and low memory consumption simultaneously. To address those issues, we propose a cost-effective deep learning (DL)-based detector based on the cutting-edge YOLOv4 to detect PCB surface defect quickly and efficiently. The YOLOv4 is improved upon with respect to its backbone network and the activation function in its neck/prediction network. The improved YOLOv4 is evaluated with a customized dataset, collected from a PCB factory. The experimental results show that the improved detector achieved a high performance, scoring 98.64% on mean average precision (mAP) at 56.98 frames per second (FPS), outperforming the other compared SOTA detectors. Furthermore, the improved YOLOv4 reduced the parameter space of YOLOv4 from 63.96 M to 39.59 M and the number of multiply-accumulate operations (Madds) from 59.75 G to 26.15 G.