RESUMEN
In this paper, a microchannel heat sink model was proposed to realize single- and double- layer flow through built-in ribs. The finite element volume method was used to analyze the influence of the length, thickness and angle of the inner rib on the flow and heat transfer characteristics of the microchannel heat sink. The pressure drop, temperature field, flow field, and thermal characteristics are given. The numerical simulation results show that the rectangular rib plate makes the fluid in the microchannel heat sink flow alternately in the upper and lower layers, which can effectively enhance heat transfer. However, with the increase in rib length, the comprehensive evaluation factor decreases. The change of the angle of the rectangular rib plate has little influence on the Nusselt number. The change rate of the comprehensive evaluation factor of the thickness of the rectangular rib plate is the largest. When the Reynolds number is 1724, the comprehensive evaluation factor of Case 9 is 4.7% higher than that of Case 2. According to the parameter study of the built-in rib plate, the optimal parameter combination is given, in which the angle is 0°, the length is 7.5 mm, and the thickness is 0.2-0.3 mm.
RESUMEN
Aiming at the problems of low detection accuracy and slow speed caused by the complex background of tea sprouts and the small target size, this paper proposes a tea bud detection algorithm integrating GhostNet and YOLOv5. To reduce parameters, the GhostNet module is specially introduced to shorten the detection speed. A coordinated attention mechanism is then added to the backbone layer to enhance the feature extraction ability of the model. A bi-directional feature pyramid network (BiFPN) is used in the neck layer of feature fusion to increase the fusion between shallow and deep networks to improve the detection accuracy of small objects. Efficient intersection over union (EIOU) is used as a localization loss to improve the detection accuracy in the end. The experimental results show that the precision of GhostNet-YOLOv5 is 76.31%, which is 1.31, 4.83, and 3.59% higher than that of Faster RCNN, YOLOv5 and YOLOv5-Lite respectively. By comparing the actual detection effects of GhostNet-YOLOv5 and YOLOv5 algorithm on buds in different quantities, different shooting angles, and different illumination angles, and taking F1 score as the evaluation value, the results show that GhostNet-YOLOv5 is 7.84, 2.88, and 3.81% higher than YOLOv5 algorithm in these three different environments.
