Design on the Winter Jujubes Harvesting and Sorting Device

Surface Defect Detection System for Carrot Combine Harvest Based on Multi-Stage Knowledge Distillation

Carrots are a type of vegetable with high nutrition. Before entering the market, the surface defect detection and sorting of carrots can greatly improve food safety and quality. To detect defects on the surfaces of carrots during combine harvest stage, this study proposed an improved knowledge distillation network structure that took yolo-v5s as the teacher network and a lightweight network that replaced the backbone network with mobilenetv2 and completed channel pruning as a student network (mobile-slimv5s). To make the improved student network adapt to the image blur caused by the vibration of the carrot combine harvester, we put the ordinary dataset Dataset (T) and dataset Dataset (S), which contains motion blurring treatment, into the teacher network and the improved lightweight network, respectively, for learning. By connecting multi-stage features of the teacher network, knowledge distillation was carried out, and different weight values were set for each feature to realize that the multi-stage features of the teacher network guide the single-layer output of the student network. Finally, the optimal lightweight network mobile-slimv5s was established, with a network model size of 5.37 MB. The experimental results show that when the learning rate is set to 0.0001, the batch size is set to 64, and the dropout is set to 0.65, the model accuracy of mobile-slimv5s is 90.7%, which is significantly higher than other algorithms. It can synchronously realize carrot harvesting and surface defect detection. This study laid a theoretical foundation for applying knowledge distillation structures to the simultaneous operations of crop combine harvesting and surface defect detection in a field environment. This study effectively improves the accuracy of crop sorting in the field and contributes to the development of smart agriculture.

Coating Process Parameters and Structural Properties of the Tubular Electrodes of Fuel Cells Based on a Self-Made Coating Device

The electrode is one of the most important components of tubular direct methanol fuel cells (DMFC), and the coating process directly determines its performance. In the present research, a tubular electrode coating device was designed based on planetary gear structures, and the influence of the coating process parameters on the electrode structure’s performance was studied. The experimental results show that: the coating layer on the electrode surface prepared by the self-made device is uniform and dense, and the coating surface quality is better than a manual coating. The best coating environment temperature is 30–40 °C, and the coating spindle speed is 6.67 r/min. Under the condition in which Nafion 117 is used as the proton exchange membrane, the fuel cell is placed in 1 mol/L H2SO4 + 0.5 mol/L CH3OH electrolyte, and high-purity oxygen is fed at a rate of 100 mL/min, the power density of the electrode coated by the self-made device can reach 20.50 mW/cm2, which is about 2.4 times that of the electrode coated manually.