Pest detection in plants is essential for ensuring high productivity. Convolutional neural networks (CNN)-based deep learning advancements recently have made it possible for researchers to increase object detection accuracy. In this study, pest detection in plants with higher accuracy is proposed by an improved YOLOv5m-based method. First, the SWin Transformer (SWinTR) and Transformer (C3TR) mechanisms are introduced into the YOLOv5m network so that they can capture more global features and can increase the receptive field. Then, in the backbone, ResSPP is considered to make the network extract more features. Furthermore, the global features of the feature map are extracted in the feature fusion phase and forwarded to the detection phase via a modification of the three output necks C3 into SWinTR. Finally, WConcat is added to the fusion feature, which increases the feature fusion capability of the network. Experimental results demonstrate that the improved YOLOv5m achieved 95.7% precision rate, 93.1% recall rate, 94.38% F₁ score, and 96.4% Mean Average Precision (mAP). Meanwhile, the proposed model is significantly better than the original YOLOv3, YOLOv4, and YOLOv5m models. The improved YOLOv5m model shows greater robustness and effectiveness in detecting pests, and it could more precisely detect different pests from the dataset.

Protecting crops from pests is a major issue in the current agricultural production system. The agricultural digital twin system, as an emerging product of modern agricultural development, can effectively achieve intelligent control of pest management systems. In response to the current problems of heavy use of pesticides in pest management and over-reliance on managers’ personal experience with pepper plants, this paper proposes a digital twin system that monitors changes in aphid populations, enabling timely and effective pest control interventions. The digital twin system is developed for pest management driven by data and model fusion. First, a digital twin framework is presented to manage insect pests in the whole process of crop growth. Then, a digital twin model is established to predict the number of pests based on the random forest algorithm optimized by the genetic algorithm; a pest control intervention based on a twin data search strategy is designed and the decision optimization of pest management is conducted. Finally, a case study is carried out to verify the feasibility of the system for the growth state of pepper and pepper pests. The experimental results show that the virtual and real interactive feedback of the pepper aphid management system is achieved. It can obtain prediction accuracy of 88.01% with the training set and prediction accuracy of 85.73% with the test set. The application of the prediction model to the decision-making objective function can improve economic efficiency by more than 20%. In addition, the proposed approach is superior to the manual regulatory method in pest management. This system prioritizes detecting population trends over precise species identification, providing a practical tool for integrated pest management (IPM).

In order to solve the problems of poor feeding environment, untimely feeding and high labor demand in poultry smart farms, the development of feeding robots is imminent, while the research on path planning algorithms is an important part of developing feeding robots. The energy consumption of the feeding robot is one of the important elements of concern in the process of path planning. In this study, the shortest path does not mean that the feeding robot consumes the least energy, because the total mass of the feeding robot keeps changing during the feeding process. It is necessary to find the most suitable path so that the feeding robot consumes the lowest amount of energy during the feeding process. A branch and bound algorithm to calculate the minimum energy consumption travel path for small-scale buckets lacking feed is proposed. The lower bound of the branch and bound on the energy consumption is obtained by the approach of preferred selection of the set of shortest edges combined with the sequence inequality, and the upper bound could be obtained based on Christofides’s Heuristic algorithm. A double-crossover operator genetic algorithm based on an upper bound on energy consumption for large-scale buckets lacking feed is proposed, and different crossover operations are performed according to the relationship between the fitness value and the upper bound of energy consumption in order to find a better path. The experiment results show that the approach proposed in this study is efficient; for small-scale buckets lacking feed, a branch and bound algorithm could calculate the minimum energy consumption path of 17 points in 300 s, and for large-scale buckets lacking feed, a double-crossover operator genetic algorithm based on an upper bound on energy consumption could calculate the minimum energy consumption travel path within 30 points in 60 s. The result is more accurate compared to the genetic algorithm with a single crossover operator.

Due to changes in light intensity, varying degrees of aphid aggregation, and small scales in the climate chamber environment, accurately identifying and counting aphids remains a challenge. In this paper, an improved YOLOv5 aphid detection model based on CNN is proposed to address aphid recognition and counting. First, to reduce the overfitting problem of insufficient data, the proposed YOLOv5 model uses an image enhancement method combining Mosaic and GridMask to expand the aphid dataset. Second, a convolutional block attention mechanism (CBAM) is proposed in the backbone layer to improve the recognition accuracy of aphid small targets. Subsequently, the feature fusion method of bi-directional feature pyramid network (BiFPN) is employed to enhance the YOLOv5 neck, further improving the recognition accuracy and speed of aphids; in addition, a Transformer structure is introduced in front of the detection head to investigate the impact of aphid aggregation and light intensity on recognition accuracy. Experiments have shown that, through the fusion of the proposed methods, the model recognition accuracy and recall rate can reach 99.1%, the value mAP@0.5 can reach 99.3%, and the inference time can reach 9.4 ms, which is significantly better than other YOLO series networks. Moreover, it has strong robustness in actual recognition tasks and can provide a reference for pest prevention and control in climate chambers.

The study of the influence of the nanoparticle volume fraction and aspect ratio of microchannels on the fluid flow and heat transfer characteristics of nanofluids in microchannels is important in the optimal design of heat dissipation systems with high heat flux. In this work, the computational fluid dynamics method was adopted to simulate the flow and heat transfer characteristics of two types of water-Al₂O₃ nanofluids with two different volume fractions and five types of microchannel heat sinks with different aspect ratios. Results showed that increasing the nanoparticle volume fraction reduced the average temperature of the heat transfer interface and thereby improved the heat transfer capacity of the nanofluids. Meanwhile, the increase of the nanoparticle volume fraction led to a considerable increase in the pumping power of the system. Increasing the aspect ratio of the microchannel effectively improved the heat transfer capacity of the heat sink. Moreover, increasing the aspect ratio effectively reduced the average temperature of the heating surface of the heat sink without significantly increasing the flow resistance loss. When the aspect ratio exceeded 30, the heat transfer coefficient did not increase with the increase of the aspect ratio. The results of this work may offer guiding significance for the optimal design of high heat flux microchannel heat sinks.