Abstract.In order to solve the problems existing in the traditional lane line detection algorithm, such as weak robustness and low accuracy, an improved Hough transform lane line detection algorithm is proposed. Firstly, the method preprocesses the road image, including gray transformation, histogram equalization, Gaussian filtering, image binarization and so on. Then the canny edge detection operator is used to detect the edge of the image to be processed, and an improved Hough transform algorithm is proposed. Simulation results show that the algorithm has stronger robustness and higher accuracy than … Read more →

Abstract.In order to further improve the accuracy of mouse species recognition, a yolo-v5 algorithm based on attention mechanism is proposed. The algorithm consists of two parts, one is the yolo-v5 backbone network, and the second part is to add attention mechanisms to the backbone network. It is used to extract global features, and then uses the attention mechanism to give different weights to the extracted features, and finally achieves the purpose of obtaining the features we need. Finally, the softmax classifier is used for classification. Experiments were validated on a homemade mouse dataset. … Read more →

Abstract.Aiming at the problems of over 100 million pixels in a single image of a large-size light guide plate, only a dozen pixels in the defect size, uneven brightness, and slow detection speed, this paper designs an improved YOLOv5s method for light guide plate defect detection. YOLOv5s is used as the basic model, and the attention mechanism CBAM is added to the backbone feature extraction network (backbone) part; PAN-Net is replaced with Bi-FPN structure in the feature fusion network (Neck) part, and a small target detection layer is added at the same time; YOLOv5s Obtain higher accuracy and … Read more →

Abstract.Lithium-ion batteries(LIBs), with their high energy density and desirable cycling performance, have become the dominant battery technology for everything from portable electronics to electric vehicles. In recent years, lithium iron phosphate (LiFePO4) has been regarded as one of the most attractive cathode materials for lithium-ion batteries due to its good cycling stability, low price and excellent safety. However, the rapid development of LiFePO4 is limited by key challenges such as low conductivity and low diffusion rate of Li+. In order to improve these defects, many studies have been … Read more →

Abstract.In recent years, with the continuous growth of China's long-distance oil and gas pipeline network, wireless communication network applications have become more and more extensive with the continuous promotion of intelligent oilfield construction, while the energy-saving problem in the process of information transmission has become increasingly prominent. In order to ensure the sustainable development of China's oil and gas industry, low-power wireless transmission has become a basic requirement for the current intelligent oil and gas pipeline communication construction. For the monitoring of … Read more →

Abstract.Power distribution is critical for the dynamic dual receiver coil wireless charging system of electric vehicles. The power distribution method of the existing wireless power transmission technology mainly distributes the power to the load according to the requirements of different resonant frequencies. However, the existing methods have the problems of low accuracy and low power consumption, so it is difficult to implement in practice. This paper presents a new power distribution method, which can dynamically and accurately distribute power to loads. This method can improve the control speed … Read more →