Aiming at the problem of target recognition of heterogeneous fusion images, the algorithm flow and network structure of the YOLO convolutional neural network model are analyzed and explained based on the deep learning of the convolutional neural network. Combining the characteristics of the fusion image, the interface, structure and parameters of the YOLOv3 convolutional neural network are improved and adjusted while the recognition effect is guaranteed, the YOLO model is streamlined, and the training is successfully implemented and the training weights are output. The algorithm is effective and stable, and the recognition speed is faster.

In order to solve the problem that there are many resonant elements and it is difficult to design the full bridge CLLLC resonant converter, an improved resonant network parameter design method combined with simulation analysis is proposed in this paper. Accurate DC voltage gain curves are obtained under different resonant parameters. A 3.5 kW simulation circuit is constructed based on the parameters of the proposed method. The simulation results confirm the correctness and feasibility of the proposed improved design method.

No abstract

No abstract