Search

Aiming at the problems of a large volume, slow processing speed, and difficult deployment in the edge terminal, this paper proposes a lightweight insulator detection algorithm based on an improved SSD. Firstly, the original feature extraction network VGG-16 is replaced by a lightweight Ghost Module network to initially achieve the lightweight model. A Feature Pyramid structure and Feature Pyramid Network (FPN+PAN) are integrated into the Neck part and a Simplified Spatial Pyramid Pooling Fast (SimSPPF) module is introduced to realize the integration of local features and global features. Secondly, multiple Spatial and Channel Squeeze-and-Excitation (scSE) attention mechanisms are introduced in the Neck part to make the model pay more attention to the channels containing important feature information. The original six detection heads are reduced to four to improve the inference speed of the network. In order to improve the recognition performance of occluded and overlapping targets, DIoU-NMS was used to replace the original non-maximum suppression (NMS). Furthermore, the channel pruning strategy is used to reduce the unimportant weight matrix of the model, and the knowledge distillation strategy is used to fine-adjust the network model after pruning, so as to ensure the detection accuracy. The experimental results show that the parameter number of the proposed model is reduced from 26.15 M to 0.61 M, the computational load is reduced from 118.95 G to 1.49 G, and the mAP is increased from 96.8% to 98%. Compared with other models, the proposed model not only guarantees the detection accuracy of the algorithm, but also greatly reduces the model volume, which provides support for the realization of visible light insulator target detection based on edge intelligence. [ABSTRACT FROM AUTHOR]

This article proposes an optimized space vector pulsewidth modulation (SVPWM) strategy with minimum common-mode voltage (CMV). Compared with earlier SVPWM methods, the proposed optimized strategy is implemented in the 45 $^\circ$ coordinates. Locating the sector triangle, calculating the duty cycles, and determining the switching sequences require only basic arithmetic operations, which greatly reduces the computational complexity. The switching state with minimum CMV corresponding to the space vector can be calculated directly. The proposed optimized modulation strategy effectively solves the problem that the traditional SVPWM is difficult to be implemented as the number of levels increases. It can be easily extended to any level converters without additional computational burden. Based on the proposed optimized SVPWM strategy with minimum CMV, the SVPWM strategy for eliminating CMV is proposed. The proposed SVPWM strategy for eliminating CMV improves the utilization of the redundant cells and reduces the total harmonic distortion of phase voltages without increasing the difficulty of implementing the SVPWM algorithm. Finally, the proposed two SVPWM strategies are verified with extensive simulations and experiments. [ABSTRACT FROM AUTHOR]