Search

To improve the work efficiency of on-site inspection personnel in diagnosing faults of power transmission lines, in this paper we propose an infrared image segmentation method based on DeepLabV3+ for identifying key components of transmission line. We collected 556 infrared images of transmission lines in our own power supply system, and expanded the original data by data augmentation method. Based on the comparison of the DeepLabV3+ model with three different backbone networks, MobileNetV2 with the best performance is selected as the main backbone network. Compared with FCN, U-Net, and SegNet, the test results show that DeepLabV3+ using MobileNetV2 (compared with ResNet50 and Xception) can segment the five types of key components in power transmission lines from infrared images more accurately and faster. The MIoU on the test set is 0.8624, which is better than the performance of FCN, U-Net, and SegNet. This lays a foundation for improving the work efficiency of on-site inspection personnel and improving the continuous power supply capacity, stability, and safe operation level of the power grid. [ABSTRACT FROM AUTHOR]

An optical limiter (OL) is a nonlinear device that protects sensitive photodetectors or human eyes from high-intensity illumination. However, current OLs have low open-state transmittance and a limited turndown ratio in some cases. In this study, first it is demonstrated that combining the insulator-to-metal transition (IMT) of vanadium dioxide (VO2) with anti-reflection layers can enable both high and broadband open-state transmittance (>-0.9 dB at the peak wavelength) while preserving a large turndown ratio (>21.8 dB). Furthermore, optothermal simulation is conducted to analyze the performance of the VO2 OL under ultrafast laser irradiation. The result reveals that IMT of the VO2 OL occurs at 0.23 µs when the incident laser intensity is 90 kW cm-2. These benefits offer a promising alternative to OLs in technologies ranging from sensor protection to human eye defense. [ABSTRACT FROM AUTHOR]