With the improvement of smart grid, utilizing unmanned aerial vehicles (UAV) to detect the operation status of insulators has attracted widespread attention. The insulator defects can lead to serious power loss, damage the service life of power lines, and even result in power outages in serious cases. The small‐scale object, complex background, and limited‐number collected data make insulator defect still a challenging problem. Benefitted by the advances in deep learning, deep learning‐based insulator defects have achieved great progress in recent years. In the paper, the authors present a novel systematic survey of these advances, where further analysis about different processing stages methods is introduced: (i) insulator processing stage methods exploit the specific image pre‐processing algorithm for data augmentation and low‐level vision information extraction; (ii) defect detection stage model can locate and classify diagnosis fault with different task targets, like sequential task strategy and multi‐task strategy. In addition, the authors also review publicly available benchmark and datasets. The future research direction and open problem are discussed to promote the development of the community.

No abstract

Water pollution is a serious problem in China and abroad. Revealing the source types and their spatio-temporal characteristics is the premise of effective watershed management and pollution prevention. Since the national control unit can better match the administrative division, it was useful for the manager to control water pollution. Taking the Fenhe River Basin as the research area, a SWAT model based on the national control unit was established in this study to reveal the current situation of water quantity and quality. Then, in combination with the differential evolution algorithm, the dynamic water environment capacities of each control unit were further discussed. The results showed that the flow upstream was lower, only 7.62–8.40 m3/s, but flow in the midstream and downstream increased to 17.58 m3/s and 18.32 m3/s. Additionally, the flow in tributaries was generally lower than that in the main stream, the flow in unit 6 and unit 11 were only 0.23 m3/s and 0.62 m3/s. The water quality upstream could meet the water quality requirements of drinking water sources, but the pollution in the midstream was the most serious after passing through Taiyuan City, the concentration of NH3-N and TP reached to 6.75 mg/L and 0.41 mg/L. The results of water environmental capacity showed that the residual capacity of ammonia nitrogen (NH3-N) and total phosphorus (TP) in the main stream were positive, indicating that the Fenhe River Basin can accommodate the current pollution load in general, but there was an obvious difference in different months of the year. Especially in the wet season, the non-point source (NPS) pollution problem in the midstream and downstream was more prominent, resulting in a high-capacity consumption rate. It showed that in Taiyuan, Jinzhong, and Linfen Yuncheng in Shanxi Province, should be wary of non-point source pollution. In addition, the water environmental capacity of different units also varied greatly. The capacity consumption of the Taiyuan Section in the midstream was the highest, which mainly occurred in the wet season. The negative values of the residual capacity of NH3-N and TP reached the highest, −131.3 tons/month and −12.1 tons/month. Moreover, the capacity consumption downstream also reached 21–40% of the whole year in the wet season. In addition to the impact of NPS pollution in the wet season, due to the impact of point source pollution, units 8, 9, and 10 downstream had high negative residual capacity in the dry season, especially in January and February. The construction of a SWAT model based on control units and the further analysis of dynamic water environment capacity could provide technical support for Fenhe River Basin management to realize accurate pollution control.

The oil in hydropower station catchment wells is a source of water pollution which can cause the downstream river to become polluted. Timely detection of oil can effectively prevent the expansion of oil leakage and has important significance for protecting water sources. However, the poor environment and insufficient light on the water surface of catchment wells make oil pollution detection difficult, and the real-time performance is poor. To address these problems, this paper proposes a catchment well oil detection method based on the global relation-aware attention mechanism. By embedding the global relation-aware attention mechanism in the backbone network of Yolov5s, the main features of oil are highlighted and the minor information is suppressed at the spatial and channel levels, improving the detection accuracy. Additionally, to address the problem of partial loss of detail information in the dataset caused by the harsh environment of the catchment wells, such as dim light and limited area, single-scale retinex histogram equalization is used to improve the grayscale and contrast of the oil images, enhancing the details of the dataset images and suppressing the noise. The experimental results show that the accuracy of the proposed method achieves 94.1% and 89% in detecting engine oil and turbine oil pollution, respectively. Compared with the Yolov5s, Faster R-CNN, SSD, and FSSD detection algorithms, our method effectively reduces the problems of missing and false detection, and has certain reference significance for the detection of oil pollution on the water surface of catchment wells.

No abstract