The lighting quality of the unmanned aerial vehicle (UAV) images is the key factor that affects the intelligent operation and maintenance efficiency in power system. When captured in low-light condition, the UAV images suffer from loss of details, leading to a decrease in object detection accuracy. However, the research is lacking with respect to low-light image enhancement for UAV-based overhead power transmission system images. In this letter, we propose a low-light image enhancement method based on Contrast Limited Adaptive Histogram Equalization (CLAHE) to robustify object detection against low-light condition. We first separate the luminance and chrominance channels of the UAV image via color space conversion so that CLAHE is used to enhance luminance contrast without introducing chrominance shift. Moreover, we optimize the contrast limit parameter in CLAHE to balance contrast enhancement and noise suppression, which further boosts object detection accuracy. Experimental results validate the effectiveness of the proposed scheme in detail enhancement without noise over-amplification, leading to a magnificent increase of insulator detection accuracy from 58.0% to 82.0%.

Room Temperature Vulcanized (RTV) silicone rubber is widely used on the surface of insulator of power transmission and transformation equipment because of its excellent hydrophobicity. With the increase of operating life, RTV coating is subject to the influence of high temperature, high humidity and complex outdoor environmental factors, which tends to fall off, seriously affecting the working state of the insulator. In this paper, based on the realization of insulator identification, the defect in RTV coating is identified, and the damage area percentage of RTV coating in the insulator shed is calculated. Experiments show that this method can effectively characterize the severity of defects in RTV coating, which provides a technical basis for the online detection and evaluation of RTV coating status.

The phenomenon of micro-cracks on the sheds is due to aging of the composite insulator. With the development of the Unmanned Aerial Vehicle (UAV) technology, the online aging characterization based on micro-cracks turns out to be a reality. In this paper, the micro-cracks identification and characterization on the sheds of composite insulators based on visible spectrum image was studied. At first, the shed area was segmented after graying and binarization operation. Then, the Laplace of Gaussian (LoG) operator and Otsu algorithm were used to extract the texture of micro-cracks. Box-counting method was used to calculate the fractal dimension of the micro-cracks on the composite insulator shed. The index of fractal dimension, a number between 1 and 2, can be used to describe the roughness and density of fractal dimension. The higher the fractal dimension was, the more severe the micro-cracks would be. The experimental results proved that the method proposed was feasible and effective on micro-cracks identification and characterization.

The strain clamps and leading wires are important components that connect conductors on overhead transmission lines and conduct current. During operation, poor contact between these components can cause abnormal overheating, leading to electric failures and threatening power system reliability. Recently, the use of unmanned aerial vehicles equipped with infrared thermal imagers for strain clamp and leading wire maintenance has become increasingly popular. Deep learning‐based image recognition shows promising prospects for intelligent fault diagnosis of overheating faults. A pre‐treatment method is proposed based on dynamic histogram equalisation to enhance the contrast of infrared images. The DeepLab v3+ network, loss function, and existing networks with different backbones are compared. The DeepLab v3+ network with ResNet101 and convolutional block attention module added, and the Focal Loss function achieved the highest performance with an average pixel accuracy of 0.614, an average intersection over union ( AIoU ) of 0.567, an F1 score of 0.644, and a frequency weighted intersection over union of 0.594 on the test set. The optimised Atrous rates has increased the AIoU by 12.91%. Moreover, an intelligent diagnosis scheme for evaluating the defect state of the strain clamps and leading wires is proposed and which achieves a diagnostic accuracy of 91.0%.

ZnO microvaristors/epoxy resin composite has drawn great attention from academia and industry for its adjustable non‐linear conductivity, high mechanical strength, and good ageing resistance. However, the sedimentation of ZnO microvaristors in epoxy resin during preparation is the key problem, which limits its application in engineering. In this study, a novel method of wet winding with polyester fibre cloth is proposed to prepare the ZnO microvaristors/epoxy resin composite. The anti‐settling effect of ZnO microvaristors in the composite is verified by scanning electron microscopy (SEM) and thermal gravimetric analysis (TGA). The microstructure shows that ZnO microvaristors distribute uniformly in the composite, and the content difference of ZnO microvaristors at the top and bottom part is only 0.4%. The composite shows typical non‐linear conductivity, and the threshold electric field and the non‐linear coefficient decrease with the content of ZnO microvaristors, while the conductivity in the insulating state shows an increasing trend. To verify the field grading effect of the composite with non‐linear conductivity (CNC), a finite element model of a needle‐plate electrode, simulating the condition of a conductive tip in a solid insulated system, is set up. CNC can adaptively grade the electric field, which reduces the surface electric field of the needle tip by 86.6% and the highest electric field in the system by 82.1%. This wet winding method solidifies the industrial application of CNC in high‐voltage power equipment.

There are a lot of quantitative performance characterisation methods for composite insulators. However, how to apply the characterisation methods with different dimensions to comprehensively assess the health state of composite insulators remains a big problem for operators and researchers. A comprehensive health assessment model for composite insulators based on the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method is proposed in this study. Fourteen composite insulators from four regions in Yunnan Province, China, and five quantitative characterisation indicators of the insulators, namely hardness, hydrophobicity, loss of hydrophobicity, recovery of hydrophobicity, and trap charge, are selected to verify the model. The results show that the Pearson correlation coefficient of the TOPSIS‐based comprehensive health score with operating time is 0.72, which is better than the other single indicator. By introducing the operating time into the TOPSIS‐based model, we can also obtain the ageing resistance performance of the composite insulator. This work provides a new idea to assess the health state and ageing performance of composite insulators.