Defective insulators seriously threaten the safe operation of transmission lines. This paper proposes an insulator defect detection method based on an improved YOLOv4 algorithm. An insulator image sample set was established according to the aerial images from the power grid and the public dataset on the Internet, combining with the image augmentation method based on GraphCut. The insulator images were preprocessed by Laplace sharpening method. To solve the problems of too many parameters and low detection speed of the YOLOv4 object detection model, the MobileNet lightweight convolutional neural network was used to improve YOLOv4 model structure. Combining with the transfer learning method, the insulator image samples were used to train, verify, and test the improved YOLOV4 model. The detection results of transmission line insulator and defect images show that the detection accuracy and speed of the proposed model can reach 93.81% and 53 frames per second (FPS), respectively, and the detection accuracy can be further improved to 97.26% after image preprocessing. The overall performance of the proposed lightweight YOLOv4 model is better than traditional object detection algorithms. This study provides a reference for intelligent inspection and defect detection of suspension insulators on transmission lines.

Breakdown voltage of the air gap is of vital importance for the design of the external insulation in high-voltage transmission and transformation projects. In this paper, a new prediction method for the breakdown voltages of typical air gaps based on the electric field features and support vector machine (SVM) was proposed. According to the finite element calculation results of static electric field distribution, the electric field values in the whole region, discharge channel, surface of the electrode and the shortest path were extracted and post-processed, which constituted the electric field features characterizing the gap structure. Then, the breakdown voltage prediction model of the air gap was established by using electric field features as the input parameters to SVM, and whether the gap breakdown would happen as the output parameters of SVM, which changing the regression problem to a binary classification problem. This model was applied to predict the power frequency breakdown voltages of different short air gaps including sphere-sphere gaps, rod-plane gaps, sphere-plane gaps and sphereplane- sphere gaps. The power frequency breakdown voltages of longer air gaps which are affected by corona, and the 50% positive switching impulse breakdown voltages of long sphere-plane gaps and rod-plane gaps were predicted as well. The predicted results agree well with experimental values and simulated results of the published models, which validate the effectiveness of the proposed model. This method supplies a new possible way to obtain the breakdown voltage of air gaps.

Foreign objects suspended on transmission and distribution lines like nests, kites, balloons, and trash, etc. may lead discharge faults and greatly affect the safety of power grid. How to perform accurate and timely detection of these foreign objects is an urgent problem. This paper proposes a lightweight YOLOv4 model with embedded dual attention mechanism (YOLOv4-EDAM) to detect foreign objects from visible images, using MobileNetV2 embedded with the squeeze and excitation networks (SENet) to replace the CSPDarkNet53 feature extraction network, the depthwise separable convolutions (DSC) to replace the standard convolutions in SPP and PANet module, and embedding the convolutional block attention module (CBAM) into SPP and PANet module to improve the detection accuracy. Firstly, an image dataset was constructed using inspection images and public datasets, and expanded by Poisson blending and some data augmentation methods. The denoising convolutional neural network (DnCNN) was applied for image preprocessing. Next, the lightweight YOLOv4-EDAM model was trained combining Mosaic data enhancement, cosine annealing and label smoothing skills. Several detection cases were carried out and the experimental results show that the proposed model has a high accuracy with the mean average precision (mAP) of 96.71%, and a fast detection speed with the frames per second (FPS) of 45, whose overall performance is better than other object detection models. This study offers a reference for power line inspection and provides a possible way to deploy edge computing devices on unmanned aerial vehicles.

It has been a long sought goal to determine the critical flashover voltages of long air gaps by mathematical calculations instead of experiments. In this paper, a predictive model is proposed for 50% discharge voltage (U50) prediction of long air gaps subjected to switching impulses. This model is developed on the basis of the physical thought that air breakdown can be viewed as out-of-limit of the capacitive energy stored in the electric field. Two groups of features are defined to characterize the energy storage status of an air gap, from the perspective of electric field distribution and impulse voltage waveform, respectively representing the space distribution and time accumulation of the energy. The predictive model is established by support vector machine (SVM), and the input data are the energy storage features. Giving an estimated applied voltage range, the predicted result of the critical flashover voltage is searched by the golden section method. Trained by 6 known experimental data, this model is used to predict the U50 of rod-plane, rod-rod and rod-conductor long air gaps subjected to negative switching impulse voltages. The mean absolute percentage errors of 5 groups of test samples are respectively 6.0%, 5.8%, 6.3%, 3.2% and 1.7%, which are in an acceptable range in the view of engineering applications. The proposed method might be useful to predict the U50 of long air gaps with various geometries and under different voltage waveshapes, therefore reducing the required test work for insulation design of high voltage equipments.

This paper attempts to establish the grey correlation between the breakdown voltage of air gap and its energy storage status before discharge inception. A new method is presented for the breakdown voltage prediction of short air gaps. This method is based on an orthogonal design array and support vector machine (SVM). A hybrid model is established to predict the power frequency breakdown voltage of three typical air gaps including sphere-sphere, rod-plane, and rod-rod gaps. The input data are fifty parameters extracted from the static electric field distribution of the air gap, and the output of the model is whether the gap will breakdown under a given voltage. This model is trained by 9 samples selected by L₉(3³) orthogonal array and applied to predict the breakdown voltage of 90 test samples. With effective feature dimension reduction and parameter optimization of the SVM model, the predicted results coincide well with the experimental data, and the mean absolute percentage error (MAPE) is only 3.9%. The SVM model is also applied to predict the breakdown voltage of some atypical short air gaps including sphere-plane gaps, rod-sphere gaps, sphere-sphere gaps with different diameters, and rod-plane-sphere gaps. The MAPEs are respectively 4.3, 3.2, 4.2, and 6.4%, which verifies the validity and generalization performance of the proposed method. This model provides a new way to gain the critical breakdown voltage of air gaps, and therefore contributes to reducing the required test work.

The correct identification of partial discharge types is of great significance to the stable operation of GIS. In order to improve the recognition accuracy and result of partial discharge, and to meet the requirements of real-time monitoring of GIS equipment, this paper proposes a GIS partial discharge defect recognition model based on YOLOv5. First, the GIS partial discharge simulation experiment is established to create the dataset of partial discharge PRPD map. Then, a YOLOv5-based GIS partial discharge defect recognition model is constructed, and different training methods are used to optimize the parameters of the model. By comparing with target detection models based on other deep learning methods, such as Faster-RCNN and YOLOv4, the YOLOv5 model discussed in the paper has significantly improved the recognition efficiency and recognition accuracy, in which mAP value is 95.89% and FPS is 28.89. In addition, the model can realize the distinction and identification of multiple PD types in a single PRPD map. At last, the YOLOv5-based GIS partial discharge defect identification model is applied to the test in a 500 kV substation. The model accurately determines the type of GIS partial discharge, which verifies the accuracy and validity of the model.