Search

Abstract Bird‐related outages greatly threaten the safety of overhead transmission and distribution lines, while electrocution and collisions of birds with power lines, especially endangered species, are significant environmental concerns. Automatic bird recognition can be helpful to mitigate this contradiction. This paper proposes a method for automatic classification of bird species related to power line faults combining deep convolution features with error‐correcting output codes support vector machine (ECOC‐SVM). An image dataset of about 20 high‐risk and 20 low‐risk bird species was constructed, and the feed‐forward denoising convolutional neural network was used for image preprocessing. The deep convolution features of bird images were extracted by DarkNet‐53, and taken as inputs of the ECOC‐SVM for model training and bird species classification. The gradient‐weighted class activation mapping was used for visual explanations of the model decision region. The experimental results indicate that the average accuracy of the proposed method can reach 94.39%, and its performance was better than other models using different feature extraction networks and classification algorithms.

Wind turbine blades are susceptible to various types of damage caused by environmental factors, external forces, and other influences. Achieving efficient and accurate detection of damage defects in wind turbine blades is essential to extend the service life of wind turbines. To this end, this paper proposes a cascaded adaptive hybrid attention network (CAHAN). Firstly, a high-resolution wind turbine blade damage defects image dataset is constructed using the dual aggregation transformation (DAT) model and the contrast enhancement algorithm. Secondly, a global contextual attention pyramid (GCAP) module is proposed to effectively integrate global and local feature information. Then, a cascaded adaptive hybrid attention (CAHA) module is developed to design a PANet feature fusion network, which can effectively filter out redundant global feature information. In addition, the dynamic head (DH) modules covering scale, space, and task awareness are applied to wind turbine blade defects detection, greatly enhancing the model’s capability to detect blade damage defects. Finally, the proposed method is tested using wind turbine blade defect images collected from open web downloads. The results show that the CAHAN model achieves an overall detection accuracy of 97.9% and boasts a fast detection speed of 149.25 frames per second (FPS), which has superior overall performance compared to other object detection models. This method is useful for defect detection of wind turbine blade damage.

The smoke and poisonous gas produced during combustion is one of the direct hazards of cable fire. For power cables laid vertically in the cable shaft of high-rise buildings, the chimney effect will speed up the spread and expand the harm of cable fire. The paper proposes a simulation method based on fire dynamics theory to analyze the diffusion and spread characteristics of cable fire. First, a three-dimensional model of the double-floor cable shaft with multiple cables laid vertically inside was built in the paper. Second, with the abnormal heating caused by overload or insulation breakdown as the excitation condition, the development process of cable fire is simulated. The diffusion of smoke and gas during the whole combustion process is studied and discussed. Then, the paper compares the simulation results of the model with different fire blocking materials. The simulation results show that the application of blocking materials will cause differences between the spread of fire and flue gases, and the difference can be used to evaluate the quality and performance of the fire blocking material. Finally, A test platform is constructed to verify the validity of the simulation analysis.

Abstract It is a long‐term goal in external insulation studies to determine the discharge voltages of complicated engineering gaps by simulation methods. Based on the one‐to‐one correspondence between air gap structure and the static electric field (EF) distribution, this paper characterizes the transmission tower gap configuration by spatial EF features, which were used for machine learning to achieve switching impulse discharge voltage prediction. An interelectrode path and a conical zone between the energized sub‐conductor and the crossarm or the tower window were considered as EF regions strongly associated with gap breakdown, where 73 parameters were extracted to construct a feature set. Taking 15 extra‐high voltage (EHV) transmission tower gaps as training samples, with different gap distances and tower configurations, their EF features were input to a support vector machine (SVM) for model training to establish the relationships with discharge voltages. The trained SVM model was used to predict the impulse discharge voltages of 20 EHV and ultra‐high voltage (UHV) transmission tower gaps. The prediction results with different feature dimensions and various sizes of conical zones were compared to the experimental values, which demonstrate similar variation trends and acceptable errors. This study contributes to realize insulation strength calculation of engineering gaps.

Abstract Efficient bird damage prevention of transmission lines is a long‐term challenge for power grid operation and maintenance. An approach combined lightweight convolutional neural network (CNN), image processing and object detection is presented in this paper to detect typical bird species related to transmission line faults. An image dataset of 20 bird species that threaten transmission line security is constructed. The YOLOv4‐tiny algorithm model is constructed and trained combining stage‐wise training, mosaic data enhancement, cosine annealing, and label smoothing. The mean average precision (mAP) can reach 92.04% on the test set by adjusting the parameters of the training process. Then, the validity of the proposed method is verified according to the test results and performance indexes by comparing with other methods, including Faster RCNN, SSD, YOLOv4 etc. Some image pre‐processing methods such as motion blur, defocus blur, contrast and brightness adjustment are used to simulate the scenarios in practical engineering applications. The proposed method can detect bird species perched around transmission lines with high‐efficiency, which is useful for differential prevention of bird‐related outages of power grids.

Abstract A high voltage current transformer of the inverted type is a commonly used measurement equipment in power grids. The thermal behaviour of the current transformer has a significant impact on its operating conditions and is directly related to its service life. The study presents a three‐dimensional simulation model of a 220 kV inverted‐type oil‐immersed current transformer, and the fluid and temperature field are analysed by the finite volume method. The simulation results show that the hot‐spot temperature under the rated load of the calculation model introduced in the study is 61.5°C, and located at the upper part of the core and the secondary winding. An experiment setup was designed to measure the temperature distribution inside a LVB‐220W3‐type current transformer. The temperature data measured under the rated load indicate that the simulation results agree well with the experimental results.

This study compared the effects of four forest canopies on throughfall chemistry in the Qinling Mountains, China. Rainfall and throughfall samples were collected in stands of Quercus aliena (Qa) var. Acuteserrata, Pinus tabulaeformis (Pt), P. armandii (Pa), and mixed broad-leaved (Mb) trees from 2009 to 2011. The results indicated that the pH of the rainfall, which was mildly acidic, increased as it passed through the forest canopy. The pH increased more within the broad-leaved forest canopy than the coniferous forest. Concentrations of decreased as rainfall passed through the Qa canopy but increased after passing through the other species. The concentrations of and Zn, Cd and Pb decreased as rainfall passed through the four canopies. The coniferous forest canopy was more effective than the broad-leaved forest in reducing in rainwater. The decreases in Cd concentrations were similar among the four canopies. The Pb concentration decreased the most among the heavy metals, and the order of the decrease was Qa > Pt > Pa > Mb. The results may provide a basis for the selection of tree species for afforestation in water sources in the Qinling Mountains and similar areas. HIGHLIGHTS The broad-leaved forest canopies increased acidic rainfall pH more than the coniferous forest canopies.; The coniferous forest canopies were more effective in reducing in the rainwater.; The order of canopy decreasing Pb concentrations was Quercus aliena > Pinus tabulaeformis > P. armandii > mixed broad-leaved trees.; The decreases in Cd concentrations were similar among the four canopies.;

Air insulation strength relates closely to the electrostatic field distribution of the gap configuration. To achieve insulation prediction on the basis of electric field (EF) simulations, the spatial structure is characterized by a feature set including 38 parameters defined on a straight line between sphere electrodes. A support vector classifier (SVC) with particle swarm optimization (PSO) is used to establish a prediction model, whose input variables are those features. The EF nonuniform coefficient f of each sample gap is calculated and used for training sample selection according to the ranges off values. Trained by only 11-sample data, the PSO-optimized SVC model is employed to predict the power frequency breakdown voltages of 260-sphere gaps with a wide range of structure sizes. The predicted values coincide with the standard data given in IEC 60052 very well, with the same trend and minor relative errors. The MAPEs of the five predictions with different training sets are within 2.0%. The model is also effective to predict the breakdown voltages of Φ9.75-cm sphere-Φ6.5-cm sphere gaps, whose MAPEs are within 2.6%. The results demonstrate the effectiveness of the EF feature set and the generalization ability of the SVC model under the case of limited samples. This paper lays the foundation for estimating the dielectric strength of other air gaps with similar structures.

This paper aims at presenting a novel approach for the analysis of vibration signals detected from circuit breaker (CB) opening or closing operations and to mechanical fault identification. An adaptive signal decomposition approach and chaotic nonlinear dynamic technique are used for extracting fault sensitive features of CB. The fault sensitive frequency band is derived using variational mode decomposition (VMD) combining with Hilbert marginal spectrum (HMS). The obtained sensitive frequency band(s) are employed for the reconstruction of the dynamical attractor (chaotic dynamics viewed from a phase space perspective, namely, the attractor-based perspective) following the Taken's embedding theorem. The invariant measures and ergodic quantities such as the largest Lyapunov exponent, correlation dimension, and Kolmogorov entropy which can be estimated on the reconstructed attractor are presented as the fault sensitive features. The CB fault is estimated in a chaotic space using these sensitive features. The effectiveness of the developed method is evaluated by using data sets recorded from several vacuum CBs with the same type.

On-line monitoring and the diagnosis of the high-voltage circuit breaker (HVCB) have been discussed and investigated significantly in the past few decades. The vibration analysis is a noninvasive and advanced diagnostic technique suitable for the detection of mechanical conditions during the HVCB operation, which plays an important role in improving the operating reliability of HVCB and reduces maintenance costs. However, due to the very complicated mechanical system and extremely short operation time of HVCB, the vibration signal has the characteristics of highly nonlinear, non-stationary, and corrupted by heavy garbage noise, which makes it very difficult to precisely extract effective features for machinery fault diagnosis. To address this issue, an energy entropy of Hilbert marginal spectrum (HMS) based on variational mode decomposition (VMD) is presented to analyze the vibration signals of HVCB in this paper. The VMD is used to decompose the vibration signal into a set of intrinsic mode functions (IMFs) reflecting its local characteristics, and then, the energy entropy of IMF's HMS, which varies from different failure modes of HVCB, is obtained by Hilbert transform and entropy-information theory. The characteristics of IMF's HMS, which reveal the variation of vibration signals, under different failure modes of HVCB, are practically analyzed and examined to illustrate the advantage of the proposed method in feature extraction. The IMF that best reflects the mechanical anomaly information of HVCB is ascertained from IMF's HMS, and its Hilbert marginal spectrum energy entropy (HMSEE), namely, IMF-HMSEE, which synthetically reflects the variations of vibration signal's amplitude, phase, and frequency, is turned out to have excellent classification performance for some mechanical anomalies of HVCB. The effectiveness of the proposed approaches is substantiated by experiments carried out in a 12-kV vacuum HVCB.

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.

Foreign objects such as kites, nests and balloons, etc., suspended on transmission lines may shorten the insulation distance and cause short-circuits between phases. A detection method for foreign objects on transmission lines is proposed, which combines multi-network feature fusion and random forest. Firstly, the foreign object image dataset of balloons, kites, nests and plastic was established. Then, the Otus binarization threshold segmentation and morphology processing were applied to extract the target region of the foreign object. The features of the target region were extracted by five types of convolutional neural networks (CNN): GoogLeNet, DenseNet-201, EfficientNet-B0, ResNet-101, AlexNet and then fused by concatenation fusion strategy. Furthermore, the fused features in different schemes were used to train and test random forest, meanwhile, the gradient-weighted class activation mapping (Grad-CAM) was used to visualize the decision region of each network, which can verify the effectiveness of the optimal feature fusion scheme. Simulation results indicate that the detection accuracy of the proposed method can reach 95.88%, whose performance is better than the model of a single network. This study provides references for detection of foreign objects suspended on transmission lines.

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.

With the rapid development of China's power grid, it is becoming increasingly common that the multi-circuit overhead transmission lines cross over each other. It is important to design the lines' configuration reasonably and evaluate whether the power-frequency electric field meets the national standard. In order to analyse the electric field distribution in the maintenance area of the 220 kV tower with an overhead 1000 kV UHV AC double circuit transmission line, a three-dimensional finite element model of the crossing tower and transmission line was established. The influences of the crossing angle, span height and offset distance on the electric field distribution in the maintenance area of the lower tower and the line worker body surface electric field were analysed. The results show that the maximum electric field strength of the tower will increase 28.7% when the cross-angle decreases from 90° to 30°, and the impact of span height on the electric field distribution is much smaller at 90° than that at 30°. At 60°, when the crossing height is 16 m, the electric field strength on the worker's body surface is much less than the limiting value.

The hybrid high-voltage direct current (HVDC) breaker combines mechanical and power electronics switching that enables it to interrupt power flows within a few milliseconds. Mechanical switch is a key component of hybrid HVDC breaker and has a number of serially connected interrupter units which ideally would divide the voltage equally. The static voltage distribution characteristics and voltage sharing design of a multi-break mechanical switch were discussed in this study. A finite-element model was developed to study the static voltage distribution characteristics and capacitance parameters of multi-break mechanical switch (which actually consists of resistance and capacitance parameters under direct current) as a preliminary study. Comparisons were made under the simulation of vertical and U-shaped arrangement forms. The results indicate that the static voltage distribution of the high-voltage terminal is at least more than 65%, whereas the severe non-uniform voltage distribution can be well improved by means of the method proposed in this study.

Full-scale discharge tests of transmission line–tower air gaps are costly and time-consuming, and they cannot exhaustively simulate all the gap configurations in practical engineering. In this paper, a machine learning model established by support vector machine is introduced to predict the switching impulse discharge voltages of the ultra-high-voltage (UHV) AC transmission line–tower air gaps. The three-dimensional finite element models of a UHV cup-type tower and a UHV compact transmission line were established for electric field calculation, and some features were extracted from the hypothetic discharge channel and the shortest path between the bundled conductor and the tower. These features under a given voltage were normalised and input to the SVM model, while the output is two binary values, respectively, representing gap withstanding or breakdown. Trained by experimental data of one type of the UHV transmission line–tower gaps, the SVM model is able to predict the discharge voltages of another gap type. The mean absolute percentage errors of the two engineering gap types, under different gap distances, are 8.31 and 4.86%, respectively, which are acceptable for engineering applications. The results provide a possible way to obtain the discharge voltages of complicated engineering gaps by mathematical calculations.

Bird activities including the defecation, nesting, and flight are easy to cause electrical faults of overhead transmission lines, study on the prevention measures of bird damage to transmission lines is of great significance to ensure the stable and reliable operation of the power system. With the establishment of finite element simulation model, the effects of box of bird guard with different material on the electric field and potential distribution on transmission line insulators are studied. Besides, combined with the theory of air discharge and the results of simulation, the influence of rainwater on the air gap around the insulator breakdown characteristics is studied when the water is drained from a scupper at the bottom of the box of bird guard, and a reasonable design scheme for the box of bird guard scupper is proposed. The research results here can provide a guidance for the selection and key parameters’ design of the box of bird guard.

During the construction of cable joints, three common defects may occur on the XLPE surface: scratches, moisture exposure, and adhered contaminated particles. To evaluate the impact of these defects on joint performance, this paper establishes a sheet model of XLPE insulation in cable joints to analyze the changes in the electric field under different defects and explore the influence of different defects on the electric field and breakdown voltage. Results of the study reveal that the electric field at the scratch site on XLPE produces severe distortion, being 1.6 times that of non-scratch areas. When exposed to moisture, the more conductive impurities present in the adhered contaminated water on the XLPE surface, the higher the conductivity of the contaminated water, thereby increasing its conductive performance and the electric field strength, which is 1.22-1.4 times that of the non-moist interface. When particles adhere to the XLPE surface, severe distortion occurs at the particle-interface electric field, approximately 1.5 times that of the defect-free interface. Scratches have the most significant impact on the electric field of XLPE insulation. Experimental results also demonstrate that the breakdown voltage without defects is 129.6 kV, while the breakdown voltage with scratch defects is 59.1 kV, moisture defects is 69.7 kV, and particle contamination defects is 59.2 kV, with scratches having the most significant impact on the breakdown voltage of XLPE insulation. These findings provide important insights into the influence of different defects on the insulation performance of cable joints. [ABSTRACT FROM AUTHOR]