Insulator Surface Condition Research Articles

Stacked Ensemble Deep Learning for Outdoor Insulator Surface Condition Classification: A Profound Study on Water Droplets

Stacked Ensemble Deep Learning for Outdoor Insulator Surface Condition Classification: A Profound Study on Water Droplets

Electrical Insulator Surface Condition Analysis Based on Joint Fully Convolutional and Multiscale Spatial Pooling Attention Network

Health condition monitoring of insulators is one of the key factors to ensure a stable power supply. This article proposes an automated insulator surface condition analysis approach based on vision measurement and the convolutional neural network (CNN). Specifically, we consider the condition analysis of insulators as an image multiclassification problem. An insulator image is first fed into a feature extractor, implemented by leveraging CNN, to extract features automatically. Then, a softmax classifier is utilized to map the feature representation into a probability vector to obtain the analysis results. Considering that neither each layer nor each location of features has the same impact on classification performance, we further focus on feature relationships and present a novel attention architectural unit, called the joint fully convolutional and multiscale spatial pooling attention (JFCMSPA) module. This new attention module not only considers the friendly fusion of different pooled information but also introduces the local similarity property of images into visual attention for the first time. These new insights allow it to efficiently learn feature importance. Finally, experimental results demonstrate the effectiveness of the proposed method and the value of its application in the inspection of power equipment.

Recognition of Hydrophobicity Class of Polymeric Insulators Employing Residual Morphological Neural Network and Granulometry-Based Image Analysis

Hydrophobicity is an important property of polymeric insulators that allow formation of discrete water droplets on the insulator surface. However, with aging or under extreme humidification, the insulator surface loses its hydrophobic property, resulting in continuous water channel formation, which may lead to dry band arcing and subsequently flashover, thereby affecting the long-term performance of the insulator. Therefore, accurate recognition of hydrophobic class (HC) is important as it provides information regarding the surface condition of the insulator. Considering the above-said facts, this article investigates the feasibility of employing residual morphological neural network (Res-Morph-NN) to accurately recognize different HCs of polymeric insulators. In addition, for better understanding of the distribution of water droplets on the insulator surface, a novel approach based on multiscale mathematical morphology, i.e., granulometry, is used in this article. Our investigations revealed significant alterations in the granulometric patterns with the change in HC of polymeric insulators. The efficacy of the proposed framework employing Res-Morph-NN has been validated on HC images obtained from the experiment as well as on large set of images obtained from an online database, which returned satisfactory results. The proposed method can be efficiently used to discriminate different hydrophobicity classes, which can be implemented for monitoring insulator surface condition in real time.

An Experimental Study Followed by a Development and a Comparison of Regression Models for Predicting TJ Electric Discharge in Insulators

Analyzes of electric discharge are sometimes tedious and relatively expensive. To overcome this problem, some scientists are working on variance analysis projects. The article presents the results of an electric discharge experiment performed on silicone, porcelain and heat tempered glass insulators at Triple Junction (TJ). The objective of this study is to develop a polynomial and Gaussian simple regression model (Polynomial Simple Linear Regression (SLR) model and Gaussian simple nonlinear regression model) considering different parameters by analyzing the observed quantitative data. The dependent variable or variable to be explained (discharge current) is a function of four independent variables (explanatory variables): voltage application time (t), solid insulator surface condition: net surface (t’), worn rubbed surface with sandpaper (t’’) and active electrode diameter (diam). Indeed, this study sets up precise prediction models generating good estimates of the studied variables values. A polynomial SLR model is proposed capable of predicting electric discharge with an adjusted coefficient of determination (R2 adj) of 0.9774 for t and t’, 0.9773 for t" and 0.9945 for diam. While (R2 adj) for the Gaussian model reaches 0.9989 for t and t’, 0.9998 for t’’. By considering this, these models are strongly recommended to better understand and characterize the discharge and contribute to the improvement of the insulation and its design for better optimization and high performance.

Multi-Modal Data Fusion Using Deep Neural Network for Condition Monitoring of High Voltage Insulator

A novel Fusion Convolutional Network (FCN) is proposed in this research for potential real-time monitoring of insulators using unmanned aerial vehicle (UAV) edge devices. Precise airborne imaging of outdoor objects, such as high voltage insulators, suffers from varied object resolution, cluttered backgrounds, unclear or contaminated surfaces, and illumination conditions. Accurate information about the insulator surface condition is essential and is of a high priority since insulator breakdown is a leading cause of electrical failure. A multi-modal information fusion (MMIF) system is developed during this research to analyze and classify possible contaminations present on the electrical insulators. A novel system, referred to as FCN, consists of a Convolutional Neural Network (CNN) and a binary Multilayer Neural Network (MNN) sub-classifier. While constructing the MMIF dataset for training and testing the novel FCN, the image classification output of the CNN is combined with the leakage current values (LCV) obtained as the classification output of MNN. Each sample of the MMIF dataset is, therefore, represented as a series of fusions. Later, sub-classifiers, of the FCN, are trained to identify the contamination types in the fusion series by implementing a voting system of sub-classifiers which is trained to identify a given class. As a result of the implementation of the proposed FCN, the classification accuracy increased by 8.4%, i.e., from 92% to 99.76%. To compare and benchmark the performance of proposed FCN, conventional classification algorithms are also implemented on the fusion of features that are extracted employing the wavelet transform and PCA methods. State-of-the-art CNN architectures are also discussed on account of their time consumption and memory usage. The conceptualization of a potential hardware implementation of the proposed FCN, on emerging edge devices, is also provided for completeness of the discussion. Pertinent outcomes of this research can be further extended to other potential applications of airborne imaging.

IN-YOLO: Real-Time Detection of Outdoor High Voltage Insulators Using UAV Imaging

The high voltage insulator requires continuous monitoring and inspection to prevent failures and emergencies. Manual inspections are costly as it requires covering a large geographical area where insulators are often subjected to harsh weather conditions. Automatic detection of insulators from aerial images is the first step towards performing real-time classification of insulator conditions using Unmanned Aerial Vehicle (UAV). In this paper, we provide a cost-effective solution for detecting insulators under the conditions of an uncluttered background, varied object resolution and illumination conditions using You Only Look Once (YOLO) deep learning neural network model from aerial images. We apply data augmentation to avoid overfitting with a training set size of 56000 image samples. It is demonstrated experimentally that this method can accurately locate insulator on UAV based real-time image data. The detected insulator images are then successfully subjected to insulator surface condition assessment for the presence of ice, snow and water using different classifiers.

High voltage outdoor insulator surface condition evaluation using aerial insulator images

High voltage insulator detection and monitoring via drone-based aerial images is a cost-effective alternative in extreme winter conditions and complex terrains. The authors examine different surface conditions of the outdoor electrical insulator that generally occur under winter condition using image processing techniques and state-of-the-art classification methods. Two different types of classification approaches are compared: one method is based on neural networks (e.g. CNN, InceptionV3, MobileNet, VGG16, and ResNet50) and the other method is based on traditional machine learning classifiers (e.g. Bayes Net, Decision Tree, Lazy, Rules, and Meta classifiers). They are evaluated to discriminate the images of insulator surface exposed to freezing, wet, and snowing conditions. The results indicate that traditional machine learning methods with proper selection of features can show high classification accuracy. The classification of the insulator surfaces will assist in determining the insulator conditions, and take preventive measures for its protection.

Analysis of 500 kV OHTL polluted insulator string behavior during lightning strokes

The lightning strokes can be very harmfull to the high voltage transmission lines especially in case polluted insulator string.In this paper, the lightning overvoltage in the El-Kuorimate - Cairo 500-kV transmission line single circuit is discussed. The leakage current and its harmonic spectrum on clean and polluted 500-kV string insulators are determined under normal condition and lightning strokes. Furthermore, the relation between back flashover and insulator surface condition are discussed under different magnitude of lightning strokes. The results show that the leakage current, thermal losses magnitudes in case polluted insulator are higher than in case clean insulator by about 97.2%. For polluted insulator, less lightning strokes peak will increase leakage current to above 60mA, and lead to serious insulator flashover faster than clean insulator. This study based on an equivalent electrical model by using Alternative Transients Program (ATP-EMTP) software.

Nonstationary effects in ozone generation by barrier discharges in N2/O2 mixtures

The yield of ozone in barrier discharges in oxygen–nitrogen mixtures containing 0.001 to 40% of nitrogen is investigated experimentally. Phenomena of the nonstationarity of processes of ozone generation that differ from the known ozone-zero phenomenon (OZP) apparent in the reduced efficiency of ozone generation in very high purity oxygen at long periods (from hours to tens of hours) of ozonator operation are found. It is established that the characteristic times (from minutes to tens of minutes) of ozone attaining stationary values after changes in the discharge parameters indicate slow adjustment of the surface condition of insulators and thus the heterogeneous decay of ozone to more rapidly changing flows of neutral and charged particles from gas discharge plasma on the surfaces of dielectrics. The possibility of such a scenario is confirmed using a new analytical approach and numerical calculations of the plasma–chemical kinetics of N2/O2 mixtures presented in the accompanying theoretical study.

S-Transform Based Time-Frequency Analysis of Leakage Current Signals of Transmission Line Insulators under Polluted Conditions

Flashover of power transmission line insulators due to contamination is a major threat to the reliable operation of power system. This paper deals with the analysis of leakage current characteristics of polymeric insulator using S-Transform technique in order to develop a better diagnostic tool to identify the surface condition of outdoor polymeric insulators. In this work, experiments were carried out on 11 kV silicone rubber insulator under AC voltage at different pollution levels. Moving average technique was adopted to find the trend followed by LC peak at different relative humidity conditions. S-Transform was used to find the relationship between energy and frequency content of the leakage current signal with respect to increase in pollution level over a period of time. From the S-Transform time-frequency contour analysis, point of transition to severe arcing due to increase in pollution and its thershold limit were evaluated. Reported results show that the surface condition of insulators could be easily identified from the S-Transform time-frequency analysis of leakage current signals.

Adaptive neuro-fuzzy inference system for monitoring the surface condition of polymeric insulators using harmonic content

This study deals with the analysis of leakage current (LC) characteristics of polymeric insulator due to pollution under wet conditions and also adaptive neuro-fuzzy inference system (ANFIS)-based surface condition monitoring system is developed based on LC characteristics. In this work, laboratory-based pollution performance tests were carried out on 11 kV polymeric insulator under AC voltage at different pollution levels with sodium chloride as a contaminant. LC waveforms during the experimental studies were measured. Fast Fourier Transform was employed to understand the frequency domain characteristics of the LC signal. Correlation analysis of the harmonic contents of LC during the experimental study has been performed. ANFIS framework for surface condition monitoring has been proposed based on the conclusion made in correlation analysis. Reported results of this preliminary study on 11 kV polymeric insulator shows that the development of flashover due to pollution could be easily identified from the analysis of harmonic contents of LC signal, and ANFIS framework could be used to monitor the surface condition of the polymeric insulators.