Classification Of Partial Discharge Sources Research Articles

Separation and Classification of Partial Discharge Sources in Substations

Separation and Classification of Partial Discharge Sources in Substations

Classification of Partial Discharge Sources in Ultra-High Frequency Using Signal Conditioning Circuit Phase-Resolved Partial Discharges and Machine Learning

This work presents a methodology for the generation and classification of phase-resolved partial discharge (PRPD) patterns based on the use of a printed UHF monopole antenna and signal conditioning circuit to reduce hardware requirements. For this purpose, the envelope detection technique was applied. In addition, test objects such as a hydrogenerator bar, dielectric discs with internal cavities in an oil cell, a potential transformer and tip–tip electrodes immersed in oil were used to generate partial discharge (PD) signals. To detect and classify partial discharges, the standard IEC 60270 (2000) method was used as a reference. After the acquisition of conditioned UHF signals, a digital signal filtering threshold technique was used, and peaks of partial discharge envelope pulses were extracted. Feature selection techniques were used to classify the discharges and choose the best features to train machine learning algorithms, such as multilayer perceptron, support vector machine and decision tree algorithms. Accuracies greater than 84% were met, revealing the classification potential of the methodology proposed in this work.

A Review on the Classification of Partial Discharges in Medium-Voltage Cables: Detection, Feature Extraction, Artificial Intelligence-Based Classification, and Optimization Techniques

Medium-voltage (MV) cables often experience a shortened lifespan attributed to insulation breakdown resulting from accelerated aging and anomalous operational and environmental stresses. While partial discharge (PD) measurements serve as valuable tools for assessing the insulation state, complexity arises from the presence of diverse discharge sources, making the evaluation of PD data challenging. The reliability of diagnostics for MV cables hinges on the precise interpretation of PD activity. To streamline the repair and maintenance of cables, it becomes crucial to discern and categorize PD types accurately. This paper presents a comprehensive review encompassing the realms of detection, feature extraction, artificial intelligence, and optimization techniques employed in the classification of PD signals/sources. Its exploration encompasses a variety of sensors utilized for PD detection, data processing methodologies for efficient feature extraction, optimization techniques dedicated to selecting optimal features, and artificial intelligence-based approaches for the classification of PD sources. This synthesized review not only serves as a valuable reference for researchers engaged in the application of methods for PD signal classification but also sheds light on potential avenues for future developments of techniques within the context of MV cables.

Partial Discharge Data Augmentation Based on Improved Wasserstein Generative Adversarial Network With Gradient Penalty

The partial discharge (PD) classification for electric power equipment based on machine learning algorithms often leads to insufficient generalization ability and low recognition accuracy. To solve the problem, this paper develops an improved Wasserstein generative adversarial network with gradient penalty (WGAN-GP) based data augmentation model. The improved WGAN-GP model can generate data samples to supplement the low-data input set in PD source classification. Firstly, an improved WGAN-GP model with conditional generation is trained and various new data samples are generated. Then the new data samples are utilized to expand the raw data set. Finally, the expanded data set is trained to get a new PD classifier. Experimental results demonstrate the proposed model can generate new high-quality data samples more stably. Moreover, the proposed method can suppress the over-fitting risk caused by low-data or imbalanced data distributions and the classification accuracy is effectively improved.

A novel image‐orientation feature extraction method for partial discharges

Partial discharge identification is of great significance in monitoring power equipment. Although substantial work has been done in partial discharge pattern recognition, most studies have been performed in noise-free environments. To improve the accuracy of partial discharge pattern recognition, this paper introduces a partial discharge image feature extraction method based on upright speeded-up robust features. Each group of phase-resolved pulse sequence data is converted into grayscale images to construct a sample library of partial discharge defects. Upright speeded-up robust features is used to extract features in grayscale images. The improved support vector machine is used to achieve the best classification of partial discharge sources. The sensitivity of local features to different phase resolutions and different image resolutions of partial discharge phase-resolved pulse sequence patterns was investigated, and the optimal phase resolution and image resolution were used to construct phase-resolved pulse sequence patterns. In addition, the recognition effect of this feature extraction method under different noise conditions was also analysed. The results prove that upright speeded-up robust features can effectively deal with noisy data. The results of this research can provide references for the storage setting and recognition of three-dimensional images of on-site partial discharge data.

Generative Adversarial Networks used for latent space Optimization: a comparative study for the Classification of Partial Discharge Sources

Hydrogenerators are strategic assets for power utilities. Their reliability and availability can lead to significant benefits. For decades, monitoring and diagnosis of hydrogenerators have been at the core of maintenance strategies. The main cause of hydrogenerator breakdown comes from failure of its high voltage stator, which is a major component of hydrogenerators. In our previous study, it was shown that more than 85% of stator failure mechanisms indicate the presence of Partial Discharges (PD) activity. PD are minute sparks that occur within voids inside high voltage insulation or in the air around the insulating system. Each PD event does not cause immediate failure, but it will slowly erode the insulation system and will lead to breakdown in years to decades. PD signal can be detected from the lead of the hydrogenerator while it is running, thus allowing for on-line diagnosis. Hydro-Québec has been collecting more than 33.000 unlabeled PD measurement files over the last decades including two types of measurement instruments. One of the instruments used is the Partial Discharge Analyzer (PDA). PDs have several different sources and each source is characterized by a specific signature. It is therefore essential to be able to automatically recognize the nature of the DPs in order to anticipate possible degradation. Expert rules to characterize these PD signals exist but these rules cannot be used as an automatic classification tool. Indeed, for certain ambiguous cases (conflict between classes) or the presence of several signatures at the same time (multi-classes), the expert's judgement remains essential.
 A Variationel AutoEncoder (VAE) is used for dimension reduction and projection into a 2D latent space to analyze the training data and then classify it. The 2D latent space of the VAE allows the data space to be restructured and reorganized to anticipate the performance of the classifier. The problem is how to optimize this latent space and thus obtain the best distribution of the different sources of PDs to maximize the chances of good responses from the classifier? To our knowledge, there is currently no method in the literature that clearly answers this question. What is certain, however, is that the optimization of the VAE learning is directly related to the quality of the learning base, i.e. a large size and a perfectly balanced database (all the cases are present and sufficiently represented). The objective of this paper is to compare the quality of the latent space obtained from the experts' rules with a latent space obtained directly from the input signal in an « End-to-End » approach.
 The first method concerns an original unsupervised deep learning method for PD recognition. Instead of labelling the PD measurement files by the expert for a supervised learning process, we use the rules developed by the experts of Hydro-Québec to create a feature vector from recognizable PD signatures. Indeed, labelling a sufficient quantity of signatures for a supervised approach is very time-consuming and therefore cannot be implemented. This is a common problem in the industry where more and more operational data is available but cannot be labelled by experts, who are busy with other tasks. Expert knowledge is then injected into a characteristic and feature vector. In the second method, several Generative Adversarial Networks (GANs) associated with several types of PDs are thus used to generate artificial signals in order to increase the size of the learning base and especially to balance it. A new latent space is thus obtained from the learning of the VAE exclusively carried out on data generated by the GANs.
 Validation tests based on the 33,000 measurements with metrics for evaluating the performances of the various latent spaces are used.

Overview and Partial Discharge Analysis of Power Transformers: A Literature Review

The high voltage power transformer is the critical element of the power system, which requires continuous monitoring to prevent sudden catastrophic failures and to ensure an uninterrupted power supply. The most common failures in the transformer are due to partial discharge (PD) in electrical insulations which are the results of the insulation degradation over time. Different approaches have been proposed to monitor, detect, and locate the partial discharge in power transformers. This paper reviews and evaluates the current state-of-the-art methods for PD detection and localization techniques, and methodologies in power transformers. Detailed comparisons of PD detection techniques have been identified and discussed in this paper. The drawbacks and challenges of different partial discharge measurement techniques have been elaborated. Finally, brief reviews of PD denoising signals, feature extraction of PD signals, and classification of partial discharge sources have been addressed.

Deep Convolutional Variational Autoencoder as a 2D-Visualization Tool for Partial Discharge Source Classification in Hydrogenerators

Hydrogenerators are strategic assets for power utilities. Their reliability and availability can lead to significant benefits. For decades, monitoring and diagnosis of hydrogenerators have been at the core of maintenance strategies. A significant part of generator diagnosis relies on Partial Discharge (PD) measurements, because the main cause of hydrogenerator breakdown comes from failure of its high voltage stator, which is a major component of hydrogenerators. A study of all stator failure mechanisms reveals that more than 85% of them involve the presence of PD activity. PD signal can be detected from the lead of the hydrogenerator while it is running, thus allowing for on-line diagnosis. Hydro-Quebec has been collecting more than 33 000 unlabeled PD measurement files over the last decades. Up to now, this diagnostic technique has been quantified based on global PD amplitudes and integrated PD energy irrespective of the source of the PD signal. Several PD sources exist and they all have different relative risk, but in order to recognize the nature of the PD, or its source, the judgement of experts is required. In this paper, we propose a new method based on visual data analysis to build a PD source classifier with a minimum of labeled data. A convolutional variational autoencoder has been used to help experts to visually select the best training data set in order to improve the performances of the PD source classifier.

Partial Discharges Pattern Recognition of Transformer Defect Model by LBP & HOG Features

Partial discharge (PD) measurement and identification have great importance to condition monitoring of power transformers. In this paper, a new method for recognition of single and multi-source of PD based on extraction of high level image features has been introduced. A database, involving 365 samples of phase-resolved PD (PRPD) data, is developed by measurement carried out on transformer artificial defect models (having different sizes of defect) under a specific applied voltage, to be used for proposed algorithm validation. In the first step, each set of PRPD data is converted into grayscale images to represent different PD defects. Two “image feature extraction” methods, the Local Binary Pattern (LBP), and the Histogram of Oriented Gradient (HOG), are employed to extract features from the obtained gray scale images. Different variants of Support Vector Machine (SVM) are adjusted for optimal classification of PD sources in this process. Impact of the employed parameters in the image processing such as image resolution, random noise, and phase shift, on identification accuracy is investigated and addressed. It is shown that by using HOG-SVM method 99.3% accuracy can be achieved. This is hardly affected by various external factors. Two case studies have been conducted on multi-source PD for evaluating the performance of the proposed algorithm. A void defect is implemented into the transformer model and the resultant recorded signal is used for the study. The DBSCAN algorithm is used as the mean of PD source clustering and sub-PRPD pattern development. It is shown that HOG-SVM method has superior performance in identifying active sources, under sub-PRPD pattern application.

A Review of Online Partial Discharge Measurement of Large Generators

Online partial discharge (PD) measurements have long been used as an effective means to assess the condition of the stator windings of large generators. An increase in the use of PD online measurement systems during the last decade is evident. Improvements in the detection capabilities are partly the reason for the increased popularity. Another reason has been the development of digital signal processing techniques. In addition, rapid progress is being made in automated single PD source classification. However, there are still some factors hindering wider application of the system, such as the complex PD mechanism and PD pulse propagation in stator windings, the presence of detrimental noise and disturbances on-site, and multiple PD sources occurring simultaneously. To avoid repetition of past work and to provide an overview for fresh researchers in this area, this paper presents a comprehensive survey of the state-of-the-art knowledge on PD mechanism, PD pulse propagation in stator windings, PD signal detection methods and signal processing techniques. Areas for further research are also presented.

Classification of partial discharge sources in mica-epoxy-glass insulation sample using statistical analysis

Partial Discharge (PD) in rotating machine insulation system is deleterious. Even though the main insulation of rotating machine is Mica, which is highly PD resistant, the discharges taking place in slot region and end windings are highly deteriorating to insulation system. In this paper, PD measurements are taken in Mica-Epoxy-Glass insulation sample using cylindrical-plane electrode system. The sample contains a defined void on the surface. Distinguished Phase Resolved Partial Discharge (PRPD) patterns are obtained for different location of void. The different PRPD patterns obtained corresponds to internal void in the bulk of insulation, void between high voltage electrode and insulation surface, void between ground electrode and insulation surface; and surface discharge. The PRPD patterns obtained from void between high voltage electrode and insulation surface, in the actual scenario, indicates PD originating near the conductor surface inside the insulation system of rotating machines. The PRPD patterns obtained from void between ground electrode and insulation surface indicates PD originating on the surface of insulation such as slot discharge, end winding discharge in rotating machine insulation system. The variation of PD parameters like Charge magnitude (q) with respect to applied voltage is shown for different location of void. Further statistical parameters like skewness and kurtosis are calculated for charge distribution (n-q) and phase distribution (n-Φ) for different PRPD patterns. It is inferred that statistical analysis of PD parameters is a good tool to classify of partial discharge sources.

Classification and separation of partial discharge ultra‐high‐frequency signals in a 252 kV gas insulated substation by using cumulative energy technique

Ultra-high-frequency (UHF) method is regarded as an effective approach for partial discharge (PD) detection in gas insulated substation (GIS). The feature parameters representing UHF signal characteristics can be extracted from its waveform, and applied to PD source classification and mixed signals separation. In this study, an UHF signal feature extraction algorithm based on cumulative energy (CE) technique is proposed. The CE functions in time domain (TCE) and frequency domain (FCE) are calculated from UHF waveforms and their fast Fourier transform spectrums, respectively. The mathematical morphology gradient (MMG) operation is applied to TCE and FCE to characterise their rising behavior. The feature parameters including width, area and sharpness are extracted from CEs and MMGs in both time and frequency domain. Moreover, the extracted features are applied to UHF signals classification and mixed signals separation. First, experiments on four kinds of typical defects in a 252 kV GIS are performed, and the classification performance of the extracted features is examined with the acquired signals. Second, by clustering the extracted features with fuzzy maximum-likelihood algorithm, mixed UHF signals originated from multiple PD sources are successfully separated. The results indicate that the proposed features are effective for representing UHF signal characteristics.

Autonomous classification of PD sources within three-phase 11 kV PILC cables

To allow utilities to fulfill self-imposed and regulative performance targets that apply to them, the demand for new tools to help judge the health of modern power distribution networks has increased. The analysis of partial discharge (PD) signals has been identified as a potential diagnostic tool for the condition monitoring of HV plant. In order to investigate the PD activity produced by a range of defects within three-phase paper insulated lead covered (PILC) distribution cable under rated conditions, an experiment has been developed. The experiment incorporates a commercially available on-line PD measurement system employing a high frequency current transformer (HFCT) to record PD data in a manner that is currently in operation in the UK. By replicating field conditions and using realistic hardware to collect experiment data, that any findings or analysis tools developed during this investigation are directly transferable to use in the field. Four defective cable samples, each containing different imperfections that are known to reduce in-service plant life have been fabricated and extensively PD tested. The raw experiment data was processed to produce a dataset containing a range of features from individual PD pulses including time, frequency and time-frequency information. This data was used to optimize and train several support vector machine (SVM) models to perform automated pulse classification. Four SVM models were tested using different combinations of pulse features to identify which characteristics were most effective at transferring source dependent information for classification. The results of the automated algorithm validated the approach returning a classification accuracy of 91.1%.

Pattern recognition techniques and their applications for automatic classification of artificial partial discharge sources

Partial discharge (PD) source classification aims to identify the types of defects causing discharges in high voltage (HV) equipment. This paper presents a comprehensive study of applying pattern recognition techniques to automatic PD source classification. Three challenging issues are investigated in this paper. The first issue is the feature extraction for obtaining representative attributes from the original PD measurement data. Several approaches including stochastic neighbour embedding (SNE), principal component analysis (PCA), kernel principal component analysis (KPCA), discrete wavelet transform (DWT), and conventional statistic operators are adopted for feature extraction. The second issue is the pattern recognition algorithms for identifying various types of PD sources. A novel fuzzy support vector machine (FSVM) and a variety of artificial neural networks (ANNs) are applied in the paper. The third issue is the identification of multiple PD sources, which may occur in HV equipment simultaneously. Two approaches are proposed to address this issue. To evaluate the performance of various algorithms in this paper, extensive laboratory experiments on a number of artificial PD models are conducted. The classification results reveal that FSVM significantly outperforms a number of ANN algorithms. The practical PD sources classification for HV equipment is a considerable complicated problem. Therefore, this paper also discusses some issues of meaningful application of the above proposed pattern recognition techniques for practical PD sources classification of HV equipment.

Partial Discharge Source Classification and De-Noising in Rotating Machines Using Discrete Wavelet Transform and Directional Coupling Capacitor

This paper introduces a new method to separate PD1 from other disturbing signals present on the high voltage genera-tors and motors. The method is based on combination of a pattern classifier, the Discrete Wavelet Transform (DWT), to de-noise PD and Time-Of-Arrival method to separate PD sources. Furthermore, it will be shown that it can recognize PD sources including rotating machine’s internal and external discharge pulses (e.g. on the bus bar).

Toward Automatic Classification of Partial Discharge Sources With Neural Networks

In this letter, we propose an automatic classification scheme of discharge sources on the basis of Fourier spectrum for received electromagnetic (EM) pulses. Confirming the reproducibility of EM pulses from each source validates this scheme. The recognition rate for six discharge sources is 80% or better. The feature of our system is time efficient and to treat hundreds of pulses.

Fractal image compression for classification of PD sources

The fractal image compression technique has a unique feature due to which physical position of blocks/regions in the input image can be extracted directly from the compressed data. Applying this technique, /spl phi/-q-n partial discharge (PD) patterns (treated as an image) are compressed and stored as affine transformations. These transformations then are used directly to extract the embedded pattern features, which are classified by a neural network. The novel route to PD pattern classification described in this paper thus addresses both the tasks of compression and feature extraction in a single step. The task of compression is essential to store and handle large quantities of pattern data acquired, especially during on-line monitoring of PD in power apparatus. Results presented illustrate that this approach can address satisfactorily the tasks of compression and classification of PD patterns.

Classification of partial discharge sources in gas-insulated substations using novel preprocessing strategies

Partial discharge activity in GIS can indicate impending breakdown. The activity is recorded as characteristic point on wave records which are classified into defect types by expert engineers. Classification assists with the assessment of the risk of catastrophic failure. An automatic technique has been developed aimed at replicating the strategy used by an expert during manual classification. Preprocessing techniques have been selected which implicitly incorporate the processes used by the expert rather than applying explicit rules. Information from the records pertinent to classification is extracted using mathematical morphology techniques allowing substantial compression of the data. An artificial neural network trained with such data has been shown to produce results indicating that classification matched that of the expert.