A new group of image features derived from two-dimensional linear discriminant analysis for partial discharge pattern recognition

This paper aims to improve recognition accuracies of single sources of partial discharge (PD) by employing image-oriented feature extraction and selection algorithms. 419 diversified samples of PD data acquired from typically artificial defect models, where the defect size, applied voltage and insulation aging are taken into account, are employed for algorithms validation. In the proposed method, the PD gray images are decomposed into various vectors by two-dimensional principal component analysis (2DPCA) on horizontal and vertical directions, respectively, in which 9 representative parameters are extracted from each image vector. Based on the 419 PD samples, the proposed image features are confirmed to achieve better PD recognition performances than typical image compression methods relevant to 2DPCA. To further improve the recognition performance and reduce the feature dimension, the feature selection technique based on non-dominated sorting genetic algorithm II (NSGA-II) is adopted to search the optimal 2DPCA features. By using the proposed image-oriented feature extraction and selection algorithm, fuzzy k-nearest neighbor classifier (FkNNC), back-propagation neural network (BPNN) and support vector machine (SVM) with 16-dimensional 2DPCA features can now achieve 96.4%, 94.4% and 97.5% accuracies, respectively. The increment of average recognition accuracies of 5%-7% are obtained by different classifiers compared with phase-resolved partial discharge (PRPD) statistical features in previous studies. The investigations on the recognition results relevant to image distortion, cavity discharge change with time and PD contaminated by random noises with different level confirm the robustness of the 16-dimensional 2DPCA features, which signify a great potential in applying the proposed method to field PD pattern recognition in the future.

<span>Partial discharge (PD) pattern recognition is useful to diagnose insulation condition. PD measurement data is commonly represented in phase-resolved partial discharge (PRPD) format. PRPD is useful as it provides a visible pattern for different PD source and various features can be extracted for PD pattern recognition. Shorter PRPD duration will enable more training data but the information in each data is less and vice versa. This works aims to investigate the effects of using very short duration PRPD data on the accuracy of PD pattern recognition. The results conclude that machine learning models such as Artificial Neural Network (ANN) and Support Vector Machine (SVM) are robust enough such that reduction of PRPD duration from 15-seconds to 1-second causes less than 5 % drop in the classification accuracy. However, this is only true for noise free condition. <span>When the same PD data is overlapped with random noise, the classification accuracy suffers a significant reduction up to 19%. Therefore, longer PRPD duration is recommended to withstand the effects of noise contamination.</span></span>

Widely used method for PD (partial discharge) measurement and analysis of existing underground power transmission cables is to store the detected signal pulses as PRPD (Phase Resolved Partial Discharge) data and to analyze the PD defect factors by the pattern type. Although the PRPD pattern data of various facility defects are acquired through the underground power transmission cable diagnosis, due to the PRPD data storage structure, the pulse generation information is destroyed over time, and reconversion into 3D PD pattern (PRPS: Phase Resolved Pulse Sequence) is impossible. Also recently, as a method for verifying the reliability of the power utility prevention diagnosis system, a simulated partial discharge is generated for each facility defect, and the diagnostic system verification that is capable of simultaneously measuring pulses and PD patterns using various sensors is performed, and it is necessary to develop a PD pulse generator based on simulated PRPS data in order to generate the pulses based on PRPS pattern using the existing PRPD pattern, and input the pulses into the system to perform the defect judgment performance test. To solve this problem, this study developed and verified a PD pattern generator that can generate pulses based on PRPS data, and an algorithm that converts existing PRPD pattern data currently owned by Korea Electric Power Corporation (KEPCO) to PRPS pattern data.

Transmission of electrical power requires various types of apparatus. All the apparatus and transmission-line conductors must be insulated from the high and extra-high voltages arising from the need of transmitting a large quantum of energy. As the need grows, the quality and reliability of the insulator must also grow to handle extra stresses. Hence an attempt is made to evaluate insulation in power apparatus based on the computerized analysis of partial discharge (PD) testing measurements and observations, leading to the identification of PD fault-sources of electrical insulation degradation. The database offers a decision-making aid for product development and supports condition monitoring, assessing the state of insulation. By conducting suitable experiments on two-electrode models, one does partial discharge characterization by considering one PD defect at a time. Using the database extracted from the various PD distributions attained from physical models fabricated, PD sources or defects in simple power apparatus such as surge arrestors, current transformers and artificially created defects such as slot models and rigid terminal connectors are identified successfully and evaluated. Successful recognition rate is achieved with the developed software package even in the presence of two PD sources; say, surface and internal discharges contributing to electrical insulation degradation.

Newton's method is one of the commonly used methods for acoustic emission partial discharge (AEPD) source localization in power transformers. The major problem in the AEPD source localization is the difficulty in accurately measuring the signal arrival time from the source to the multiple sensors. The exact instant at which the partial discharge (PD) occurs is not known. Therefore, instead of the absolute time, the time-delay in signal reception of each sensor with respect to the sensor nearest to the PD source is estimated. In the present study the effect of time-delay error on the accuracy of the PD source localization is analyzed through numerical experimentations. The solution of the Newtons's method in turn depends on the choice of the initial guess. Hence, different initial guesses are selected for Newton's method randomly. For a fixed set of coordinates for the four sensors and the PD source positions, the time-delays are theoretically calculated. The error is systematically increased in the calculated time-delay to form different groups of time-delays. The PD source is localized using each initial guess for all the groups of time-delays to analyze the effect of error in time-delay on accuracy of PD source localization. The error in time-delay greatly affects the AEPD source localization. Moreover, if Newton's method with a bad initial guess is used then the errors in AEPD source localizations are not systematic.

This study is focused on solution to the problem that may occur due to noise signals when using the image obtained through the conventional partial discharge preprocessing methods as inputs to the CNN-based partial discharge pattern classifier. To solve such problem, a new data preprocessing method is proposed by considering a projection technique. In the data information obtained through the conventional partial discharge preprocessing methods, data information of useless noise signal leads to the problem of performance degradation when constructing highly qualified pattern classifier based on the data information of partial discharge signal. The proposed preprocessing method called as ‘Projection’ in this study is designed to solve this problem and improve a classification performance of CNN-based partial discharge pattern classifier. First of all, through GIS simulation, one-dimensional partial discharge data is obtained as five cases such as corona discharge, floating discharge, insulator discharge, free particle discharge, and steady state (noise) in an environment with a noise signal by using a UHF sensor. After that, by applying the two conventional partial discharge preprocessing methods such as PRPS(Phase Resolved Pulse Sequence), PRPD(Phase Resolved Partial Discharge) and the proposed partial discharge preprocessing method, one-dimensional partial discharge data is transformed into 3 data types such as image set of PRPS, image set of PRPD, and image set of Projection. Finally each image set is used as inputs to the designed CNN-based partial discharge pattern classifier. Through the comparative analysis of the feature maps of each layer in CNN as well as the performance accuracy of partial discharge pattern classification for each image set, the superiority of the proposed preprocessing method is demonstrated.

This paper presents an investigation on the off-line Partial Discharge (PD) and localization for 1 unit of in-service 5 MVA 33/6.9 kV oil immersed transformer. First, Dissolved Gas Analysis (DGA) was performed to confirm the existence of PD activities. Next, offline PD measurements were carried out on both LV and HV windings. Once the transformer has been energized, PD localization was performed at different sections of the transformer tank. It is found that HV windings are having possible multiples PD activities based on offline Phase-Resolved Partial Discharge (PRPD) pattern and PD localization.

High voltage equipment can be damaged when there is a failure of the insulation. Failure would be indicated by the Partial Discharge (PD) phenomenon during the pre-breakdown condition. PD detection methods commonly used, such as thermography and acoustic emission (AE), still have some weaknesses. Based on these conditions, this study discusses the detection method of PD containing Ultra High Frequency (UHF) in air insulation using an antenna that can capture electromagnetic waves. The electrodes used are needle to plane. The variables used are the shape and distance of the electrode. Characteristics analyzed during Partial Discharge Inception Voltage (PDIV). The data retrieved would be processed so that it would display Phase Resolved Partial Discharge (PRPD). The results obtained from the antenna would be compared with the leakage current method using the High Frequency Current Transformer (HFCT). PDIV pattern can be observed in the PRPD analysis, and each electrode has the characteristics of PD at a specific phase angle. The dominant PD point electrodes occur at an angle of 331.2 ° to 342 °, the dominant PD box electrodes occur at an angle of 334.8 ° to 356.4 °, and the dominant PD blunt electrode occurs at an angle of 306 ° to 313.2 °. So, it can be concluded that the loop antenna can detect and observe PDIV patterns in air insulation.

The reliability of electrical assets is greatly influenced by the quality of their insulations. Key power installations such as power cables are manufactured with polymer-based materials as part of their insulation system. However, accelerated ageing of equipment insulations due to manifestation of defect(s), and partial discharges (PDs) can offset the operation of these systems or even lead to breakdowns. In this study, a non-deterministic model to simulate the phenomenon of repetitive discharges in a spherical air-filled cavity within a practical power cable has been investigated. In addition, the work contributes to the understanding of PD behaviour and field distribution under different ageing conditions considering changes in cavity surface conductivity. First, a section of the practical XLPE cable containing the cavity is developed in 2D using COMSOL software, and a finite element analysis (FEA) of the electric field distribution within the cable insulation is performed. The magnitude of the cavity local field, that is enough to ignite a PD, is investigated. Alongside the COMSOL model, the activity of sustained internal PD is simulated in MATLAB by introducing a random sample generating factor and adjusting the model’s parameters to obtain something close to the practical results. Furthermore, the impact of continuous PD in the power cable under different cavity dimensions and surface conductivity is likewise investigated, and a phase resolved PD (PRPD) pattern is established. The result shows that the magnitude and number of PDs per cycle increase as the cavity size and its surface conductivity increase. Finally, when the cavity surface conductivity rises, the amplitude of the electric field generated by the surface charge distribution and the number of PDs per cycle approach their maximum values.

Partial discharges (PD) measurement is a well-known technique for judgment of the condition of power transformer offline. Phase-resolved PD measurement is a normalized technique for PD tests, but noise, especially by PD-measurements onsite is sometimes difficult to reject, and a post-processing of a pattern is necessary to separate different sources. Higher-frequency-detection devices and processing strategies are useful for PD classification and identification. Recently, ultra-high-frequency (UHF) detection by means of antennas has been shown to be a promising detection system for both offline and online PD-measurements. However, it is necessary to assess whether PD source separation and classification is possible by means of pulse analysis because some additional UHF noise sources are coupled to the detected signals, and it is not clear whether different sources produce different pulses. In this study, the attenuation effect of the metallic tank of a power transformer on the inner PD activity when measured outside the tank was studied. Additionally, experiments were conducted to detect and characterize two different PD sources (internal and external discharges) using two antennas measuring the same phenomenon inside and outside of a transformer. It will also be shown that broadband UHF signals are useful for PD recognition and that a deep study of frequencies below 500 MHz can separate PD occurring inside from those occurring outside when measured with an antenna outside the tank.

This paper proposes a new method to locate the partial discharge (PD) sources inside the high-voltage power transformers with ultra-high frequency (UHF) sensors, based on the time difference of arrival (TDOA) database. A TDOA database includes the TDOA information of possible PD sources inside a power transformer, which is established under the construction of the system of the tested power transformer and the high accuracy of the minimum distance between a possible PD source and a UHF sensor. We employ the tangent transmission model of PD signals and the shortest path algorithm to solve the distance problem in case of an obstacle obstructing the transmission of PD signals. In order to verify the feasibility and accuracy of this new TDOA database method, we carry out two experiments. One experiment was conducted with a 110kV power transformer and the other was carried out with a platform for PD of electric power equipment. The experimental research results which are composed of location coordinates, transmission path and TDOA information indicate that the TDOA database method can locate single PD source as well as multiple PD sources simultaneously with the location error less than 0.3m.

GIS partial discharge data enhancement method based on self attention mechanism VAE-GAN

Partial Discharge (PD) detection is one of the important methods used to evaluate the insulation condition of in-service high voltage (HV) electrical equipment. On-site PD detection methods are preferred compared to other methods as non-intrusive sensors are easier to install and have no interruptions on the operation. An electrical PD testing utilizing High Frequency Current Transformer (HFCT) installed at the ground terminal of the in-service instrument transformer was used to detect partial discharge activities. However, the limitation of this method is the measurement often lacks of accuracy due to interference in the measured PD waveforms. Therefore, such PD signals are hard to be distinguished from the stochastic noise pulses. Hence, the characteristics of PD signals and interference signals are studied in the Phase Resolved Partial Discharge (PRPD) pattern in order to identify the extent of PD occurrence in the signals. The discharge magnitude could increase significantly because of the noise signals superposed with PD signals. Therefore a method that can remove high magnitude noise will be proposed by using statistical signal processing technique.

This paper proposes a novel phase-resolved partial discharge (PRPD) sensor embedded in a MV-class bushing for high-accuracy insulation analysis. The design, fabrication, and evaluation of a PRPD sensor embedded in a MV-class bushing aimed to achieve the detection of partial discharge (PD) pulses that are phase-synchronized with the applied primary HV signal. A prototype PRPD sensor was composed of a flexible printed circuit board (PCB) with dual-sensing electrodes, utilizing a capacitive voltage divider (CVD) for voltage measurement, the D-dot principle for PD detection, and a signal transducer with passive elements. A PD simulator was prepared to emulate typical PD defects, i.e., a metal protrusion. The voltage measurement precision of the prototype PRPD sensor was satisfied with the accuracy class of 0.2 specified in IEC 61869-11, as the maximum corrected voltage error ratios and corrected phase errors in 80%, 100%, and 120% of the rated voltage (13.2 kilovolts (kV)) were less than 0.2% and 10 min, respectively. In addition, the prototype PRPD sensor had good linearity and high sensitivity for PD detection compared with a conventional electrical detection method. According to performance evaluation tests, the prototype PRPD sensor embedded in the MV-class bushing can measure PRPD patterns phase-synchronized with the primary voltage without any additional synchronization equipment or system. Therefore, the prototype PRPD sensor holds potential as a substitute for conventional commercial PD sensors. Consequently, this advancement could lead to the enhancement of power system monitoring and maintenance, contributing to the digitalization and minimization of power apparatus.

This paper proposes a practical partial discharge (PD) severity analysis based on three factors as repetition rate, amplitude and gap time between positive and negative pattern on a phase resolved partial discharge (PRPD) pattern. The PDs are measured by using conventional and unconventional method. The PD amplitude represents PD size. Repetition rate is an average number of PD pulses per second. Gap time is a time distance between two clusters on positive and negative sides in PRPD pattern. Seven 6.6 kV motors were investigated by analysing three parameters, the results show that seven motors encountered high, moderate and low PD severity according to amplitude, repetition rate and gap time. In the first motor, the PRPD pattern shows slot discharge with a high repetition rate and a narrow gap time. This indicates the high risk to motor failure within a short period. The slot discharge was found at stator conductor through ground wall insulation to stator core. In the second motor, the PRPD pattern shows the slot discharge with high repetition rate with the gap time about 5.88 ms. Subsequently, a conventional method according to IEC60270 was performed. The problem was confirmed by visual inspection as stator slot damage by loosen wedge. Finally, the repetition rate, amplitude and gap time analysis were performed with another 5 motors. The results show the different PD severity that were further investigated and confirmed by visual inspection. This PD severity analysis could help to easily analyse, identify problem, predict PD severity and possibility of failure.