Phase Resolved Partial Discharge Research Articles

PMSNet: Multiscale Partial-Discharge Signal Feature Recognition Model via a Spatial Interaction Attention Mechanism

Partial discharge (PD) is a localized discharge phenomenon in the insulator of electrical equipment resulting from the electric field strength exceeding the local dielectric breakdown electric field. Partial-discharge signal identification is an important means of assessing the insulation status of electrical equipment and critical to the safe operation of electrical equipment. The identification effect of traditional methods is not ideal because the PD signal collected is subject to strong noise interference. To overcome noise interference, quickly and accurately identify PD signals, and eliminate potential safety hazards, this study proposes a PD signal identification method based on multiscale feature fusion. The method improves identification efficiency through the multiscale feature fusion and feature aggregation of phase-resolved partial-discharge (PRPD) diagrams by using PMSNet. The whole network consists of three parts: a CNN backbone composed of a multiscale feature fusion pyramid, a down-sampling feature enhancement (DSFB) module for each layer of the pyramid to acquire features from different layers, a Transformer encoder module dominated by a spatial interaction–attention mechanism to enhance subspace feature interactions, a final categorized feature recognition method for the PRPD maps and a final classification feature generation module (F-Collect). PMSNet improves recognition accuracy by 10% compared with traditional high-frequency current detection methods and current pulse detection methods. On the PRPD dataset, the validation accuracy of PMSNet is above 80%, the validation loss is about 0.3%, and the training accuracy exceeds 85%. Experimental results show that the use of PMSNet can greatly improve the recognition accuracy and robustness of PD signals and has good practicality and application prospects.

Passive Wireless Partial Discharge Sensors with Multiple Resonances.

Partial discharge (PD) is the dominant insulating defect in Gas-Insulated Switchgear (GIS). The existing detection methods are mainly divided into built-in wire-connected disk antennas with destructive drilling and external ultra-high frequency antennas with poor anti-interference ability. This research introduces a passive wireless PD sensor implanted inside GIS on the observation window. The sensor is implemented by a sheeting branch-inductor with multiple resonances which is able to enhance detection sensitivity. A coaxially aligned readout circuit, positioned outside the GIS, interrogates the PD sensor to wirelessly obtain the PD signal. The proposed sensing scheme improves signal-to-noise ratio and ensures minimal disruption to the electric field distribution inside GIS. An experimental setup was established in a controlled laboratory environment to benchmark the multi-resonant sensor against the commercial UHF sensor. A 2.5-times enhancement of signal strength was observed. Since our sensor was implanted inside the GIS, a high signal-to-noise ratio (68.82 dB) was obtained. Moreover, we constructed a wireless calibration test to investigate the accuracy of the proposed sensor. The precision of the signal test was as high as 0.72 pC. The pulse phase distribution information was collected to demonstrate a phase-resolved partial discharge (PRPD) pattern. The experiment results validate the effectiveness of the proposed method and demonstrate excellent performance in PD detection.

Novel Self-Organizing Probability Maps Applied to Classification of Concurrent Partial Discharges from Online Hydro-Generators

In this paper, we present an unprecedented method based on Kohonen networks that is able to automatically recognize partial discharge (PD) classes from phase-resolved partial discharge (PRPD) diagrams with features of various simultaneous PD patterns. The PRPD diagrams were obtained from the stator windings of a real-world hydro-generator rotating machine. The proposed approach integrates classification probabilities into the Kohonen method, producing self-organizing probability maps (SOPMs). For building SOPMs, a group of PRPD diagrams, each containing a single PD pattern for training the Kohonen networks and single- and multiple-class-featured samples for obtaining final SOPMs, is used to calculate the probabilities of each Kohonen neuron to be associated with the various PD classes considered. At the end of this process, a self-organizing probability map is produced. Probabilities are calculated using distances, obtained in the space of features, between neurons and samples. The so-produced SOPM enables the effective classification of PRPD samples and provides the probability that a given PD sample is associated with a PD class. In this work, amplitude histograms are the features extracted from PRPDs maps. Our results demonstrate an average classification accuracy rate of approximately 90% for test samples.

Innovative Approach for Detecting Early-Stage Partial Discharges in Instrument Transformers via Ultrasound and Random Forest Analysis

This article introduces a novel technique for detecting and classifying Partial Discharges in Instrument Transformers, addressing the gradual breakdown of external insulation in high-voltage electrical equipment through ultrasound measurements. The use of hand-held probe-microphones for ultrasonic sensing gains prominence for its versatility and online diagnostic capabilities. The proposed method combines insights into partial discharge types and the pollution level within the equipment, thereby transforming ultrasonic readings into useful information and facilitating informed decision-making. Laboratory tests simulate real-world conditions to which current and voltage transformers of 145 kV and 245 kV are subjected. These tests result in ultrasonic and apparent charge measurements, also known as Phase-Resolved Partial Discharges (PRPD). A random forest model achieves over 92 % accuracy in classifying ultrasonic signals into eight class: normal, light partial discharge, light corona, corona, light superficial, light saline pollution, moderate saline pollution and heavy saline pollution; enhancing the understanding and predictive maintenance of instrument transformers.

Unknown PD distinction in HVAC/HVDC by antenna-sensor with pulse sequence analysis

Ultra-high frequency (UHF) antenna-sensors are becoming popular for non-invasive detection of unwanted electric discharge i.e., partial discharge (PD) in high-voltage (HV) systems. Early PD signals are weak for detection and classification by UHF antenna-sensors. Early PD detection and distinction are crucial to prevent equipment failure. Typically, PD signals are distinguished in HVAC by phase resolved PD (PRPD) patterns. Whereas in HVDC, some unconventional methods are applied. However, a blind distinction of PDs under unknown HVAC/HVDC conditions still remains a challenge. In this article, we address this issue by using a lotus-shaped UHF antenna-sensor for early PD detection. Unlike cut-and-try technique-based conventionally designed bio-inspired antennas, our sensor is designed by a precisely derived equivalent circuit model to systematically optimize antenna gain over size to detect early PDs. The fabricated sensor has a size of 18×11 cm2, an average realized gain of 3.05 dBi in 740–1600 MHz frequencies, and a sensitivity index of 154.04 dBi/m2. The sensor prototype is applied to wirelessly distinguish PD signals from unknown sources under HVAC and HVDC by pulse sequence analysis. Early detection, characterization, and distinction of unknown PD signals are ensured by the proposed sensor and interpretation technique. This work offers a distinctive PD sensing method for HVAC/HVDC converter stations.

Investigation of partial discharge characteristics in XLPE cable insulation under increasing electrical stress

Insulation degradation in power components is a looming issue that can have a significant impact on the reliability of power system if not attended timely. Partial discharge (PD) diagnostics is a key technique used for the condition monitoring and health assessment of insulation. Inception of PD is a primary indicator which shows degradation and decreased local dielectric strength of the insulation. PD magnitude can increase with time and level of stress, which may result in failure of insulation. This article investigates the behavior of PD characteristics in a medium voltage (MV) cross-linked polyethylene (XLPE) cable sample, containing a defect at the cable termination, under elevated electrical stresses. PD behavior is studied by investigating the key PD characteristics, such as partial discharge inception voltage (PDIV), phase of occurrence (ɸ), mean amplitude (Vmean), pulse repetition rate (PRR), and phase span (ɸspan). These quantities are extracted from a phase-resolved partial discharge (PRPD) pattern using a pulse detection algorithm. Later, these characteristics are analyzed in correlation with the electrical stress. Various regression models are implemented and compared to find the best fit model that represents trending attributes of major PD characteristics. The presented study can be used as an effective process to analyze the measured PD data for evaluation of the insulation condition in the power components.

Multi-source partial discharge pattern recognition algorithm based on DCGAN-Yolov5

This study aims to overcome the complication that deep learning-based pattern recognition in partial discharge (PD) diagnosis of gas-insulated switchgear (GIS) can only identify single-source partial discharge but not multi-source partial discharge. Specifically, a GIS multi-source partial discharge detection algorithm based on Deep Convolution Generative Adversarial Networks and You Only Look Once (DCGAN-YOLOv5) is proposed. First, the Phase Resolved Partial Discharge (PRPD) features of multi-source PD are analyzed, a GIS experiment platform is established, and four typical PD defects are simulated. Besides, sample data are collected, and the DCGAN network is used for sample expansion. Then, a YOLOv5 network model is designed, and a spatial and channel attention mechanism is added to the feature extraction network with a positive sample equilibrium strategy. Finally, the effectiveness of the proposed algorithm is verified using laboratory data and field data collected from a 220 kV substation. The experimental results demonstrate that the proposed algorithm can effectively detect the multi-source PD features in PRPD patterns under complex noise and thus successfully identify the types of multi-source PD. The mean Average Precision (mAP) can reach 98.4%. The precision of single-source PD and multi-source PD can reach 95.2% and 89.3%, when testing with field data.

Supervised Contrastive Learning for Fault Diagnosis Based on Phase-Resolved Partial Discharge in Gas-Insulated Switchgear

Supervised contrastive learning (SCL) has recently emerged as an alternative to conventional machine learning and deep neural networks. In this study, we propose an SCL model with data augmentation techniques using phase-resolved partial discharge (PRPD) in gas-insulated switchgear (GIS). To increase the fault data for training, we employ Gaussian noise adding, Gaussian noise scaling, random cropping, and phase shifting for supervised contrastive loss. The performance of the proposed SCL was verified by four types of faults in the GIS and on-site noise using an on-line ultra-high-frequency (UHF) partial discharge (PD) monitoring system. The experimental results show that the proposed SCL achieves a classification accuracy of 97.28% and outperforms the other algorithms, including support vector machines (SVM), multilayer perceptron (MLP), and convolution neural networks (CNNs) in terms of classification accuracy, by 6.8%, 4.28%, 2.04%, respectively.

The Design, Fabrication, and Evaluation of a Phase-Resolved Partial Discharge Sensor Embedded in a MV-Class Bushing.

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.

The Influence of Cavity Size and Location Within Insulation Paper on the Partial Discharge Activities

This paper examines the influence of cavity size and location in the insulation paper on the Partial Discharge (PD) activities through Finite Element Method (FEM). The model consisted of a conductor wrapped with insulation paper. Two different locations of the spherical cavities were introduced in this study, namely Location 1 (L1) and Location 2 (L2), located at the center and left corner of the insulation paper. The model introduced two different sizes of cavities with diameters of 0.5 mm and 0.8 mm. An AC voltage source of 17 kV, 50 Hz, was applied at the conductor while the bottom of the insulation paper was grounded. The real and apparent PDs were obtained by integrating the current flowing through the cavity and ground electrode with the respective surface area. The simulation was carried out for 100 cycles. The resultant model was used to study the PD occurrence, magnitude, and Phase Resolved Partial Discharge (PRPD) within the insulation paper. It is found that the large cavity size produces a lower number of PD occurrences per cycle than the small cavity size. The large cavity size produces a higher charge magnitude as compared with the small cavity size. The PD occurrence per cycle and charge magnitude are higher for the cavity location at L1 compared to L2. The PRPD yields the same pattern for cavity location at L1 and L2, whereby the differences are only on the charge magnitude and PD occurrence per cycle.

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

The reliability of geographic information system (GIS) partial discharge fault diagnosis is crucial for the safe and stable operation of power grids. This study proposed a data enhancement method based on a self-attention mechanism to optimize the VAE-GAN method and solve the problem of the lack of partial discharge samples and the unbalanced distribution between different defects. First, the non-subsampled contourlet transform (NSCT) algorithm was used to fuse the UHF and optical partial discharge signals to obtain a photoelectric fusion phase resolved partial discharge (PRPD) spectrum with richer information. Subsequently, the VAE structure was introduced into the traditional GAN, and the excellent hidden layer feature extraction ability of the VAE was used to guide the generation of the GAN. Then, the self-attention mechanism was integrated into the VAE-GAN, and the Wasserstein distance and gradient penalty mechanisms were used to optimize the network loss function and expand the sample sets to an equilibrium state. Finally, the KAZE and polar coordinate distribution entropy methods were used to extract the expanded samples. The eigenvectors of the sets were substituted into the long short-term memory (LSTM) network for partial discharge fault diagnosis. The experimental results show that the sample generation quality and fault diagnosis results of this method were significantly better than the traditional data enhancement method. The structure similarity index measure (SSIM) index is increased by 4.5% and 21.7%, respectively, and the average accuracy of fault diagnosis is increased by 22.9%, 9%, 5.7%, and 6.5%, respectively. The data enhancement method proposed in this study can provide a reference for GIS partial discharge fault diagnosis.

Development of a Microcontroller-Based Phase-Resolved Partial Discharge Measurement System With Application to the Monitoring of Flash Sintering Discharge Patterns

Development of a Microcontroller-Based Phase-Resolved Partial Discharge Measurement System With Application to the Monitoring of Flash Sintering Discharge Patterns

Generator Stator Partial Discharge Pattern Recognition Based on PRPD-Grabcut and DSC-GoogLeNet Deep Learning

Partial discharge (PD) pattern recognition of typical defects from generator stator bars is the basis of generator condition monitoring and fault diagnosis. A PD pattern recognition method for generator stator bars based on a phase-resolved partial discharge graph cut (PRPD-Grabcut) and Depthwise Separable Convolution GoogLeNet (DSC-GoogLeNet) deep learning neural network is proposed in this paper. First, five typical defects are designed on stator bars in the laboratory. A long-term high voltage test is carried out, and 37500 PRPD original graphs are obtained. Second, a PRPD-Grabcut method based on image segmentation is proposed, which is designed to extract key components of the PRPD map. Finally, a DSC-GoogLeNet based PD pattern recognition method is proposed, which combines the GoogLeNet inception module and depth-wise separable convolution. Experimental results show that the PRPD-Grabcut contributes to certain improvements in the recognition accuracy and training efficiency of the neural network. The DSC-GoogLeNet shows superiority in recognition accuracy, cross-entropy loss, and training time compared to a variety of existing lightweight neural networks. In addition, compared with other networks, the DSC-GoogLeNet greatly improves the recognition accuracy of PD types with similar but different risk levels for stator insulation.

Ensemble Deep-Learning Model for Phase-Resolved Partial Discharge Diagnosis in Hydrogenerators

Condition monitoring of hydrogenerators is extremely essential for the optimisation of the power supply system’s maintenance, especially in a context where energy consumption will increase more and more. Industry investigations have consistently shown that the electrical insulation used in stator windings is one of the most potential components for breakdown. One of the major causes of this breakdown was shown to be partial discharges (PDs). PDs are designated as defects in electrical insulation, and their presence may cause future insulation failures in equipment. Online monitoring of PD activity is essential to anticipate degradation and avoid a sudden shutdown with a high economic impact. Thus, automating the recognition of PD sources by an intelligent system is a major issue in a Condition-Based Maintenance (CBM) process for hydrogenators. First, a method based on the U-Net model is used to isolate the main sources of a Phase-Resolved PD signal (PRPD). Afterwards, a set of deep learning models (DLM) is then applied to automatically recognize the PD sources. Finally, a decision-making method is then proposed to find the optimal output category considering the posterior and the prior probability estimated by various individual models. Experimental results on real signals from hydrogenerators show an accuracy of 87% on the detection of gap sources, and respectively 91%, 95%, 96% and 94% for the Internal, Corona, Slot and Delamination PD. The proposed decision-making method shows a significant advantage of the final decision over the performances of each individual DL model.

Deep Learning and Long-Duration PRPD Analysis to Uncover Weak Partial Discharge Signals for Defect Identification

This study focuses on improving the defect recognition accuracy under weak partial discharges (PDs) in epoxy resin through phase-resolved partial discharge (PRPD) analysis. The method is to refine the data rather than enhance the algorithm. Two measurement conditions are compared until PRPD pattern saturation is achieved: one-minute and one-hour durations. The PD data specifically target three void types located at different positions within the epoxy material. The aim is to evaluate how the presence of weak PDs at the PD extinction voltage (PDEV) influences defect recognition accuracy. This research sheds light on the potential implications of neglecting the significance of weak PD signals in defect detection. A convolutional neural network (CNN) model is trained using PRPD data recorded at the repetitive PD inception voltage (RPDIV) and tested using the new PRPD data from both conditions recorded from a lower PDIV to a PDEV. The trained CNN model achieves a defect recognition accuracy of 100% for a one-hour duration, highlighting the importance of not neglecting weak PD signals. This emphasizes the significance of extended measurement duration and pattern saturation in capturing and analyzing weak PD signals for an improved defect recognition. This study contributes to the advancement of practical applications by understanding the behavior of the epoxy material and enhancing defect detection techniques.

Partial Discharge Pattern-Recognition Method Based on Embedded Artificial Intelligence

This paper proposes a method for detecting and recognizing partial discharges in high-voltage (HV) equipment. The aim is to address issues commonly found in traditional systems, including complex operations, high computational demands, significant power consumption, and elevated costs. Various types of discharges were investigated in an HV laboratory environment. Discharge data were collected using a high-frequency current sensor and a microcontroller. Subsequently, this data underwent processing and transformation into feature sets using the phase-resolved partial discharge analysis technique. These features were then converted into grayscale map samples in PNG format. To achieve partial discharge classification, a convolutional neural network (CNN) was trained on these samples. After successful training, the network model was adapted for deployment on a microcontroller, facilitated by the STM32Cube.AI ecosystem, enabling real-time partial discharge recognition. The study also examined storage requirements across different CNN layers and their impact on recognition efficacy. To assess the algorithm’s robustness, recognition accuracy was tested under varying discharge voltages, insulation media thicknesses, and noise levels. The test results demonstrated that the algorithm could be effectively implemented on a microcontroller, achieving a recognition accuracy exceeding 98%.

Use of partial discharges measurements and video recordings to investigate the influence of relative humidity on zinc oxide subjected to high electric fields

This study investigates the influence of humidity on the high voltage behaviour of zinc oxide porous pellets at room temperature, using the phase resolved partial discharge (PRPD) method. The experimental configuration corresponds to the one that would be used for flash sintering cylindrical ZnO pellets at low temperatures in possibly scalable conditions: planar Pt electrodes without Pt paste. The study explores the incubation period by increasing the 50 Hz AC electric field up to 8 kV cm−1 (applied by steps or with a continuous ramp) in an air atmosphere with varying relative humidity (RH). Experiments were repeated on several samples and showed that the maximum amplitude of PDs decreased while their number increased as the RH increased. With the support of video recording of the experiments, different characteristics in the PD pattern evolution with increasing AC voltage could be attributed to various locations between the electrodes, at the sample surface, or at the interface with the electrodes. By examining the PRPDs, it was possible to identify two distinct types of PDs having different thresholds of inception: one type corresponds to PDs occurring mostly at the triple junction ‘ZnO-platinum-air’ or in the ZnO-electrodes gap and depends strongly on the RH level and; the other type corresponds to electric arcs between the electrodes, with an inception threshold much less affected by the RH level.

Comparative Study on Partial Discharge Characteristics of Seven Accessory Defects Under Four On-Site Testing Voltages of a 10-kV Cable Line

Due to the increase in voltage levels and line lengths of power cables, the commonly used alternating current resonance (ACR) voltage is challenging to meet the growth rate of the capacitance of ultra-high-voltage cables for the on-site partial discharge (PD) tests. PD research on power-frequency-like voltages such as damped alternating current (DAC) voltage, very low-frequency sine wave (VLF-Sine) voltage, and very low-frequency cosine rectangular wave (VLF-CR) voltage, has important engineering value for evaluating the cable insulation conditions. In this paper, a PD test and measurement system of a 10 kV XLPE cable line with a 2 km length is established. Seven typical accessory defects are made artificially, including insulation hole, insulation screen tip, ring-cut tool mark, and stress cone installation dislocation defects at the terminals, and connector tip, conductive impurity, and stress cone installation dislocation defects at the joints. PD tests under four kinds of testing voltages of ACR, DAC, VLF-Sine, and VLF-CR are carried out to compare the PD inception voltages (PDIV), phase-resolved PD (PRPD) patterns, and PD location results of various defects. PD equivalence between power-frequency-like voltages and ACR is characterized by PDIV equivalent coefficient <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">PDIV</sub> , PRPD pattern characteristic quantities and discharge amplitudes. The results show that DAC and VLF-Sine have an outstanding ability to detect and characterize the severity of PD. DAC and VLF-CR have a good ability to recognize the type of PD. And DAC, VLF-Sine and VLF-CR can accurately locate PD. This study provides an important reference for on-site cable defect diagnosis and PD assessment.

Partial Discharge Suppression of the Oil-impregnated Paper by Depositing PTFE Thin Film via Magnetron Sputtering

The rapid development of HVDC (High Voltage Direct Current) transmission technology brings new challenges to insulation materials. Oil-paper insulation needs to be strengthened to prevent possible breakdown failure. In this paper, the PTFE functional film was fabricated by magnetron sputtering on the insulation pressboard surface to suppress partial discharge. The partial discharge test was conducted to compare the withstanding ability of the modified pressboard and the untreated pressboard. The results showed that partial discharge inception voltage increased by 18% for the modified pressboard. Phase-resolved partial discharge results also showed a great enhancement in partial discharge withstanding the ability of the PTFE function layer on the pressboard. The molecular simulation was conducted to give a possible explanation for the improvement. Higher bond levels and a large band gap of PTFE played a vital role.

Application of a Phase Resolved Partial Discharge Pattern Analysis for Acoustic Emission Method in High Voltage Insulation Systems Diagnostics

An alternative method for analysis of acoustic emission (AE) signals generated by partial discharges (PD), based on a correlation between voltage phase run and AE pulses, so called phase resolved PD pattern (PRPD), is presented in the paper. PRPD pattern is a well-known analysis tool commonly used in such PD diagnostic methods as conventional electrical and UHF ones. Moreover, it yields various signal analysis abilities and allows a direct correlation indication between measurement results achieved using different methods. An original PRPD measurement methodology applied for AE method as well as some exemplary measurement results and further data analysis capabilities are presented in the paper. Also a comparative analysis of PRPD patterns achieved using various measurement methods and different PD source configurations have been investigated. All presented experiments were done under laboratory conditions using PD model sources immersed in the insulation oil. The main purpose of the presented research is to indicate an all-embracing analytical tool that yields an ability to direct comparison (qualitative as well as quantitative) of the AE measurement results with other commonly applied PD measurement methods. The presented results give a solid fundamental for further research work concerning a direct correlation method for AE and other described in the paper diagnostic techniques, mainly in order to continue PD phenomena analysis and assessment in real life high voltage apparatus insulation systems under normal onsite operation conditions.