Typical Partial Discharge Research Articles

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.

Comprehensive Simulation Research on Microprocess and Macroscopic Electromagnetic Signals of Surface Discharge in SF6

The surface discharge on the dielectric is a common type of partial discharge in GIS, but the microscopic development process of surface discharge in SF <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sub> is unclear. To find out the micro-process of surface discharge and its correlation mechanism with the partial discharge detection signals of GIS, the fluid-chemical simulation model of the streamer is used to simulate the micro-process of surface discharge in SF <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">6</sub> . Then the current signal obtained by the micro-process simulation is used as the excitation to simulate the electromagnetic signals based on the FITD method. A close connection between the microscopic discharge and the macroscopic signals is established. The results show that the electron concentration at the streamer head and the streamer velocity decrease first and then increase during the discharge, with an average velocity of about 9.84×105m/s. The discharge current reached a peak value of about 0.22A when the surface streamer reaches the cathode. In terms of waveform correlation, the absolute value of the average correlation coefficient between the electric field signals simulated in this paper and the actual measured signals is above 0.7, which is much higher than the simulated signal excited by the Gaussian source. By changing the applied voltage and comparing with the experiment results, it is found that the simulation method in this paper can reflect the change of signals under the influence of external conditions. As the applied voltage rises, the amplitude of the electric field signals increases, and the main frequency component on the frequency spectrum grows, with the main frequency value at about 1.2 GHz. The research in this paper is an effective supplement to the existing study on the microscopic mechanism of partial discharge signals.

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.

Application of a Rogowski Coil Sensor for Separating Internal and External Partial Discharge Pulses in Power Transformers

Partial discharge (PD) measurement is an essential tool for evaluating the health condition of a transformer insulation system. The Conventional PD measurement systems have a major drawback since they cannot discriminate the internal PD pulses and external pulse-shaped interferences, especially in online and on-site conditions. Various de-noising techniques (e.g. wavelets) have been also used in the literature, which is effective for extracting the PD signal from the noisy signals or classifying the PD types. However, the PD pulses and some of the randomly external pulse-shaped interferences have similar time-frequency characteristics, which makes them difficult to separate. In this paper, a new cost-effective and simple logic method is proposed for the separation of these interferences. This uses the polarity comparison of the output voltages of the Rogowski Coil (RC) sensor, mounted on the bushing, and measurement impedance, connected to the test tap. The same polarity represents the internal pulse, while the opposite polarity indicates the external pulses. A distribution transformer ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$20/0.4\ {\bm{kV}},\ 500\ {\bm{kVA}})$</tex-math></inline-formula> and a condenser bushing ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$72.5\ {\bm{kV}})$</tex-math></inline-formula> were considered to evaluate the performance of the proposed system. The results confirm the effectiveness of the proposed PD measurement system for separating the pulses.

A PRPD-Based UHF Filtering and Noise Reduction Algorithm for GIS Partial Discharge.

The online detection of partial discharge (PD) in gas-insulated switchgear (GIS) is a crucial and powerful tool for maintaining their reliability. However, extracting weak discharge signals from strong disturbances is a significant challenge. The presence of noise can hamper the identification and localization of PD types, making the extraction of pure PD signals the focus of current research. This paper proposes a PRPD-based PD filtering algorithm that analyzes interference using the output information from PRPD and sets threshold parameters for noise reduction processing. This method is mainly used for secondary noise reduction at a later stage, without analyzing the noise source, to achieve effective signal acquisition while retaining the characteristics of the PD signals, thereby improving the system's sensitivity and the signal's purity.

ONLINE PARTIAL DISCHARGE MEASUREMENT FOR CONDITION-BASED MAINTENANCE OF HV POWER CABLES IN RAILWAY INFRASTRUCTURE

Partial discharge (PD) measurement as one of well-known method to evaluate the condition of high voltage (HV) power cables has been studied over many decades. Cable insulation failure could result in a power outage, which could then cause a loss of service in the transportation system and even dangerous events like fire accidents. It is of a great interest to railway infrastructure operators to monitor and identify the cable faults before any possible accident occurs. The paper focuses on the diagnostic problem to detect the HV cable fault based on the Phase Resolved Partial Discharge (PRPD) patterns. Classification models, such as Random Forest and Convolutional Neural Network, are considered to classify the pattern of PRPD based on the mostly occurring PD types in HV cables, such as corona, surface, and void patterns. Experiments are performed and the PRPD data from the experiments are collected. The optimal model is applied in the online monitoring program which will be used continuously to evaluate the cable condition and arrange the optimal schedule for maintenance. According to the analysis, both algorithm perform well in the PRPD pattern categorization, with accuracy up to 83.45%. This indicates that due to the more effective behavior, PD assessment with PD sensors is preferable.

Multi-source partial discharge diagnosis in gas-insulated switchgear via zero-shot learning

Partial discharge (PD) diagnosis in gas insulation switchgear (GIS) has been continuously studied as a hot issue. The diagnostic model developed at this stage requires the possible combination of all single PDs, and each combination has sufficient data. However, the demand for the number of multi-source PD samples increases in the form of an index due to the accidental and concurrency of different types of PD, where it is unrealistic to collect sufficient PD samples. To this end, we proposed zero-shot learning (ZL) to diagnose multi-source PD. The ZL diagnosis multi-source PD only required single PD for training. Specifically, an attention residual network was introduced for feature extraction. Then, a novel semantic descriptor was proposed to obtain the semantic attributes, and the semantic embedded features were mapped to the visual space with a full connection network. Finally, the relationship network adopted the similarity between the visual features and semantic embedded features, and the multi-source PD diagnosis was realized. In addition, the multi-source PD experiment in GIS was constructed to verify the proposed ZL. The experimental results demonstrated that the ZL could achieve 90.25 % accuracy when only single PD participated in the training. It provided novel solutions for the diagnosis of multi-source PD in GIS.

Feature extraction based on time-series topological analysis for the partial discharge pattern recognition of high-voltage power cables

In the partial discharge (PD) pattern recognition of power cables, the existing time–frequency features often exert an impact on recognition accuracy because of insufficient discrimination. A novel PD feature extraction and identification method on the basis of time-series topological data analysis (TDA) was proposed in this paper. Firstly, original PD sequence was reconstructed as point cloud in phase space based on optimized symbolic entropy. Then, a PD topological space is constituted with point cloud to extract its persistent homology features. On this basis, persistence diagrams and barcodes were calculated and visually expressed as Betty curves. Finally, Betty curves were input into an optimized 1D convolution neural network (1D-CNN) model to recognize four typical PD patterns and carry out comparison experiments. The visualization produced by t-distributed stochastic neighbor embedding (t-SNE) shows that TDA features possess significant discrimination, experiencing an increase of 11.25% in the overall recognition accuracy and reaching 98.00% compared with original PD sequence and time–frequency features. Meanwhile, the computation cost of the proposed algorithm is optimized within the permissible range for real-time applications.

External Partial Discharge Detection of Gas-Insulated Switchgears Using a Low-Noise and Enhanced-Sensitivity UHF Sensor Module

Ultra-high frequency (UHF) partial discharge (PD) detection is essential for routine maintenance of gas-insulated switchgear (GIS). Realizing low-noise detection with cost-effectiveness and ease of installation is promising but challenging. This paper presents a novel broadband noise-shaping network (BNSN) integrated with a printed monopole antenna (PMA) sensor to realize sufficient noise rejection and good impedance matching. Moreover, by analyzing the equivalent noise circuit and codesigning a high-speed preamplifier circuit with the proposed sensor, the detection sensitivity and anti-interference of the proposed sensor module are improved. The effectiveness and superiority of the proposed sensor are first verified in accordance with IEC 62478, followed by validations using a PD simulator and a real 24-kV GIS. The experimental results demonstrate that the proposed sensor module has the capability to identify different PD types even in noisy environments.

Partial Discharge Monitoring Method in Switchgear with Bushing High-Voltage Sensor

10 kV and 35 kV switchgear are the key equipment in the power grid, and the safety of their insulation is related to the stability of the entire power grid. But the accuracy of the traditional partial discharge detection method is difficult to meet the detection requirements of the new SF6 insulated switchgear. This work analyzes the feasibility of using the high-voltage sensor in the bushing to detect partial discharge, and the analysis shows that the synchronous signal and the partial discharge signal can be obtained from the bushing sensor. Detection experiments were carried out using three typical partial discharge models, with both HFCT and a bushing sensor. The measurement results show that the bushing sensor can effectively detect the partial discharge in the switchgear and obtain a PRPD plot similar to HFCT. It is also found that adjusting the sampling resistance can change the partial discharge detection range of the bushing sensor.

GIS Partial Discharge Pattern Recognition Based on Multi-Feature Information Fusion of PRPD Image

Partial discharge (PD) pattern recognition is a critical indicator for evaluating the insulation state of gas-insulated switchgear (GIS). Aiming at the disadvantage of traditional PD pattern recognition methods, such as single feature extraction and low recognition accuracy, a pattern recognition method of PD based on multi-feature information fusion is proposed in this paper. Firstly, a recognition model based on quasi-Hausdorff distance is established according to the statistical characteristics of the phase-resolved partial discharge (PRPD) image, and then a modified convolutional neural network recognition model is established according to the image features of the PRPD image. Finally, Dempster–Shafer (D–S) evidence theory is used to fuse the two pattern recognition results and complement the advantages of the two approaches to improve the accuracy of partial discharge pattern recognition. The experimental results show that the total recognition accuracy rate of this method for four typical PD is more than 94.00%, and the recognition rate is significantly improved compared to support vector machine and normal convolution neural network. Maintaining stability in typical bipedal robots is challenging due to two main reasons.

Detection technology of partial discharge in transformer based on optical signal

The detection of partial discharge (PD) in transformers is of great significance for preventing insulation defects from developing into insulation failures. Transformer partial discharge detection technology includes pulse current method, radio frequency measurement method, UHF method, ultrasonic detection method, gas chromatography, and optical detection method. Among them, the optical detection method has the characteristics of strong anti-electromagnetic interference ability, and the signal can be transmitted and received without loss. The optical detection method has unique advantages. In this paper, an optical signal measuring device for partial discharge inside the transformer is designed and fabricated, the typical insulation defect inside the transformer is simulated, and the optical signal characteristics of typical partial discharge are obtained. Compared with the pulse current method, it is found that the magnitude of partial discharge can be characterized by the integral of the optical signal. The characteristic of the optical signal phase resolved partial discharge (PRPD) spectrum of typical insulation defects is obtained. The PRPD spectrum of the optical signals of different defects is obviously different. It is feasible to draw the PRPD spectrum and identify the defect types according to the optical signal, which can be further applied to the identification of internal faults in transformers.

Stage division strategy for gas insulation surface discharge based on multi-physical information

The internal insulation defects in gas insulated equipment leading to partial discharges will affect the insulation performance of the equipment. Among them, surface discharges are a typical type of partial discharge, which often occurs at basin-type insulators. To realize effective discharge detection and discharge degree determination, a refined discharge stage division strategy for gas-insulated creeping discharge based on multi-physical information is investigated in this study. First, an experimental platform for gas-insulated multi-physical signal detection is established, of which high frequency current transformer (HFCT), silicon photomultiplier (SiPM), ultra-high frequency (UHF) and acoustic emission (AE) sensors are applied to measurement the multi-physical energy releases in the process of creeping discharge. Then an artificial surface discharge defect is developed following the actual surface discharge of basin insulator. Subsequently, the relative optical radiation power, electromagnetic radiation power and ultrasonic radiation power produced in the process of discharge are deduced from the multi-physical information. Meanwhile, the relationships among the three energy releases are carried out for variation of different energy with the applied voltage increases. Finally, development path of multi-physical energy ratio for surface discharge is proposed to evaluate the severity of discharge.

Adopting integration of multispectral time resolved analysis and graph-based deep learning method in partial discharge type identification

Partial discharge (PD) is treated as one of the major threats for gas insulated switchgear (GIS). By using the new generation multispectral detection sensor named as SiPM-based multispectral discharge sensor (SMDS), the time resolved partial discharge with multispectral information (named as MTRPD) for creeping discharge, suspension discharge and tip discharge, respectively. It indicates that the MTRPD for the specific discharge defect perform unique spectral fingerprints in discharge mode. Based on the graph characteristics of MTRPD, we introduced the convolution neural network (CNN) to implement PD type identification whose overall accuracy of Δqi-Δqi+1 and Δti-Δti+1 were 99.7% and 98.9%, respectively. This paper provides a new technique tool for fine diagnosis of PD independent of phase analysis.

GIS Partial Discharge Pattern Recognition Based on Time-Frequency Features and Improved Convolutional Neural Network

Different types of partial discharge (PD) in gas-insulated switchgear (GIS) cause different damage to GIS insulation, correctly identifying the PD type is very important for evaluating the insulation status of GIS. This paper proposes a PD pattern recognition method based on an improved feature fusion convolutional neural network (IFCNN) to fully use the time-frequency features of PD pulses to realize PD pattern recognition. Firstly, the one-dimensional time-domain feature sequence of the PD pulse and the corresponding wavelet time-frequency diagram are applied as inputs. Secondly, the convolutional neural network (CNN) with two parallel channels is used for feature extraction, the extracted fault information is fused, and the shallow features of the wavelet time-frequency diagram are fused to prevent feature loss caused by pooling operation. Finally, the extracted features are sent to the classifier to recognize different types of PD. The discharge data of different types of PD are obtained for testing by experiments and simulation. Compared with 1-D CNN and 2-D CNN under the same specification, the proposed method can mine more potential local features of discharge pulses by fusing the time-frequency features of PD pulses in different dimensions, and improves the recognition accuracy to 95.8%.

Audible acoustic characteristics of epoxy resins with partial discharge

The epoxy resin is the main solid insulating material for electrical equipment. PD (partial discharge) is an important factor leading to epoxy resin aging or failure. Fault detection technology based on audible acoustic imaging has the advantages of real-time monitoring, visibility, and flexibility and is gradually being used in the field of electrical equipment insulation state monitoring. However, the audible voiceprint features of epoxy resins with typical PD defects are not clear, which is not conducive to effective detection and fault diagnosis. Therefore, in this study, the study of audible voiceprint features of epoxy resins with a metal burr, pollution, metal foreign matters, and surface discharge defects was carried out. The discharge audible signals were obtained, and their time and frequency domain features were analyzed. The results show that the discharge audible signals of four PD defects can reflect the occurrence of PD simultaneously with pulse current signals. But the characteristics are obviously different in the time domain, which are embodied in listening perception, persistence, amplitude, and phase. In the frequency domain, the frequency spectra of discharge audible signals of four defects are mainly 5–10 and 13–24 kHz. Furthermore, the three feature vectors of frequency spectrum complexity, high-frequency energy factor, and maximum frequency point are extracted, which can well distinguish the discharge audible signals of four PD defects.

A GIS Partial Discharge Defect Identification Method Based on YOLOv5

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.

Partial discharge ultrasonic signals pattern recognition in transformer using BSO-SVM based on microfiber coupler sensor

Detection and pattern recognition of different types of partial discharge (PD) signals in transformer are of great significance for the safe and stable operation of transformers. This paper demonstrates the application of microfiber coupler sensor (MFCS) to the pattern recognition of PD ultrasonic signals with an optimized support vector machine (BSO-SVM) algorithm. First, a PD ultrasonic detection system based on MFCS is built, compared with the traditional piezoelectric sensor, the MFCS can be directly implanted in the transformer oil to detect the PD signals, avoiding the attenuation of ultrasonic signals as they propagate to the transformer outer wall. Then, four kinds of PD ultrasonic signals are collected by the PD detection system, and feature extraction is carried out for the time domain and frequency domain characteristics of PD ultrasonic signals. Finally, a BSO-SVM classification algorithm is proposed, which uses the beetle antennae search (BAS) and the particle swarm optimization (PSO) algorithm to jointly optimize the support vector machine (SVM) algorithm. The BSO-SVM classifier is used to classify four kinds of PD signals, the classification accuracy is 93%, and the number of convergence is 5. In addition, the BSO-SVM algorithm is compared with the GA-SVM and PSO-SVM algorithms. The results show that the BSO-SVM algorithm has higher recognition accuracy and faster convergence speed. The research results show that it is feasible to use MFCS combined with BSO-SVM to identify PD patterns of transformers, and it has certain significance for transformer fault diagnosis.

Research on data diagnosis method of acoustic array sensor device based on spectrogram

Acoustic array sensor device for partial discharge detection is widely used in power equipment inspection with the advantages of non-contact and precise positioning compared with partial discharge detection methods such as ultrasonic method and pulse current method. However, due to the sensitivity of the acoustic array sensor and the influence of the equipment operation site interference, the acoustic array sensor device for partial discharge type diagnosis by phase resolved partial discharge (PRPD) map might occasionally presents incorrect results, thus affecting the power equipment operation and maintenance strategy. The acoustic array sensor detection device for power equipment developed in this paper applies the array design model of equal-area multi-arm spiral with machine learning fast fourier transform clean (FFT-CLEAN) sound source localization identification algorithm to avoid the interference factors in the noise acquisition system using a single microphone and conventional beam forming algorithm, improves the spatial resolution of the acoustic array sensor device, and proposes an acoustic array sensor device based on the acoustic spectrogram. The analysis and diagnosis method of discharge type of acoustic array sensor device can effectively reduce the system misjudgment caused by factors such as the resolution of the acoustic imaging device and the time domain pulse of the digital signal, and reduce the false alarm rate of the acoustic array sensor device. The proposed method is tested by selecting power cables as the object, and its effectiveness is proved by laboratory verification and field verification.

A Novel Method for Pattern Recognition of GIS Partial Discharge via Multi-Information Ensemble Learning.

Partial discharge (PD) is the main feature that effectively reflects the internal insulation defects of gas-insulated switchgear (GIS). It is of great significance to diagnose the types of insulation faults by recognizing PD to ensure the normal operation of GIS. However, the traditional diagnosis method based on single feature information analysis has a low recognition accuracy of PD, and there are great differences in the diagnosis effect of various insulation defects. To make the most of the rich insulation state information contained in PD, we propose a novel multi-information ensemble learning for PD pattern recognition. First, the ultra-high frequency and ultrasonic data of PD under four typical defects of GIS are obtained through experiment. Then the deep residual convolution neural network is used to automatically extract discriminative features. Finally, multi-information ensemble learning is used to classify PD types at the decision level, which can complement the shortcomings of the independent recognition of the two types of feature information and has higher accuracy and reliability. Experiments show that the accuracy of the proposed method can reach 97.500%, which greatly improves the diagnosis accuracy of various insulation defects.