Partial Discharge In Gas-insulated Switchgear Research Articles

Gas Insulated Switchgear Partial Discharge Type Identification Based on Frequency Division Features and Improved Long Short-Term Memory Neural Networks

In order to ensure the safe and stable operation of gas insulated switchgear (GIS), a new method for identifying the type of partial discharge in GIS is proposed. First, the GIS partial discharge experimental platform produced four partial discharge signals. Second, the energy moments are calculated at each frequency to produce the frequency division features after the four partial discharge signals have been decomposed using variational modal decomposition (VMD). Finally, the type of GIS partial discharge is determined using the LSTM model enhanced by the quantum cuckoo search (QCS) algorithm. The experimental results show that the proposed method can successfully identify four types of partial discharge in GIS with an accuracy of 99%.

Recognition of partial discharge in GIS based on image feature fusion

<p>Partial discharge (PD) is a significant electrical fault in gas-insulated switchgear (GIS), with various types posing different risks to insulation. Accurate identification of PD types is essential for enhancing GIS management and ensuring the reliability of electrical grids. This study proposes a novel approach for PD identification in GIS integrating completed local binary pattern (CLBP) feature extraction, feature engineering, and an optimized support vector machine (SVM). PD faults were simulated in GIS and phase-resolved pulse sequence (PRPS) data for four different forms of PD were gathered. CLBP was used to extract image features, and then the support vector machine recursive feature elimination (SVM-RFE) algorithm was used to evaluate feature importance. Then, linear discriminant analysis (LDA) was used to fuse the selected features and reduce redundancy. The fused features were classified using a bald eagle search algorithm combined with differential evolution (IBES)-optimized SVM, achieving a recognition accuracy of 99.38%. The results indicate that the proposed method effectively distinguishes between different PD PRPS patterns in GIS.</p>

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.

Deep Domain-Invariant Long Short-Term Memory Network for Partial Discharge Localization in Gas-Insulated Switchgear

Localization based on differences in the timing of an ultrahigh-frequency signal is difficult to apply in actual settings because of the strict requirement for accurate calculation of the difference in arrival time between discharge pulses. With the development of digital twinning, the operational state of equipment is mapped onto a digital virtual model, and large-scale simulation data can be obtained to assist in localization of partial discharge (PD) in gas-insulated switchgear (GIS). With this aim, this paper proposes a novel deep domain-invariant long short-term memory network (LSTM) for GIS PD localization. Firstly, an attention residual LSTM is constructed to automatically extract discriminative features and effectively obtain the temporal and spatial dependences between features. Collaborative domain adaptation is proposed to transfer the diagnostic knowledge learned from large-scale simulation data to GIS PD localization. Via maximum mean discrepancy-based domain adaptation and domain adversarial training, discrepancies between samples in the two domains are reduced so as to achieve a more perfect match. The domain-invariant LSTM achieved an average localization accuracy of less than 11 cm, and the standard deviation of the error reached 8.15. The domain-invariant LSTM thus provides a novel solution for the high-precision and robust localization of PD in GIS.

A DFT study on the adsorption properties of Ti3C2O2 MXene towards SF6 decomposition gases

Detecting the partial discharge in gas-insulated switchgear (GIS) equipment by detecting the type and concentration of SF6 characteristic decomposition products is very important and effective in ensuring the regular operation of GIS equipment. In this study, VTi-Ti3C2O2 (Ti-deficient Ti3C2O2) and TM-doped (TM = Ti, Pt, Au) α-type Ti3C2O2 were carried out as the gas-sensing materials. The gas adsorption structures of SO2, SOF2, and SO2F2 on the surfaces of TM-modified Ti3C2O2 were established. Different adsorption systems' adsorption energies, electron densities, state densities, and times for gas desorption were examined using DFT calculations. Following the analysis, physical adsorption of SO2, SOF2, and SO2F2 occurs on the surface of Pt-Ti3C2O2 and Au-Ti3C2O2, while chemical adsorption occurs on the surface of VTi-Ti3C2O2. As a result, it is challenging to remove the gas molecules from the surface of VTi-Ti3C2O2, while it is simple to remove them from Pt-Ti3C2O2 and Au-Ti3C2O2 surfaces. At the same time, compared with gas adsorption on the surface of pristine Ti3C2O2, TM-modified Ti3C2O2 can improve the adsorption performance of pristine Ti3C2O2 on the characteristic decomposition products of SF6 to a certain extent.

Partial discharge localization using time reversal: Application to gas insulated switchgear

• Single sensor partial discharge (PD) localization in gas insulated switchgear. • Localization of PD using electromagnetic the time reversal (EMTR) method. • Investigation of the effect of noise, PD length, location, and orientation. • Single sensor localization of multiple, simultaneous PD in gas insulated switchgear. Gas-insulated switchgear (GIS) are some of the most reliable and most expensive equipment that are nowadays used in power systems. Condition monitoring of the power system equipment can help operators detect defects like partial discharges (PDs) early, prevent severe damage to the insulation of the apparatus and the related costs. Different techniques such as time difference of arrival (TDoA) have already been implemented to localize PDs. The TDoA technique requires four synchronized sensors to find the 3D location, it does not yield accurate results in a realistic situation when having multiple PDs, noise, scattering or obstacles which mask the line of sight between the sensor(s) and the PD. To have a powerful and accurate technique that can localize single or multiple PDs in power transformers in the presence of noise, scattering, obstacles, etc., using a single sensor, the time reversal (TR) technique has recently been proposed in both the acoustic and electromagnetic regimes. In this paper, the electromagnetic time reversal (EMTR) technique is applied to localize PDs in GIS, which have a more complicated structure than a transformer. The performance of the method is demonstrated considering several realistic case studies involving two pipe-shape and T-shape parts of a GIS.

Novel metric-based meta-learning model for few-shot diagnosis of partial discharge in a gas-insulated switchgear

Data-driven diagnosis methods have been systematically investigated for the diagnosis of gas-insulated switchgear (GIS) partial discharge (PD). However, because of the scarcity of samples on-site, an operational gap exists between the diagnostic methods and their actual application. To settle this issue, a novel metric-based meta-learning (MBML) method is proposed. First, a hybrid self-attention convolutional neural network is constructed for feature extraction and trained through supervised learning. Then, the episodic MBML is used to train other parts, and the metric classifier is employed for diagnosis. The proposed MBML exhibits an accuracy of 93.17% under 4-way 5-shot conditions, which is a significant improvement over traditional methods. When the number of support sets is small, the benefits of MBML are more prominent, providing a viable solution for the on-site diagnosis of PD in GISs.

DFT Insight to Ag2O Modified InN as SF6-N2 Mixture Decomposition Components Detector

In gas-insulated switchgear (GIS), partial discharge (PD) can be monitored by detecting sulfur hexafluoride-nitrogen (SF6-N2) decomposition components. In this paper, silver oxide (Ag2O) modification was introduced to improve the gas-sensing properties of graphene-like indium nitride (InN). The adsorption process of NO2, SO2F2, SOF2 and SOF4 on Ag2O-InN was simulated based on the first principles calculation and density functional theory (DFT). The gas sensing mechanism was revealed by density of states theory and molecular orbital theory. It is found that Ag2O doping greatly improves the adsorption properties of InN to NO2 and SOF2 molecules. The adsorption capacity of Ag2O-InN to the four gas molecules is: NO2 > SOF2 > SOF4 > SO2F2. All adsorptions can proceed spontaneously, and the gas molecules are electron donors and Ag2O-InN is an electron acceptor. Through the analysis of recovery time, it is found that NO2 is difficult to desorb from the substrate due to the significant adsorption energy of −2.201 eV, while SOF4, SOF2 and SO2F2 have a moderate adsorption energy of −0.185 eV, −0.754 eV and 0.173 eV and extremely short desorption time. The conductivity of the whole system changed after these four gases were adsorbed on the Ag2O-InN monolayer. In summary, Ag2O-InN can be used as NO2 adsorbent and gas sensors to detect SOF4, SOF2 and SO2F2. This paper provides a method for on-line monitoring of partial discharge in GIS.

A novel federated deep learning framework for diagnosis of partial discharge in gas-insulated switchgear

In recent years, many different deep learning methods have been developed to ensure the safe and stable operation of gas-insulated switchgear (GIS). However, the use of these methods to achieve excellent results depends on obtaining as much training data as possible, which is difficult to accomplish because of conflicts of interest among different clients and privacy concerns. To address this issue, this paper proposes a novel federated deep learning (FDL) for the diagnosis of partial discharge (PD) in GIS. A federated learning (FL) based on an improved federated averaging algorithm is proposed, which allows different clients to collaboratively participate in model training and preserves data privacy. In addition, a novel subtractive attention Siamese network is introduced for feature extraction and classification, which achieves the high-precision classification of unbalanced data. Experimental results showed that the diagnostic accuracy of the proposed FDL reached 95.61%, which was significantly higher than that achieved by other methods. The proposed FDL can also achieve excellent performance in the case of unbalanced samples and small samples. As a distributed learning, FL does not require clients to share data, and clients can collaboratively develop an effective global diagnostic model, which provides a novel solution for GIS PD diagnosis.

The Study on a New Method for Detecting Corona Discharge in Gas Insulated Switchgear

Partial discharge (PD) is the main cause of insulation deterioration and failure of gas-insulated switchgear (GIS). Corona discharge (CD) is a typical type of PD in gas-insulated switchgear. Accurate and sensitive measurement of CD in GIS is of great significance for theoretical research in the laboratory and fault prediction of GIS in the actual operation. A novel method for detecting CD in GIS is proposed in this article. A coaxial structure model for simulating GIS is established. The CD detecting sensor based on the proposed method is designed for this model. An artificial tip defect is designed on the internal high voltage conductor of the coaxial model to simulate CD in GIS. A 50 Hz ac power supply, a dc negative power supply, and a dc positive power supply are applied as excitations to generate the CD at the defect, respectively. The discharge pulse signal is detected by the proposed sensor. The results show that the proposed sensor can completely obtain the information of the CD pulse signal. The proposed method has the same anti-electromagnetic interference ability as the ultrahigh-frequency method and has a high sensitivity to CD in GIS.

Adsorption characteristics of H2S, SO2, SO2F2, SOF2, and N2 on NiO–MoSe2 monolayer for gas-sensing applications

Gas insulated switchgear (GIS) is an important equipment in the power transmission and distribution system, which commonly fills with SF6/N2 insulating gas mixture. Due to the partial discharge in GIS, SF6 gas is likely to ionize and react with impurities inside the GIS, and produces SO2, H2S, SO2F2, and SOF2 characteristic gases. This work was devoted to detect the partial discharge by exploring new gas-sensing materials for characteristic gases detection. First, four possible modification sites of NiO on MoSe2 surface were built and optimized, it was found that the B2 site modification was the most stable one. Then, the optimal adsorption structure was obtained by analyzing the adsorption structures of gases on NiO–MoSe2 with different initial positions. Finally, the adsorption mechanism and gas-sensing characteristics were studied based on the density of state theory and molecular orbital theory. The results show that NiO doping greatly enhances the surface activity of MoSe2 for gas adsorption. The order of adsorption ability is H2S > SO2 > SOF2 > N2 > SO2F2, and the moderate adsorption energy indicates that NiO–MoSe2 could be a suitable gas-sensing material, which lays a theoretical foundation for the design of NiO–MoSe2 sensors. This research provides a new method to ensure the stability of GIS operation.

A Novel Sensor Detection Method of Partial Discharge in GIS based on the UHF Electromagnetic Wave

UHF electromagnetic wave has been widely used in various PD measurements of GIS (gas insulated switchgear) because of its high sensitivity, strong anti-interference ability, large effective detection range, fault location and pattern recognition. In this paper, a new method of detecting partial discharge of pouring hole on GIS insulator is studied. The transmission characteristics of UHF electromagnetic wave are simulated by FDTD. Based on the computer simulation technology (CST), a dipole antenna UHF sensor is developed. Finally, the sensitivity and validity of the sensor are tested on the 110kvgis experimental platform. Compared with the conventional method, the sensitivity of PD detection in GIS is obviously improved.

Partial Discharge Detection and Discharge Type Identification of Gas Insulated Switchgear Based on Photoelectric Detection

Gas insulated switchgear (GIS) is a relatively common high-voltage substation equipment. Due to the internal complex structure and integrated switch, it is easy to cause insulation defects, burrs and partial discharge of metal particles, thereby reducing the insulation of equipment performance, which has attracted the attention of many researchers. In this study, aiming at the problem of partial discharge in GIS, a detection device of partial discharge based on photomultiplier instrument is proposed. In this device, Zemax software is used to simulate a front-end optical signal receiving module that enhances the photosensitive surface and enhances the optical signal aggregation effect. In terms of signal processing, the output voltage signal of the photomultiplier instrument is filtered, and the corresponding signal is extracted for amplification. The partial discharge detecting device designed in the experiment is used to judge the internal insulation defects of the GIS, and to discriminate the metal protrusion defects, the metal particle defects on the insulator surface, the free metal particle defects, and the air gap defects between the insulator and the high voltage conductor, respectively. The partial discharge signal ϕ-u-v spectra of different defect models are constructed. Through the image simulation of partial discharge signals corresponding to defects, it is verified that the detection device can distinguish the partial discharge caused by different defects, which is helpful to prevent the occurrence of malignant discharge accidents and maintain the stable operation of GIS equipment.

A Novel PD Detection Technique for Use in GIS Based on a Combination of UHF and Optical Sensors

Detecting partial discharge (PD) in gas-insulated switchgear (GIS) is an effective way to diagnose the insulation state of GIS. When PD occurs in GIS, optical and electromagnetic signals will be emitted from the discharge source. PD can be detected by analyzing these signals. At present, the ultrahigh-frequency (UHF) method is one of the most popular methods for detecting the PD in GIS. However, the optical method has not been in the field due to the problem of mounting optical sensor into GIS, even though it has higher sensitivity and better anti-interference performance. To settle this problem, a novel GIS PD detection sensor integrated with the optical fiber and UHF method is developed in this paper, which can fully utilize the advantages both of UHF and optical methods. The simulation results indicate that the integrated sensor can be mounted into GIS on the premise of not affecting the electric field distribution in GIS. In addition, the integrated sensor has a good UHF performance. The PD signals of typical defects at several locations were measured in a physical GIS using the integrated sensor. The results show that the integrated sensor can detect the optical and UHF signals induced by PD at the same time. The optical method has higher sensitivity than the UHF method for the protrusion defect. The amplitude and the number of the optical signals induced by PD clearly decrease with the increase in the detection distance. The studies in this paper are helpful to improve the accuracy and sensitivity of PD detection in GIS on site.

Optimal Placement of UHF Sensors for Accurate Localization of Partial Discharge Source in GIS

This paper proposes an optimal placement model of ultra-high frequency (UHF) sensors for accurate location of partial discharge (PD) in gas-insulated switchgear (GIS). The model is based on 0-1 program in consideration of the attenuation influence on the propagation of electromagnetic (EM) waves generated by PD in GIS. the optimal placement plan improves the economy, observability, and accuracy of PD locating. After synchronously acquiring the time of the initial EM waves reaching each UHF sensor, PD occurring time can be obtained. Then, initial locating results can be acquired by using the Euclidean distance measuring method and the extended time difference of arriving (TDOA) location method. With the information of all UHF sensors and the inherent topological structure of GIS, the locating accuracy can be further improved. The method is verified by experiment, showing that the method can avoid the influence of false information and obtain higher locating accuracy by revising initial locating results.

Study of comparison between Ultra-high Frequency (UHF) method and ultrasonic method on PD detection for GIS

GIS (gas insulated switchgear), is an important equipment in power system. Partial discharge plays an important role in detecting the insulation performance of GIS. UHF method and ultrasonic method frequently used in partial discharge (PD) detection for GIS. However, few studies have been conducted on comparison of this two methods. From the view point of safety, it is necessary to investigate UHF method and ultrasonic method for partial discharge in GIS. This paper presents study aimed at clarifying the effect of UHF method and ultrasonic method for partial discharge caused by free metal particles in GIS. Partial discharge tests were performed in laboratory simulated environment. Obtained results show the ability of anti-interference of signal detection and the accuracy of fault localization for UHF method and ultrasonic method. A new method based on UHF method and ultrasonic method of PD detection for GIS is proposed in order to greatly enhance the ability of anti-interference of signal detection and the accuracy of detection localization.

Study of New Method Combined Ultra-High Frequency (UHF) Method and Ultrasonic Method on PD Detection for GIS

GIS (gas insulated switchgear), is an important equipment in power system. Partial discharge plays an important role in detecting the insulation performance of GIS. UHF method and ultrasonic method frequently used in partial discharge (PD) detection for GIS. It is necessary to investigate UHF method and ultrasonic method for partial discharge in GIS. However, very few studies have been conducted on the method combined this two methods. From the view point of safety, a new method based on UHF method and ultrasonic method of PD detection for GIS is proposed in order to greatly enhance the ability of anti-interference of signal detection and the accuracy of fault localization. This paper presents study aimed at clarifying the effect of the new method combined UHF method and ultrasonic method. Partial discharge tests were performed in laboratory simulated environment. Obtained results show the ability of anti-interference of signal detection and the accuracy of fault localization for this new method combined UHF method and ultrasonic method.

Influence of trace O<inf>2</inf> on SF<inf>6</inf> decomposition characteristics under partial discharge based on oxygen isotope tracer

As an excellent electrical insulation and arc-interruption medium, sulfur hexafluoride (SF 6 ) has been widely used in gas-insulated switchgear (GIS). Insulation failures in GIS are usually evolved from the partial discharges which are induced by hidden defects, such as metal protrusions, free conducting particles, floating components. In the presence of discharges, SF 6 decomposes into various by-products. Accordingly, these decomposition by-products are often used to detect and identify partial discharges in GIS based on SF 6 decomposition characteristics. Oxygen (O 2 ) as an impurity plays an important role in the formation of SF 6 decomposition by-products. In this paper, the influence of O 2 on SF 6 decomposition characteristics under partial discharge has been investigated based on oxygen isotope tracer 18O 2 and 16O 2 . In our experiments, SF 6 isotopic decomposition by-products were induced, as severity degree of partial discharge or ratio of 18O 2 to 16O 2 varied. The isotopic decomposition by-products were measured by gas chromatograph mass spectrometer. Based on the results, the sequences of reactions that lead to SO 2 F 2 and SO 2 were described. It is shown that the formation of SO 2 F 2 depends not only on O 2 but also H 2 O, whereas the formation of SO 2 has little dependence on O 2 .

UHF Signal Processing and Pattern Recognition of Partial Discharge in Gas-Insulated Switchgear Using Chromatic Methodology.

The ultra-high frequency (UHF) method is widely used in insulation condition assessment. However, UHF signal processing algorithms are complicated and the size of the result is large, which hinders extracting features and recognizing partial discharge (PD) patterns. This article investigated the chromatic methodology that is novel in PD detection. The principle of chromatic methodologies in color science are introduced. The chromatic processing represents UHF signals sparsely. The UHF signals obtained from PD experiments were processed using chromatic methodology and characterized by three parameters in chromatic space (H, L, and S representing dominant wavelength, signal strength, and saturation, respectively). The features of the UHF signals were studied hierarchically. The results showed that the chromatic parameters were consistent with conventional frequency domain parameters. The global chromatic parameters can be used to distinguish UHF signals acquired by different sensors, and they reveal the propagation properties of the UHF signal in the L-shaped gas-insulated switchgear (GIS). Finally, typical PD defect patterns had been recognized by using novel chromatic parameters in an actual GIS tank and good performance of recognition was achieved.

Investigation of disc-type sensors using the UHF method to detect partial discharge in GIS

The disc-type UHF sensor is considered among the simplest couplers for partial discharge (PD) detection in gas-insulated switchgear (GIS). This paper mainly focuses on the improvement of the sensitivity of the disc-type sensor. Disc-type sensors with different dimensions were tested on a 220 kV model GIS to find the critical parameters that determine the sensitivity of the sensor. The waveform of the PD signal and the twoport insertion loss were measured to see the amplitude of the output signal and the transmission rate on different frequencies. The FD-TD method was used to investigate the dimension factors in detail along with the effect of the dimension of the tank in which the sensors are installed. The transformation process between the TEM mode and the higher-order modes of the electromagnetic (EM) wave was also simulated to investigate the receiving efficiency of the disc-type sensors for different propagation modes. The results showed that the diameter of the disc and the ratio of the height of the disc to the thickness of the insulation were the most critical parameters that determined the sensitivity of the disc-type sensor.