scholarly journals Identification of ultra-high-frequency PD signals in gas-insulated switchgear based on moment features considering electromagnetic mode

High Voltage ◽  
2020 ◽  
Vol 5 (6) ◽  
pp. 688-696
Author(s):  
Feng Bin ◽  
Feng Wang ◽  
Qiuqin Sun ◽  
She Chen ◽  
Jingmin Fan ◽  
...  
Keyword(s):  
High Frequency ◽  
Electromagnetic Mode ◽  
Ultra High Frequency ◽  
Gas Insulated Switchgear ◽  
Moment Features

Present Situation and Prospect of Internal Sensors for UHF Detection in GIS

2015 ◽  
Vol 738-739 ◽  
pp. 38-41
Author(s):  
Yu Bing Duan ◽  
Hao Zhang ◽  
Jun Yong ◽  
Bo Yang ◽  
Xiao Li Hu ◽  
...  
Keyword(s):  
Performance Indicators ◽  
High Frequency ◽  
Partial Discharge ◽  
Present Situation ◽  
Ultra High Frequency ◽  
Gas Insulated Switchgear ◽  
Discharge Detection

This paper summarizes the application situation of the ultra-high frequency (UHF) method in gas insulated switchgear (GIS) partial discharge detection, as well as the differences between internal and external UHF sensors. The performance indicators of internal sensors are introduced, and five main types of internal sensors are discussed and evaluated. In addition, several problems to be solved are posed for researchers.

Experimental Research on the Sensitivity of Partial Discharge Ultra High Frequency Sensor Structure Parameters

2021 ◽  
Vol 16 (6) ◽  
pp. 911-918
Author(s):  
Wen-Yi Li
Keyword(s):  
High Frequency ◽  
Partial Discharge ◽  
Structural Parameter ◽  
Test Model ◽  
Frequency Signal ◽  
High Frequency Signal ◽  
Ultra High Frequency ◽  
Gas Insulated Switchgear ◽  
Sensor Structure ◽  
Sensing Sensitivity

With the development of intelligent high voltage switch, online gas insulated switchgear discharge detection technology has been more and more widely applied. Because of the high sensing sensitivity and good antiinterference performance of build-in partial discharge sensor, it is currently required to install them on gas insulated switchgear products with voltage levels of 220 kV and above at the factory. The structural parameters of the build-in partial discharge sensor is of great importance to its sensing sensitivity. Therefore, in this paper, the influence of the structure change on the sensitivity of axisymmetric gas insulated switchgear build-in partial discharge sensor is experimentally studied. A practical gas insulated switchgear test model was established in the laboratory, and the frequency domain measurement system based on Spectrogram analyzer and synchronous sweep signal generator was adopted. By comparing the insertion loss generated by the build-in sensor when receiving sweep signal, the influence of structural parameter changes on the sensing sensitivity was analyzed. The results show that the diameter of the build-in sensor should be matched with the diameter of the hand-hole. The match of the larger diameter of the hand-hole and the smaller diameter of the sensor can increase the sensing sensitivity, but when the diameter of the sensor is close to the diameter of the hand-hole, the sensitivity will be significantly reduced. In addition, metal bolts with the sensor electrode and its insulating support fixed to the hand-hole cover can also result in a significant reduction in sensing sensitivity. Using the same measuring principle and system, the propagation attenuation characteristics of partial discharge ultra high frequency signal in gas insulated switchgear typical structures (linear and L-shaped structures) are also experimentally studied. The results show that the average attenuation of partial discharge ultra high frequency signal in gas insulated switchgear along the linear distance is 0.3 dB/m, and the attenuation through every L-shaped structure is 4.2 dB.

scholarly journals One-Shot Learning for Partial Discharge Diagnosis Using Ultra-High-Frequency Sensor in Gas-Insulated Switchgear

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5562
Author(s):  
Vo-Nguyen Tuyet-Doan ◽  
The-Duong Do ◽  
Ngoc-Diem Tran-Thi ◽  
Young-Woo Youn ◽  
Yong-Hwa Kim
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
High Frequency ◽  
Electrical Equipment ◽  
Training Data ◽  
Ultra High Frequency ◽  
Frequency Sensor ◽  
Gas Insulated Switchgear ◽  
Insulation Systems ◽  
Metric Function

In recent years, deep learning has been successfully used in order to classify partial discharges (PDs) for assessing the condition of insulation systems in different electrical equipment. However, fault diagnosis using deep learning is still challenging, as it requires a large amount of training data, which is difficult and expensive to obtain in the real world. This paper proposes a novel one-shot learning method for fault diagnosis using a small dataset of phase-resolved PDs (PRPDs) in a gas-insulated switchgear (GIS). The proposed method is based on a Siamese network framework, which employs a distance metric function for predicting sample pairs from the same PRPD class or different PRPD classes. Experimental results over the small PRPD dataset that was obtained from an ultra-high-frequency sensor in the GIS show that the proposed method achieves outstanding performance for PRPD fault diagnosis as compared with the previous methods.

Sign in / Sign up

Export Citation Format

Share Document