<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This paper first introduces the main types of GIS insulation defects and explores the discharge mechanism of GIS insulation. Then, the space of discharge features of GIS insulation defects in a complex electromagnetic environment is constructed, and the feature dimensionality reduction is carried out by using principal component analysis. Then, the support vector machine algorithm is explored and optimized with the immune algorithm to identify and detect the local features of insulation defects. Finally, the local discharge characteristics of GIS insulation defects are investigated through simulation experiments, and the discharge results are analyzed. The results show that the average peak-to-peak value is around 31mV and the power distribution band is 133~168MHZ for the spiky insulation defects, the average peak-to-peak value is around 19.8mV and the power distribution band is around 202MHZ for the metallic particles insulation, and the peak value of the air gap is less than 8mV and more than 48mV for some, and the power distribution band is 98MHZ~146MHZ. The localized discharge characteristics of the defects of the GIS insulation parts are identified and detected by the immune optimization of the support vector machine algorithm. The overall recognition rate of immunodeficient partial discharges of insulating parts is around 0.90. This study is able to detect the type of partial discharges in GIS insulating parts well.</p>
</abstract>

This paper first introduces the main types of GIS insulation defects and explores the discharge mechanism of GIS insulation. Then, the space of discharge features of GIS insulation defects in a complex electromagnetic environment is constructed, and the feature dimensionality reduction is carried out by using principal component analysis. Then, the support vector machine algorithm is explored and optimized with the immune algorithm to identify and detect the local features of insulation defects. Finally, the local discharge characteristics of GIS insulation defects are investigated through simulation experiments, and the discharge results are analyzed. The results show that the average peak-to-peak value is around 31mV and the power distribution band is 133~168MHZ for the spiky insulation defects, the average peak-to-peak value is around 19.8mV and the power distribution band is around 202MHZ for the metallic particles insulation, and the peak value of the air gap is less than 8mV and more than 48mV for some, and the power distribution band is 98MHZ~146MHZ. The localized discharge characteristics of the defects of the GIS insulation parts are identified and detected by the immune optimization of the support vector machine algorithm. The overall recognition rate of immunodeficient partial discharges of insulating parts is around 0.90. This study is able to detect the type of partial discharges in GIS insulating parts well.

Partial Discharge Detection Technology for GIS Insulation Defects under Complex Electromagnetic Environment

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

This paper first introduces the main types of GIS insulation defects and explores the discharge mechanism of GIS insulation. Then, the space of discharge...

Partial Discharge Detection Technology for GIS Insulation Defects under Complex Electromagnetic Environment

Online veröffentlicht: 29. Nov. 2023

Seitenbereich: -

Eingereicht: 23. Jan. 2023

Akzeptiert: 09. Juni 2023

DOI: https://doi.org/10.2478/amns.2023.2.01293

Schlüsselwörter
Partial discharge, Feature construction, Principal component analysis, Immune algorithm, Support vector machine, Defective GIS insulation parts

© 2023 Chentian et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Partial Discharge Detection Technology for GIS Insulation Defects under Complex Electromagnetic Environment

Online veröffentlicht: 29. Nov. 2023

Seitenbereich: -

Eingereicht: 23. Jan. 2023

Akzeptiert: 09. Juni 2023

DOI: https://doi.org/10.2478/amns.2023.2.01293

SchlüsselwörterPartial discharge, Feature construction, Principal component analysis, Immune algorithm, Support vector machine, Defective GIS insulation parts

© 2023 Chentian et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Partial discharge, Feature construction, Principal component analysis, Immune algorithm, Support vector machine, Defective GIS insulation parts