Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning System
This paper addresses the critical challenge of detecting, separating, and classifying partial discharges in substations. It proposes two solutions: the first involves developing a signal conditioning system to reduce the sampling requirements for PD detection and increase the signal-to-noise ratio....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/7/2226 |
| _version_ | 1797211935473664000 |
|---|---|
| author | Itaiara Felix Carvalho Edson Guedes da Costa Luiz Augusto Medeiros Martins Nobrega Allan David da Costa Silva |
| author_facet | Itaiara Felix Carvalho Edson Guedes da Costa Luiz Augusto Medeiros Martins Nobrega Allan David da Costa Silva |
| author_sort | Itaiara Felix Carvalho |
| collection | DOAJ |
| description | This paper addresses the critical challenge of detecting, separating, and classifying partial discharges in substations. It proposes two solutions: the first involves developing a signal conditioning system to reduce the sampling requirements for PD detection and increase the signal-to-noise ratio. The second approach uses machine learning techniques to separate and classify PD based on features extracted from the conditioned signal. Three clustering algorithms (K-means, Gaussian Mixture Model (GMM), and Mean-shift) and the Support Vector Machine (SVM) method were used for signal separation and classification. The proposed system effectively reduced high-frequency components up to 50 MHz, improved the signal-to-noise ratio, and effectively separated different sources of partial discharges without losing relevant information. An accuracy of up to 93% was achieved in classifying the partial discharge sources. The successful implementation of the signal conditioning system and the machine learning-based signal separation approach opens avenues for more economical, scalable, and reliable PD monitoring systems. |
| first_indexed | 2024-04-24T10:34:23Z |
| format | Article |
| id | doaj.art-3bbb2a35ae3e4776b2c1d4b2979e6588 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T10:34:23Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3bbb2a35ae3e4776b2c1d4b2979e65882024-04-12T13:26:32ZengMDPI AGSensors1424-82202024-03-01247222610.3390/s24072226Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning SystemItaiara Felix Carvalho0Edson Guedes da Costa1Luiz Augusto Medeiros Martins Nobrega2Allan David da Costa Silva3Department of Electrical Engineering, Federal University of Campina Grande, Aprigio Veloso 882, Universitário, Campina Grande 58429-900, BrazilDepartment of Electrical Engineering, Federal University of Campina Grande, Aprigio Veloso 882, Universitário, Campina Grande 58429-900, BrazilDepartment of Electrical Engineering, Federal University of Campina Grande, Aprigio Veloso 882, Universitário, Campina Grande 58429-900, BrazilDepartment of Electrical Engineering, Federal University of Campina Grande, Aprigio Veloso 882, Universitário, Campina Grande 58429-900, BrazilThis paper addresses the critical challenge of detecting, separating, and classifying partial discharges in substations. It proposes two solutions: the first involves developing a signal conditioning system to reduce the sampling requirements for PD detection and increase the signal-to-noise ratio. The second approach uses machine learning techniques to separate and classify PD based on features extracted from the conditioned signal. Three clustering algorithms (K-means, Gaussian Mixture Model (GMM), and Mean-shift) and the Support Vector Machine (SVM) method were used for signal separation and classification. The proposed system effectively reduced high-frequency components up to 50 MHz, improved the signal-to-noise ratio, and effectively separated different sources of partial discharges without losing relevant information. An accuracy of up to 93% was achieved in classifying the partial discharge sources. The successful implementation of the signal conditioning system and the machine learning-based signal separation approach opens avenues for more economical, scalable, and reliable PD monitoring systems.https://www.mdpi.com/1424-8220/24/7/2226signal conditioning systempartial dischargeclassification of partial discharges |
| spellingShingle | Itaiara Felix Carvalho Edson Guedes da Costa Luiz Augusto Medeiros Martins Nobrega Allan David da Costa Silva Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning System Sensors signal conditioning system partial discharge classification of partial discharges |
| title | Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning System |
| title_full | Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning System |
| title_fullStr | Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning System |
| title_full_unstemmed | Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning System |
| title_short | Identification of Partial Discharge Sources by Feature Extraction from a Signal Conditioning System |
| title_sort | identification of partial discharge sources by feature extraction from a signal conditioning system |
| topic | signal conditioning system partial discharge classification of partial discharges |
| url | https://www.mdpi.com/1424-8220/24/7/2226 |
| work_keys_str_mv | AT itaiarafelixcarvalho identificationofpartialdischargesourcesbyfeatureextractionfromasignalconditioningsystem AT edsonguedesdacosta identificationofpartialdischargesourcesbyfeatureextractionfromasignalconditioningsystem AT luizaugustomedeirosmartinsnobrega identificationofpartialdischargesourcesbyfeatureextractionfromasignalconditioningsystem AT allandaviddacostasilva identificationofpartialdischargesourcesbyfeatureextractionfromasignalconditioningsystem |