In this paper, PD signals are analyzed to localize defects in insulation systems. The task of automatic defect localization with respect to electrodes has a wide range of industrial applications. In fact, depending on the apparatus type, risk assessment is remarkably affected by defect location with respect to the electrodes. In this study, various parameters are first extracted from PD distributions, and statistical analysis is performed to select the most significant parameters concerning localization. Then, the localization process is carried out through numerical classification. Three different classification methods are compared to find the best approach for this application. Comparing a k-nearest neighbour classifier, a probabilistic neural network and a support vector machine (SVM) based classifier, the best results are gained with SVM, although the former two are simpler to implement and easier to tune. SVM based classification has not been applied in PD analysis before this approach.
Titolo: | INSULATION DEFECT LOCALIZATION THROUGH PARTIAL DISCHARGE MEASUREMENTS AND NUMERICAL CLASSIFICATION |
Autore/i: | S. Poyhonen; CONTI, MARCO; CAVALLINI, ANDREA; MONTANARI, GIAN CARLO; FILIPPETTI, FIORENZO |
Autore/i Unibo: | |
Anno: | 2004 |
Titolo del libro: | Proceedings of the IEEE International Symposium on Industrial Electronics, IEEE ISIE 2004, Ajaccio May 2004 |
Pagina iniziale: | 417 |
Pagina finale: | 422 |
Abstract: | In this paper, PD signals are analyzed to localize defects in insulation systems. The task of automatic defect localization with respect to electrodes has a wide range of industrial applications. In fact, depending on the apparatus type, risk assessment is remarkably affected by defect location with respect to the electrodes. In this study, various parameters are first extracted from PD distributions, and statistical analysis is performed to select the most significant parameters concerning localization. Then, the localization process is carried out through numerical classification. Three different classification methods are compared to find the best approach for this application. Comparing a k-nearest neighbour classifier, a probabilistic neural network and a support vector machine (SVM) based classifier, the best results are gained with SVM, although the former two are simpler to implement and easier to tune. SVM based classification has not been applied in PD analysis before this approach. |
Data prodotto definitivo in UGOV: | 27-set-2005 |
Appare nelle tipologie: | 4.01 Contributo in Atti di convegno |