Comparison of the performance of artificial neural networks and fuzzy logic for recognizing different partial discharge sources.

Mas'ud, Abdullahi Abubakar; Ardila-Rey, Jorge Alfredo; Albarrac�n, Ricardo; Muhammad-Sukki, Firdaus; Bani, Nurul Aini

Abstract

This paper compared the capabilities of the artificial neural network (ANN) and the fuzzy logic (FL) approaches for recognizing and discriminating partial discharge (PD) fault classes. The training and testing parameters for the ANN and FL comprise statistical fingerprints from different phase-Amplitude-number (f-q-n) measurements. Two PD fault classes considered are internal discharges in voids and surface discharges. In the void class, there are single voids, serial voids and parallel voids in polyethylene terephthalate (PET), while the surface discharge class comprises four different surface discharge arrangements on pressboard in oil at different voltages and angular positioning of the ground electrode on the respective pressboards. Previously, the ANN and FL have been investigated for PD classification, but there is no work reported in the literature that compares their performance, specifically when applied for real time PD detection problem. As expected, both the ANN and FL can recognize PD defect classes, but the results show that the ANN appears to be more robust as compared to the FL, but these conclusions required to be further investigated with complex PD examples. Finally, both the ANN and FL were assessed as practical PD classification. Despite of the limitations of the ANN, it is concluded that the ANN is better suited for practical PD recognition because of its ability to provide accurate recognition values and the severity level of PD defects.

Citation

MAS'UD, A.A., ARDILA-REY, J.A., ALBARRACIN, R., MUHAMMAD-SUKKI, F. and BANI, N.A. 2017. Comparison of the performance of artificial neural networks and fuzzy logic for recognizing different partial discharge sources. Energies [online], 10(7), article number 1060. Available from: https://doi.org/10.3390/en10071060

• Journal Article Type: Article
• Acceptance Date: Jan 6, 2017
• Online Publication Date: Jul 21, 2017
• Publication Date: Jan 30, 2017
• Deposit Date: Aug 28, 2017
• Publicly Available Date: Aug 28, 2017
• Journal: Energies
• Electronic ISSN: 1996-1073
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 10
• Issue: 7
• Article Number: 1060
• DOI: https://doi.org/10.3390/en10071060
• Keywords: Partial discharge; Fuzzy logic; Artifical neural network; Polyethylene terephthalate
• Public URL: http://hdl.handle.net/10059/2470
• Contract Date: Aug 28, 2017