Back to Search
Start Over
New approach for accurate discrimination and location of power transformers with different internal winding faults.
- Source :
-
PloS one [PLoS One] 2024 Oct 11; Vol. 19 (10), pp. e0309926. Date of Electronic Publication: 2024 Oct 11 (Print Publication: 2024). - Publication Year :
- 2024
-
Abstract
- Power transformers are essential elements in power systems and thus their protection schemes have critical importance. In this paper, a scheme is proposed for accurate discrimination and location of internal faults in power transformers using conventional measuring devices attached to the transformer. Different types of internal winding faults are intensely considered: partial discharge, inter-disk faults, series and shunt short circuit faults and axial displacement. Depending on the transformer measured output voltage, input voltage and the input current, the construction of a locus diagram (ΔV-Iin) serves as an indicator for any physical modification to the winding. Using five suggested features extracted from the developed locus, an artificial neural network (ANN) technique is applied to accurately distinguish any deviation from the transformer healthy condition. The exact location of each fault inside the windings of power transformer is then determined. The obtained results validate the usefulness of the proposed scheme for different internal faults. The superiority of the proposed scheme is extensively examined by comparing its results with some published schemes.<br />Competing Interests: NO authors have competing interests.<br /> (Copyright: © 2024 Youssef et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
- Subjects :
- Algorithms
Neural Networks, Computer
Electric Power Supplies
Subjects
Details
- Language :
- English
- ISSN :
- 1932-6203
- Volume :
- 19
- Issue :
- 10
- Database :
- MEDLINE
- Journal :
- PloS one
- Publication Type :
- Academic Journal
- Accession number :
- 39392809
- Full Text :
- https://doi.org/10.1371/journal.pone.0309926