Application of probabilistic neural networks using high-frequency components’ differential current for transformer protection schemes to discriminate between external faults and internal winding faults in power transformers

Simple item page
dc.contributor.authorChiradeja, Pathomthat
dc.contributor.authorPothisarn, Chaichan
dc.contributor.authorPhannil, Nattanon
dc.contributor.authorAnanwattananporn, Santipont
dc.contributor.authorLeelajindakrairerk, Monthon
dc.contributor.authorNgaopitakkul, Atthapol
dc.contributor.authorThongsuk, Surakit
dc.contributor.authorPornpojratanakul, Vinai
dc.contributor.authorBunjongjit, Sulee
dc.contributor.authorYoomak, Suntiti
dc.date.accessioned2026-08-06T10:33:53Z
dc.date.available2026-08-06T10:33:53Z
dc.date.issued2021-11-01
dc.description.abstractInternal and external faults in a power transformer are discriminated in this paper using an algorithm based on a combination of a discrete wavelet transform (DWT) and a probabilistic neural network (PNN). DWT decomposes high-frequency fault components using the maximum coefficients of a 1/4 cycle DWT as input patterns for the training process in a decision algorithm. A division algorithm between a zero sequence of post-fault differential current waveforms and the differential current coefficient in the 1/4 cycle DWT is used to detect the maximum ratio and faults. The simulation system uses various study cases based on Thailand’s electricity transmission and distribution systems. The simulation results demonstrated that the PNN and BPNN are effectively implemented and perform fault detection with satisfactory accuracy. However, the PNN method is most suitable for detecting internal and external faults, and the maximum coefficient algorithm is the most effective in detecting the fault. This study will be useful in differential protection for power transformers.
dc.identifier.citationApplied Sciences Switzerland, 11(22), 2021
dc.identifier.doi10.3390/app112210619
dc.identifier.issn20763417
dc.identifier.other2-s2.0-85119249643
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/12373
dc.sourceApplied Sciences Switzerland
dc.subjectDifference relay
dc.subjectFault detection
dc.subjectPower transformer
dc.subjectProbabilistic neural network (PNN)
dc.subjectWavelet transform (WT)
dc.titleApplication of probabilistic neural networks using high-frequency components’ differential current for transformer protection schemes to discriminate between external faults and internal winding faults in power transformers
dc.typeArticle

Files

Collections

Research