Localisation of inter-layer partial discharges in transformer windings by logistic regression and different features extracted from current signals

• Published in: IET science, measurement & technology Vol. 14; no. 10; pp. 913 - 922
• Main Authors: Júnior, Arismar M.G, de Paula, Hélder, Boaventura, Wallace C, Lopes, Sofia M.A, Flauzino, Rogério A, Alberto Correa Altafim, Ruy
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 20.12.2020
• Subjects: current signals; detailed comparative analysis; discharge occurrence points; feature extraction; high‐frequency current signals; incipient failures; interlayer partial discharges; localisation structure; location method; logistic regression models; partial discharges; PD localisation; PD signals; power transformers; prototype winding; regression analysis; Research Article; transformer windings; winding endings; PD signals; power transformers; localisation structure; regression analysis; interlayer partial discharges; winding endings; detailed comparative analysis; PD localisation; transformer windings; current signals; feature extraction; discharge occurrence points; incipient failures; high-frequency current signals; prototype winding; logistic regression models; partial discharges; location method
• ISSN: 1751-8822; 1751-8830
• DOI: 10.1049/iet-smt.2020.0186

Partial discharge (PD) investigations can identify and localise incipient failures in power transformers early, thus avoiding considerable financial losses. The feature extraction of PD signals is a fundamental step for the development of such location techniques since it directly influences the performance of a location method. This study presents a detailed comparative analysis of four traditional approaches for the obtaining of attributes towards a better set of signal features for the location of PDs. The approaches were critically compared regarding their ability to locate experimentally generated discharges between adjacent layers of a prototype winding. In order to perform such analysis, a localisation structure based on logistic regression models was elaborated, capable of determining both layers and sections of the winding affected by PDs and easily applicable in practice. The results show energy features of wavelet coefficients, obtained through the decomposition of high-frequency current signals acquired at the winding endings, achieve better performance in the PD localisation, accurately indicating discharge occurrence points among layers and sections of the winding.