Premium
Fault diagnosis of transformer based on modified grey wolf optimization algorithm and support vector machine
Author(s) -
Huang Xinyi,
Huang Xiaoli,
Wang Binrong,
Xie Zhenyu
Publication year - 2020
Publication title -
ieej transactions on electrical and electronic engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 30
eISSN - 1931-4981
pISSN - 1931-4973
DOI - 10.1002/tee.23069
Subject(s) - support vector machine , particle swarm optimization , transformer , fault (geology) , algorithm , electric power system , power grid , computer science , differential evolution , optimization algorithm , genetic algorithm , engineering , artificial intelligence , mathematical optimization , power (physics) , machine learning , mathematics , physics , quantum mechanics , voltage , seismology , geology , electrical engineering
Power transformers are important pieces of equipment for the operation of power systems. Accurate diagnosis of their fault is closely related to the stable operation of the entire power grid. In order to improve the diagnostic accuracy of transformer fault, the grey wolf optimization (GWO) algorithm is introduced, and the differential evolution mechanism is integrated into the algorithm. Therefore, this paper proposes a transformer fault diagnosis method based on the modified grey wolf optimization algorithm (MGWO) and support vector machine (SVM), so that the application method realizes optimization of the penalty factor and the kernel parameter in SVM. Through the analysis of existing data examples, the SVM model optimized by the MGWO algorithm has the advantages of good generalization and strong predictive ability, and its fault diagnostic accuracy is higher than those of the genetic algorithm, particle swarm optimization algorithm, and GWO algorithm. This method has practical application significance. © 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.