Open AccessPCA Fault Feature Extraction in Complex Electric Power Systems
Author(s) -
Yuhai ZHANG,
Zixuan Wang,
JingLe Zhang,
Jing Ma
Publication year - 2010
Publication title -
advances in electrical and computer engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.254
H-Index - 23
eISSN - 1844-7600
pISSN - 1582-7445
DOI - 10.4316/aece.2010.03017
Subject(s) - feature extraction , computer science , fault (geology) , feature (linguistics) , electric power system , pattern recognition (psychology) , electric power , extraction (chemistry) , artificial intelligence , power (physics) , data mining , geology , chemistry , linguistics , philosophy , physics , chromatography , quantum mechanics , seismology
Electric power system is one of the most complex artificial systems in the world. The complexity is determined by its characteristics about constitution, configuration, operation, organization, etc. The fault in electric power system cannot be completely avoided. When electric power system operates from normal state to failure or abnormal, its electric quantities (current, voltage and angles, etc.) may change significantly. Our researches indicate that the variable with the biggest coefficient in principal component usually corresponds to the fault. Therefore, utilizing real-time measurements of phasor measurement unit, based on principal components analysis technology, we have extracted successfully the distinct features of fault component. Of course, because of the complexity of different types of faults in electric power system, there still exists enormous problems need a close and intensive study