eduzhai > Applied Sciences > Engineering >

Intelligent Protection & Classification of Transients in Two-Core Symmetric Phase Angle Regulating Transformers

  • Save

... pages left unread,continue reading

Document pages: 9 pages

Abstract: This paper investigates the applicability of time and time-frequency featuresbased classifiers to distinguish internal faults and other transients -magnetizing inrush, sympathetic inrush, external faults with currenttransformer saturation, and overexcitation - for Indirect Symmetrical PhaseAngle Regulating Transformers (ISPAR). Then the faulty transformer unit(series exciting) of the ISPAR is located, or else the transient disturbance isidentified. An event detector detects variation in differential currents andregisters one-cycle of 3-phase post transient samples which are used to extractthe time and time-frequency features for training seven classifiers. Threedifferent sets of features - wavelet coefficients, time-domain features, andcombination of time and wavelet energy - obtained from exhaustive search usingDecision Tree, random forest feature selection, and maximum Relevance MinimumRedundancy are used. The internal fault is detected with a balanced accuracy of99.9 , the faulty unit is localized with balanced accuracy of 98.7 and theno-fault transients are classified with balanced accuracy of 99.5 . The resultsshow potential for accurate internal fault detection and localization, andtransient identification. The proposed scheme can supervise the operation ofexisting microprocessor-based differential relays resulting in higher stabilityand dependability. The ISPAR is modeled and the transients are simulated inPSCAD EMTDC by varying several parameters.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×