A neural net based approach for fault diagnosis in distribution networks Conference Paper

abstract

• A neural network based approach is proposed for the fault diagnosis in electric distribution networks. The method allows the detection of low or high impedance faults in the presence of arcing in grounded or ungrounded systems that are normally not detected by conventional overcurrent protection devices. The method uses a signal preprocessor and a supervised clustering based diagnosis system. The effectiveness of the fault diagnosis method is demonstrated for a field test system using data recorded at two four-wire utility distribution systems.

name of conference

• IEEE Power Engineering Society. 1999 Winter Meeting (Cat. No.99CH36233)

authors

• Butler-Purry, Karen

published proceedings

• IEEE POWER ENGINEERING SOCIETY - 1999 WINTER MEETING, VOLS 1 AND 2

author list (cited authors)

• Butler, K. L., & Momoh, J. A.

citation count

• 4

complete list of authors

• Butler, KL||Momoh, JA

publication date

• January 1999

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

keywords

• 40 Engineering
• 4007 Control Engineering, Mechatronics And Robotics
• 4010 Engineering Practice And Education
• 46 Information And Computing Sciences
• 4611 Machine Learning

Digital Object Identifier (DOI)

• 10.1109/PESW.1999.747478

International Standard Book Number (ISBN) 10

• 0-7803-4894-X

start page

• 353

end page

• 356

volume

• 1

URL

• http://dx.doi.org/10.1109/pesw.1999.747478