Application of Neural Networks to Fault Diagnosis for HVDC Systems
This paper describes a neural network design and its simulation results for fault diagnosis for thyristor converters and the HVDC power system. Fault diagnosis is carried out by mapping input data pattern, which represent the behaviour of the system, to one or more fault conditions. The behaviour of the converters is described in terms of the time varying patterns of conducting thyristors, pulse zone periods, voltage zone periods and ac & dc fault characteristics.
A three-layer neural network consisting of 24 input nodes, 12 hidden nodes and 13 output nodes are used. 13 different faults were considered, although a lot of research still ne.ed to be done, the neural network approach shows a great potential as a more effective strategy for fault diagnosis.
KeywordsHide Layer Fault Diagnosis Hide Node Fault Condition Conduction Pattern
Unable to display preview. Download preview PDF.
- 1.L.L. Lai and X.F. Wang, “Application of artificial neural network to power system control”, Proceedings of the Ninth Conference on Electric Power Supply Industry, The Association of the Electricity Supply Industry of East Asia and the Western Pacific, Hong Kong, Vol 4, Nov 1992, pp 349–357.Google Scholar
- 3.K.S. Swarup and H.S. Chandrasekharaiah, “FDES: fault diagnosis expert systems for HVDC systems”, Second Symposium on Expert Systems for HVDC Systems, University of Washington, August 1989, 296–302.Google Scholar
- 4.R.P. Lippman, “An introduction to computing with neural nets”, IEEE ASSP Magazine, April 1987, 4-22.Google Scholar
- 6.J. Reeve, “Logic behaviour of h.v.d.c. convertors during normal and abnormal conditions”, Proc IEE, Vol 114, No 12, Dec 1967, 1937–1946.Google Scholar
- 7.J. Reeve, “Direct digital protection of HVDC convertor”, Proc IEE, Vol 114, No 12, Dec 1967, 1947–1954.Google Scholar