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.