Counterpropagation network based fault classification for double-circuit lines

The work described in this paper addresses the problem of fault type detection in double-circuit lines due to mutual coupling under fault conditions, and the mutual coupling is nonlinear. However, a combined unsupervised/supervised training technique (counterpropagation neural network) provides the ability to classify the fault type by identifying different patterns of the associated voltages and currents. It is then tested under different fault type, location, resistance, inception angle and different source impedance cases are also studied. All test results show that the proposed fault classifier is well suited for double-circuits.