Two new methods for very fast fault type detection by means of parameter fitting and artificial neural networks

A new method for the detection of the type of a fault in generator circuits and transmission systems is introduced. Already within a quarter of a cycl e after fault inception the method can distinguish between the various faul t types. Fitting the parameters of a set of simple equations to voltage and current measurements immediately before and after a fault identifies the f ault type. The procedure includes a new method for phasor computation and t akes less than 1 ms computation time. As a variant of this method neural ne tworks are employed. Verification using EMTP modeling proved satisfactory o peration of both methods even when the current signals were superimposed wi th heavy noise. Fast decisions for single pole tripping and a crucial basis for algorithms for synchronous switching under fault conditions are provid ed.