Translationally adaptive fuzzy classifier for transformer impulse fault identification

The determination of transformer fault categories using soft-computing based techniques has been the subject of much research in the recent past. The development of an adaptive fuzzy classifier which can effectively determine various classes or categories of series and shunt impulse faults in a wide range of power transformers is described. The system employs a self-generating module to automatically derive a fuzzy rule base from predefined input and output membership functions (MFs) and a given data set for different fault classes. The accuracy of the system is further improved by translationally adapting output MF(s) either forward or backward, keeping their size and shape invariant. The database for different classes of faults is developed from FFT operation on current and voltage waveforms, obtained for different possible fault conditions simulated for given transformer models (EMTP) using an electromagnetic transients program. This database is used to create training and testing data sets required to design the fuzzy based classifier system. The usefulness of the proposed fuzzy based classifier is demonstrated on the basis of performances shown for four example power transformers of 1 MVA, 3 MVA, 5 MVA and 60 MVA ratings.