A pattern-based fault classification algorithm for distribution transformers

In this paper, we propose a fault diagnosis method for a group of distribution transformers using the graphical information of frequency responses. For a group of transformers with similar capacities and ratings, the patterns of transformerʹs magnitude plots appear to be almost identical with minor variations of amplitudes and locations of existing peaks and valleys in the plots. Therefore, it is reasonable to establish prototypes composed of several peaks and valleys for magnitude plots and to investigate their changes for the purpose of diagnosis. We select six most significant regions for check regions, and their movements are encoded into a ternary string which is then compared with strings already constructed for various types of faults. Each string-by-string comparison is quantified into correlation values by computing Hamming distances and weighting selected bits. The fault type whose correlation values is largest is determined as a most probable fault in a test transformer. The diagnosis performance of the proposed method is proven to be reliable via experiment data on several types of faults.