Application of fuzzy data processing for fault diagnosis of power transformers

Based on the data of dissolved gas analysis (DGA), fuzzy cluster analysis (FCA) technique is applied to identify the fault patterns of power transformers in this paper. FCA consists of some trial and instructive strategies absorbing useful experiences from the mid-results. Its clustering centers are dynamic, as a result, the approach can classify and recombine different samples sucessfully. Compared with the conventional methods, it reveals the practical advantages of unsupervised systems, including the ability to produce categories without supervision.