Extreme learning machine based fault diagnosis of power transformer using IEC TC10 and its related data

The dissolved gas-in-oil analysis (DGA) is a prevailing methodology being widely used to detect incipient faults in power transformers. However various methods have been developed to interpret DGA results, they may sometimes fail to diagnose precisely. The incipient fault identification accuracy of various artificial intelligence (AI) based methodology is varied with variation of input variable. Thus, selection of input variable to an AI model is major research area. In this paper, principle component analysis using RapidMiner software is applied to IEC TC10 and related datasets to identify most relevant input variables for incipient fault classification. Thereafter, extreme learning machine (ELM) is implemented to classify the incipient faults of power transformer and its performance is compared with fuzzy-logic and artificial neural network. The compared results shows that ELM provides better diagnosis results with proposed input variables.