Intelligent systems for power transformers monitoring

In recent years for monitoring of power transformers intelligent systems as artificial neural networks (ANN), expert systems (ES), fuzzy sets (FS) and others have been proposed. Artificial neural networks have been most successfully applied to power transformer failure diagnosis. The objective of this work is to create ANN models for power transformer failures forecasting, based on chromatography analysis (using dissolved gas concentrations). The proposed combined ANN model was tested with real transformer failures. It was found that combined ANN model increasing accuracy of power transformer diagnostic.