Comprehensive method detecting the status of the transformer based on the artificial intelligence

Transformer is one of the most important equipment in power system, diagnosis of abnormal power transformer is important for the reliability of the power system and detecting the operating status of transformer accurately in time is of vital importance. A combined artificial neural network and expert systems tool (ANNES) is developed for transformer fault diagnosis using dissolved gas-in-oil analysis (DGA), ANNEPS takes advantage of the inherent positive features of each method and offers a further refinement of present techniques. The knowledge base of its expert system (ES) is derived from IEEE and IEC DGA standards and expert experiences to include as many known diagnosis rules as possible. The topology and training data set of its ANN are carefully selected to extract known as well as unknown diagnosis correlations implicitly. The combination of the ANN and ES outputs has an optimization mechanism to ensure high diagnosis accuracy for all genera! fault types. ANNES is database enhanced to facilitate archive management of equipment conditions, trend analysis, and further revision of the diagnosis rules. Depending on the analysis results, maintenance engineers can arrange corresponding maintenance plan and different maintenance contents. This Paper also issues a new condition-based power device maintenance method integrated with management information system (MIS). Several test show this method is very reliable an practical and the system has better performance than ANN or ES used.