Study On Transformer Condition Evaluation And Information Management System

With the constant promotion of the condition based maintenance in the power system, it has been an important subject that how to apply transformer condition information efficiently and scientifically to judge the transformer's state. Then, the dissertation systematically analyzes the transformer's faults and fault detection technique. After analyzing shortcoming of neural network and D-S Evidence theory respectively, we develop a method of hierarchical information fusion condition evaluation based on neural network and D-S Evidential theory, and discuss the principle and steps in detail. Having considered the situation of transformer prevention tests, the dissertation selected the necessary status information, and proved that the method has good veracity and reliability of diagnosis. With Delphi and SQL Server 2000 database, the transformer condition evaluation and information management system has been set up. Supported by its operation, the system can completely take on the condition information management and provide substantial boosts for transformer condition maintenance under the real conditions.