The Research And Development On The System Of Power Transformer Online Monitoring And Fault Diagnosis

Power Transformer is one of the most critical equipments in power system, and its running state is directly related to the security and stability of the power system. In case of transformer failure, it can cause a large scale power failure, even worse it could cause an explosion or fire, which could make a great economic loss and casualties. Therefore, to ensure the safety, reliability, economic operational quality of the power system, early detection of the latent failure and improve the maintenance level of power transformer is very important.This paper uses neural networks for on-line transformer monitoring and fault diagnosis system. It achieves the status from data of running transformer. When transformer is in fault, the system can diagnose the type of fault and decision-making and alert clerk in time. The main work of this dissertation is as follows:1. The overall structure of transformer on-line monitoring and fault diagnosis system is designed on the basis of analysis of the functional requirements of the entire system.2. The structure of database is designed on the basis of analysis of the operations of database.3. Several ways to implement the theory of the transformer diagnose is analyzed. Due to the complexity of transformer failure, a diagnostic algorithms based on DGA and BP Net is adopted to improve the system failure diagnosis.4. Visual C++ 6.0, MYSQL are used to design the monitoring terminal and main surface of the system.