Power transformer multi-parameter fault fusion diagnosis method

The fault diagnosis for large oil-immersed power transformer is generally carried out through preventive test data. However, the preventive test data must be obtained until power-off time, and the amounts and accuracy of the field data is limited. When a fault occurs in the running time, it always accompanies by the variations of the appearance such as color, sound, temperature and oil level, etc. That is the symptom phenomenon which can reflect the transformer failures quickly and accurately. Therefore, an idea that integrates both the preventive test data and the symptom phenomenon in the transformer fault diagnosis is proposed. According to a large number of data which reflect the transformer operation states, the corresponding relationships of failure modes and failure characteristic parameters is build up through the transformer composition structure. The characteristic parameters are divided into test data and symptoms phenomenon. After the diagnosis for both of the test data and the symptom phenomenon, their diagnostic results are fused. The given example shows that the established model can integrate various states information. It can be used as a kind of simple, accurate way for the on-scene application.