Transformer fault diagnosis method

Abstract

The invention provides a transformer fault diagnosis method, and the method combines a tri-ratio method, a BP neural network and case-based reasoning for the fault diagnosis of a transformer, therebygreatly improving the fault diagnosis judgment accuracy of the transformer, reducing the maintenance cost, and reducing the maintenance risk. The method can achieve the better organization of all professionals, achieves the effective use of various types of state data of equipment, provides a technical support for the more accurate judgment of the states of equipment and the providing of an auxiliary decision making suggestion, and also lays a solid technical foundation for the good full-cycle management of grid assets. The method provides a reliable technical and management guarantee for thesafe, stable, reliable, long-period and good-quality operation of power grid equipment.

Description

technical field [0001] The invention relates to the technical field of transformer fault diagnosis, in particular to a transformer fault diagnosis method. Background technique [0002] Transformer is an important equipment in the power system, and its operating status directly affects the safety level of the power system. However, since the transformer is a closed whole that integrates multi-disciplinary technologies such as machinery, electricity, chemistry, and thermodynamics, the causes of its faults are intricate, and fault diagnosis requires various data and knowledge. The conclusion will inevitably lead to misjudgment or missed judgment. At present, the common fault diagnosis methods are the three-ratio judgment method, the overheating discharge diagram judgment method, the HAE triangular diagram judgment method, the characteristic gas method, etc. Although each single diagnosis method has a high recognition rate for some specific faults, it is also There are disadva...

AI Technical Summary

Problems solved by technology

However, for overheating type faults, when it is further judged whether it belongs to the overheating of the magnetic conduction circuit or the conductive circuit, the correct rate will be greatly reduced. It is not reliable enough to determine the fault only by a single fault diagnosis method, and it cannot meet the engineering needs.

Images