Transformer fault diagnosis method based on membership degree

Abstract

The invention relates to transformer fault diagnosis techniques, in particular to a transformer fault diagnosis method based on the membership degree. Classic chromatographic data corresponding to each kind of fault is obtained by utilizing the data of dissolved gas in oil of a transformer in the known fault type and a clustering method; the similarity of the to-be-diagnosed dissolved gas data inoil and the classic chromatographic data of each kind of fault is computed one by one, the similarity is normalized to obtain the membership degree of each kind of fault, and the membership degree isused to present the membership degree of the to-be-diagnosed data on each kind of fault so that fault diagnosis is achieved. The method overcomes the shortcomings that misjudgment are prone to occur near the fault boundary in traditional methods such as a three-ratio method and a Duval's triangle method, and can precisely present the seriousness degree of the overheating fault and the dischargingfault, the fault diagnosis correct rate is high, and the method has the simple and practical mathematical process when compared with intelligent diagnosis methods such as support vector machines and artificial neural networks.

Description

technical field [0001] The invention belongs to the technical field of transformer fault diagnosis, in particular to a transformer fault diagnosis method based on membership degree. Background technique [0002] Power transformers and associated reactors, current transformers, voltage transformers, etc. are the most important electrical equipment in power systems. The operating status of these electrical equipment filled with mineral insulating oil and using paper or laminated cardboard as insulating materials (especially the operating status of power transformers) has a decisive effect on the reliability of power system operation. Gas chromatography is widely used in power systems to find transformer insulation defects. Many hidden dangers have been discovered in time in the preventive tests of power equipment. The analysis of dissolved gases in transformer oil is the most common method for transformer fault diagnosis. The internal structure of oil-filled power transformer...

AI Technical Summary

Problems solved by technology

In the above two methods, there is a strict boundary between faults, and data near the boundary is prone to misjudgment

Various intelligent classifiers based on modern intelligent algorithms, such as artificial neural network, support vector machine and other methods are also used in transformer fault diagnosis, but the diagnosis results of these methods rely on a large number of samples for training and learning, and are usually more complicated. Apps in are restricted

Images