Oil-immersed transformer fault diagnosis method based on clustering optimization

Abstract

The invention discloses an oil-immersed transformer fault diagnosis method based on clustering optimization, and the method is characterized in that the method comprises the following steps: S1, obtaining a data set of dissolved gas in fault transformer oil; s2, carrying out initialization processing on the gas data set; S3, clustering the dissolved gas data set by using the reconstructed clustering algorithm. and S4, according to a clustering result, counting the number of each fault type in each fault subset in each data subset, wherein the fault type with the maximum number of the fault types is the fault type of the fault subset. The fuzzy clustering algorithm is reconstructed, the DGA data analysis method based on membership calculation is provided, the convergence speed is high, and the number of iterations is small. The algorithm solves the problem of initial value sensitivity, and the classification result is stable. The membership function of the algorithm is a monotonic function of the distance and is reduced along with the increase of the difference between the element and the clustering center or the distance.

Description

technical field [0001] The invention relates to the field of transformer electrical performance testing, in particular to a cluster optimization-based oil-immersed transformer fault diagnosis method. Background technique [0002] The power transformer is the central equipment of energy conversion and transmission in the power system, which is crucial to the safe and reliable operation of the power grid. Under the action of high temperature and strong electromagnetic environment, the insulating material inside the transformer may have various forms of defects, resulting in overheating or discharge failure. Correctly diagnosing the latent faults of power transformers, especially large oil-immersed power transformers, is of great significance to improve the operation safety and reliability of power systems. But the fuzzy clustering analysis method is an important pattern recognition method and has a good application prospect in DGA data analysis. However, the algorithm has pr...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problems of initial value sensitivity, slow convergence speed, and many iterations in the fault diagnosis algorithm for the analysis of dissolved gas in transformer oil in the prior art, and provide a method that reduces the initial value sensitivity, reduces the number of iterations, and has a fast convergence speed. A Fault Diagnosis Method for Oil-immersed Transformer Based on Cluster Optimization

Images