Transformer fault diagnosis method based on improved fuzzy C-means clustering algorithm

Abstract

The invention discloses a transformer fault diagnosis method based on an improved fuzzy C-means clustering algorithm. The method includes the following steps: acquiring transformer oil dissolved gas data and fault type data as samples, and dividing the samples into training samples and test samples; processing the transformer oil dissolved gas data in the samples, and determining the number of categories of the training samples and the initial clustering center corresponding to each category; using an improved fuzzy C-means clustering algorithm to further determine the new clustering center corresponding to each category of the training samples, and calculating the probability that each test sample belongs to each category; and calculating the occurrence probability that each test sample corresponds to each fault type according to the probability that each test sample belongs to each category and the proportion of each fault type in each category, and determining the fault type of eachtest sample according to the occurrence probability. The fault of a transformer can be quickly diagnosed through clustering analysis of the historical data of the dissolved gas in the transformer oiland the fault types.

Description

technical field [0001] The invention belongs to the technical field of transformer fault diagnosis, and in particular relates to a transformer fault diagnosis method based on an improved fuzzy C-means clustering algorithm. Background technique [0002] The power industry has always been a basic industry related to the national economy and people's livelihood. Since the 13th Five-Year Plan, the Party Central Committee and the State Council have placed power supply and security at an important level that is related to the national security strategy and the overall economic and social development. As the key hub equipment of the power system, the operation status of the transformer is directly related to the safety and stability of the whole power system. Once a transformer fails, it will cause huge economic losses and potential safety hazards, and even cause serious social impacts. Therefore, it is very necessary to carry out fault diagnosis on the transformer. Dissolved ga...

AI Technical Summary

Problems solved by technology

[0003] Aiming at the shortcomings of low fault diagnosis accuracy in the prior art and unable to meet engineering requirements, the present invention provides a transformer fault diagnosis method based on an improved fuzzy C-means clustering algorithm

Images