Random-forest-model-based power transformer fault diagnosis method

Abstract

The invention discloses a random-forest-model-based power transformer fault diagnosis method, which comprises the following steps of: acquiring transformer state overhauling data, training a random forest model by utilizing the transformer state overhauling state, checking the sensitivity of the random forest model, and diagnosing a fault of a transformer by using the trained and checked random forest model. The method provided by the invention is high in adaptability and interpretability; and criticality between normality and the fault is separated by utilizing a k-means clustering method, and a system is endowed with fault early warning capability.

Description

technical field [0001] The invention relates to a power transformer fault diagnosis method, in particular to a power transformer fault diagnosis method based on a random forest model. Background technique [0002] The power transformer is an important equipment in the power system. Due to the complex internal structure of the transformer, the distribution of the electric field is uneven, and with the increase of the voltage level, the accident rate is on the rise. According to incomplete statistics, there are several major transformer accidents in China every year, causing direct economic losses of millions of yuan. In addition, according to the statistical analysis results of the national power reliability released by the China Electricity Council Electric Power Reliability Management Center in recent years, the part with the highest failure rate is the internal insulation of the transformer. Poor, transformer manufacturing quality problems. As the main equipment of the p...

AI Technical Summary

Problems solved by technology

The application practice has proved that the random forest has the advantages of fast speed, anti-noise, can handle any type of data, and can output the importance of factors, etc., but it has not been applied in the fault diagnosis of power transformers.