Research On Fault Diagnosis Of Oil-immersed Transformer Based On Improved Grey Correlation Analysis

The power transformer is one of the important equipment of the power system and the heart of the power supply of industrial and mining enterprises.The main function is to transform the voltage of electric energy to meet the needs of various situations.The performance of power transformers will have a significant impact on the reliability of power supply,the normal operation of the system,and the normal production and life of power users.Therefore,it is of great significance to ensure the normal and safe operation of power transformers.At present,judging whether the power transformer is operating normally based on the dissolved gas in the transformer oil is the most commonly used monitoring and measurement method.Based on the analysis of the gas in the oil,the stability and accuracy of the fault diagnosis is further improved.This is the current fault diagnosis of the power transformer.Top issues for research.This article first discusses the related knowledge of power transformer faults,and summarizes the composition and content of dissolved gas in oil-immersed transformer oil,and uses the three-ratio method to conduct preliminary fault diagnosis on the faulty transformer as a later stage Contrast when verifying the feasibility of the method used in the thesis.Secondly,by discovering the shortcomings of the three-ratio method,the method of general gray correlation analysis is proposed.Because the previous gray correlation analysis has the problem of inaccurate or difficult to determine the standard sequence,it should be proposed before the second fault diagnosis.Fuzzy clustering method is used to determine the standard sequence for the actual oil-immersed transformer fault data.Then,on the basis of the second fault diagnosis,it is clarified that the general gray correlation analysis has the problem of insufficient accuracy.In order to solve this problem,the entropy weight method is introduced,and the correlation coefficient is objectively assigned to construct an improved gray correlation analysis.model.Finally,the third fault diagnosis is carried out by using MATLAB software in combination with examples,and the diagnosis results are compared with the previous two times to verify the feasibility and effectiveness of the improved gray correlation method.The summary analysis of the composition and content of the gas dissolved in the transformer oil when the oil-immersed transformer fails,as well as the improvement of the general gray correlation analysis standard sequence and correlation calculation model,provide a new basis for transformer fault diagnosis.This paper has certain practical significance for realizing the economical and stable operation of oil-immersed transformers and improving the reliability of power systems.