A kind of abnormal identification method of dissolved gas in transformer oil

Abstract

The invention discloses a method for identifying an exception of dissolved gas in transformer oil. The method comprises the steps of obtaining historical data of the dissolved gas in the transformer oil and preprocessing the data; calculating a gradient component, a periodic component and a random self-regression component of the dissolved gas in the transformer oil; establishing a combination function according to the gradient component, the periodic component and the random self-regression component of the dissolved gas; and calculating an output error of the combination function, and judging the exception of the dissolved gas according to the output error. Compared with a conventional exception identification method, the method has the advantages that a complex correlation relationship of multi-dimensional parameters is simplified, real-time detection of the exception is realized, and the accuracy of identifying the exception of the dissolved gas is improved.

Description

technical field [0001] The invention relates to the technical field of transformers, in particular to a method for identifying abnormalities of dissolved gas in transformer oil. Background technique [0002] At present, the dissolved gas in the transformer oil is an important index to evaluate the operation status of the transformer. At present, the power sector generally uses the threshold method to warn transformers. In the traditional abnormality identification method, the dissolved gas in the transformer oil is monitored. When a certain characteristic gas detected exceeds the preset attention value, the monitoring system will give Corresponding alarm information, but this traditional threshold judgment has limitations. On the one hand, the utilization rate of equipment information and the correct rate of status evaluation are low. On the other hand, it is difficult to detect latent faults and fault types of equipment. It is difficult to combine the fixed threshold value...

AI Technical Summary

Problems solved by technology

At present, the power sector generally uses the threshold method to warn transformers. In the traditional abnormality identification method, the dissolved gas in the transformer oil is monitored. When a certain characteristic gas detected exceeds the preset attention value, the monitoring system will give Corresponding alarm information, but this traditional threshold judgment has limitations. On the one hand, the utilization rate of equipment information and the correct rate of status evaluation are low. On the other hand, it is difficult to detect latent faults and fault types of equipment. It is difficult to combine the fixed threshold in the equipment operating conditions with the difference, so the accuracy of the traditional abnormal identification method is low

Images