Intelligent transformer fault diagnostic method based on RBF (radial basis function) neural network

Abstract

The invention discloses an intelligent transformer fault diagnostic method based on an RBF (radial basis function) neural network. The intelligent method includes (1), acquiring three ratios of five gases C2H2 / C2H4, CH4 / H2, C2H4 / C2H6 as training sample data by the utilizing IEC (international electrotechnical commission) three ratio method; (2) performing fuzzily processing on the three ratios by utilizing a membership function; (3), coding fault types; (4), training the RBF neural network according to the training sample data until the RBF neural network meets precision requirements; (5), inputting to-be-diagnosed samples after being fuzzily processed; and (6), outputting diagnosed results. The intelligent transformer fault diagnostic method has good reasoning ability and high diagnosed precision, overcomes the defects of the IEC three ratio method, and can precisely display all transformer fault problems.

Description

technical field [0001] The invention relates to the field of transformer fault diagnosis, in particular to an intelligent method for transformer fault diagnosis based on RBF neural network. Background technique [0002] At present, the transformer is one of the important pivotal equipment in the power system. It undertakes the important task of transforming voltage, distributing and transmitting electric energy, and is of great significance to the economical transmission, flexible distribution and safe use of electric energy. Its operating status directly affects the entire electric power system. The safe operation and stability of the system. [0003] There are many methods for transformer fault diagnosis, most of which use the property that different types of transformer faults correspond to different dissolved gas concentrations in transformer oil, and at the same time analyze the concentration of various fault characteristic gases to find potential faults of transformers...

AI Technical Summary

Problems solved by technology

However, the IEC three-ratio method has the following deficiencies: ①Because the internal faults of the transformer are very complex, the code combination recommended by the three-ratio method obtained from the statistical analysis of typical accidents often occurs in practical applications and is not included in the code list of the fault type judgment method Errors corresponding to code combinations

If the three-ratio method is used regardless of whether the transformer is faulty or not, it may cause misdiagnosis of the normal transformer.

③In practical applications, when there are multiple faults combined, the corresponding ratio combination may not be found in the code combination and fault type correspondence table. often misjudged

Due to the ambiguity of fault classification, the fault state may cause multiple fault features, and one fault feature can also reflect multiple fault states to varying degrees, so the three-ratio method cannot fully reflect the fault state

There is ambiguity in the fault itself, and there is also ambiguity between each group of codes and the fault type. The three-ratio value cannot include and reflect all forms of transformer internal faults

Images