Transformer fault diagnosis method

Abstract

The invention discloses a transformer fault diagnosis method. The method comprises the steps of collecting historical preventive test data and fault data of a transformer in a power system and preprocessing the historical preventive test data and fault data; analyzing correlation between preprocessed data items by using a correlation analysis strategy to obtain a characteristic quantity set; optimizing a support vector machine through combination of the characteristic quantity set and an ant lion optimization strategy to obtain an optimized support vector machine model; and performing fault diagnosis on the transformer by using the support vector machine model. According to the method, a large amount of preventive test data and historical fault data of the transformer are combined, the relevance among the data is analyzed, fault information in the pre-test data of the transformer is extracted, a training data set and a test data set are established, and transformer fault diagnosis is performed by using the support vector machine model after ant lion optimization, so the method has the advantages of high accuracy and short training time, and has practical engineering application value.

Description

technical field [0001] The invention relates to the technical field of power systems, in particular to a transformer fault diagnosis method. Background technique [0002] Whether the power system can operate safely and stably and avoid accidents as much as possible depends largely on the power equipment in the system. Once the equipment fails, the safe operation state of the power grid will be very likely to be destroyed. Therefore, the safe operation of power equipment is the first line of defense to avoid major accidents in the power grid. As the hub equipment of the power system, power transformers are expensive and expensive to maintain. , will directly affect whether the power grid can operate safely and stably. [0003] The preventive test of the transformer detects and evaluates various characteristic quantities according to the operation of the transformer, which brings a large amount of pre-test data. The operating status, especially reflects various fault conditi...

AI Technical Summary

Problems solved by technology

At present, the commonly used fault diagnosis methods are mostly intelligent algorithms based on operating data, and there are problems such as insufficient data application and inability to efficiently select associated data

Images