Transformer fault diagnosis method based on multi-classification support vector machine

Abstract

The invention relates to a transformer fault diagnosis method based on a multi-classification support vector machine, and the method comprises the following steps: S1, selecting the contents of at least two characteristic gases in a power transformer as sample data, and forming a sample set; s2, quantifying sample data in the sample set in the step S1; s3, establishing a multi-classification support vector machine fault diagnosis model, training the multi-classification support vector machine fault diagnosis model by using the sample data obtained in the step S2, and carrying out parameter optimization on the multi-classification support vector machine fault diagnosis model by using a training result; and S4, inputting the sample data of the power transformer to be diagnosed into the trained multi-classification support vector machine fault diagnosis model, and outputting a diagnosis type by the multi-classification support vector machine fault diagnosis model.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of power transformer equipment, and more specifically, to a transformer fault diagnosis method based on a multi-classification support vector machine. Background technique [0002] As the first line of defense for power grid security, power transformer failure has always been one of the most important factors that endanger the safety of the entire power grid. Once the power transformer fails, it may cause a large-scale power outage and cause huge economic losses. Therefore, improving the operation, maintenance and repair level of power transformers, preventing and reducing the probability of failures are key issues that need to be solved urgently in the power industry. [0003] The common latent faults of power transformers are mainly divided into three categories: mechanical faults, overheating faults and discharge faults. The faults have different symptoms during the development process...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical defects of low accuracy and poor reliability in the transformer fault diagnosis method in the prior art, the present invention provides a transformer fault diagnosis method based on multi-classification support vector machine, which can pass the relevant sample data of the transformer Carry out fault diagnosis on transformers with high accuracy and reliability

Images