GIS Fault Diagnosis Method Based on The Identification of SF6 Gas Decomposition Product Fault Characteristics

The analysis of SF6 gas decomposition components is the key to the fault diagnosis of GIS equipment in substations. In order to explore the fault information in the SF6 gas decomposition products before the GIS failure, this paper proposes a GIS fault diagnosis method based on SF6 gas decomposition product fault feature identification.Firstly, a model based on information entropy theory is proposed for SF6 gas decomposition products, and the contribution of each feature is solved and ranked by using principal component analysis. Secondly, the fault diagnosis model of support vector machine algorithm is introduced to achieve GIS fault discrimination. After comparison and validation, it is shown that the proposed method can effectively improve the GIS fault identification rate.