Transformer oil chromatography fault diagnosis method and system based on multiple linear regression

The invention provides a transformer oil chromatography fault diagnosis method and system based on multiple linear regression. The method comprises the following steps: obtaining transformer characteristic gas information; obtaining a transformer fault diagnosis result according to the characteristic gas information and a preset transformer oil chromatography fault diagnosis model; the transformer oil chromatography fault diagnosis model utilizes a multiple linear regression model to predict characteristic gas components, and judges the operation state of a transformer based on a characteristic gas prediction quantity and a characteristic gas preset threshold value. The characteristic gas is subjected to related research and analysis, the characteristic gas preset threshold is combined, the running state of the transformer is monitored in real time, potential faults in the transformer are found in time, precautions are taken in advance, and the running reliability of a power system is improved. 本公开提供了一种基于多元线性