Oil-immersed transformer fault diagnosis method based on LGEO-gcForest

The invention belongs to the technical field of transformer fault diagnosis, and relates to an oil-immersed transformer fault diagnosis method based on LGEO-gcForest, and the method comprises the steps: calculating a non-coding ratio of dissolved gas in oil according to a data sample of the dissolved gas in the oil of a transformer, carrying out the standardization of the non-coding ratio, and dividing a training set and a test set; taking the size of a multi-granularity scanning window of the gcForest model and the maximum cascade number allowed by the cascade forest as optimization parameters, and taking the fault diagnosis accuracy of the gcForest model as fitness; optimizing the gcForest model by using a golden eagle optimization algorithm, and returning an optimal parameter; and constructing an LGEO-gcForest fault diagnosis model according to the returned optimal parameters, wherein the LGEO-gcForest fault diagnosis model is used for obtaining a transformer fault diagnosis result. According to the method