Transformer top oil temperature prediction method based on grey-autoregressive differential moving average model

The invention discloses a transformer top oil temperature prediction method based on a grey-autoregressive differential moving average model, and aims to solve the technical problems of complex oil temperature prediction process, large calculated amount and large prediction error in the prior art. The method comprises the following steps: preprocessing historical oil temperature data; performing fitting training on the preprocessed historical oil temperature data based on a gray model, and constructing an initial prediction model of the top oil temperature of the transformer; calculating a deviation sequence of the initial predicted oil temperature and the actual oil temperature; performing fitting training on the deviation sequence based on an autoregressive differential moving average model to obtain a deviation prediction value; and constructing a transformer top oil temperature prediction model based on the deviation prediction value and the initial prediction model to obtain a transformer top oil tempera