Transformer fault diagnosis method and system based on digital twinning technology

The invention discloses a transformer fault diagnosis method and system based on a digital twinborn technology, and the method comprises the following steps: collecting transformer entity parameters and transformer operation data collected by a transformer sensor, and building a transformer digital twinborn body; establishing a transformer fault diagnosis model based on a weighted distance reciprocal support vector machine by using transformer digital twinborn historical data; and inputting transformer digital twinborn real-time data to the transformer fault diagnosis model, and outputting a transformer state in real time. According to the method, the digital twin of the transformer is established, the support vector machine model is combined for real-time fault diagnosis analysis, the weighted distance reciprocal method is applied to the fuzzy membership degree of the support vector machine, the problem of model overfitting caused by unbalanced training samples is solved, the accuracy of the diagnosis model