Automatic diagnosis method for experimental data of power system

The invention provides an automatic diagnosis method for experimental data of a power system. The method comprises the following steps: S1, collecting experimental data of an oil product and establishing an experimental database of the power system; s2, extracting a first index of an oil product of the electric power system; s3, the first indexes form a decision tree, the decision tree is trained, results are synthesized, and weight assignment of all the first indexes is obtained; s4, setting a scoring standard of weight assignment, and automatically calculating and updating the health value of the oil product of the electric power system in real time based on the scoring standard and the weight assignment; and S5, comparing and analyzing the health values of the same equipment in the same workshop section at different times, predicting the risk and assigning a maintenance strategy. The problems that an existing diagnosis method is single, low in efficiency, low in automation degree and the like, a large amou