Feature sample-based hydroelectric generating set fault diagnosis method and system

The invention discloses a hydroelectric generating set fault diagnosis method and system based on feature samples, and the method comprises the steps: collecting the feature data of a water turbine in a hydroelectric generating set in each normal state to form a feature sample set, and determining each feature data threshold according to the feature sample set; actual measurement data formed by water turbine water inflow, core component temperature and water turbine vibration frequency of the hydroelectric generating set in the current state are collected; and judging whether the hydroelectric generating set in the current state is abnormal or not based on the distance and the similarity between the feature data set and the measured data. The method has the characteristic of data driving, does not need to deeply understand the internal structure and mechanism of the hydroelectric generating set, has better generalization ability and robustness, and has wide application prospects in fault diagnosis of the hydr