Wind turbine generator blade anomaly detection method and device based on vibration

The embodiment of the invention discloses a vibration-based wind turbine generator blade anomaly detection method and device. The method comprises the following steps: acquiring SCADA data and cabin vibration data of a wind turbine generator in a target time period; inputting the acquired data into a pre-trained paddle anomaly detection model, the paddle anomaly detection model comprising a vibration feature extraction layer, an SCADA feature extraction layer and an anomaly detection layer, the vibration feature extraction layer is used for extracting vibration features in the cabin vibration data based on a variational mode decomposition technology and a kernel principal component analysis technology, and the SCADA feature extraction layer is used for extracting SCADA features in the SCADA data according to an ABT network. The anomaly detection layer is used for outputting a detection result according to a comparison result of the target residual value and a normal residual value range obtained by pre-traini