Wind turbine fault diagnosis method and system based on CNN and hotspot map

The invention discloses a wind turbine generator fault diagnosis method and system based on a CNN and a hotspot map, and the method comprises the steps: collecting the data of a data collection and monitoring system under different working conditions of a wind turbine generator, and carrying out the preprocessing of the data; converting the preprocessed data into a hotspot map, and dividing the hotspot map into a training set and a test set; constructing a ResNet50 convolutional neural network model, inputting the training set and the test set into the ResNet50 convolutional neural network model, and determining an optimal ResNet50 convolutional neural network model; and acquiring new 24-hour operation data before the fault, preprocessing the new 24-hour operation data, generating a hotspot map, and inputting the hotspot map into the optimal ResNet50 convolutional neural network model to realize fault identification and classification. According to the method, the data 24 hours before normal operation and fau