Abstract:In order to overcome the noise accumulation problem of traditional convolutional neural network in（CNN）pooling operation，this paper proposes a fault diagnosis method for inter-turn short circuit of dual three-phase permanent magnet motor based on CNN and long short term memory（LSTM）. CNN is responsible for feature extraction，and LSTM is responsible for learning features and data classification，to extract features in the sequence more efficiently， reduce the influence of noise on classification results，and improve the fault identification rate. By inputting the processed current sample into the CNN-LSTM，the inter-turn short circuit fault of the winding of different phases of the motor can be diagnosed. In this paper，simulation data and experimental data verify the effectiveness of the CNN-LSTM in fault diagnosis.