Abstract:Aiming at the high fault rate of rotating machinery and the large workload and low efficiency of manual participation in fault diagnosis,a fault diagnosis method for rotating machinery based on cloud model and LSTM algorithm was proposed.The original vibration fault data were collected by the experimental bench,and the EEMD data were preprocessed uniformly.The cloud model was used to extract the fault feature data,and they were input to the LSTM neural network model for fault diagnosis.The feature extraction was carried out through the cloud model and the energy method,and they were input to the support vector machine and the LSTM neural network model respectively to compare the diagnosis results.The results show that the algorithm base on the cloud model and the LSTM algorithm has the highest fault diagnosis accuracy,reaching 98.75%,which proves that the method can be effectively used in fault diagnosis of rotating machinery.