Fault diagnosis of rolling bearing based on adaptive attention network and federated learning

Abstract For rolling bearings in actual industrial scenarios, the problem of low diagnostic accuracy is caused by the large difference in data distribution under different working conditions and the complexity of working conditions with a lot of redundant information, in this paper, a combination of the federated adaptive attention network based fault diagnostic model is proposed. Firstly, the fault information is randomly divided into multiple sequences, by utilizing dual convolutional layers and adaptive attention mechanism to process abundant vibration data, it enables accurate identification of fault information distribution in the original signal while removing superfluous information and fusing characteristics to improve diagnostic accuracy. Furthermore, a federated learning model incorporating attention mechanism is proposed. It performs asynchronous updates based on local data distribution, improving the efficiency and accuracy of data analysis uploads, and enhancing the model’s generalization capability. Simulation experiments have been carried out using the datasets from Case Western Reserve University and Jiangnan University, and after comparative analysis, the proposed method has better performance and generalization ability.