A novel prediction network for remaining useful life of rotating machinery

With the increasing complexity of CNC machine tools and other rotating machinery, it becomes more and more important to improve the reliability of such machines. It is necessary to estimate the remaining useful life (RUL) of the important parts such as bearings of these devices. However, the operating conditions of such parts are often very complicated, and there is a great difference between different devices. Therefore, it is difficult to use the traditional mechanism analysis method, which not only is very hard, but also generally has low prediction accuracy. In order to solve the above problems, this paper proposes a feature-transferred prediction network (FTPN), which can adapt to various working conditions, combining with the neural network method in the field of artificial intelligence, and effectively realizes RUL prediction. Since the existing neural network methods were originally proposed to solve the problems in other fields, such as semantic recognition, this paper uses the feature transfer method to improve them. Firstly, the source network based on convolutional neural network (CNN) is pre-trained for fault recognition, and the fault feature information extracted after training is stored in the fault feature layer. Second, CNN and gate recurrent unit (GRU) are used to build target networks and fit the relationship between time series and remaining longevity. Finally, a special loss function is designed to transfer the features extracted from the source network to the target network to help the target network learn fault features and better predict the mechanical RUL. In order to verify the effectiveness of the proposed method, experiments are carried out using the public data set of accelerated life of bearings, and high prediction accuracy is obtained, which proves that the proposed method has certain generalization. The comparison with the existing methods on the same data set shows that the proposed method has a broad industrial application prospect.