Rolling bearing fault recognition method based on improved relation network

Abstract

The invention discloses a rolling bearing fault recognition method based on an improved relation network, relates to the technical field of bearing fault recognition, and is used for solving the problem that an existing rolling bearing fault recognition model is poor in fault recognition effect under the condition of a small number of marked samples. The method is technically characterized by comprising the steps that a data set is divided according to a meta-learning training strategy, a residual shrinkage module and an SELU activation function are introduced into an embedded module of a relation network, and the residual shrinkage module automatically determines a threshold value through an attention mechanism and removes redundant information in signals; extracting sample features by using an embedding module, splicing the support set sample features and the query set features, and inputting the spliced features into a relation module; and finally, classifying the query set samples according to the relation scores to realize rolling bearing fault recognition. According to the method, the fault recognition model can be trained by using a small number of marked samples, and the problem that a model trained on bearing data of a certain model is poor in generalization ability and cannot be effectively used for fault recognition of bearings of other models is solved.

Description

technical field [0001] The invention relates to the technical field of bearing fault classification, in particular to a rolling bearing fault identification method with improved relational network. Background technique [0002] Rolling bearings are important parts of rotating machinery. Once a failure occurs, it will directly affect the performance of the mechanical equipment, and even cause life-threatening accidents. Therefore, it is of great significance to accurately diagnose the health status of bearings [1] . Rolling bearings usually work under different loads, and the bearing models in different mechanical equipment may be different, which will increase the difficulty of bearing fault diagnosis [2] . In actual engineering, the availability of bearing data with sufficient health marker information is scarce, which makes bearing fault diagnosis more and more challenging [3] . [0003] Fault diagnosis plays an important role in the health management of mechanical eq...

AI Technical Summary

Problems solved by technology

[0007] In view of the above problems, the present invention proposes an improved relational network rolling bearing fault identification method to solve the problem that the existing rolling bearing fault classification model is not effective for fault classification and identification in the case of a small number of labeled samples

Images