Rolling bearing fault diagnosis method and system based on relational knowledge distillation

Abstract

The invention discloses a rolling bearing fault diagnosis method and system based on relational knowledge distillation, and belongs to the technical field of fault diagnosis. After the original vibration signals of the bearing are collected, a time-frequency diagram is constructed for each processing sample to serve as a fault sample, the fault sample serves as input of a fault diagnosis system, and due to the fact that the time-frequency diagram contains complete time-frequency information of the vibration signals, the real-time response efficiency and accuracy of fault diagnosis are improved. A student model is adopted to simultaneously learn a multivariate relationship between the output soft label of Softmax of a teacher model and output of a plurality of samples in the last pooling layer, namely, a student network learns from two aspects of a teacher structure and output of a single sample in the teacher network; and the classification performance of the fault diagnosis system is effectively improved under the condition that the memory and the training time are not increased. According to the invention, bearing fault diagnosis is realized by using a relational knowledge distillation transfer learning method, and the calculation complexity is effectively reduced through the idea of replacing a large model with a small model.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis, and more specifically relates to a rolling bearing fault diagnosis method and system based on relational knowledge distillation. Background technique [0002] Rolling bearings are a key component of rotating machinery and one of the components with a high failure rate. According to incomplete statistics, 30% of the failures of rotating equipment are caused by rolling bearing failures. Condition monitoring and fault diagnosis of rolling bearings play an important role in understanding the operating performance of equipment and discovering potential faults, which can effectively improve the management level of mechanical equipment and the efficiency of maintenance. [0003] At present, a new round of artificial intelligence technology represented by deep learning has made the establishment of an end-to-end deeply integrated intelligent fault diagnosis method a new goal in the era of industr...

AI Technical Summary

Problems solved by technology

[0005] However, there are the following defects: 1) Most of them extract effective features by analyzing the collected time-series signals, such as extracting the most relevant fault features as a fault classifier through multiple screenings such as preprocessing of the collected vibration signals and feature screening. input, but artificial screening takes a long time, and it is easy to lose effective information; 2) The student model only learns to learn the output of the Softmax at the end of the teacher model, that is, only the performance of a single sample on the teacher model is considered, which leads to the fault diagnosis of the student model The accuracy rate is not high

Images