Rolling bearing fault diagnosis method under variable working conditions based on a vibration diagram and transfer learning

Abstract

The invention relates to the technical field of mechanical rotating equipment fault diagnosis. The invention specifically discloses a rolling bearing fault diagnosis method under variable working conditions based on a vibration diagram and transfer learning. The method comprises the following steps: 1, collecting a fault data sample set A of a rolling bearing under known working conditions; 2, carrying out EMD decomposition noise reduction and time-frequency conversion on A; 3, converting a one-dimensional time domain signal and a frequency domain signal obtained by time-frequency conversion into a two-bit vibration diagram; 4, extracting fault features in the vibration diagram to form a fault feature set T1 and repeating the above steps for to-be-tested data to form T2; 5, adopting transfer learning to learn T1 and T2 to obtain a new feature set T3, and carrying out classification training on T3 to obtain a classification model; and 6, adopting the classification model to carry out fault diagnosis on a sample B to be tested. According to the invention, automatic extraction of fault sensitive features is realized, effective diagnosis of rolling bearing faults under different working conditions is realized, and the method has high diagnosis accuracy.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis of mechanical rotating equipment, in particular to a rolling bearing fault diagnosis method under variable working conditions based on vibration diagrams and transfer learning. [0002] technical background [0003] Rolling bearings are the key components of rotating machinery. Their main function is to bear the weight and working load of the rotating body while ensuring the rotation accuracy of the rotating body. Its operating status directly determines the performance of the entire unit. However, affected by harsh and complex working conditions, rolling bearing failures occur frequently, which has a great impact on the normal production and operation of the company. Therefore, in order to ensure the normal operation of the equipment, it is of great significance to carry out fault diagnosis on rolling bearings. [0004] In recent years, scholars at home and abroad have done a lot of resea...

AI Technical Summary

Problems solved by technology

However, under variable working conditions, the distribution of the original vibration signal of the bearing is changeable, and the extraction of fault sensitive features is difficult, which makes it difficult for the existing migration learning algorithm suitable for the field of image processing to be effectively applied in the field of fault diagnosis.

Images