A Deep Learning Method for Rolling Bearing Fault Diagnosis Based on Attention Mechanism and Graham Angle Field

Focusing on the low accuracy and timeliness of traditional fault diagnosis methods for rolling bearings which combine massive amounts of data, a fault diagnosis method for rolling bearings based on Gramian angular field (GAF) coding technology and an improved ResNet50 model is proposed. Using the Graham angle field technology to recode the one-dimensional vibration signal into a two-dimensional feature image, using the two-dimensional feature image as the input for the model, combined with the advantages of the ResNet algorithm in image feature extraction and classification recognition, we realized automatic feature extraction and fault diagnosis, and, finally, achieved the classification of different fault types. In order to verify the effectiveness of the method, the rolling bearing data of Casey Reserve University are selected for verification, and compared with other commonly used intelligent algorithms, the results show that the proposed method has a higher classification accuracy and better timeliness than other intelligent algorithms.

Automated summary

This study proposes a fault diagnosis method for rolling bearings based on Gramian angular field (GAF) coding technology and an improved ResNet50 model to address the low accuracy and timeliness of traditional fault diagnosis methods. By recoding the one-dimensional vibration signal into a two-dimensional feature image using GAF technology and using it as input for the model, combined with the advantages of ResNet algorithm in image feature extraction and classification recognition, automatic feature extraction and fault diagnosis are achieved, and classification of different fault types is accomplished.