Resnet-1DCNN-REA bearing fault diagnosis method based on multi-source and multi-modal information fusion

• Published in: Electronic research archive Vol. 32; no. 11; pp. 6276 - 6300
• Main Authors: Chen, Xu, Chang, Wenbing, Li, Yongxiang, He, Zhao, Ma, Xiang, Zhou, Shenghan
• Format: Journal Article
• Language: English
• Published: AIMS Press 01.01.2024
• Subjects: attention mechanism; bearing fault; cnn; fault diagnosis; residual block; resnet
• DOI: 10.3934/era.2024292
• ISSN: 2688-1594

In order to address the issue of multi-information fusion, this paper proposed a method for bearing fault diagnosis based on multisource and multimodal information fusion. Existing bearing fault diagnosis methods mainly rely on single sensor information. Nevertheless, mechanical faults in bearings are intricate and subject to countless excitation disturbances, which poses a great challenge for accurate identification if only relying on feature extraction from single sensor input. In this paper, a multisource information fusion model based on auto-encoder was first established to achieve the fusion of multi-sensor signals. Based on the fused signals, multimodal feature extraction was realized by integrating image features and time-frequency statistical information. The one-dimensional vibration signals were converted into two-dimensional time-frequency images by continuous wavelet transform (CWT), and then they were fed into the Resnet network for fault diagnosis. At the same time, the time-frequency statistical features of the fused 1D signal were extracted from the integrated perspective of time and frequency domains and inputted into the improved 1D convolutional neural network model based on the residual block and attention mechanism (1DCNN-REA) model to realize fault diagnosis. Finally, the tree-structured parzen estimator (TPE) algorithm was utilized to realize the integration of two models in order to improve the diagnostic effect of a single model and obtain the final bearing fault diagnosis results. The proposed model was validated using real experimental data, and the results of the comparison and ablation experiments showed that compared with other models, the proposed model can precisely diagnosis the fault type with an accuracy rate of 98.93%.