RESUMEN
Bearings, as widely employed supporting components, frequently work in challenging working conditions, leading to diverse fault types. Traditional methods for diagnosing bearing faults primarily center on time-frequency analysis, but this often requires expert experience for accurate fault identification. Conversely, intelligent fault recognition and classification methods frequently lack interpretability. To address this challenge, this paper introduces a convolutional neural network with an attention mechanism method, denoted as CBAM-CNN, for bearing fault diagnosis. This approach incorporates an attention mechanism, creating a Convolutional Block Attention Module (CBAM), to enhance the fault feature extraction capability of the network in the time-frequency domain. In addition, the proposed method integrates a weight visualization module known as the Gradient-Weighted Class Activation Map (Grad-CAM), enhancing the interpretability of the convolutional neural network by generating visual heatmaps on fault time-frequency graphs. The experimental results demonstrate that utilizing the dataset employed in this study, the CBAM-CNN achieves an accuracy of 99.81%, outperforming the Base-CNN with enhanced convergence speed. Furthermore, the analysis of attention weights reveals that this method exhibits distinct focus of attention under various fault types and degrees. The interpretability experiments indicate that the CBAM module balances the weight allocation, emphasizing signal frequency distribution rather than amplitude distribution. Consequently, this mitigates the impact of the signal amplitude on the diagnostic model to some extent.
RESUMEN
The strain of the ring gear can reflect the dynamic characteristics of planetary gearboxes directly, which makes it an ideal signal to monitor the health condition of the gearbox. To overcome the disadvantages of traditional methods, a new approach for the dynamic measurement of ring gear strains using fiber Bragg gratings (FBGs) is proposed in this paper. Firstly, the installation of FBGs is determined according to the analysis for the strain distribution of the ring gear. Secondly, the parameters of the FBG are determined in consideration of the accuracy and sensitivity of the measurement as well as the size of the ring gear. The strain measured by the FBG is then simulated under non-uniform strain field conditions. Thirdly, a dynamic measurement system is built and tested. Finally, the strains of the ring gear are measured in a planetary gearbox under normal and faulty conditions. The experimental results showed good agreement with the theoretical results in values, trends, and the fault features can be seen from the time domain of the measured strain signal, which proves that the proposed method is feasible for the measurement of the ring gear strains of planetary gearboxes.