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.

Compressors serve as fundamental power units in underground natural gas storage facilities and frequently need to accommodate wide-range operational condition adjustments. However, their inherent nonlinear characteristics, coupled with high-noise and uncertain operating environments, pose significant challenges to precise control and safe operation. To accurately predict compressor operational status and provide reliable decision-making information for operation and maintenance, this study proposes an operating-state prediction method for gas storage compressors based on vibration-sequence analysis and a Bidirectional Long Short-Term Memory (BiLSTM) network. Singular Spectrum Analysis (SSA) is first applied to decompose and reconstruct monitoring signals, extracting dominant trend components while suppressing background noise. A Convolutional Neural Network (CNN) is subsequently employed to capture multi-scale local features, after which the BiLSTM network learns temporal evolution patterns from the extracted features. The Adam optimizer is utilized to enhance training stability and prediction accuracy. Experimental validation using real monitoring data from gas storage compressors indicates that the proposed method achieves precise and reliable prediction of compressor operating states.