Optimized Variational Mode Decomposition and Convolutional Block Attention Module-Enhanced Hybrid Network for Bearing Fault Diagnosis

Abstract

Accurate fault diagnosis remains a critical but unresolved issue in predictive maintenance, as industrial environments typically involve large amounts of electromagnetic interference and mechanical noise that can severely degrade the signal quality. In this study, we propose an innovative diagnostic framework to address the challenging problem of bearing fault diagnosis in vibration signals under complex noise conditions. We develop the VMD-CNN-BiLSTM-CBAM model by systematically integrating the variational mode decomposition (VMD), convolutional neural network (CNN), bi-directional long and short-term memory network (BiLSTM), and convolutional block attention module (CBAM). The framework starts with VMD-based signal decomposition, which effectively separates the noise component from the bearing vibration features. Based on this denoising, a CNN architecture is employed to extract multi-scale spatio-temporal features through its hierarchical learning mechanism. The subsequent BiLSTM layer captures bidirectional temporal dependencies to model fault-evolution patterns, while the CBAM module strategically highlights key diagnostic features through adaptive channel spatial attention. Experimental validation using the Case Western Reserve University and Jiangnan University bearing datasets demonstrates the excellent performance of the model, with average accuracies of 99.76% and 99.40%, respectively. Finally, additional validation through our customized testbed confirms the usefulness of the model with an average accuracy of 99.70%. These results demonstrate that the proposed approach greatly improves fault diagnosis in noisy industrial environments through its synergistic architectural design and enhanced noise immunity.