Few-Shot Fault Diagnosis of Rolling Bearings Using Generative Adversarial Networks and Convolutional Block Attention Mechanisms

In modern industrial systems, diagnosing faults in the rolling bearings of high-speed rotating machinery remains a considerable challenge due to the scarcity of reliable fault samples and the inherent complexity of the diagnostic task. To address these limitations, this study proposes an intelligent fault diagnosis method that integrates a generative adversarial network (GAN) with a convolutional block attention mechanism (CBAM). First, after systematically evaluating several loss functions, a GAN based on the Wasserstein distance loss function was adopted to generate high-quality synthetic vibration samples, effectively augmenting the training dataset. Subsequently, a convolutional block attention mechanism-based convolutional neural network (CBAM-CNN) was developed. By adaptively emphasizing salient features through channel and spatial attention modules, the CBAM-CNN improves feature extraction and recognition performance under limited-sample conditions. To validate the proposed method, an experimental platform for a two-speed automatic mechanical transmission (2AMT) of an electric vehicle was developed, and diagnostic experiments were conducted on high-speed rolling bearings. The results indicate that, under extremely severe conditions, CBAM-CNN achieves a diagnostic accuracy of 96.64% for rolling element pitting defects using only 10% of authentic samples. For composite faults, the model maintains an average accuracy above 97%, demonstrating strong generalization capability. These findings provide solid theoretical support and practical engineering guidance for rolling bearing fault diagnosis under few-shot conditions.