A Novel Bearing Fault Data Generation Strategy Combining Physical Modeling and CycleGAN Variant for Fault Diagnosis Without Real Samples

The number and quality of fault samples significantly impact the effectiveness of mechanical component fault diagnosis. However, fault data are scarce in real scenarios due to the high cost and risk of obtaining such samples. Additionally, collected data often exhibit distribution bias and are therefore unsuitable for real engineering applications. This paper proposes a novel fault data generation strategy combining the physical model and the cycle generative adversarial network (CycleGAN) variant for bearing fault diagnosis. First, a bearing dynamics model is developed to obtain sufficient labelled fault simulation samples as the source domain. Healthy operational signals in real scenarios are then collected as the target domain. After that, a CycleGAN variant is designed to minimize the gap between simulation and reality. Specifically, the generator is built upon Bi-directional long short-term memory to capture the temporal dependencies of vibration signals. Meanwhile, a Multi-Head Self-Attention mechanism is introduced to enhance multi-scale feature extraction and reduce computational complexity. Moreover, auxiliary classification labels are embedded to generate type-specific fault data. Finally, the proposed method achieved satisfactory performance in both non-transfer and transfer diagnosis scenarios, demonstrating its potential as a reliable solution when real fault data is unavailable.