Mechanism-constrained decomposition diffusion network for compound bearing fault diagnosis in rotating machinery

Abstract The identification of compound mechanical faults in bearings from vibration signals is challenging due to the concurrence and coupling of different fault types and the exponentially growing number of possible fault modes. Existing artificial intelligence-based models can extract fault features when there is a large number of labeled compound fault samples, but this is impractical in industrial scenarios. To address this gap, we propose a mechanism-constrained decomposition diffusion network (McDDN) framework tailored for compound bearing fault diagnosis in rotating machinery, which only requires labeled single-fault samples and unlabeled compound fault signals for training. The framework integrates a mechanism-constrained decomposition UNet into the diffusion process, leveraging the feature mode decomposition principle as a physical constraint via a specially designed training loss. This allows the decomposition of compound fault signals into interpretable single-fault components, which are then diagnosed using a pre-trained single-fault classifier. Experimental validation on the PU bearing dataset and the BJTU-RAO industrial dataset demonstrates that the McDDN achieves high diagnostic accuracy for bearing compound faults, outperforming state-of-the-art methods in both closed-set and cross-domain scenarios. Rigorous analyses, including model interpretability, ablation studies, and hyperparameter sensitivity tests, validate the robustness and stability of the proposed approach. While focused on bearings, the framework provides a generalizable paradigm for compound fault diagnosis of other rotating machinery components by incorporating component-specific physical constraints, offering new insights for intelligent maintenance systems in industrial applications.