[4F2] A novel compound fault decoupling and diagnosis framework based on physics-constraint denoising diffusion probabilistic model
Z Guo¹, J Xie¹, T Wang¹, Y Ta¹, B Yang² and Q Yin²
¹Central South University, China
²Hunan University, China
Accurate identification of compound mechanical faults through vibration analysis remains a critical challenge in industrial condition monitoring, primarily due to the non-linear interaction of multiple failure modes and combinatorial explosion of potential fault combinations. While contemporary data-driven diagnostic methods demonstrate feature extraction capabilities when abundant labelled compound fault data exists, such idealised data conditions rarely occur in practical engineering applications. This paper presents a novel mechanism-guided decomposition diffusion network (McDDN) for resource-efficient compound fault diagnosis requiring only single-fault labelled samples for training. The proposed framework incorporates a physics-informed decomposition UNet (McD-UNet) within a diffusion-based learning architecture to disentangle overlapping fault signatures through mechanism-constrained signal separation. Feature mode decomposition (FMD) principles are mathematically encoded as regularisation terms in the network’s optimisation objective, enabling data-driven learning of decomposition patterns while preserving physical interpretability. The diagnostic pipeline performs hierarchical fault identification through mechanism-guided signal decomposition into constituent single-fault components by single-fault classification. Experimental validation on the Paderborn University (PU) bearing dataset and Beijing Jiaotong University – Rail Autonomous Operations (BJTU-RAO) high-speed train bogie dataset demonstrates superior performance, achieving 89.3% diagnostic accuracy for simultaneous bearing-gear-motor faults in multi-component rotating systems. Comparative analysis reveals 12-15% accuracy improvements over conventional model-based and pure data-driven benchmarks, validating the effectiveness of the hybrid approach in knowledge-scarce compound fault scenarios.
