Few-Shot Fault Diagnosis of Rotating Machinery Using Complex Convolution and Disentangled Representation Learning

Few-shot fault diagnosis is a challenging task in rotating machinery health monitoring because only limited labeled fault samples are available in practical industrial scenarios. Under such conditions, deep learning models are prone to overfitting and may fail to extract stable fault-sensitive features from vibration signals. Moreover, the weak fault-related components are usually coupled with operating-condition variations, background vibration, and environmental noise, which further degrades the discriminability and generalization ability of diagnostic models. To address these problems, this paper proposes a complex-valued disentangled representation learning network for few-shot fault diagnosis of rotating machinery. First, a direction-pair complex augmentation strategy is developed for triaxial vibration measurements. Two directional vibration components are selected and organized as the real and imaginary branches of a complex-valued input, which increases sample diversity under few-shot conditions. Then, a lightweight complex-valued convolution block is designed to model the coupled dynamic characteristics between different vibration directions and extract fault-sensitive representations. Furthermore, a dual-branch disentangled representation structure is developed to decompose the learned features into fault-sensitive representations and condition-related interference representations. To enhance the separability of fault embeddings under limited samples, a cosine-based disentangled representation loss is introduced, which improves intra-class compactness and inter-class discrimination while suppressing irrelevant interference information. Finally, a few-shot diagnosis strategy is constructed to identify fault categories with only a small number of labeled samples. Experimental results demonstrate that the proposed method consistently outperforms representative methods in terms of diagnostic accuracy, feature separability, and robustness, especially under extremely limited labeled samples.