Physics-aware dynamic spectral modeling integrated with weakly supervised few-shot learning for planetary gearbox fault diagnosis

Currently, intelligent fault diagnosis methods based on deep learning have demonstrated considerable promise in various industrial applications. However, the efficacy of most models is contingent upon the availability of substantial labeled datasets for training, a requirement that often proves impractical in real-world industrial scenarios. To address this challenge, this research proposes a novel approach: physics-aware dynamic spectral modeling integrated with weakly supervised few-shot learning (PADSM-WSFL) for fault diagnosis in planetary gearboxes. This methodology efficiently leverages substantial unlabeled data while building a robust deep learning model with extreme limited labeled samples. The PADSM-WSFL framework comprises three key components: a physics-aware dynamic spectral modeling approach, a graph construct module for feature extraction, and the integration of weakly supervised learning with few-shot learning models. Validated on two machinery fault diagnosis datasets, PADSM-WSFL demonstrates improved robustness and generalization capabilities compared to state-of-the-art methods, offering a solution to the pervasive issue of limited labeled data in industrial fault diagnosis.