A Novel Open-Set Domain Generalization Approach via Meta-Learning-Based Dual-Level Gradient Alignment for Intelligent Fault Diagnosis

The effectiveness of existing domain generalization-based fault diagnosis (DGFD) methods usually relies on the assumption that the label space of the source domain (SD) is consistent with that of the unseen target domain (TD). However, in actual industrial scenarios, the unknown fault classes that do not exist in the SDs may appear in the TD, resulting in the degradation of the diagnosis accuracies of DGFD methods on the unseen TD. Therefore, a novel open-set domain generalization (OSDG) approach via meta-learning-based dual-level gradient alignment (MLDGA) for intelligent fault diagnosis (FD) is proposed. Firstly, a meta-learning optimization strategy with dual-level gradient alignment is designed to optimize the gradient update directions of the inter-domain and inter-class tasks simultaneously by gradient matching, so as to ensure that the decision boundaries are located in the optimal positions between each fault class. Secondly, an entropy-guided dynamic weighting strategy is designed to improve the discrimination ability and accuracy of the model in the multi-class fault classification tasks. Finally, a classification-clustering dual-guided open decision boundary construction strategy is designed to improve the recognition capability of unknown fault classes and the adaptability of the class decision boundaries in fault classification tasks. The experimental results confirm that the proposed approach can effectively identify both known and unknown fault classes.