Knowledge correlation graph-guided multi-source interaction domain adaptation network for rotating machinery fault diagnosis

Leveraging generalized knowledge from multiple source domains with rich labels to the target domain without labeled data is a more realistic and challenging issue compared with single-source domain adaptation. Furthermore, the distribution discrepancies between each source domain and the expansion of data categories increase the difficulty of aligning each source domain with the target domain. To alleviate these issues, a knowledge correlation graph-guided multi-source interaction domain adaptation network (KCGMIDAN) is developed for rotating machinery fault diagnosis. Firstly, a random mini-batch is randomly selected to update comprehensive feature representations (CFR) extracted from each data category across all domains, thus promoting the knowledge interaction of acquired CFR between the current and the next epochs. Then, a knowledge correlation graph (KCG) is established on all CFR to boost knowledge propagation among various domains. To improve the compactness of characteristics within the same category and the separation of various categories, two losses are designed in this procedure to place constraints on the relationships between categories. Finally, query samples are added into KCG to construct the extended KCG, and the recognition of samples is completed by using built deep graph network based on the extended KCG. Extensive experimental results verify that KCGMIDAN can achieve better recognition performance than existing methods.