Machinery typically operates under constantly changing working conditions in real-time production. Directly applying a diagnostic model, which has been trained solely on monitoring data from a single working condition, to a new unseen working condition poses a notably challenging task called single-source domain generalization (SSDG) fault diagnosis. Current research mainly aims to augment source-domain training samples but struggles to maintain health state information invariance for diverse augmented samples. Therefore, a targeted augmentation domain-mixed network (TADNet) is proposed in this paper for SSDG fault diagnosis of rotating machinery. The TADNet constructs a targeted augmentation chain, which generates samples in an augmented domain with different distributions from the source-domain samples through a chained generation structure, and ensures the semantic consistency of state features. Additionally, a domain random mixing strategy is established to synthesize a new mixed domain with diverse distributions, through probabilistically and randomly mixing the feature statistics of the samples from the source and augmented domains, for further augmentation of samples. The TADNet effectively balances the distribution diversity and semantic consistency of augmented samples in the course of model training. The superior diagnosis generalization ability of the proposed method to unseen working conditions is demonstrated on two rotating machinery datasets.

Multi-source domain adaptation (MSDA) has demonstrated superior performance in intelligent fault diagnosis (IFD) compared to single-source domain adaptation (SSDA), as it can provide more comprehensive and diverse information from multiple fully-labeled source domains. However, in many real industrial scenarios, acquiring multiple fully-labeled source domains is challenging because labeling all the source domains is as expensive and laborious as labeling the target domain. Given this concern, a cross-supervised multisource prototypical network (CSMPN) is proposed for multi-source few-shot fault diagnosis. Specifically, a domain-shared and a domain-individual branch are constructed to realize shared domain alignment across all the source and target domains and individual domain alignment of source-target domain pairs, respectively. Within two branches, domain alignment is realized by the designed prototypical contrastive learning (PCL) module. In the PCL module, we propose a prototype calibration strategy to address the issue of biased prototype estimation owing to outlier samples. In addition, a two-stage pseudo-labeled sample selection mechanism is proposed to enhance the feature representation ability of two branches. At the end of the two branches, we design a cross-supervised learning (CSL) module to realize mutual and collaborative learning between the two branches, which can further improve the diagnosis performance on the target domain. Experiments on two different bearing datasets are implemented to verify the superiority of the proposed method compared with the comparison methods. Our code is available at https://github.com/YNWA-Zhang/CSMPN .