In real industry, due to changes in operating conditions and differences in systems of interest, domain shift is a common problem, which results in the degradation of the diagnostic performance. Moreover, insufficient labeled or unlabeled samples greatly limit the adaptability of fault diagnosis methods. To solve these problems, the latest domain adversarial transfer learning techniques are studied. However, most of the existing studies just reduce the distribution discrepancy of two domains with fixed distance metrics, which cannot adapt well to distribution variation during testing. This article proposes a new deep transfer learning method based on Wasserstein generative adversarial networks (WGAN) and minimum singular value for non-nomologous bearings, where the training samples and the testing samples are from related not the same machinery. In the proposed method, a domain critic network is adopted to provide the discrepancy metric for improving domain adaptation ability. In addition, the minimum singular value is used to capture effective categories information measurement in the classifier training process. The proposed method is verified by two different bearing datasets from Case Western Reserve University and the Intelligent Maintenance System. The experiments indicated that the proposed method can achieve superior performance over other existing methods in terms of diagnosis accuracy.

Achieving deep learning-based bearing fault diagnosis heavily relies on large labeled training samples. However, in real industry applications, labeled data are scarce or even impossible to obtain. In this study, we addressed a challenging few-shot bearing fault diagnosis problem with few or no training labeled samples of novel categories. To tackle this problem, we considered a semi-supervised prototype network based on few-shot bearing fault diagnosis with pseudo-labels. The existing prototypical networks with pseudo-label methods train a pseudo label model to label unlabeled samples using high-dimensional labeled data, which cannot eliminate the instability of the pseudo-label model caused by dimensional labeled features. To mitigate this issue, we used kernel principal component analysis to reduce the dimensions of and remove redundant information from high-dimensional data. Specifically, we used the pseudo-label prediction algorithm with probability distance to label unlabeled samples, aiming to improve the labeling accuracy. We applied two well-known bearing data sets for the validation experiments with symmetry parameters. The findings illustrated that the classification accuracy of the proposed method is higher than that of other existing methods.

Transfer learning, leveraging the gaps through learned knowledge from source domain to target domain recognition, has achieved impressive performance in bearing fault diagnosis with two domains which have only weak distribution discrepancy. From different devices, collected vibration signal always suffered from big distribution discrepancy, which has limited the generalization of these existing transfer learning-based methods significantly. To overcome this challenge, the partial domain transfer learning methods are studied latest. However, most of these available techniques only focus on reducing the discrepancy of two domains using statistical distance metrics, which cannot consider the Riemannian manifold hidden in distribution space that impacted the accuracy of discrepancy measurement during testing. This paper proposes a Log-CORAL–based deep residual shrinkage network for partial domain adaptation bearing fault diagnosis scenario, where the domains data from different machinery are selected. Specifically, the log-correlation alignment (Log-CORAL), as a domain discrepancy metric, is explored to weaken the influence by Riemannian manifold, which disturbed the discrepancy measurement dependability. In addition, adversarial domain discriminator is embedded into deep residual shrinkage network to reduce the discrepancy between the two domains by maximizing the loss of domain discriminator. Comparison experiments with the SOTA methods on three well-known bearing datasets are conducted to verify effectiveness of the proposed method.

In few-shot fault diagnosis tasks in which the effective label samples are scarce, the existing semi-supervised learning (SSL)-based methods have obtained impressive results. However, in industry, some low-quality label samples are hidden in the collected dataset, which can cause a serious shift in model training and lead to the performance of SSL-based method degradation. To address this issue, the latest prototypical network-based SSL techniques are studied. However, most prototypical network-based scenarios consider that each sample has the same contribution to the class prototype, which ignores the impact of individual differences. This article proposes a new SSL method based on pseudo-labeling multi-screening for few-shot bearing fault diagnosis. In the proposed work, a pseudo-labeling multi-screening strategy is explored to accurately screen the pseudo-labeling for improving the generalization ability of the prototypical network. In addition, the AdaBoost adaptation-based weighted technique is employed to obtain accurate class prototypes by clustering multiple samples, improving the performance that deteriorated by low-quality samples. Specifically, the squeeze and excitation block technique is used to enhance the useful feature information and suppress non-useful feature information for extracting accuracy features. Finally, three well-known bearing datasets are selected to verify the effectiveness of the proposed method. The experiments illustrated that our method can receive better performance than that of the state-of-the-art methods.

Under small distribution discrepancies between source and target domains, the existing domain adaptation-based fault diagnosis methods can achieve encouraging results. However, in practical industrial applications, various machines and working conditions change unpredictably, significant inter-domain distribution discrepancies occur, seriously affecting the performance of domain adaptation-based methods. To tackle this problem, most of existing domain adaptation scenarios for fault diagnosis of different machines only focus on single-level domain adaptation, which cannot comprehensively consider discrepancy variations from the target domain. In this paper, a multi-levels domain alignment adaptation-based transfer fault diagnosis method for different machines was proposed, where the source domain and target domain originate from different machinery with significant distribution discrepancies. In the proposed method, intra-class spatial reconstitution is explored to excavate the potential category information hidden in the target domain for improving the performance and generalization of domain adaptation. Moreover, a multi-levels domain information alignment strategy is employed to address the shortcoming caused by single-level domain alignment that does not consider the influences of multi-levels distribution discrepancy fluctuation. Two well-known bearing datasets and a real industrial application dataset are used to verify the proposed method. The results show that the proposed method can achieve better performance than the SOTA methods.

Few-shot learning (FSL) effectively addresses performance degradation caused by insufficient labeled data in the fault diagnosis of rotating machinery bearings. However, prevailing methods are confined to the contribution of the features from a single view, leaving unconsidered the information latent in other views capable of helping improve model accuracy. To address the issue of limited labeled samples in practical industrial processes, this paper proposes a deep multi-view meta-learning-based semi-supervised few-shot fault diagnosis method. In the proposed method, a deep multi-view feature fusion (MVFF) technique is explored to obtain more discriminative information features for training. Moreover, a feature layer self-attention variational autoencoder (FLSAVAE) is proposed and integrated into the feature extractor to pay attention to these hidden information contributed to model accuracy. Finally, a semi-supervised prototype refinement (SSPR) strategy is adopted to reduce the risk of low prototype accuracy in FSL, which is refined with the clustering centers of unlabeled data iteratively. Two well-known bearing datasets and a real industrial application dataset are selected to verify the proposed method. The results show that the proposed method can achieve better performance than SOTA methods.