Traditional deep learning-based fault diagnosis scenarios always rely on a certain type of deep neural networks(DNNs) to extract its inherent features, which can overcome the drawbacks of shallow model methods. However, the invariant features extracted have some inevitable limitations, which lead to the performance degeneration and lower generalization ability of these scenarios. To address this problem, we propose a feature integration boosting based discriminative stacked auto-encoder(D-SAE) network for bearing fault diagnosis. Specifically, multiple D-SAEs are used as weak classifiers to extract features from the raw signal. To relax the inevitable limitations of a single DNN, D-SAE networks are employed to build the features by integrating boosting into the feature level adaptively, which can combine the weighted features extracted by the D-SAEs according to the classification accuracy. Additionally, the classification information is stored in the hidden layer of the networks, preventing any potential loss of classification information that may occur as the D-SAE becomes more complex. This ensures that the performance of the classifiers does not deteriorate. With extensive experiments on the Case Western Reserve University dataset and a real petrochemical industrial unit dataset, the results indicate that significant improvements over several existing other previous methods were achieved.

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.