Domain adaptation-based methods have been proved success for cross-machine fault diagnosis. However, such methods suffer from limited diagnosis performance because the utilized networks typically rely on convolution layers with local receptive fields, failing to extract informative fault features, and the information on machine domain and fault category is not fully utilized, which prevents the transferability of fault features across machines. Towards these issues, a novel ConvFormer-based biconditional domain adaptation method (CFBDAM) is proposed to explore informative and highly-transferable fault features for accurate diagnosis. The proposed ConvFormer network first extracts global-local fault features in a parallel manner via a linear transformer and a separable shuffled CNN, respectively. The resulting features are then fed into a cross-attention feature fusion module to form informative diagnostic knowledge. Our ConvFormer is deployment-friendly owing to lightweight designs, such as linear and separation operations. To enhance cross-machine transferability of the informative fault features extracted by ConvFormer, a biconditional domain adaptation strategy is designed. It imposes biconditional constraints by using the information of both machine domain and fault category, thereby leading to highly-transferable fault features with domain insensitivity and category discriminability. Comprehensive experiments are conducted on six transfer diagnosis tasks across three machines. The experimental results show that CFBDAM achieves potential cross-machine diagnostic performance.

Domain generalization-based methods perform cross-domain fault diagnosis by learning fault-discriminative and domain-invariant diagnostic knowledge between available working conditions (source domains) and unseen conditions (target domains). However, existing approaches ignore domain specificity within discriminative knowledge, preventing optimal fault discrimination across diverse domains. Moreover, since the target domain is inaccessible during model training, obtaining sufficient domain-invariant knowledge from the limited source domains poses a significant challenge. For the weaknesses, a specific task-guided collaborative domain generalization network (STCDGN) is proposed to enhance bearing fault diagnosis under unseen working conditions. Specifically, we construct a channel attention-guided multi-scale feature extractor and task-specific classifiers to establish adaptive decision boundaries for domain specificity. The boundaries interact with the extracted features to enhance fault-discriminative representations. To further mine domain invariance within these representations, we propose a two-stage training strategy through decision boundary divergence maximization and multi-scale hierarchical feature discrepancy minimization, effectively alleviating intra-class domain shift for improved diagnostic generalization. Finally, we propose an entropy-guided decision selection strategy for reliable inference diagnostic results. The average accuracies on the two public datasets reach 98.72% and 89.13%, respectively, indicating significant diagnostic generalization to the unseen target samples. The visualized experimental results further demonstrate the method’s effectiveness in learning fault-discriminative and domain-invariant diagnostic knowledge.

In recent years, deep learning has been applied to intelligent fault diagnosis and has achieved great success. However, the fault diagnosis method of deep learning assumes that the training dataset and the test dataset are obtained under the same operating conditions. This condition can hardly be met in real application scenarios. Additionally, signal preprocessing technology also has an important influence on intelligent fault diagnosis. How to effectively relate signal preprocessing to a transfer diagnostic model is a challenge. To solve the above problems, we propose a novel deep transfer learning method for intelligent fault diagnosis based on Variational Mode Decomposition (VMD) and Efficient Channel Attention (ECA). In the proposed method, the VMD adaptively matches the optimal center frequency and finite bandwidth of each mode to achieve effective separation of signals. To fuse the mode features more effectively after VMD decomposition, ECA is used to learn channel attention. The experimental results show that the proposed signal preprocessing and feature fusion module can increase the accuracy and generality of the transfer diagnostic model. Moreover, we comprehensively analyze and compare our method with state-of-the-art methods at different noise levels, and the results show that our proposed method has better robustness and generalization performance.

Domain adaptation-based bearing fault diagnosis methods have recently received high attention. However, the extracted features in these methods fail to adequately represent fault information due to the versatility of the work scenario. Moreover, most existing adaptive methods attempt to align the feature space of domains by calculating the sum of marginal distribution distance and conditional distribution distance, without considering variable cross-domain diagnostic scenarios that provide significant cues for fault diagnosis. To address the above problems, we propose a deep convolutional multi-space dynamic distribution adaptation (DCMSDA) model, which consists of two core components: two feature extraction modules and a dynamic distribution adaptation module. Technically, a multi-space structure is proposed in the feature extraction module to fully extract fault features of the marginal distribution and conditional distribution. In addition, the dynamic distribution adaptation module utilizes different metrics to capture distribution discrepancies, as well as an adaptive coefficient to dynamically measure the alignment proportion in complex cross-domain scenarios. This study compares our method with other advanced methods, in detail. The experimental results show that the proposed method has excellent diagnosis performance and generalization performance. Furthermore, the results further demonstrate the effectiveness of each transfer module proposed in our model.