Adaptive attenuation self-attention adversarial network for cross-domain fault diagnosis under imbalanced conditions

作者：Fucan Huang, Qingyao Zhang, Baokun Han, Jinrui Wang, Zongzhen Zhang, Rongkang Ge, Huan Gong · 发表于：Measurement Science and Technology · 年份：2025 · DOI：10.1088/1361-6501/ae1e21 · 被引用次数：1 · 研究领域：Machine Fault Diagnosis Techniques、Domain Adaptation and Few-Shot Learning、Anomaly Detection Techniques and Applications

Abstract The acquisition of fault samples is often constrained by factors such as the low occurrence probability of faults and the high costs associated with data collection, leading to an imbalanced distribution of fault types and impairing the ability of the model to accurately recognize minority fault classes. In response to this challenge, this paper proposes an adaptive attenuation self-attention adversarial network. In the feature extraction phase, the model incorporates an attention mechanism utilizing a spatial attenuation matrix and bidirectional decomposition, which effectively mitigates the interference of irrelevant distant information while enhancing the ability of the model to capture local feature representations and reducing computational overhead. In the classification phase, an adaptive loss-weighting strategy is introduced, which dynamically adjusts loss weights based on both sample distribution and variations in inter-class accuracy, thereby improving the recognition performance of minority fault classes. For domain adaptation, the model combines conditional domain adversarial network, guided by an entropy filtering mechanism, with supervised contrastive learning to align features across domains and mitigate the adverse effects of class imbalance. Experimental results on two bearing datasets demonstrate that the proposed model significantly outperforms comparison methods across multiple evaluation metrics, validating its effectiveness and potential for rea...