Recently, domain adaptation (DA) algorithms have been extensively employed in many fault diagnosis applications. Most prior researches perform well under a general assumption: the distributions of samples are balanced. Nevertheless, the unbalanced distributions of samples are common in practical applications which may cause the performances of these researches drop dramatically. To overcome this deficiency, an enhanced transfer joint matching (TJM) approach is proposed in this paper. Two main contributions are concluded as follows. (1) To our knowledge, it is a pioneering work to apply the maximum variance discrepancy (MVD) for combining with the maximum mean discrepancy (MMD) for the feature matching. (2) The row ℓ2-norm is applied for different domains to improve the generalization ability of the proposed model. In addition, z-score normalization is adopted for the softmax regression classifier. Comprehensive experimental results validate that the enhanced TJM can significantly outperform competitive approached for cross-domain bearing defect diagnosis.

最近，领域适应（DA）算法已在许多故障诊断应用中得到广泛采用。在一般的假设下，大多数先前的研究表现良好：样本的分布是平衡的。尽管如此，样品的不平衡分布在实际应用中还是很普遍的，这可能导致这些研究的性能急剧下降。为了克服这一缺陷，本文提出了一种增强的传输接头匹配（TJM）方法。得出以下两个主要贡献。（1）据我们所知，将最大方差差异（MVD）与最大平均差异（MMD）结合用于特征匹配是一项开创性的工作。（2）排ℓ将2-范数应用于不同的域以提高所提出模型的泛化能力。另外，softmax回归分类器采用z分数归一化。全面的实验结果证明，增强的TJM可以大大胜过跨域轴承缺陷诊断的竞争方法。