Accurate fault diagnosis of rotating machinery is critical to avoid catastrophic accidents. However, insufficient fault data seriously limit the performance of fault diagnosis in industrial applications. In this paper, a novel domain adaptive and adversarial network (DAAN) is proposed for data-driven fault diagnosis of the rotating machinery, which consists of a deep feature extractor, a domain classifier, and a label adaptive predictor. The deep feature extractor and domain classifier are constructed to obtain domain-invariant features by domain-adversarial training. Then, in the label adaptive predictor, a domain adaptation technique is used to reduce the feature discrepancy between the source domain and the target domain, so as to establish a mapping relationship between the data feature distribution of the two domains. Furtherly, a new transfer diagnosis method is proposed by using the DAAN, which combines the data generated by experimental simulation with deep transfer learning, to realize end-to-end intelligent fault diagnosis of the in-service machinery with few unlabeled fault samples. The proposed method explores a new solution for applying laboratory data to intelligent fault diagnosis in real scenarios. Several transfer experiments are implemented to verify the effectiveness of the proposed method by using 55 roller bearings and 4 gearboxes under various scenarios. The experimental results show that the diagnostic performance of proposed method is much better than other transfer learning methods and non-transfer learning methods.

中文翻译：

---

使用域自适应和对抗网络对旋转机械进行跨域智能诊断


旋转机械的准确故障诊断对于避免灾难性事故至关重要。然而，故障数据不足严重限制了工业应用中故障诊断的性能。该文提出了一种新的领域自适应对抗网络（DAAN），用于旋转机械的数据驱动故障诊断，该网络由深度特征提取器、领域分类器和标签自适应预测器组成。构建深度特征提取器和域分类器，通过域对抗训练获得域不变特征。然后，在标签自适应预测器中，采用域自适应技术来减小源域和目标域之间的特征差异，从而建立两个域的数据特征分布之间的映射关系。进一步，利用 DAAN 提出了一种新的转移诊断方法，该方法将实验仿真产生的数据与深度迁移学习相结合，以很少的未标记故障样本实现在役机械的端到端智能故障诊断。所提出的方法探索了一种将实验室数据应用于实际场景中智能故障诊断的新解决方案。实施了多次传递实验，以验证所提方法在各种场景下使用 55 个滚子轴承和 4 个齿轮箱的有效性。实验结果表明，所提方法的诊断性能远优于其他迁移学习方法和非迁移学习方法。