Abstract:
Bearing fault diagnosis is significant in ensuring large machinery and equipment\'s safe and stable operation. However, inconsistent operating environments can lead to data distribution differences between source and target domains. As a result, models trained solely on source-domain data may not perform well when applied to the target domain, especially when the target-domain data is unlabeled. Existing approaches focus on improving domain adaptive methods for effective transfer learning but neglect the importance of extracting comprehensive feature information. To tackle this challenge, we present a bearing fault diagnosis approach using dual-path convolutional neural networks (CNNs) and multi-parallel graph convolutional networks (GCNs), called DPC-MGCN, which can be applied to variable working conditions. To obtain complete feature information, DPC-MGCN leverages dual-path CNNs to extract local and global features from vibration signals in both the source and target domains. The attention mechanism is subsequently applied to identify crucial features, which are converted into adjacency matrices. Multi-parallel GCNs are then employed to further explore the structural information among these features. To minimize the distribution differences between the two domains, we incorporate the multi-kernel maximum mean discrepancy (MK-MMD) domain adaptation method. By applying the DPC-MGCN approach for diagnosing bearing faults under diverse working conditions and comparing it with other methods, we demonstrate its superior performance on various datasets.
摘要:
轴承故障诊断对于保证大型机械设备的安全稳定运行具有重要意义。然而,不一致的操作环境会导致源域和目标域之间的数据分布差异。因此,仅在源域数据上训练的模型在应用于目标域时可能表现不佳,尤其是当目标域数据未标记时。现有方法侧重于改进领域自适应方法以进行有效的迁移学习,但忽略了提取综合特征信息的重要性。为了应对这一挑战,我们提出了一种使用双路径卷积神经网络(CNN)和多并行图卷积网络(GCN)的轴承故障诊断方法,叫做DPC-MGCN,这可以应用于可变的工作条件。要获得完整的特征信息,DPC-MGCN利用双路径CNN从源和目标域的振动信号中提取局部和全局特征。注意力机制随后被应用于识别关键特征,将其转换为邻接矩阵。然后采用多并行GCN来进一步探索这些特征之间的结构信息。为了最小化两个域之间的分布差异,我们引入了多核最大均值差异(MK-MMD)域自适应方法。通过应用DPC-MGCN方法诊断不同工况下的轴承故障,并与其他方法进行比较,我们在各种数据集上展示了其卓越的性能。