摘要：

多传感数据融合方法能够提升轴承故障诊断的准确性, 但在电机轴承故障诊断中, 现有大多数多传感数据融合方法存在传感数据类型单一、难以充分挖掘不同模态数据间冗余性和互补性的问题。为此, 提出一种基于多约束模态不变图卷积融合网络(MCMI-GCFN)的轴承故障诊断方法。首先, 通过卷积自编码器(CAE)和挤压-激励模块(SE block)对原始电流、振动信号进行特征提取; 其次, 引入源域分类器和域鉴别器在域对抗训练的基础上捕获不同模态数据间的模态不变性, 充分挖掘多模态数据间的冗余性和互补性; 最后, 利用图卷积神经网络(GCN)的空间聚合特性捕获电流、振动模态相近时间步特征之间的依赖关系, 以精确融合其上下文语义信息。在德国帕德伯恩大学公开的轴承损伤电流、振动数据集上进行验证, 实验结果表明, MCMI-GCFN方法达到了99.6%的轴承故障诊断精度, 比非融合方法高9~11.4百分点, 验证了所提模型的有效性。

关键词: 深度学习, 轴承故障诊断, 数据融合, 域对抗训练, 图卷积神经网络

Abstract:

Multisensor data fusion methods can enhance the accuracy of bearing fault diagnoses. However, in the context of motor-bearing fault diagnosis, most existing multisensor data fusion methods suffer from issues such as a single type of sensor data and difficulty in fully exploiting the redundancy and complementarity among different modal data. To address this issue, a bearing fault diagnosis method based on a Multiple-Constraint Modal-Invariant Graph Convolutional Fusion Network (MCMI-GCFN) is proposed. First, features are extracted from the original current and vibration signals using a Convolutional Auto-Encoder (CAE) and Squeeze-and-Excitation block (SE block). Second, a source domain classifier and domain discriminator are introduced to capture the modal invariance among different modal data based on domain adversarial training, thereby fully exploiting the redundancy and complementarity among multimodal data. Finally, the spatial aggregation characteristics of the Graph Convolutional Neural Network (GCN) are utilized to capture the dependency relationships between features at similar time steps in the current and vibration modalities, enabling precise fusion of their contextual semantic information. This method is validated using a publicly available bearing damage current and vibration dataset obtained from the University of Paderborn, Germany. The experimental results demonstrate that the MCMI-GCFN method achieves a bearing fault diagnosis accuracy of 99.6%, which is 9 to 11.4 percentage points higher than that achieved by nonfusion methods, thereby verifying the effectiveness of the proposed model.

Key words: deep learning, bearing fault diagnosis, data fusion, domain adversarial training, Graph Convolutional Neural Network (GCN)