The description of class labels of MFPT.

Learning powerful discriminative features is the key for machine fault diagnosis. Most existing methods based on convolutional neural network (CNN) have achieved promising results. However, they primarily focus on global features derived from sample signals and fail to explicitly mine relationships between signals. In contrast, graph convolutional network (GCN) is able to efficiently mine data relationships by taking graph data with topological structure as input, making them highly effective for feature representation in non-Euclidean space. In this article, to make good use of the advantages of CNN and GCN, we propose a graph attentional convolutional neural network (GACNN) for effective intelligent fault diagnosis, which includes two subnetworks of fully CNN and GCN to extract the multilevel features information, and uses Efficient Channel Attention (ECA) attention mechanism to reduce information loss. Extensive experiments on three datasets show that our framework improves the representation ability of features and fault diagnosis performance, and achieves competitive accuracy against other approaches. And the results show that GACNN can achieve superior performance even under a strong background noise environment.

学习具备强判别力的特征是机械故障诊断的核心任务。现有绝大多数基于卷积神经网络(Convolutional Neural Network, CNN)的方法已取得了优异的诊断效果。然而，这类方法主要聚焦于从样本信号中提取的全局特征，未能显式挖掘信号间的内在关联。与之相对，图卷积神经网络(Graph Convolutional Network, GCN)能够以具备拓扑结构的图数据作为输入，高效挖掘数据间的关联关系，因此在非欧几里得空间的特征表征任务中表现出色。为充分结合卷积神经网络与图卷积神经网络的优势，本文提出一种面向智能故障诊断的图注意力卷积神经网络(Graph Attentional Convolutional Neural Network, GACNN)，该模型包含全卷积与图卷积两个子网络，用于提取多层级特征信息，并引入高效通道注意力(Efficient Channel Attention, ECA)机制以降低信息损失。在三个公开数据集上开展的大量对比实验表明，所提框架能够有效提升特征的表征能力与故障诊断性能，与其他主流方法相比具备竞争力的准确率。此外，实验结果证实，即使在强背景噪声环境下，GACNN仍可取得优异的故障诊断表现。