一种适用于轴承故障诊断半监督学习分类的多层图卷积注意力融合网络  

Multi-layer graph product attention fusion network for semi-supervised learning classification of bearing fault diagnosis

作　　者：魏春虎 程峰 曾玉海 杨世飞 WEI Chunhu;CHENG Feng;ZENG Yuhai;YANG Shifei(School of Mechanical Engineering,Jiangnan University,Wuxi 214122,China;Nanjing Chaos Data Technology Co.,Ltd,Nanjing 210012,China)

机构地区：[1]江南大学机械工程学院,江苏无锡214122 [2]南京凯奥斯数据技术有限公司,江苏南京210012

出　　处：《机电工程》2024年第8期1364-1375,共12页Journal of Mechanical & Electrical Engineering

基　　金：国家重点研发计划政府间国际科技创新合作项目(2022YFE014300);山东省重大科技创新工程自主项目(2019JZZY020111)。

摘　　要：图卷积网络的平滑运行会导致其无法通过深度网络堆叠捕获深层信息,为了解决这个问题,提出了一种适用于滚动轴承故障诊断半监督学习分类的多层图卷积注意力融合网络(MGCAN)。首先,采用频域构图法将数据转换为图模型,捕获了数据的内在结构信息,将构建好的图数据输入网络,逐层提取特征信息,从浅层到深层逐步加深对数据特征的理解;然后,对每一层图卷积信息进行了有序拼接,同时引入了图注意力机制,使网络能够自动关注对分类任务比较重要的信息,从而提高了网络的性能和鲁棒性;最终,通过迭代学习,网络能够不断优化模型参数,对故障信息进行了准确识别;对不同工作条件下的滚动轴承进行了多次实验,并将该方法与传统的基于深度学习的方法进行了分析比较。研究结果表明:即使在标记数据只有10%的前提下,采用该网络依旧能够达到88%以上的识别准确度,并且适用于匀速和变速等不同的工况。上述结果证明,在选择适当方法保留多层图卷积中的有用信息后,深度图卷积网络可以成为诊断滚动轴承故障的一大利器。The smooth operation of graph convolution network leads to the problem that it can not capture deep information through deep network stacking.In order to solve this problem,a multi-layer graph convolution attention fusion network(MGCAN)suitable for semi-supervised learning classification of rolling bearing fault diagnosis was proposed.Firstly,the frequency domain graphing method was adopted to transform data into a graph model,the inherent structural information within the data was captured.The constructed graph data was inputted into the network,and feature information was extracted layer by layer,progressively deepening the network s understanding of data features from shallow to deep layers.Then,each layer of graph convolution information was orderly concatenated.Meanwhile,the graph attention mechanism was incorporated,the network was enabled to automatically focus on the important information for classification tasks.As a result,the performance and robustness of the network were enhanced.Finally,through iterative learning,the model parameters were continuously optimized,fault information was accurately identified by the networks,and multiple experiments on rolling bearings under different working conditions was conducted.This method was compared with traditional deep learning methods.The research results indicate that even with only 10%of labeled data,the network can still achieve an accuracy of over 88%,and it is applicable to various conditions such as uniform speed and variable speed.The results confirm that,after employing an appropriate method to retain useful information in multi-layer graph convolutions,deep graph convolutional networks can be a powerful tool for diagnosing faults in rolling bearings.

关 键 词：轴承故障诊断 多层图卷积注意力融合网络 多层图卷积信息 图注意力机制 k-近邻图 深度学习 识别准确度 

分 类 号：TH133.3[机械工程—机械制造及自动化]