摘要
针对实际工程环境复杂多变而导致模型识别准确率不高的问题,提出了一种融合马尔科夫转移场和图注意力网络(Markov transition field and graph attention networks,MTF-GAT)的滚动轴承故障诊断模型。利用MTF保留信号时间相关性的优点,将一维信号转换为二维特征图并定义图的节点和边;利用图注意力层可自适应地对邻近节点分配不同权重的特点,提高模型捕获有用故障特征的能力,并采用深层卷积模块进一步提取图的抽象信息;通过模拟实际工程环境,将各类故障信号输入到训练好的MTF-GAT模型进行故障诊断,并在两个数据集上进行试验验证。结果表明,本文所提出的模型在多种环境下均能准确地完成故障分类任务,相较于其他常用的深度学习模型,MTF-GAT模型具有更好的识别精度和泛化性能。
Aiming at the problem that the recognition accuracy of the model is not high due to the complex and variable engineering environment,a rolling bearing fault diagnosis model integrating Markov transition field and graph attention networks(MTFGAT)is proposed in this paper.Using the advantage of MTF to retain the time correlation of the signal is applied to transform onedimensional signals into two-dimensional feature maps,and the nodes and edges of the graph are defined.The graph attention layer can adaptively assign different weights to adjacent nodes to improve the ability of the model to capture useful fault features,and the abstract information of the graph is further extracted through the deep convolution module.By simulating the actual engineering environment,the various fault signals are input into the trained MTF-GAT model for fault diagnosis,and the model is verified by experiments on two data sets.The results show that the proposed model in this paper can accurately complete the task of fault classification in a variety of environments.Compared with other deep learning models,the MTF-GAT model has better recognition accu-racy and generalization performance.
作者
雷春丽
薛林林
夏奔锋
焦孟萱
史佳硕
LEI Chun‑li;XUE Lin‑lin;XIA Ben‑feng;JIAO Meng‑xuan;SHI Jia‑shuo(School of Mechanical and Electronical Engineering,Lanzhou University of Technology,Lanzhou 730050,China;Key Laboratory of Digital Manufacturing Technology and Application,Ministry of Education,Lanzhou University of Technology,Lanzhou 730050,China)
出处
《振动工程学报》
EI
CSCD
北大核心
2024年第12期2158-2167,共10页
Journal of Vibration Engineering
基金
国家自然科学基金资助项目(51465035)
甘肃省自然科学基金资助项目(20JR5RA466)。
关键词
故障诊断
滚动轴承
图注意力网络
多头注意力机制
马尔科夫转移场
fault diagnosis
rolling bearings
graph attention networks
multi-head attention mechanism
Markov transition field
作者简介
雷春丽(1977-),女,博士,教授。E-mail:lclyq2004@163.com;通讯作者:夏奔锋(1996-),男,硕士研究生。E-mail:xbf3511826@163.com。
