摘要
针对现有卷积神经网络无法充分提取滚动轴承时域信号间的关联特征,模型训练所需样本多以及泛化性不足的问题,提出一种基于增强卷积神经网络模型的滚动轴承多工况故障诊断方法。根据滚动轴承转速和采样频率计算轴承单圈故障特征信号长度,采用格拉姆角场编码技术对单圈时域信号完整信息进行编码,生成相应特征图像,使神经网络在视觉上对时域信号关联特征进行学习;利用ACNet网络模型中的非对称卷积对ConvNeXt模型的7×7深度卷积层进行重构:即采用2个3×3,1个1×3和1个3×1的非对称小卷积核以多分支结构组合的形式重构其7×7卷积层,增强ConvNeXt模型的特征提取效率;对ConvNeXt模型中的数据增强模块及学习率衰减策略进行改进,提高ConvNeX模型在小样本训练下的泛化性,以此搭建增强深度卷积神经网络IConvNeXt模型。使用凯斯西储大学不同故障直径轴承、东南大学滚动轴承复合故障和加拿大渥太华变转速滚动轴承故障数据集进行试验验证,结果表明:所提IConvNeXt模型对滚动轴承不同故障直径和复合故障识别准确率为100%,对变转速轴承故障识别率为99.63%。将所提方法与RP+ResNet、RP+IConvNeXt、MLCNN⁃LSTM、MTF+ICon⁃vNeXt等方法进行对比,结果表明,所提模型在更少样本训练下的故障诊断效果均优于其他方法,并具有较强的泛化性能。
Aiming at the problems that the existing convolutional neural network cannot fully extract the correlation features between rolling bearing time domain signals,the large number of samples required for model training and the insufficient generalization,A new method for diagnosing multi-condition faults of rolling bearings based on an enhanced convolutional neural network model is proposed.The length of the bearing singlerevolution fault characteristic signal is calculated according to the rolling bearing speed and sampling frequency,then the complete information of the singlerevolution time domain signal is encoded by Gramian Angular Difference Field coding technology to generate the corresponding feature image,enabling the neural network can visually learn the time domain signal correlation features.The 7×7 deep convolutional layer of the ConvNeXt model is reconstructed by using the asymmetric convolution in the ACNet network model:that is,two 3×3,one 1×3 and one 3×1 asymmetric small convolution kernel are used to reconstruct the 7×7 convolutional layer in the form of a multi-branch structure combination,which enhances the feature extraction efficiency of the ConvNeXt model.The data augmentation module and learning rate decay strategy of the ConvNeXt model are improved to raise the generalization of the ConvNeX model under small-sample training,to build an enhanced deep convolutional neural network model IConvNeXt.Different fault diameters of Case Western Reserve University,composite rolling bearing faults of Southeast University and variable speed bearing fault data sets of Ottawa,Canada are used for experimental verification,the results show that the proposed IConvNeXt model achieves a fault diagnosis rate of 100%for different fault diameters and composite faults of rolling bearings,and a fault diagnosis rate of 99.63%for variable speed bearings.The proposed method is experimentally compared with RP+ResNet,RP+IConvNeXt,time-frequency graph+DCNN,MLCNNLSTM,MTF+IConvNeXt and other methods,the results were condicted to validate that the fault diagnosis effect of the proposed model is better than that of other methods under less sample training and has strong generalization performance.
作者
郭盼盼
张文斌
崔奔
郭兆伟
赵春林
尹治棚
刘标
GUO Panpan;ZHANG Wenbin;CUI Ben;GUO Zhaowei;ZHAO Chunlin;YIN Zhipeng;LIU Biao(School of Mechanical and Electrical Engineering,Kunming University of Science and Technology,Kunming 650500,China;School of Mechanical and Electrical Engineering,Kunming University,Kunming 650214,China;Tianjin Junliangcheng Power Generation Co.,Ltd.,Tianjin 300300,China;School of Computer Science and Engineering,North Minzu University,Yinchuan 750021,China;CHN Energy Star Technology Co.,Ltd.,Beijing 100089,China)
出处
《振动工程学报》
北大核心
2025年第1期96-108,共13页
Journal of Vibration Engineering
基金
国家自然科学基金资助项目(51769007)
云南省地方本科高校基础研究联合专项重点项目(202001BA070001-002)
兴滇英才支持计划资助项目(YNWR-QNBJ-2018-349)
云南省地方高校联合专项面上项目(202001BA070001-015)。
关键词
故障诊断
滚动轴承
多工况
格拉姆角场
增强卷积神经网络
fault diagnosis
rolling bearing
multi-working conditions
Gramian angular field
enhanced convolutional neural network
作者简介
第一作者:郭盼盼(1999―),男,硕士研究生。E-mail:panpan3012022@163.com;通信作者:张文斌(1981―),男,博士,教授。E-mail:190322507@qq.com。
