基于GADF-CNN的滚动轴承故障诊断方法

PDF(2237 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (5) : 247-253.

论文

仝钰，庞新宇，魏子涵

作者信息 +

Fault diagnosis method of rolling bearing based on GADF-CNN

TONG Yu, PANG Xinyu, WEI Zihan

Author information +

文章历史 +

摘要

针对一维信号作为卷积神经网络输入时无法充分利用数据间的相关信息的问题，提出GADF-CNN的轴承故障诊断模型。利用格拉姆角差域(GADF)对采集到的振动信号进行编码，可以很容易地进行角度透视，从而识别出不同时间间隔内的时间相关性并生产相应特征图，之后将其输入卷积神经网络（CNN）自适应的完成滚动轴承故障特征的提取与分类。为了验证模型性能，采用凯斯西储大学轴承数据集进行轴承故障诊断分析，同时引入常见神经网络作为对比，检验不同模型的分类性能。结果表明，相较于其他图像编码方式与神经网络，该模型在载荷变化以及噪声污染时，仍保持了良好的诊断性能。

Abstract

Aiming at the problem that when one-dimensional signals are used as input to convolutional neural networks, the relevant information between the data cannot be fully utilized, a bearing fault diagnosis model of GADF-CNN is proposed. Using the Gradient Angle Difference Domain (GADF) to encode the collected vibration signals, angle perspective can be easily performed to identify the time correlation in different time intervals and produce corresponding feature maps, which are then input into the convolutional nerve Network (CNN) adaptively completes the extraction and classification of rolling bearing fault features. In order to verify the model performance, the Case Western Reserve University bearing data set was used for bearing fault diagnosis and analysis, and common neural networks were introduced as a comparison to test the classification performance of different models. The results show that, compared with other image coding methods and neural networks, the model still maintains good diagnostic performance under load changes and noise pollution.

导出引用

仝钰，庞新宇，魏子涵. 基于GADF-CNN的滚动轴承故障诊断方法[J]. 振动与冲击, 2021, 40(5): 247-253

TONG Yu, PANG Xinyu, WEI Zihan. Fault diagnosis method of rolling bearing based on GADF-CNN[J]. Journal of Vibration and Shock, 2021, 40(5): 247-253

参考文献

[1] 雷亚国, 贾峰, 周昕, et al. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, v.51(21):55-62.
Lei Yaguo, Jia Feng, Zhou Xin, et al. Big data health monitoring method of mechanical equipment based on deep learning theory [J]. Journal of Mechanical Engineering, 2015, v.51 (21): 55-62.
[2] 胥永刚,孟志鹏,陆明.基于双树复小波包变换和SVM的滚动轴承故障诊断方法[J].航空动力学报,2014,29(01):67-73.
Xu Yonggang, Meng Zhipeng, Lu Ming. Rolling bearing fault diagnosis method based on dual-tree complex wavelet packet transform and SVM [J] .Aerodynamics, 2014,29 (01): 67-73.
[3] 乔美英,刘宇翔,兰建义.基于VMD和马氏距离SVM的滚动轴承故障诊断[J].中山大学学报(自然科学版),2019,58(05):8-16
Qiao Meiying, Liu Yuxiang, Lan Jianyi. Fault diagnosis of rolling bearings based on VMD and Mahalanobis distance SVM [J] .Journal of Sun Yat-sen University (Natural Science Edition), 2019,58 (05): 8-16
[4] Y. G. Lei, Z. J. He, and Y. Y. Zi, ‘‘Application of an intelligent classification method to mechanical fault diagnosis,’’ Expert Syst. Appl., vol. 36, no. 6, pp. 9941–9948, 2009.
[5] Shao H , Jiang H , Zhang X , et al. Rolling bearing fault diagnosis using an optimization deep belief network[J]. Measurement Science & Technology, 2015, 26(11):115002.
[6] 王奉涛,邓刚,王洪涛,于晓光,韩清凯,李宏坤.基于EMD和SSAE的滚动轴承故障诊断方法[J].振动工程学报,2019,32(02):368-376.
Wang Fengtao, Deng Gang, Wang Hongtao, Yu Xiaoguang, Han Qingkai, Li Hongkun. Rolling bearing fault diagnosis method based on EMD and SSAE [J]. Journal of Vibration Engineering, 2019,32 (02): 368-376.
[7] Chen Z , Li W . Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network[J]. IEEE Transactions on Instrumentation & Measurement, 2017:1-10.
[8] Long, Wen, Xinyu, et al. A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method[J]. IEEE Transactions on Industrial Electronics, 2017.
[9] Lu C , Wang Y , Ragulskis M , et al. Fault Diagnosis for Rotating Machinery: A Method based on Image Processing[J]. PLoS ONE, 2016, 11(10):e0164111.
[10] 刘炳集,熊邦书,欧巧凤,陈新云.基于时频图和CNN的滚动轴承故障诊断[J].南昌航空大学学报(自然科学版),2018,32(02):86-91.
Liu Bingji, Xiong Bangshu, Ou Qiaofeng, Chen Xinyun. Fault diagnosis of rolling bearing based on time-frequency graph and CNN [J] .Journal of Nanchang Hangkong University (Natural Science Edition), 2018,32 (02): 86-91.
[11] Udmale S S , Patil S S , Phalle V M , et al. A bearing vibration data analysis based on spectral kurtosis and ConvNet[J]. Soft Computing A Fusion of Foundations Methodologies & Applications, 2018.
[12] Wang Z , Oates T .Imaging Time-Series to Improve Classification and Imputation[J]. 2015.
[13] Feri Setiawan, Bernardo Nugroho Yahya Deep activity recognition on imaging sensor data[J] ELECTRONICS LETTERS,2019,PP 928–931.
[14] 薛宇航. 基于卷积神经网络的中介轴承故障诊断研究[D].大连理工大学,2019.
Xue Yuhang. Research on Fault Diagnosis of Intermediate Bearings Based on Convolutional Neural Network [D] .Dalian University of Technology, 2019.
[15] 曹戈. 基于深度卷积神经网络的人脸图像分类应用研究[D].吉林大学,2019.
Cao Ge. Application of face image classification based on deep convolutional neural network [D] .Jilin University, 2019.
[16] 文铭. 基于深度神经网络的语音识别前端处理[D].中国科学技术大学,2019.
Wen Ming. Front-end processing of speech recognition based on deep neural network [D] .University of Science and Technology of China, 2019.
[17] Krizhevsky A , Sutskever I , Hinton G . ImageNet Classification with Deep Convolutional Neural Networks[C]// NIPS. Curran Associates Inc. 2012.
[18] Kingma D , Ba J.Adam: A Method for Stochastic Optimization[J]. Computer Science, 2014.
[19] Case Western Reserve University Bearing Data Center[EB/
OL]. 2018. https:// cse groups. case. edu/ bearing data center/ pages/ download- data- file.
[20] Akata Z , Perronnin F , Harchaoui Z , et al. Label-Embedding for Image Classification[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 38(7):1425-1438.
[21] Huang Z , Xie Y . Fault Diagnosis Method of Rolling Bearing Based on BP Neural Network[C]// International Conference on Measuring Technology & Mechatronics Automation. IEEE Computer Society, 2009.
[22] Wang L , Hope A D . Bearing fault diagnosis using multi-layer neural networks[J]. Insight - Non-Destructive Testing and Condition Monitoring, 2004, 46(8):451-455