基于卷积门控循环网络的滚动轴承故障诊断

杨平; 苏燕辰

doi:10.13224/j.cnki.jasp.2019.11.015

基于卷积门控循环网络的滚动轴承故障诊断

doi: 10.13224/j.cnki.jasp.2019.11.015

杨平,
苏燕辰

西南交通大学机械工程学院,成都 610031

计量
- 文章访问数: 489
- HTML浏览量: 9
- PDF量: 541
- 被引次数: 0
出版历程
- 收稿日期: 2019-04-14
- 刊出日期: 2019-11-28

Faultdiagnosis of rolling bearing based on convolution gated recurrent network

School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China

摘要

摘要: 针对许多基于深度学习的滚动轴承故障诊断方法在小样本数据集下诊断性能下降的问题,提出一种基于卷积门控循环神经网络的轴承故障诊断模型。该模型使用两层的卷积网络来从输入信号中提取特征,同时使用tanh函数作为激活函数,且池化层使用大池化核来进行重叠下采样。将所提取得到的高层特征连接到双向门控循环网络。合并循环网络正向和逆向的最后一个状态,并连接一层全连接层进行输出。选用凯斯西储大学的轴承故障数据集来验证模型在小样本数据集下的诊断性能,实验结果表明,相比于其他类型的模型,该模型在仅有20个训练样本的情况下依然保持97%的识别准确率。
- 滚动轴承 /
- 故障诊断 /
- 卷积网络 /
- 门控循环单元 /
- 重叠池化
Abstract: In view of the phenomenon of the degraded diagnostic performance of many rolling bearing fault diagnosis methods based on deep learning under the small sample data set, a bearing fault diagnosis model based on convolution gated recurrent neural network was proposed. This model used a two-layer convolution network to extract features from the input signal, using the tanh function as the activation function, and the pooling layer used the large pooled kernel for overlapping downsampling. The extracted high-level features were connected to the bidirectional gated recurrent network. The last states of the forward and reverse directions of the recurrent network were combined, and a layer of fully connected layers was connected for output. The bearing fault data set of Case Western Reserve University was used to verify the diagnostic performance of the model under the small sample data set. The experimental results showed that the model still maintained 97% accuracy with only 20 training samples compared with other types of models.
- rolling bearing /
- fault diagnosis /
- convolution network /
- gated recurrent unit /
- overlapping pooling

HTML

参考文献(22)

[1]	MEDOUED A,MORDJAOUI M,SOUFI Y,et al.Induction machine bearing fault diagnosis based on the axial vibration analytic signal［J］.International Journal of Hydrogen Energy,2016,41(29):12688-12695.
[2]	JENA D P,PANIGRAHI S N.Automatic gear and bearing fault localization using vibration and acoustic signals［J］.Applied Acoustics,2015,98:20-33.
[3]	JANSSEN O,SCHULZ R,SLAVKOVIKJ V,et al.Thermal image based fault diagnosis for rotating machinery［J］.Infrared Physics and Technology,2015,73:78-87.
[4]	刘仁德,陶德华,胡申辉,等.油液分析技术在振动筛故障诊断中的应用［J］.润滑与密封,2003(2):66-68.LIU Rende,TAO Dehua,HU Shenhui,et al.Application of oil analysis in the failure diagnosis of vibrating sizer［J］.Lubrication Engineering,2003(2):66-68.(in Chinese)
[5]	JIANG Y,ZHU H,LI Z.A new compound faults detection method for rolling bearings based on empirical wavelet transform and chaotic oscillator［J］.Chaos Solitons and Fractals,2016,89:8-19.
[6]	向丹,岑健.基于EMD熵特征融合的滚动轴承故障诊断方法［J］.航空动力学报,2015,30(5):1149-1155.XIANG Dan,CEN Jian.Method of roller bearing fault diagnosis based on feature fusion of EMD entropy［J］.Journal of Aerospace Power,2015,30(5):1149-1155.(in Chinese)
[7]	马风雷,陈小帅,周小龙.改进希尔伯特-黄变换的滚动轴承故障诊断［J］.机械设计与制造,2018(5):75-78.MA Fenglei,CHEN Xiaoshuai,ZHOU Xiaolong.Rolling bearing fault diagnosis based on improved hilbert-huang transform［J］.Machinery Design and Manufacture,2018 (5):75-78.(in Chinese)
[8]	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(1):67-73.XU Yougang,MENG Zhipeng,LU Ming.Fault diagnosis method of rolling bearing based on dual-tree complex wavelet packet transform and SVM［J］.Journal of Aerospace Power,2014,29(1):67-73.(in Chinese)
[9]	MURALIDHARAN V,SUGUMARAN V.A comparative study of Nave Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis［J］.Applied Soft Computing Journal,2012,12(8):2023-2029.
[10]	向玲,郭鹏飞,高楠,张力佳.基于IITD和FCM聚类的滚动轴承故障诊断［J］.航空动力学报,2018,33(10):2553-2560.XIANG Ling,GUO Pengfei,GAO Nan,et al.Rolling bearing fault diagnosis based on IITD and FCM clustering.［J］.Journal of Aerospace Power,2018,33(10):2553-2560.(in Chinese)
[11]	ZAREI J,TAJEDDINI M A,KARIMI H R.Vibration analysis for bearing fault detection and classification using an intelligent filter［J］.Mechatronics,2014,24(2):151-157.
[12]	HINTON G,OSINDERO S,TEH Y.A fast learning algorithm for deep belief nets［J］.Neural omputation,2006,18(7):1527-1554.
[13]	SUN W J,SHAO S Y,ZHAO R,et al.A sparse auto-encoder-based deep neural network approach for induction motor faults classification［J］.Measurement,2016,89:171-178.
[14]	张西宁,向宙,唐春华.一种深度卷积自编码网络及其在滚动轴承故障诊断中的应用［J］.西安交通大学学报,2018,52(7):1-8,59.ZHANG Xining,XIANG Zhou,TANG Chunhua.A deep convolutional auto-encoding network and its application in fault diagnosis［J］.Journal of Xi’an Jiaotong University,2018,52(7):1-8,59.(in Chinese)
[15]	GAN M,WANG C,ZHU C.Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings［J］.Mechanical Systems and Signal Processing,2016,72-73:92-104.
[16]	LONG W,LI X,LIANG G,et al.A new convolutional neural network-based data-driven fault diagnosis method［J］.IEEE Transactions on Industrial Electronics,2018,65(7):5990-5998.
[17]	ZHANG W,LI C,PENG G,et al.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load［J］.Mechanical Systems and Signal Processing,2017,100:439-453.
[18]	LI S,LIU G,TANG X,et al.An ensemble deep convolutional neural network model with improved D-S evidence fusion for bearing fault diagnosis［J］.Sensors,2017,17(8):1729-1750.
[19]	佘博,田福庆,梁伟阁.基于深度卷积变分自编码网络的故障诊断方法［J］.仪器仪表学报,2018,39(10):27-35.SHE Bo,TIAN Fuqing,LIANG Weige.Fault diagnosis based on a deep convolution variational autoencoder network［J］.Chinese Journal of Scientific Instrument,2018,39(10):27-35.(in Chinese)
[20]	CHO K,VAN B,GULCEHRE C,et al.Learning phrase representations using rnn encoder-decoder for statistical machine translation［C］∥Empirical Methods in Natural Language rocessing.Doha,Qatar:ACL,2014:1724-1734.
[21]	ZHANG W,PENG G,LI C,et al.A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals:［J］.Sensors,2017,17(2):425-446.
[22]	LAURENS V,HINTON G.Visualizing data using t-SNE［J］.Journal of Machine Learning Research,2008,9:2579-2605.