卷积神经网络和峭度在轴承故障诊断中的应用

李俊; 刘永葆; 余又红

doi:10.13224/j.cnki.jasp.2019.11.014

卷积神经网络和峭度在轴承故障诊断中的应用

doi: 10.13224/j.cnki.jasp.2019.11.014

海军工程大学动力工程学院,武汉 430032

基金项目: 海军工程大学自然科学自主立项项目(425317K004,425317K137)

计量
- 文章访问数: 883
- HTML浏览量: 13
- PDF量: 397
- 被引次数: 0
出版历程
- 收稿日期: 2019-05-24
- 刊出日期: 2019-11-28

Application of convolutional neural network and kurtosis in fault diagnosis of rolling bearing

College of Power Engineering,Naval University of Engineering,Wuhan 430032,China

摘要

摘要: 针对传统智能诊断方法依靠专家知识和人工提取数据特征工作量大的问题,结合深度学习方法在特征提取和处理大数据方面的优势,研究了一种基于卷积神经网络和振动信号峭度指标的滚动轴承故障诊断方法。该方法将深度学习应用于轴承故障诊断,提取滚动轴承正常状态、内圈故障、外圈故障和滚动体故障4种状态的振动信号,将振动信号分段处理得到峭度指标,使用数据到图像的转换方法将峭度指标转换为灰度图,送入卷积神经网络模型完成故障分类。在进行滚动轴承故障诊断的实验时,所提的模型诊断准确率达到99.5%,高于传统支持向量机(SVM)算法的95.8%。
- 深度学习 /
- 滚动轴承 /
- 故障诊断 /
- 卷积神经网络 /
- 峭度
Abstract: Traditional intelligent diagnosis method relying much on expert knowledge and manual extraction data features takes a lot of work. Based on the advantages of deep learning in feature extraction and processing of big data,a method of rolling bearing fault diagnosis based on convolution neural network and kurtosis was studied. This method was used to analyse four kinds of vibration signal of the normal state,the inner race fault,the outer race fault and the ball fault. The vibration signal was processed in segments to obtain kurtosis, which was converted into gray images by data-to-image method. Finally, these were fed into convolution neural network model to complete rolling bearing fault classification. In the case of rolling bearing fault diagnosis, the improved model had a diagnostic accuracy of 99.5%, which was higher than 95.8% of the traditional support vector machine (SVM) algorithm.
- deep learning /
- rolling bearing /
- fault diagnosis /
- convolution neural network /
- kurtosis

HTML

参考文献(18)

[1]	吴昭同,杨世锡.旋转机械故障特征提取与模式分类新方法［M］.北京：科学出版社,2012.
[2]	李永波,滚动轴承故障特征提取与早期诊断方法研究［D］.哈尔滨：哈尔滨工业大学,2017.LI Yongbo.Investigation of fault feature extraction and early fault diagnosis for rolling bearings［D］.Harbin: Harbin Institute of Technology,2017.(inChinese)
[3]	高艺源,于德介,王好将,等.基于图谱指标的滚动轴承故障特征提取方法［J］.航空动力学报,2018,33(8):2033-2040.GAO Yiyuan,YU Dejie,WANG Haojiang,et al.Fault feature extraction method of rolling bearing based on spectral graph indices［J］.Journal of Aerospace Power,2018,33(8):2033-2040.(in Chinese)
[4]	王宏超,杜文辽.基于强抗噪威格纳威利分析的滚动轴承故障诊断［J］.航空动力学报,2019,34(4):772-777.WANG Hongchao,DU Wenliao.Fault diagnosis of rolling bearing based on noise-resistant Wigner-Vile analysis［J］.Journal of Aerospace Power,2019,34(4):772-777.(in Chinese)
[5]	张新鹏,胡茑庆,程哲,等.信号稀疏分解理论在轴承故障检测中的应用［J］.国防科技大学学报,2016,38(3):141-147.ZHANG Xinpeng,HU Niaoqing,CHENG Zhe,et al.Application of signal sparse decomposition theory inbearing fault detection［J］.Journal of National University of Defense Technology,2016,38(3):141-147.(in Chinese)
[6]	HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks［J］.Science,2006,313(5786):504-507.
[7]	GUO S,YANG T,GAO W.A novel fault diagnosis method for rotating machinery based on a convolutional neural network［J］.Sensors,2018,18(5):1429-1447.
[8]	XIE J,DU G,SHEN C.An end-to-end model based on improved adaptive deep belief network and its application to bearing fault diagnosis［J］.IEEE Access,2018,6:63584-63596.
[9]	SHAO H,JIANG H,ZHANG H.Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network［J］.IEEE Transactions on Industrial Electronics,2018,65(3):2727-2736.
[10]	姜建国,王庆.基于MEEMD和峭度-相关系数电机轴承故障诊断［J］.自动化技术与应用,2018,37(1):65-70.JIANG Jianguo,WANG Qing.Motor bearing fault diagnosis based on MEEMD and kurtosis-relevant coefficient［J］.Techniques of Automation and Applications,2018,37(1):65-70.(in Chinese)
[11]	李彦冬,郝宗波,雷航.卷积神经网络研究综述［J］.计算机应用,2016,36(9):2508-2515.LI Yandong,HAO Zongbo,LEI Hang.Survey of convolutional neural network［J］.Journal of Computer Applications,2016,36(9):2508-2515.(in Chinese)
[12]	ZHAO R,YAN R,CHEN Z.Deep learning and its applications to machine health monitoring［J］.Mechanical Systems and Signal Processing,2019,115:213-237.
[13]	KHAN S,YAIRI T.A review on the application of deep learning in system health management［J］.Mechanical Systems and Signal Processing,2018,107:241-265.
[14]	HINTON G E,SRIVASTAVA N,KRIZHEVSKY A.Improving neural networks by preventing co-adaptation of feature detectors.［EB/OL］.［2012-07-03］.https://arxiv.org/abs/1207.0580.
[15]	彭畅.旋转机械轴承振动信号分析方法研究［D］.重庆:重庆大学,2014.PENG Chang.Vibration signal analysis of bearings in the rotating machinery［D］.Chongqing:Chongqing University,2014.(in Chinese)
[16]	ABADI M.TensorFlow: learning functions at scale［J］.ACM(Association for Computing Machinery) Sigplan Notices,2016,51(9):1.
[17]	张荣,李伟平,莫同.深度学习研究综述［J］.信息与控制,2018,47(4):385-397.ZHANG Rong,LI Weiping,MO Tong,Review of deep learning［J］.Information and Control,2018,47(4):385-397.(in Chinese)
[18]	胡越,罗东阳,花奎,等.关于深度学习的综述与讨论［J］.智能系统学报,2019,14(1):1-19.HU Yue,LUO Dongyang,HUA Kui,et al.Overview and discussion on deep learning［J］.Chinese Association of Artificial Intelligence Transactions on Intelligent Systems,2019,14(1):1-19.(in Chinese)