基于深度学习特征提取和WOA-SVM状态识别的轴承故障诊断

摘要
图/表
参考文献(19)
相关文章 (15)

全文: PDF (2607 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对滚动轴承故障诊断问题，利用深度学习神经网络、鲸鱼优化算法（Whale optimization algorithm，WOA）和支持向量机(Support vector machine,SVM)等技术，提出了一种基于深度学习特征提取和WOA-SVM状态识别相结合的故障诊断模型。先通过深度学习自适应提取故障频谱特征，并将其与数理统计方法提取的时域特征相融合，再通过WOA-SVM对融合后的联合特征进行故障诊断。该模型在对滚动轴承试验台的故障诊断中实现了不同工况下多种故障类型的可靠识别，并且在一定程度上提高了故障分类的准确性。为了验证WOA-SVM在深度学习提取特征的轴承故障识别中的可行性和有效性，对比了粒子群支持向量机和遗传支持向量机，结果表明WOA-SVM具有较高的收敛精度和收敛速度。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：鲸鱼优化算法, 支持向量机, 轴承故障, 深度学习

Abstract：For the fault diagnosis of rolling bearings, a fault diagnosis model based on the deep learning feature extraction and WOA-SVM state recognition was proposed.The fault frequency domain feature was extracted by the depth learning adaptive method, and then it was fused with the time domain feature extracted by the mathematical statistics method.The fused joint features were used in diagnosis through the processing of WOA-SVM.By the model, it has realized the reliable identification of various fault types of rolling bearings under different working conditions on a test bench and improves the accuracy of fault classification to a certain extent.In order to verify the feasibility and effectiveness of bearing fault identification based on WOA-SVM, the diagnosis results were compared with those by the PSO-SVM and GA-SVM.The results show that WOA-SVM has higher convergence accuracy and convergence speed.

Key words： Whale optimization algorithm Support vector machine Bearing failure Deep learning;

收稿日期: 2018-07-12 出版日期: 2019-05-15

引用本文:

赵春华1, 2 胡恒星2 陈保家1, 2 张毅娜2 肖嘉伟2. 基于深度学习特征提取和WOA-SVM状态识别的轴承故障诊断[J]. 振动与冲击, 2019, 38(10): 31-37.
ZHAO Chunhua HU Hengxing CHEN Baojia ZHANG Yina XIAO Jiawei. Bearing fault diagnosis based on the deep learning feature extraction and WOA SVM state recognition. JOURNAL OF VIBRATION AND SHOCK, 2019, 38(10): 31-37.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2019/V38/I10/31

[1] 李志农,朱明,褚福磊,等.基于经验小波变换的机械故障诊断方法研究[J].仪器仪表学报,2014,35(11):2423-2432.
LI Zhinong,ZHU Ming,CHU Fulei, et al. Research on mechanical fault diagnosis method based on empirical wavelet transform[J]. Journal of Instruments and Instruments,2014,35(11):2423-2432.
[2] 刘长良,武英杰,甄成刚.基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断[J].中国电机工程学报,2015,35(13):3358-3365.
LIU Changliang, WU Yingjie,ZHEN Chenggang, Fault diagnosis of rolling bearing based on variational mode decomposition and fuzzy C-means clustering[J]. Chinese Journal of Electrical Engineering,2015,35(13):3358-3365.
[3] 李万清.基于朴素贝叶斯方法和权值分析方法的电机轴承故障诊断[J].机电工程,2012,29(04):390-393.
LI Wanqing. Fault diagnosis of motor bearings based on naive Bayes method and weight analysis method[J]. Mechanical and Electrical Engineering, 2012,29(04):390-393
[4] 付大鹏, 翟勇, 于青民. 基于EMD和支持向量机的滚动轴承故障诊断研究[J]. 机床与液压, 2017, 45(11): 184-187.
FU Dapeng, ZHAI Yong, YU Qingmin. Research on rolling bearing fault diagnosis based on EMD and support vector machine[J]. Machine Tool and Hydraulic Pressure,2017,45(11):184-187.
[5] 周将坤,陆森林.基于EMD平均能量法的滚动轴承故障诊断[J].轻工机械,2010,28(02):36-40.
ZHOU Jiangkun, LU Senlin. Fault diagnosis of rolling bearing based on EMD mean energy method[J]. Light Industrial Machinery,2010,28(02):36-40.
[6] 赵春华, 汪成康, 华露, 等. 基于融合特征约减和支持向量机的控制图模式识别[J]. 中国机械工程, 2017. 28(8): 930-935.
ZHAO Chunhua, WANG Chengkang, HUA Lu, et al. Pattern recognition of control diagram based on fusion feature reduction and support vector machine[J]. Chinese Journal of Mechanical Engineering,2017.28(8):930-935.
[7] BENGIO Y, GOODFELLOW J, Courville A.Deep Learning[J]. Nature,2015,521:436-444.
[8] LeCun Y, Bengio Y, Hinton G. Deep Learning[J]. Nature,2015,521(7553):436-444.
[9] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionalitu of data with neurl network[J]. Science,2006,313(5786)：504-507.
[10] 李巍华,单外平,曾雪琼.基于深度信念网络的轴承故障分类识别[J].振动工程学报,2016,29(02):340-347.
LI Weihua, SHAN Waiping, ZENG Xueqiong. Bearing fault classification and recognition based on deep belief network[J]. Journal of Vibration Engineering, 2016,29(02):340-347.
[11] 朱煜奇,黄双喜,杨天祺,等. 基于栈式降噪自编码的故障诊断[J].制造业自动化,2017,39(03):152-156.
ZHU Yuqi,HUANG Shuangxi,YANG Tianqi, et al. Fault diagnosis based on stack noise reduction self-coding[J]. Manufacturing Automation, 2017,39(03):152-156.
[12] 温江涛,闫常弘,孙洁娣,等.基于压缩采集与深度学习的轴承故障诊断方法[J].仪器仪表学报,2018,39(01):171-179.
WEN Jiangtao, YAN Changhong, SUN Jiedi, et al. Bearing Fault diagnosis method based on Compression acquisition and deep learning[J]. Journal of Instruments and Instruments, 2018,39(01):171-179.
[13] BENGIO Y, Learning deep architectures for AI[J], Foundations and Trends in Machine Learning,2009, 2(1):1-127.
[14] VINCENT P, LAROCHELLE H, BENGIO Y, et al. Extracting and composing robust features with denoising autoencoders[C]. International Conference on Machine Learning,2008：1096 – 1103.
[15] 雷亚国, 贾峰, 周昕, 等. 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,2015,51(21):49-56.
LEI Yaguo, JIA Feng, ZHOU Xin, et al. Health monitoring method of mechanical equipment big data based on deep learning theory[J]. Journal of Mechanical Engineering,2015,51(21):49-56.
[16] VINCENT P, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010,11(6): 3371-3408.
[17] BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks[C]. Advances in Neural Information Processing Systems , 2007:153-160.
[18] MIRJALIILI S, MIRJALILI S M, LEWIS A. The Whale optimization algorithm[J]. Advances in Engineering Software,2016,95(5):51-67.
[19] Bing Li, Peng-yuan Liu, Ren-xi Hu, et al. Fuzzy lattice classifier and its application to bearing fault diagnosis[J]. Applied Soft Computing Journal,2012,12(6): 1708-1719.