基于深度信念网络的轴承故障分类识别

被引：303

作者：

李巍华 ^{[1
,2
]}

单外平 ^{[1
]}

曾雪琼 ^{[1
]}

机构：

[1] 华南理工大学机械与汽车工程学院

[2] 机械制造系统工程国家重点实验室

来源：

振动工程学报 | 2016年 / 29卷 / 02期

基金：

中央高校基本科研业务费专项资金资助;

关键词：

故障诊断; 特征提取; 受限玻尔兹曼机; DBN; 故障分类;

D O I：

10.16385/j.cnki.issn.1004-4523.2016.02.020

中图分类号：

TH133.3 [轴承];

学科分类号：

082805 [农业机械化与装备工程];

摘要：

特征提取是故障智能诊断的关键步骤,然而不同的特征提取方法所得到的特征不同,导致诊断结果也可能有所差异,增加了人工特征选择的难度和不确定性。深度信念网络(Deep Belief Network,DBN)是一种典型的深度学习(Deep Learning)方法,可以通过组合低层特征形成更加抽象的高层表示,发现数据的分布式特征。DBN可直接从低层原始信号出发,通过逐层智能学习得到更好的特征表示,避免特征提取与选择的人工操作,增强识别过程的智能性。将DBN直接应用于轴承振动原始信号的处理,实现轴承故障的分类识别。试验结果表明,DBN可以直接通过原始数据对轴承故障进行分类识别,优先调节时间复杂度偏导数较大的参数,可有效控制DBN的计算成本。

引用

页码：340 / 347

页数：8

共 15 条

[1]

Failure diagnosis using deep belief learning based health state classification.[J].Prasanna Tamilselvan;Pingfeng Wang.Reliability Engineering and System Safety.2013,

[2]

An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks [J].

Van Tung Tran ;

AlThobiani, Faisal ;

Ball, Andrew .

EXPERT SYSTEMS WITH APPLICATIONS, 2014, 41 (09) :4113-4122

[3]

Fuzzy lattice classifier and its application to bearing fault diagnosis [J].

Li, Bing ;

Liu, Peng-yuan ;

Hu, Ren-xi ;

Mi, Shuang-shan ;

Fu, Jian-ping .

APPLIED SOFT COMPUTING, 2012, 12 (06) :1708-1719

[4]

Fault diagnosis of sensor by chaos particle swarm optimization algorithm and support vector machine [J].

Zhao Chenglin ;

Sun Xuebin ;

Sun Songlin ;

Jiang Ting .

EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (08) :9908-9912

[5]

A novel intelligent gear fault diagnosis model based on EMD and multi-class TSVM.[J].Zhongjie Shen;Xuefeng Chen;Xiaoli Zhang;Zhengjia He.Measurement.2011, 1

[6]

Feature extraction for rolling element bearing fault diagnosis utilizing generalized S transform and two-dimensional non-negative matrix factorization.[J].Bing Li;Pei-lin Zhang;Dong-sheng Liu;Shuang-shan Mi;Guo-quan Ren;Hao Tian.Journal of Sound and Vibration.2010, 10

[7]

Wavelet support vector machine for induction machine fault diagnosis based on transient current signal.[J].Achmad Widodo;Bo-Suk Yang.Expert Systems With Applications.2007, 1

[8]

Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling: A method for bearing prognostics.[J].Hasan Ocak;Kenneth A. Loparo;Fred M. Discenzo.Journal of Sound and Vibration.2007, 4

[9]

To recognize shapes; first learn to generate images.[J].Geoffrey E. Hinton.Progress in Brain Research.2007,

[10]

A fast learning algorithm for deep belief nets [J].

Hinton, Geoffrey E. ;

Osindero, Simon ;

Teh, Yee-Whye .

NEURAL COMPUTATION, 2006, 18 (07) :1527-1554

← 1 2 →