一种新型深度自编码网络的滚动轴承健康评估方法

被引：50

作者：

佘道明

贾民平

张菀

机构：

[1] 东南大学机械工程学院

来源：

东南大学学报(自然科学版) | 2018年 / 48卷 / 05期

关键词：

深度自编码; 健康指标; 最小量化误差; 融合评价准则;

D O I：

暂无

中图分类号：

TH133.33 [滚动轴承];

学科分类号：

082805 [农业机械化与装备工程];

摘要：

为了准确描述滚动轴承性能退化的动态过程,结合深度学习强大特征提取能力的优势,提出了一种新型深度自编码和最小量化误差方法相结合的滚动轴承全寿命健康评估方法.用深度自编码模型对原始特征进行压缩提取,将压缩特征按趋势进行排序,选取趋势大的特征运用最小量化误差方法构建健康指标.针对基于一个度量的评价准则常具有偏差的问题,提出基于遗传算法的融合评价准则. 2组实例分析结果表明,用该方法构建的健康指标的趋势值、单调性值、鲁棒性值、融合评价准则值都大于单层的自编码模型(AE)和传统的PCA降维方法,第1个实例中,该方法构建的健康指标融合评价准则值比PCA,AE方法分别增加了13. 30%,3. 17%;第2个实例中,该方法构建的健康指标融合评价准则值比PCA,AE方法分别增加了9. 68%,3. 85%.基于遗传算法的融合评价准则比单一的评价准则更具有说服力.

引用

页码：801 / 806

页数：6

共 10 条

[1]

Machinery health prognostics: A systematic review from data acquisition to RUL prediction.[J].Yaguo Lei;Naipeng Li;Liang Guo;Ningbo Li;Tao Yan;Jing Lin.Mechanical Systems and Signal Processing.2018,

[2]

Degradation Feature Selection for Remaining Useful Life Prediction of Rolling Element Bearings [J].

Zhang, Bin ;

Zhang, Lijun ;

Xu, Jinwu .

QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 2016, 32 (02) :547-554

[3]

Enhanced Restricted Boltzmann Machine With Prognosability Regularization for Prognostics and Health Assessment [J].

Liao, Linxia ;

Jin, Wenjing ;

Pavel, Radu .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2016, 63 (11) :7076-7083

[4]

Bearing fault prognostics using Rényi entropy based features and Gaussian process models.[J].Pavle Boškoski;Matej Gašperin;Dejan Petelin;Đani Juričić.Mechanical Systems and Signal Processing.2015,

[5]

Prognostics of slurry pumps based on a moving-average wear degradation index and a general sequential Monte Carlo method.[J].Dong Wang;Peter W. Tse.Mechanical Systems and Signal Processing.2015,

[6]

Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method.[J].Sheng Hong;Zheng Zhou;Enrico Zio;Kan Hong.Digital Signal Processing.2014,

[7]

Bearing performance degradation assessment using locality preserving projections.[J].Jian-Bo Yu.Expert Systems With Applications.2010, 6

[8]

Application of relevance vector machine and survival probability to machine degradation assessment.[J].Achmad Widodo;Bo-Suk Yang.Expert Systems With Applications.2010, 3

[9]

Using Minimum Quantization Error chart for the monitoring of process states in multivariate manufacturing processes [J].

Yu, Jian-Bo ;

Wang, Shijin .

COMPUTERS & INDUSTRIAL ENGINEERING, 2009, 57 (04) :1300-1312

[10]

Robust performance degradation assessment methods for enhanced rolling element bearing prognostics [J].

Qiu, H ;

Lee, J ;

Lin, J ;

Yu, G .

ADVANCED ENGINEERING INFORMATICS, 2003, 17 (3-4) :127-140

← 1 →