FAULT DIAGNOSIS METHOD OF ROLLING BEARINGS BASED ON ELMD AND KERNEL DENSITY ESTIMATION

WU HaiYan; HAI Jie; YUAN Hao

doi:10.16579/j.issn.1001.9669.2017.02.004

您当前的位置：

首页 >

文章列表页 >

FAULT DIAGNOSIS METHOD OF ROLLING BEARINGS BASED ON ELMD AND KERNEL DENSITY ESTIMATION

更新时间：2022-09-22

- FAULT DIAGNOSIS METHOD OF ROLLING BEARINGS BASED ON ELMD AND KERNEL DENSITY ESTIMATION
- Journal of Mechanical Strength Vol. 39, Issue 2, Pages: 261-266(2017)
- 作者机构：
  
  1. 郑州大学西亚斯国际学院
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2017.02.004
  CLC：
扫描看全文
WU HaiYan, HAI Jie, YUAN Hao. FAULT DIAGNOSIS METHOD OF ROLLING BEARINGS BASED ON ELMD AND KERNEL DENSITY ESTIMATION. [J]. 39(2):261-266(2017)
DOI：

WU HaiYan, HAI Jie, YUAN Hao. FAULT DIAGNOSIS METHOD OF ROLLING BEARINGS BASED ON ELMD AND KERNEL DENSITY ESTIMATION. [J]. 39(2):261-266(2017) DOI： 10.16579/j.issn.1001.9669.2017.02.004.

摘要

针对滚动轴承非平稳性的振动信号,提出了基于总体局域均值分解(Ensemble Local Mean Decomposition,ELMD)及核密度估计的滚动轴承故障诊断方法。首先,对振动信号进行ELMD分解,获得一系列乘积函数(Production Function,PF),计算包含主要故障的PF分量的有效值、峭度、偏度系数,将其组合成特征向量;根据核密度估计的特性提出基于核密度估计的分类器,将特征向量输入分类器进行训练与测试,从而识别滚动轴承的工作状态和故障类型。实验结果表明,该方法能够有效的对滚动轴承故障进行识别,且效果较LMD方法好。

Abstract

Aiming at the no stationary characteristic of a gear fault vibration signal,a method based on Ensemble local mean decomposition and Kernel density estimation is proposed in this paper. First,the vibration signal is decomposed to be a series PF component by ELMD,calculating RMS、kurtosis、skewness coefficient of PF components,which contains main fault information,then they are combined into a feature vector,the Classification based on kernel density estimation is proposed,multiple sets of vibration signal feature vectors are used to train and test,identify their fault condition. The results showed that this method can effectively identify the fault of rolling bearing,and it is better than the LMD method

关键词

滚动轴承ELMD核密度估计故障诊断

Keywords

Rolling bearingELMDKernel density estimationFault diagnosis

references

Views

148

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

ROLLING BEARING FAULT DIAGNOSIS BASED ON FUSION CNN AND PSO-SVM

ROTATING MACHINERY FAULT DIAGNOSIS BASED ON TWO-DIMENSIONAL CONVOLUTION NEURAL NETWORK

APPLICATION OF COMPRESSIVE SENSING AND IMPROVED DEEP WAVELET NEURAL NETWORK IN BEARING FAULT DIAGNOSIS

DYNAMIC MODELING AND SIMULATION OF ROLLING BEARING WITH PITTING FAILURE

ROLLING BEARING FAULT FEATURE EXTRACTION RESEARCH BASED ON IMPROVED CEEMDAN AND RECONSTRUCTION

Related Author

No data

Related Institution

College of Engineering Science and Technology,Shanghai Ocean University

Mechanical and Automotive Engineering,Qingdao University of Technological

School of Mechanical-electronic and Automobile Engineering,Beijing University of Civil Engineering and Architecture

Beijing Engineering Research Center of Monitoring for Construction Safety

Xinxiang Vocational and Technical College

⁰