Fault Diagnosis of Bearing based on Local Characteristic-scale Decomposition and Base-scale Entropy

Zhu Liangming; Cui Weicheng

doi:10.16578/j.issn.1004.2539.2017.09.037

您当前的位置：

首页 >

文章列表页 >

Fault Diagnosis of Bearing based on Local Characteristic-scale Decomposition and Base-scale Entropy

更新时间：2022-10-20

- Fault Diagnosis of Bearing based on Local Characteristic-scale Decomposition and Base-scale Entropy
- Vol. 41, Issue 9, Pages: 183-188(2017)
- 作者机构：
  
  1. 海军航空工程学院
- 作者简介：
- 基金信息：
- DOI：10.16578/j.issn.1004.2539.2017.09.037
  CLC：
扫描看全文
[1]朱良明,崔伟成.基于局部特征尺度分解与基本尺度熵的轴承故障诊断[J].机械传动,2017,41(09):183-188.

Zhu Liangming, Cui Weicheng. Fault Diagnosis of Bearing based on Local Characteristic-scale Decomposition and Base-scale Entropy. [J]. 41(9):183-188(2017)
[1]朱良明,崔伟成.基于局部特征尺度分解与基本尺度熵的轴承故障诊断[J].机械传动,2017,41(09):183-188. DOI： 10.16578/j.issn.1004.2539.2017.09.037.

Zhu Liangming, Cui Weicheng. Fault Diagnosis of Bearing based on Local Characteristic-scale Decomposition and Base-scale Entropy. [J]. 41(9):183-188(2017) DOI： 10.16578/j.issn.1004.2539.2017.09.037.

摘要

为了准确进行轴承故障诊断,提出了基于局部特征尺度分解与基本尺度熵的故障特征提取及诊断方法。首先,分析了基本尺度熵提取轴承振动信号蕴涵的故障信息的合理性,针对基本尺度熵的参数选择问题,提出了基于相空间重构理论的延迟时间和嵌入维数选择方法;然后,运用局部特征尺度分解对基本尺度熵进行自适应多尺度化,充分提取了故障特征;最后,将原始信号的降噪数据及有用分量的基本尺度熵作为特征向量,通过支持向量机进行故障诊断。以轴承振动试验信号为例进行了验证,结果表明,所提方法能有效识别正常、内圈故障、外圈故障及滚动体故障等4种状态。

Abstract

Aiming at diagnosing the fault of roller bearing accurately,a method based on Local Characteristic-scale Decomposition（ LCD） and Base-scale Entropy（ BE） is proposed. Firstly,the rationality of using the BE to extract the fault information of the bearing vibration signal is analyzed,according to the parameter selection problem of BE,a method based on phase space reconstruction theory is proposed,and the delay time and embedding dimension are selected. Secondly,in order to extract the fault feature fully,a kind of adaptive multi-scale BE based on LCD is proposed. Finally,the denoising signal and the useful components of LCD are selected to compute the BEs as the feature vector of support vector machine（ SVM） to fault diagnosis. The analysis of the bearing fault data shows that the method can identify the normal,inner ring fault,outer ring fault and rolling fault effectively.

关键词

局部特征尺度分解基本尺度熵相空间重构多尺度支持向量机

Keywords

Local characteristic-scale decompositionBase-scale entropyPhase space reconstructionMulti-scaleSupport vector machine

references

Views

115

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Bearing Fault Diagnosis based on Singular Value Decomposition Denoising and Local Characteristic-scale Decomposition

Fault Diagnosis of Fan Bearings Based on an Improved Grey Wolf Optimization Algorithm and SVM

Fault Diagnosis of Gearboxes Based on AO-VMD and IAO-SVM

Gearbox Fault Diagnosis Based on Dynamic Weighted Feature Fusion with Maximum Information Coefficient

Gearbox Fault Diagnosis Based on ALIF-PE-GOLSSVM

Related Author

No data

Related Institution

Department of Aircraft Engineering,Naval Aeronautical and Astronautical University

School of Electrical Engineering, Xinjiang University

Zhengzhou Research Institute of Mechanical Engineering Co., Ltd.

School of Mechanical and Electrical Engineering, Henan University of Technology

Department of Mechanical Engineering, Guangzhou Maritime University

⁰