ROLLING BEARING FAULT DIAGNOSIS BASED ON ADAPTIVE FEATURE SELECTION <italic style="font-style: italic">k</italic>-SUB CONVEX HULL

HU AiRu; WU ZhanTao; YANG Yu; CHENG JunSheng

doi:10.16579/j.issn.1001.9669.2024.02.001

您当前的位置：

首页 >

文章列表页 >

ROLLING BEARING FAULT DIAGNOSIS BASED ON ADAPTIVE FEATURE SELECTION k-SUB CONVEX HULL

更新时间：2024-07-05

- ROLLING BEARING FAULT DIAGNOSIS BASED ON ADAPTIVE FEATURE SELECTION k-SUB CONVEX HULL
- Journal of Mechanical Strength Vol. 46, Issue 2, Pages: 255-263(2024)
- 作者机构：
  
  1. 湖南大学机械与运载工程学院
  2. 湖南大学装备服役质量保障湖南省重点实验室
- 作者简介：
- 基金信息：
  
  The project supported by National Key Research and Development Program of China(No. 2020YFB2009602), the National Natural Science Foundation of China (No. 51875183,51975193), and the Scientific Research Project of Hunan Provincial Education Department (No. 21A0017).
- DOI：10.16579/j.issn.1001.9669.2024.02.001
  CLC： TH165.3
- Published：15 April 2024，
- 稿件说明：
移动端阅览
HU AiRu, WU ZhanTao, YANG Yu, et al. ROLLING BEARING FAULT DIAGNOSIS BASED ON ADAPTIVE FEATURE SELECTION k-SUB CONVEX HULL. [J]. Journal of Mechanical Strength , 2024,46(2):255-263.
DOI：

HU AiRu, WU ZhanTao, YANG Yu, et al. ROLLING BEARING FAULT DIAGNOSIS BASED ON ADAPTIVE FEATURE SELECTION k-SUB CONVEX HULL. [J]. Journal of Mechanical Strength , 2024,46(2):255-263. DOI： 10.16579/j.issn.1001.9669.2024.02.001.

摘要

滚动轴承故障诊断中往往将特征选择和分类器的设计分别进行研究，从而难以获得满意的分类精度。将特征选择和分类器寻优结合起来，提出了一种自适应特征选择

子凸包（Adaptive Feature Selection

-sub Convex Hull，AFSKCH）的分类模型，从而实现了故障特征自适应选择和分类的一体化。首先，利用凸包距离函数保持数据流形上的局部邻域结构，通过交替构造

子凸包得到特征权值矩阵；其次，采用线性规划接近度方法求解

子凸包距离，利用乘子交替方向法得到自适应特征空间；最后，根据测试点到

子凸包的最小重构距离进行分类。滚动轴承故障振动信号分析结果表明，该方法特征选择性能优于其他特征选择方法，且具有较高的分类精度。

Abstract

Feature selection and classifier design are often studied separately in rolling bearing fault diagnosis

so it is difficult to obtain satisfactory classification accuracy. An adaptive feature selection

-sub convex hull (AFSKCH) classificationmodel was proposed by combining feature selection and classifier optimization

which realized the integration of adaptive featureselection and classification. Firstly

the convex hull distance function was used to maintain the local neighborhood structure on the data manifold

and the feature weigh

t matrix was obtained by alternately constructing

-sub convex hulls. Secondly

thedistance was solved by the method of linear programming proximity

and the adaptive feature space was obtained by using the multiplier alternating direction method. Finally

the classification was carried out according to the minimum reconstruction distance from the test point to the

-sub convex hull. The analysis results of rolling bearing fault vibration signals show that the feature selection performance of this method is better than other feature selection methods

and the classification accuracy is higher.

关键词

自适应特征选择邻域嵌入k子凸包滚动轴承故障诊断

Keywords

references

Views

221

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

RESEARCH ON ROLLING BEARING FAULT DIAGNOSIS BASED ON IMPROVED HHO-LSTM

FAULT FEATURE EXTRACTION METHOD FOR ROLLER BEARINGS BASED ON LCD AND LOCAL HILBERT MARGINAL ENERGY SPECTRUM

REVIEW AND PROSPEСT OF ROLLING BEARINGSLIPPAGE RESEARCH

FAULT DIAGNOSIS METHOD OF ROLLING BEARING BASED ON ICEEMD-FastICA

基于SAVMD与CNN结合的轴承故障诊断方法

Related Author

ZHU SiJia

SHAO LiangShan

LI DongWen

ZENG Ming

YANG Pan

WANG Hao

WANG JiaMing

LUO Ya

Related Institution

System Engineering Institute,Liaoning Technical University

School of Business Administration,Liaoning Technical University

State Key Laboratory of Advanced Design and Manufacture for Vehicle Body,College of Mechanical and Vehicle Engineering,Hunan University

湖南大学汽车车身先进设计制造国家重点实验室

School of Mechatronic and Vehicle Engineering, East China Jiaotong University

⁰

ROLLING BEARING FAULT DIAGNOSIS BASED ON ADAPTIVE FEATURE SELECTION k-SUB CONVEX HULL

DOI：10.16579/j.issn.1001.9669.2024.02.001

摘要

Abstract

关键词

Keywords

references