JOURNAL ARTICLE

Rolling Bearing Fault Diagnosis Based on Supervised Laplaian Score and Principal Component Analysis

Ou Lu

Year: 2014 Journal:   Journal of Mechanical Engineering Vol: 50 (5)Pages: 88-88

Abstract

摘要: 在拉普拉斯分值(Laplaian score,LS)方法的基础上,提出一种监督拉普拉斯分值(Supervised laplaian score,SLS)特征选择方法。该方法同时考虑数据的标号信息和局部几何结构,避免LS方法中要设定近邻图参数的问题。将SLS和主元分析(Principal component analysis,PCA)相结合,提出基于SLS和PCA的滚动轴承故障诊断方法。该方法在时域和频域对滚动轴承振动信号进行特征提取,组成初始特征矢量;利用SLS进行特征选择,形成故障特征矢量;再对特征矩阵进行PCA降维处理,并用K近邻(K-nearest neighbor algorithm,KNN)分类算法实现滚动轴承不同故障类型的识别。应用实例表明,该方法能有效提取滚动轴承振动信号特征,诊断滚动轴承故障,且故障分辨率优于基于LS和PCA的故障诊断方法。

Keywords:
Principal component analysis Bearing (navigation) Component (thermodynamics) Fault (geology) Artificial intelligence Pattern recognition (psychology) Computer science Component analysis Statistics Mathematics Geology Seismology Physics

Metrics

14
Cited By
0.00
FWCI (Field Weighted Citation Impact)
0
Refs
0.47
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Gear and Bearing Dynamics Analysis
Physical Sciences →  Engineering →  Mechanical Engineering
Machine Fault Diagnosis Techniques
Physical Sciences →  Engineering →  Control and Systems Engineering
Advanced Measurement and Detection Methods
Physical Sciences →  Engineering →  Electrical and Electronic Engineering
© 2026 ScienceGate Book Chapters — All rights reserved.