基于敏感特征选择与流形学习维数约简的故障诊断

苏祖强;汤宝平;姚金宝

振动与冲击 ›› 2014, Vol. 33 ›› Issue (3) : 70-75.

PDF(1487 KB)
PDF(1487 KB)
振动与冲击 ›› 2014, Vol. 33 ›› Issue (3) : 70-75.
论文

基于敏感特征选择与流形学习维数约简的故障诊断

  • 苏祖强,汤宝平,姚金宝

作者信息 +

Fault Diagnosis method based on Sensitive Feature Selection and Manifold learning Dimension reduction

  • Su Zuqiang, Tang Baoping, Yao Jinbao

Author information +
文章历史 +

摘要

针对故障诊断中特征集包含非敏感特征和维数过高的问题,提出基于特征选择(Feature selection, FS)与流形学习维数约简的故障诊断方法。提出了一种改进的核空间距离测度特征选择方法(Improved kernel distance measurement feature selection, IKMD-FS),在核空间中计算样本类间距离和类内散度,优选出使样本类间距大、类内散度小的特征,并根据特征的敏感程度对特征进行加权。通过线性局部切空间排列算法(Linear local tangent space alignment, LLTSA)对由敏感特征组成的特征子集进行特征融合,提取出对故障分类更加敏感的融合特征,并输入加权k最近邻分类器(Weighted k nearest neighbor classifier, WKNNC)进行故障识别。WKNNC具有比k最近邻分类器(k nearest neighbor classifier, KNNC)更加稳定的识别精度。最后,通过滚动轴承故障模拟实验验证了本文方法的有效性。

Abstract

Fault diagnosis method based on feature selection (FS) and linear local tangent space alignment (LLTSA) is proposed, aiming to solve the problem of non-sensitive features and the high dimension of the feature set. An improved kernel distance measurement feature selection method (IKMD-FS) is proposed, which considers both the distance between classes and the dispersion within class, and the selected sensitive features are weighted by their sensitive-values. The weighted sensitive feature subset is compressed through LLTSA to reduce dimension and get the compressed more sensitive feature subset. Then, the feature subset is fed into weighted k nearest neighbor classifier (WKNNC), whose recognition accuracy is more stable compared with k nearest neighbor classification (KNNC), to recognize the fault type. At last, the validity of the proposed method is verified by the instance of the fault diagnosis of a rolling bearing.



关键词

故障诊断 / 特征选择 / 改进的核空间距离测度 / 线性局部切空间排列 / 加权k最近邻分类器

Key words

fault diagnosis / feature selection / improved kernel distance measurement / linear local tangent space alignment / weighted k nearest neighbor classifier

引用本文

导出引用
苏祖强;汤宝平;姚金宝. 基于敏感特征选择与流形学习维数约简的故障诊断[J]. 振动与冲击, 2014, 33(3): 70-75
Su Zuqiang;Tang Baoping;Yao Jinbao. Fault Diagnosis method based on Sensitive Feature Selection and Manifold learning Dimension reduction [J]. Journal of Vibration and Shock, 2014, 33(3): 70-75

PDF(1487 KB)

Accesses

Citation

Detail

段落导航
相关文章

/