基于独立特征选择与流形学习的故障诊断

PDF(1287 KB)

振动与冲击 ›› 2018, Vol. 37 ›› Issue (16) : 77-83.

论文

基于独立特征选择与流形学习的故障诊断

杜伟，房立清，齐子元

作者信息 +

Fault diagnosis based on individual feature selection and manifold learning

DU Wei，FANG Liqing，QI Ziyuan

Author information +

文章历史 +

摘要

为了有效利用特征集所包含的敏感特征进行故障诊断，提出基于独立特征选择（Individual feature selection，IFS）与流形学习的故障诊断方法。首先，从多个角度提取振动信号的混合特征，构建原始高维特征集。然后，采用一种改进的核Fisher特征选择方法为每两类故障状态独立选择敏感特征集，并通过线性局部切空间排列（Linear local tangent space alignment，LLTSA）算法挖掘出可区分度更高的特征子集。最后，采用“一对一”的方法训练多个二类分类支持向量机（SVM），将得到的低维特征输入多分类故障诊断模型进行识别。液压泵故障诊断实验表明，所提方法具备较高的诊断准确率。

Abstract

In order to diagnose fault effectively by using sensitive features contained in a feature set, a fault diagnosis method based on individual feature selection (IFS) and manifold learning was proposed.Firstly, the mixed feature of the vibration signal was extracted from multiple domains, and the original high-dimensional feature set was constructed.Then, an improved kernel Fisher feature selection method was proposed and used to select individual sensitive feature subset for each pair of classes, and the mining performance of the feature subset with higher distinguishability was further implemented by using Linear local tangent space alignment (LLTSA).Finally, a one-against-one approach was applied to train several SVM binary classifiers, and low-dimensional feature was input into the multi-class fault diagnosis model for recognizing the fault types.The experimental results of hydraulic pump indicate that the proposed method is of high diagnostic accuracy.


导出引用

杜伟，房立清，齐子元. 基于独立特征选择与流形学习的故障诊断[J]. 振动与冲击, 2018, 37(16): 77-83

DU Wei，FANG Liqing，QI Ziyuan. Fault diagnosis based on individual feature selection and manifold learning[J]. Journal of Vibration and Shock, 2018, 37(16): 77-83

参考文献

[1] Tenenbaum J B, Silva V, Langford J C. A global geometric framework for nonlinear dimensionality reduction [J]. Science, 2000, 290(5500)：2319-2323.
[2] 陈鹏飞，赵荣珍，彭斌，等. 等距映射和局部线性嵌入算法集成的转子故障数据降维方法 [J]. 振动与冲击, 2017, 36(6): 45-50.
CHENG Peng-fei, ZHAO Rong-zhen, PENG Bin, et al．Method for the dimension reduction of rotor fault data sets by using ISOMAP and LLE [J]. Journal of Vibration and Shock, 2017, 36(6): 45-50.
[3] 张前图，房立清. 基于图像形状特征和LLTSA的故障诊断方法 [J]. 振动与冲击, 2016, 35(9): 172-177.
ZHANG Qian-tu, FANG Li-qing. Fault diagnosis method based on image shape features and LLTSA [J]. Journal of Vibration and Shock, 2016, 35(9): 172-177.
[4] ZHAI L D，DING Z Y，JIA Y，et al． A word position-related LDA model [J]. International Journal of Pattern Recognition and Artificial Intelligence, 2011, 25(6)：909-925.
[5] MIKA Sebastian. Fisher Discriminant Analysis With Kernels [J]. Neural Networks for Signal Processing, 1999, 9：41-48.
[6] Wang Lei. Feature Selection with Kernel Class Separability [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(9)：1534-1546.
[7] 王广斌，刘义伦，黄良沛. 基于核schur正交局部Fisher判别的转子故障诊断 [J]. 仪器仪表学报, 2010, 31(5)：1005-1009.
WANG Guang-bin, LIU Yi-lun, HUANG Liang-pei. Rotor fault diagnosis based on kernel schur-orthogonal local Fisher discriminant [J]. Chinese Journal of Scientific Instrument, 2010, 31(5)：1005-1009.
[8] 周勇，何创新. 基于独立特征选择与相关向量机的变载荷轴承故障诊断 [J]. 振动与冲击, 2012, 31(3)：157-161.
ZHOU Yong, HE Chuang-xin. Bearing fault diagnosis under varying load condition based on individual feature selection and relevance vector machine [J]. Journal of Vibration and Shock, 2012, 31(3)：157-161.
[9] Ye LV, Hui-zhong YANG. A Multi-model Approach for Soft Sensor Development Based on Feature Extraction Using Weighted Kernel Fisher Criterion [J].Chinese Journal of Chemical Engineering, 2014, 22(2)：146-152.
[10] 杨宇，何知义，潘海洋，等. 基于LCD-Hilbert谱奇异值和QRVPMCD的滚动轴承故障诊断方法 [J]. 振动与冲击, 2015, 34(7): 121-126.
YANG Yu, HE Zhi-yi, PAN Hai-yang, et al. Rolling bearing fault diagnosis method based on Hilbert spectrum singular values and QRVPMCD [J]. Journal of Vibration and Shock, 2015, 34(7): 121-126.
[11] Chaudhuri A, De K, Chatterjee D. A Comparative Study of Kernels for the Multi-class Support Vector Machine [C]// International Conference on Natural Computation, IEEE, 2008, 2:3-7.
[12] Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines [J]. IEEE Transactions on Neural Networks, 2002, 13(4):1026.
[13] JOHN S T，NELLO C． Kernel methods for pattern analysis [M]． London: Cambridge University Press，2004: 54－132．
[14] 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 Zu-qiang, Tang Bao-ping, YAO Jin-bao. Fault diagnosis method based on sensitive feature selection and manifold learning dimension reduction [J]. Journal of Vibration and Shock, 2014, 33(3)：70-75.
[15] 李锋，汤宝平，陈法法. 基于线性局部切空间排列维数化简的故障诊断[J]. 振动与冲击, 2012,31(13):36-40.
LI Feng, TANG Bao-ping, CHEN Fa-fa. Fault diagnosis model based on dimension reduction using linear local tangent space alignment [J]. Journal of Vibration and Shock, 2012,31(13):36-40.
[16] 姚全珠，蔡婕. 基于PSO的LS-SVM特征选择与参数优化算法 [J]. 计算机工程与应用, 2010, 46(1):134-136.
YAO Quan-zhu, CAI Jie. Feature selection and LS-SVM parameters optimization algorithm based on PSO [J]. Computer Engineering and Applications, 2010, 46(1):134-136.