摘要
为了有效利用故障特征集中对故障敏感的特征进行故障诊断,对核Fishier判别分析(KFDA)进行改进,提出基于改进KFDA独立特征选择的故障诊断方法。该方法首先从多个角度提取故障振动信号的故障特征,构建原始高维多域混合故障特征集。然后,采用改进的核Fisher特征选择方法为每两类故障状态独立选择敏感特征集。最后,采用"一对一"的方法训练多个二分类相关向量机(RVM),将得到的敏感特征集输入多分类故障诊断模型进行识别。齿轮故障诊断实例表明,所提方法具备较高的诊断准确率。
In order to diagnose fault effectively by using sensitive features contained in the feature set, KFDA was improved in this paper and a fault diagnosis method based on improved KFDA individual feature selection was proposed. Firstly, the mixed feature of the fault vibration signal was extracted from different angels, and the original high-dimensional and multi-domain 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 class. Finally, a one-against-one approach was applied to train several relevance vector machine(RVM) binary classifiers, and sensitive feature was input into the multi-class fault diagnosis model for recognizing the fault types. The experimental results of gear indicate that the proposed method is of high diagnostic accuracy.
引文
[1] 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 (In Chinese).
[2] 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 BaoPing,CHEN FaFa.Fault diagnosis model based on dimension reduction using linear local tangent space alignment [J].Journal of Vibration and Shock,2012,31(13):36-40 (In Chinese).
[3] 李峰,王家序,杨荣松.有监督不相关正交局部保持映射故障辨识[J].仪器仪表学报,2013,34(5):1113-1120.LI Feng,WANG JiaXu,YANG RongSong.Fault identification method based on supervised uncorrelated orthogonal locality preserving projection[J].Chinese Journal of Scientific Instrument,2013,34(5):1113-1120 (In Chinese).
[4] ZHAI L D,DING Z Y,JIA Y,et al.A word positionrelated 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 GuangBin,LIU YiLun,HUANG LiangPei.Rotor fault diagnosis based on kernel schurorthogonal local Fisher discriminant [J].Chinese Journal of Scientific Instrument,2010,31(5):1005-1009 (In Chinese).
[8] Ye LV,Huizhong YANG.A Multimodel 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.
[9] 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 ChuangXin.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 (In Chinese).
[10] Hsu C W,Lin C J.A comparison of methods for multiclass support vector machines [J].IEEE Transactions on Neural Networks,2002,13(4):10-26.
[11] 张良,张前图.基于LCD模糊熵和流行学习的故障特征提取方法[J].机械强度,2016,38(2):225-230ZHANG Liang,ZHANG QianTu.Fault feature extraction method based on LCD fuzzy entropy and manifold learning[J].Journal of Mechanical Strength,2016,38(2):225-230 (In Chinese).