doi:

DOI: 10.3724/SP.J.1187.2009.07051

Journal of Electronic Measurement and Instrument (电子测量与仪器学报) 2009/23:7 PP.51-55

State monitoring approach based on improved principal component analysis


Abstract:
In order to meet the demands of multidimensional and mass data in traction motor state monitoring, a new kind of Principal Component Analysis (PCA) approach is proposed. This method, whose data preprocessing is improved, is an effective way which can not only reduce the dimension of motor index and eliminate correlation between process variables, but also reserve enough information of original data characteristics needed for modeling. Based on PCA model, a state monitoring experiment is carried out on a traction motor with SPE and T2 statistics. The experiment results validate that the approach can build an accurate monitoring model and detect abnormal state of motor effectively.

Key words:state monitoring,PCA,traction motor,data preprocessing

ReleaseDate:2014-07-21 14:53:39



[1] JIA L M, JIANG Q H. Study on essential characteristics of RITS[J]. IEEE ISADS’03, 2003: 216-221.

[2] BLOD M, GRANJON P, RAISON B, ROSTAING G. Models for bearing damage detection in induction mo-tors using stator current monitoring[J]. IEEE Transaction on Industrial Electronics, 2008, 55(4): 1813-1822.

[3] BENEDUCE L, LOVIENO S, MASUCCI A,et al. De-tection broken rotor bar in cage induction motor[J]. In-ternational Symposium on Power Electronics, Electrical Drives, Automation and Motion, 2006, S9-1–S9-5.

[4] 付华, 尹丽娜. 小波包分解在电机故障诊断中的应用[J]. 微电机, 2007, 40(5): 86-89. FU H, YIN L N. Application of wavelet packet decom-position in motor fault diagnosis[J]. Micro-motors, 2007, 40(5): 86-89.

[5] NIU ZH, NIU Y G. The application of PCA-based fault detection in the power plant process[J]. Shanghai: ISSST’2004, 2004.

[6] 王承, 陈光 , 谢永乐. 基于主元分析与神经网络的模拟电路故障诊断[J].电子测量与仪器学报, 2005, 19(5): 14- 17. WANG CH, CHEN G J, XIE Y L. Fault diagnosis in analog circuits based on principal component analysis and neural networks[J]. Journal of Electronic Measure-ment and Instrument, 2005, 19(5): 14-17.

[7] 张杰, 阳宪惠. 多变量统计控制过程[M]. 北京: 化学工业出版社, 2000. ZHANG J, YANG X H. Multivariate statistical process control[M]. Beijing: Chemical Industry Press, 2000.

[8] JACKSON J E, MUDHOLKAR G S. Control procedures for residuals associated with principal component analy-sis[J]. Technometrics, 21: 341-349, 1979.

[9] 纪荣芳. 主成分分析法中数据处理方法的改进[J]. 山东科技大学学报, 2007, 26(5): 95-98. JI R F. Improvement of data processing method in prin-cipal component analysis[J]. Journal of Shandong Uni-versity of Science and Technology, 2007, 26 (5): 95- 98.

PDF