Infrared Spectroscopy Analysis of SF6 Using Multiscale Weighted Principal Component Analysis
PENG Xi1, WANG Xian-pei1, HUANG Yun-guang2
1. Laboratory of System Integrated and Fault Diagnosis, Wuhan University, Wuhan 430079, China 2. Guangxi Research Institute of Electric Power, Nanning 530023, China
Abstract:Infrared spectroscopy analysis of SF6 and its derivative is an important method for operating state assessment and fault diagnosis of the gas insulated switchgear (GIS). Traditional methods are complicated and inefficient, and the results can vary with different subjects. In the present work, the feature extraction methods in machine learning are recommended to solve such diagnosis problem, and a multiscale weighted principal component analysis method is proposed. The proposed method combines the advantage of standard principal component analysis and multiscale decomposition to maximize the feature information in different scales, and modifies the importance of the eigenvectors in classification. The classification performance of the proposed method was demonstrated to be 3 to 4 times better than that of the standard PCA for the infrared spectra of SF6 and its derivative provided by Guangxi Research Institute of Electric Power.
Key words:Infrared spectroscopy;Sulfur-hexafluoride;Gas insulated switchgear;Multiscale weighted principal component analysis
[1] Zhou Q, Tang J, Tang M, et al. IEEE Transactions on Dielectrics and Electrical Insulation, 2007, 14: 30. [2] Chang C, Chang C S, Jin J, et al. IEEE Transactions on Dielectrics and Electrical Insulation, 2005, 12: 374. [3] Beyer C, Jenett H, Klockow D. IEEE Transactions on Dielectrics and Electrical Insulation, 2000, 7: 234. [4] Youshi M, Robin-Jouan Ph, Kanzari Z. IEEE Transactions on Dielectrics and Electrical Insulation, 2005, 12: 1193. [5] Derdouri A, Casanovas J, Hergli R J. Appl. Phys., 1989, 65: 1852. [6] Soppart O, Pilzecker P, Baumbach J I. IEEE Transactions on Dielectrics and Electrical Insulation, 2000, 7: 229. [7] Braun J M, Chu F Y. IEEE Transactions on Power Delivery, 1986, 1: 81. [8] Kurte R, Beyer C, Heise H M. Anal. Bioanal. Chem., 2002, 373. [9] Kirby M, Sirovich L. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(1): 103. [10] Turk M, Pentland A. J. Cognitive Neuroscience, 1991, 13(1): 71. [11] Belhumeur P N, Hespanha J P, Kriegman D J. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(5): 711. [12] Martnez A M, Kak A C. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2): 228-233. [13] Bartlett M S, Movellan J R, and Sejnowski T J. IEEE Transactions on Neural Networks, 2002, 13(6): 1450. [14] Yuen P C, Lai J H. Pattern Recognition, 2002, 35(6): 1247. [15] Yang M H. Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition, 2002. 215. [16] Rellier G, Descombes X, Falzon F, et al. IEEE Transactions on Geoscience and Remote Sensing, 2004, 42(7): 1543. [17] Mallat S G. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674. [18] Bhavik R B. AIChE Journal, 1998, 44(7): 1596. [19] Ding W, Hayashi R, Ochi K. IEEE Transactions on Dielectrics and Electrical Insulation, 2006, 13: 1200.