Study of Data Fusion Method for Fault Diagnosis Based on FDR Feature Selection Algorithm and HMM/SVM Model

Article Preview

Abstract:

To effectively avoid the loss of useful information, in this paper, we extract feature information from the fault signal of rotating machinery in different aspects such as amplitude-domain, time-domain and time-frequency domain. Then for the multi-dimensional feature extraction is prone to the problem of “dimension disaster”, introduce the principles of FDR in data mining to determine the classification ability of each individual feature, and introduce the cross correlation coefficient to solve the problem that dealing with individual feature neglects the interrelationship between the features, and construct a new feature level data fusion algorithm. Finally, According to the characteristics of the HMM (Hidden Markov model), SVM (Support Vector Machine) and its hybrid model, we construct a new decision-level data fusion model.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 591-593)

Pages:

2046-2050

Citation:

Online since:

November 2012

Export:

Price:

[1] Waltz E L, Bued D M. Data fusion and decision support for command and control. IEEE Trans on Systems Man and Cybernetics, 1986, 16(6): 865~ 879.

DOI: 10.1109/tsmc.1986.4309005

Google Scholar

[2] Yuan F Z. Integration of multiple sensor into a robotic system and its performance evaluation. IEEE Trans on Robotics and Automation, 1989, 5(5): 658~ 669.

DOI: 10.1109/70.88083

Google Scholar

[3] Filippetti F G, Franceschini G, Tassoni C, et al .Recent developments of induction mo-tor drives fault diagnosis using Al techniques [J]. IEEE Transactions on Industrial Electronics, 2000, 47 (5): 994~ 1004.

DOI: 10.1109/41.873207

Google Scholar

[4] VALET L, MAUR ISG, BOLON PH. Statistical Overview of Recent Lite rapture in Information Fusion [J]. IEEE AESS Systems Magazine, 2001, (March): 7~ 14.

Google Scholar

[5] ALAN N STEINBERG. Data Fusion System Engineering [J]. IEEE AESS Systems Magazine, 2001, (June): 7~ 14.

Google Scholar

[6] JIA YUQIN, WANG PE IXIA, LI YUE. Study of Manufacturing System Based on Neural Network Multi-sensor Data Fusion and Its Application [J]. Robotics Intelligent Systems and Signal Processing, 2003, 2(8- 13): 1022~ 1026.

DOI: 10.1109/rissp.2003.1285729

Google Scholar

[7] ZHU Da-qi, LIU Yong-an. Information fusion method for fault diagnosis [J]. Control and Decision, Vol.22 No.12, 2007:1321~ 1326.

Google Scholar

[8] ZHU Da-qi, YU Sheng-lin.Survey of knowledge-based fault diagnosis methods [J]. Journal of Anhui University of Technology, 2002, 19(3):197-204.

Google Scholar

[9] Shengzhao Shun, Yin Qiling.Technology and Application of Condition Monitoring and Fault Diagnosis [M]. Chemical Industry Press, 2003:38-42.

Google Scholar

[10] Zhu Qibing. Research on Feature Extraction of non-stationary signal based on Wavelet Theory and Intelligent Diagnosis [D], Shenyang, Northeastern University, 2005.

Google Scholar

[11] Jong Min Lee, Seung-Jong Kim et al. Diagnosis of mechanical fault signal using continuous hidden Markov model. Journal of Sound and Vibration, 2004, 276: 1065-1080.

DOI: 10.1016/j.jsv.2003.08.021

Google Scholar

[12] Sergios Theodoridis, Konstantinos Koutroumbas. Pattern Recognition [M]. Publishing House of Electronics Industry, BEIJING, 2006:148-151.

Google Scholar

[13] Su K.Y, Lee C.H. Speech recognition using weighted HMM and subspace projection approaches [J]. IEEE Translation on speech and Audio Processing, Vol. 2(1), pp.69-79, 1994.

DOI: 10.1109/89.260336

Google Scholar

[14] Huang Xi-Yue, Xiao-Bing, Ma Xiao-Xiao, Theory and Application of modern intelligent algorithm [M], Science Press,(2005),p.406.

Google Scholar