Adaptive Algorithm Based on Wavelet and SVM for Turbopump Fault Detection

Abstract:

An adaptive fault detection algorithm based on wavelet and SVM (Support Vector Machine) is proposed for LRE(Liquid Rocket Engine) turbopump real-time fault detection. The algorithm firstly divides the historical signals into some segments by reasonable step length. Then for each segment it gets M-layer detail signals through Daubechies wavelet transform. Thirdly it divides every layer into K average segments and calculates there RMS values, gets M RMS sequences of detail signals. After that it constructs M-dimensional RMS vector as fault feature by extracting RMS values at the same position in every RMS sequence, and extracts all the fault feature vectors of historical signal to construct SVM training sample set and then obtains SVM classifier. At last the classifier will be real-time updated by a reasonable method in the testing process to improve the classification accuracy. To validate the algorithm, a track of the vibration acceleration signal of a certain type of turbopump was chosen as the test object. The test results showed that the algorithm met its demands of accuracy and real-time performance.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 994-1002
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.994
• Online since: September 2014
• Authors: Tao Hong*, Shuo Yang
• Keywords: Adaptive, SVM, Turbopump Real-Time Fault Detection, Wavelet Transform (WT)

References

[1] G. J. Xie, H. F. Hu, G. J. Qin: The health monitoring system of turbo pump for liquid rocket engine, Journal of National University of Defense Technology, vol. 27 (2005), pp.40-44.

[2] C. F. Xu, G. K. Li. Practical wavelet method, Wuhan: Huazhong University Press(2001), pp.92-103.

[3] X. Z. Feng: Automatic modulation recognition using support vector machines based on wavelet transform, Journal of Electronic Measurement and Instrument, vol. 23 (2009), pp.87-92.

[4] Fei Sike Technology R&D Center. Wavelet analysis theory and MATLAB7 application, Beijing: Electronics Industry Press (2005), pp.444-452.

[5] X. B. Yu, T. Dong: Fast decomposition and reconstruction algorithm on discrete wavelet transform, Journal of Southeast University, vol. 32 (2002), pp.1-5.

[6] Z. H. Zhao: Fault diagnosis of roller bearing based on relative wavelet energy, Journal of Electronic Measurement and Instrument, vol. 25 (2011), pp.44-47.

DOI: 10.3724/sp.j.1187.2011.00044

[7] L. R. Xia: Research on key technology and system for turbo pump health monitoring of liquid rocket engine, Changsha: National University of Defense Technology(2010), pp.56-58.

[8] Z. S. Zhang, L. J. L i, Z. J. He: Multi-fault classifier based on support vector machine and its applications, Mechanical Science and Technology, vol. 23(2004), pp.536-538.

[9] Q. H. Xu, J. Shi: Some studies in aero-engine fault diagnosis using support vector machine, Acta Aeronoutica et Astronautica Sinica, vol. 26(2005), pp.686-690.

[10] X. M. Liu, J. Qiu, G. J. Liu: HMM-SVM based mixed diagnostic model and its application, Acta Aeronoutica et Astronautica Sinica, vol. 26 (2005), pp.496-500.

[11] Z. Y. Yang, T. Peng, J. B. Li, et al: Bayesian inference LSSVM based fault diagnosis method for rolling bearing, Journal of Electronic Measurement and Instrument, vol. 24 (2010), pp.420-424.

DOI: 10.3724/sp.j.1187.2010.00420

[12] W. L. Jiang, S. Q. Wu: Multi-data fusion fault diagnosis method based on SVM and evidence theory, Chinese Journal of Scientific Instrument, vol. 31 (2010), pp.1738-1743.

[13] G. J. Liu, Y. D. Su, C. H. Pan: Fault diagnosis method based on integrated fuzzy support vector machine and its application, Chinese Journal of Scientific Instrument, vol. 30 (2009), pp.1363-1367.

[14] J. Y. Tang, Y. B. Shi, D. Jiang: Analog circuit fault diagnosis using proximal support vector machine ensemble, Journal of Electronic Measurement and Instrument, vol. 24 (2010), pp.107-112.

DOI: 10.3724/sp.j.1187.2010.00107

[15] J. G. Yang: Wavelet analysis and its engineering applications, Beijing: China Machine Press(2005), pp.26-62.

[16] X. M. Liu, J. Qiu, G. J. Liu: HMM-SVM based mixed diagnostic model and its application, Acta Aeronoutica et Astronautica Sinica, vol. 26 (2005), pp.496-500.