Electronic Equipment Combination Fault Prediction Technology Research Based on LSSVM-HMM

Abstract:

In order to solve the problem of complicated electronic equipment structure, inadequate fault information, hard to predict the fault and the existing failure prediction method cannot predict the state of the electronic equipment and other issues directly, we propose a combination failure prediction methods of least squares support vector machine (LSSVM) and hidden Markov model (HMM) based on Condition Based Maintenance (CBM). First, according to sensitivity analysis to determine the circuit elements to be changed to set the circuit by changing the parameters of the different components degraded state; secondly, create a combination failure prediction model; Finally, the circuit state prediction. The results show that the proposed method can directly predict the different states of the circuit, so as to realize the fault state prediction of the electronic equipment directly, the prediction accuracy can reach 93.3%.

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 978-983
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.978
• Online since: November 2014
• Authors: Yan Ping Tian, Xiao Hui Ye, Ming Yin
• Keywords: CBM, Failure Prediction, HMM, LSSVM

References

[1] Jianshe Kang, Jian Yin, Xixing Wang. CBM systems and equipment condition monitoring [J] . Journal of Scientific Instrument , 2006, 27 (6) : 1748-1751.

[2] Yu Peng, Datong Liu, Xiyuan Peng. Prognostics and Health Management Technology Overview [J]. Journal of Electronic Measurement and Instrument, 2010, 24 (1): 1-9.

[3] Ying Wen, Mingqing Xiao, Leigang Hu. Prediction of avionics equipment failult based on rough neural network [J]. Computer Measurement and Control. 2010, 18(4): 807-809.

[4] Wang Q, Zhang S, Kang R. Research of small samples avionics prognostics based on Support Vector Machine[C], Prognostics and System Health Management Conference (PHM-Shenzhen), 2011, 2011: 1-5.

DOI: 10.1109/phm.2011.5939510

[5] Geng Fan, Dengwu Ma, Li Deng. Fault prediction model based on gray correlation vector machine [J]. Systems Engineering and Electronics, 2012, 34 (2): 424-428.

[6] Fuzhou Feng, Aiwei Si, Pengcheng Jiang. Wavelet relevant permutation entropy and HMM Application in Fault Prediction [J]. Vibration Engineering. 2013, 26(2): 269-275.

[7] Jinjun Cheng, Zhixun Xia, Leigang Hu. Aviation equipment failure prediction based on genetic neural network [J]. Air Force Engineering University 2011, 12(1): 15-19.

[8] JIANG H, LI X W, LIU C J. Large margin hidden Markov models for speech recognition[J]. IEEE Transactions on Audio, Speech and Language Processing, 2006, 9(5): 1584-1594.

DOI: 10.1109/tasl.2006.879805

[9] Jingde Huang, Xueliang Hao, Yi Huang. Potential electronic fault state to recognition model based on improved HMM [J]. Journal of Scientific Instrument, 2011, 32(11): 2481-2486.

[10] Xiaodong Tan. HMM-based rolling bearing fault prediction techniques [D] . Beijing: National University of Defense Technology Science, 2008: 30-44.

[11] Lijia Xu. Electronic Systems Prognostics and Health Management Research [D] . Chengdu: University of Electronic Science and Technology, (2009).

[12] J M Lee, et al. Diagnosis of mechanical fault signals using continuous hidden Markov model [J]. Journal of Sound and Vibration, 2004, 27 (6): 1065 - 1080.

DOI: 10.1016/j.jsv.2003.08.021

[13] Guangyao Lian, Xiaoming Lv, Kaoli Huang. Research on complex equipment failure prediction based on least squares support vector machine[J]. Computer Measurement and Control, 2011, 19 ( 5 ) : 1030-1032.