The Fault Diagnosis of Elevator Based on the Autoregressive Model and the Support Vector Machine

Abstract:

The paper proposed the fault diagnosis of elevator based on the autoregressive(AR) model and the support vector machine. At first, build the AR model with the processing signals. The AR coefficient was used as the input of the support vector machine, the normal condition and the fault condition were used as output. By studying and predicting of the support vector machine(SVM) can reaching automatic identification. This method has high accuracy of diagnosis while resolved the problem of lacking samples.

• Periodical: Applied Mechanics and Materials (Volumes 271-272)
• Pages: 1689-1694
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.271-272.1689
• Online since: December 2012
• Authors: Shan Xu, Yi Jian Huang
• Keywords: Autoregressive Model, Bispectrum, Fault Diagnosis, Support Vector Machine (SVM)

References

[1] Peiliang Wang, Wuming He, Wenjun Yan. Fault Diagnosis of Elevator Braking System Based On Wavelet packet algorithm and Fuzzy Neural Network[J], IEEE The Ninth International Conference on Electronic Measurement & Instruments, 2009, (4): 1028.

DOI: 10.1109/icemi.2009.5274152

[2] Jin Tong, Zhaotong Wu, Gongbiao Yan. Study on the HMM-AR in process of large rotating machinery fault diagnosis[J], Journal Of Vibration and Shock, 1999, 18(2): 79~80.

[3] Zhijun Peng, Yijian Huang. Fault diagnosis of relief valve using AR bispectrum[J], Mechanical Science and Technology for Aerospace Engineering, 2007, (7): 90-911.

[4] Yi Zheng. Theory and methods of time series[M], Beijing: Higher Education Press, (2001).

[5] Shuzi Yang, Ya Wu, Jianping Xuan. Time Series Analysis in Engineering Application[M], Huazhong University of Science and Technology Press, (1994).

[6] Fusheng Liu, Pengfei Luo. Statistical signal processing[M], Changsha: National Defense Science and Technology University Press, (1999).

[7] O Chapelle, V Vapnik, O Bousquet, Choosing multiple parameters for support vector machines[M], Machine Learning 46 (1–3) (2002): 131–159.

DOI: 10.1023/a:1012450327387

[8] S.F. Yuan, F.L. Chu, Support vector machines-based fault diagnosis for turbo-pump rotor[M], Mechanical Systems and Signal Processing , 2006, 20 (4) : 939–952.

DOI: 10.1016/j.ymssp.2005.09.006

[9] S.F. Yuan, F.L. Chu, Fault diagnostics based on particle swarm optimization and support vector machines[M], Mechanical Systems and Signal Processing , 2007, 21 (4): 1787–1798.

DOI: 10.1016/j.ymssp.2006.07.008

[10] Corinna C，Vapnik V． Support-vector network［M］． MachineLearning，1995，20: 273 -297.

[11] Minfen Shen, Fenglin Shen. Non-Gaussian AR model and its application in analysis of heart sound[J], Signal Processing, 1997, 13(3)：253.