Please wait a minute...
浙江大学学报(工学版)
J4  2010, Vol. 44 Issue (7): 1251-1254    DOI: 10.3785/j.issn.1008-973X.2010.07.003
    
Fault prediction for state-dependent fault based on online learning neural network
XU Gui-bin, ZHOU Dong-hua
(Department of Automation, Tsinghua University, Beijing 100084, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

The concept of external and internal stimulated faults was proposed, and the fault prediction problem of nonlinear system with statedependent fault was investigated. The fault model of nonlinear system was formulated as a general nonlinear function with external and internal stimulated faults coupled together, and the structure of the function was unknown. The back propogation (BP) neural network was applied to learn the fault function online in order to approximate the fault model, and an online neural network based statedependent fault prediction algorithm was given. The algorithm can detect the fault online, and iteratively estimate and predict the fault and the system state. The failure time of the system was predicted online by using the predicted value of the system state. The generalization of fault model showed the effect of the system state on the fault, which made the algorithm more applicable. Simulation results demonstrated the effectiveness of the method.

Published: 01 July 2010
CLC:  TP 277  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

XU Gui-Bin, ZHOU Dong-Hua. Fault prediction for state-dependent fault based on online learning neural network. J4, 2010, 44(7): 1251-1254.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2010.07.003     OR     http://www.zjujournals.com/eng/Y2010/V44/I7/1251


基于在线学习神经网络的状态依赖型故障预测

提出外部激励故障和内部激励故障的概念,研究非线性系统状态依赖型故障的预测问题.将非线性系统的故障模型描述成外部激励与内部激励相耦合的一般非线性函数形式,函数的结构未知.通过反向传播(BP)神经网络在线学习故障函数模型实时逼近故障模型,提出基于在线神经网络的状态依赖型故障的预测算法.该算法能够实时地检测故障,对系统状态和故障进行迭代估计和预测.利用系统状态的预测值实时预测了系统的失效时间.故障模型的一般化拓展充分体现了系统状态对故障的影响,增强了算法的实用性.仿真结果验证了该方法的有效性.

［1］ BARRY R F. Failure prediction for preventive maintenance ［C］∥ Proceedings of the Joint Conference on Automatic Test Systems. London: IERE, 1970: 549568.

［2］ CHELIDZE D, CUSUMANO J P. A dynamical systems approach to failure prognosis ［J］. Journal of Vibration and Acoustics Transactions of the ASME, 2004, 126(1): 28.

［3］ WANG X H, RONG M Z, QIU J, et al. Research on mechanical fault prediction algorithm for circuit breaker based on sliding time window and ANN ［J］. IEICE Transactions on Electronics, 2008, E91C(8): 12991305.

［4］ XU Z, JI Y, ZHOU D. Realtime reliability prediction for a dynamic system based on the hidden degradation process identification ［J］. IEEE Transactions on Reliability, 2008, 57(2): 230242.

［5］ ORCHARD M E, VACHTSEVANOS G J. A particlefiltering approach for online fault diagnosis and failure prognosis ［J］. Transactions of the Institute of Measurement and Control, 2009, 31(3/4): 221246.
［6］ ZHANG L B, WANG Z H, ZHAO S X. Shortterm fault prediction of mechanical rotating parts on the basis of fuzzygrey optimizing method ［J］. Mechanical Systems and Signal Processing, 2007, 21(2): 856865.
［7］ ZHANG Z D, HU S S. A new method for fault prediction of modelunknown nonlinear system ［J］. Journal of the Franklin InstituteEngineering and Applied Mathematics, 2008, 345(2): 136153.
［8］ XU G, ZHOU D. Fault prediction for dynamic systems with statedependent faults ［C］∥ Proceedings of the 4th International Conference on Innovative Computing, Information and Control. Piscataway, NJ, USA: IEEE, 2009: 207210.
［9］ XIA R, MENG K, QIAN F, et al. Online wavelet denoising via a moving window ［J］. /Acta Automatica Sinica, 2007, 33(9): 897901.
［10］ WERBOS P J. Beyond regression: new tools for prediction and analysis in the behavioral sciences ［D］. Massachusetts: Harvard University, 1975.
［11］ WERBOS P J. Building and understanding adaptive systems: a statistical/numerical approach to factory automation and brain research ［J］. IEEE Transactions on Systems, Man and Cybernetics, 1987, 17(1): 720.
［12］ WERBOS P J. Backpropagation: past and future ［C］∥ IEEE International Conference on Neural Networks. New York: IEEE, 1988: 343353.
［13］ 周东华, 叶银忠. 现代故障诊断与容错控制［M］. 北京: 清华大学出版社, 2000: 137139.
［14］ XIE X Q, ZHOU D H, JIN Y H. Strong tracking filter based adaptive generic model control ［J］. Journal of Process Control, 1999, 9(4): 337350.
[1] DUAN Bin, LIANG Jun, FEI Zheng-shun, YANG Min, HU Bin. Nonlinear semi-parametric modeling mothed based on GA-ANN[J]. J4, 2011, 45(6): 977-983.
[2] DU Wen-Chi, WANG Kun, JIAN Feng. Feature space dimensionreduction based process monitoring of solvent dehydration separation process[J]. J4, 2010, 44(7): 1255-1259.
[3] LIN Yong, ZHOU Xiao-Jun, YANG Xian-Yong, DENG. Intelligent fault diagnosis methods based on bispectrum recognition and artificial immune network[J]. J4, 2009, 43(10): 1777-1782.