基于相关分析和组合神经网络的退化预测

党香俊; 姜同敏

基于相关分析和组合神经网络的退化预测

北京航空航天大学可靠性与系统工程学院, 北京 100191

详细信息

中图分类号: TB 114.3
计量
- 文章访问数: 1562
- HTML全文浏览量: 135
- PDF下载量: 615
- 被引次数: 0
出版历程
- 收稿日期: 2011-10-24
- 网络出版日期: 2013-01-31

Degradation prediction based on correlation analysis and assembled neural network

School of Reliability and Systems Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China

摘要

摘要: 产品剩余寿命预测是加速退化试验和故障预测与健康管理两大热点领域中的关键技术之一.为了解决复杂退化的预测问题,提出了一种新型预测方法,对退化轨迹能够实现较长距离的预测.此方法首先对复杂退化数据进行小波变换,通过Durbin-Watson方法和偏相关图分析各级分解序列的自相关性,最后根据序列的特点,组合BP(Back Propagation)和小波神经网络对退化轨迹进行预测.为了验证所提组合神经网络方法的有效性,采用小波神经网络的预测结果进行对比分析.实际退化数据的预测结果表明,所提方法比单独采用小波神经网络,具有更小的均方差(MSE,Mean Square Error),对剩余寿命(RUL,Remaining Useful Life)也具有更高的预测精度.
- 退化预测 /
- 剩余寿命 /
- 小波神经网络 /
- 相关分析
Abstract: Efficient prognosis for remaining useful life of product is critical for both accelerated degradation testing and prognostics and health management, which are two hot points in recent years. A novel degradation prediction model was proposed to improve the long prediction capability for complex degradation path. Durbin-Watson method and partial correlation graph were utilized to analyze the decomposition results of wavelet transformation. Then, according to the characters of series, back propagation(BP) and wavelet neural network were assembled to predict degradation path. To verify the proposed method, wavelet neural network was selected as comparison. A practical degradation result demonstrates that this model can offer smaller mean square error (MSE) and higher prediction accuracy for remaining useful life (RUL).
- degradation prediction /
- remaining useful life /
- wavelet neural network /
- correlation analysis

HTML全文

参考文献(11)

[1]	Luo J,Bixby A,Pattipati K,et al. An interacting multiple model approach to model-based prognostics [C]//Proceedings of the IEEE International Conference on Systems,Man and Cybernetics. New York:Institute of Electrical and Electronics Engineers Inc,2003:189-194
[2]	Byington C S,Watson M,Edwards D,et al. A model-based approach to prognostics and health management for flight control actuators [C]//2004 IEEE Aerospace Conference Proceedings. New York:Institute of Electrical and Electronics Engineers Inc, 2004:3351-3362
[3]	周玉辉,康锐,苏荔,等. 基于加速磨损试验的止推轴承磨损寿命预测[J]. 北京航空航天大学学报,2011,37(8):10161020 Zhou Yuhui,Kang Rui,Su Li,et al. Life prediction of thrust bearings based on accelerated wear test [J]. Journal of Beijing University of Aeronautics and Astronautics,2011,37(8):10161020(in Chinese)
[4]	Biagetti T,Sciubba E. Automatic diagnostics and prognostics of energy conversion processes via knowledge based systems [J]. Energy,2004,29(12-15):2553-2572
[5]	Liu Y,Li S Q. Decision support for maintenance management using Bayesian networks [C]//2007 International Conference on Wireless Communications, Networking and Mobile Computing. New York:Institute of Electrical and Electronics Engineers Inc, 2007:5708-5711
[6]	Dong M,He D. Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis [J]. European Journal of Operational Research,2007,178(3):858878
[7]	王小林,程志君,郭波. 基于维纳过程金属化膜电容器的剩余寿命预测[J]. 国防科技大学学报,2011,33(4):146-151 Wang Xiaolin,Cheng Zhijun,Guo Bo. Residual life forecasting of metallized film capacitor based on wiener process [J]. Journal of National University of Defense Technology,2011,33(4):146151(in Chinese)
[8]	Zhang S,Ganesan R. Self-organizing neural networks for automated machinery monitoring systems [J]. Mechanical Systems and Signal Processing,1996,10(5):517-532
[9]	Huang Runqing,Xi Lifeng,Li Xinglin,et al. Residual life predictions for ball bearings based on self-organizing map and back propagation neural network methods [J]. Mechanical Systems and Signal Processing,2007,21(1):193-207
[10]	Gebraeel N Z,Lawley M A. A neural network degradation model for computing and updating residual life distributions [J]. IEEE Transactions on Automation Science and Engineering, 2008,5(1):156-163
[11]	Zhang Q,Benveniste A. Wavelet networks [J]. IEEE Transactions on Neural Networks,1992,3(6):889-898