基于动态限的周期非稳定工况的实时故障检测模型

Abstract
Figure/Table
References
Related Citation (1)

Download: PDF (393 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The traditional multivariate statistical methods could not detect the fault effectively under the non-steady condition of complex system. For these problems above,the concept of the dynamic limit and the same peak-valley are given in this paper. And,the paper proves that the T² statistics of the multivariable parameters is periodic if the system is under the periodic non-steady condition. Then,this paper proposes a model of real-time fault detection under the periodic non-steady condition and gives the real time and the feasibility analysis of the model. At last,the model is applied to the periodic non-steady conditions in real time.

Key words： Relative principal component analysis(RPCA) T2-chart non-steady condition real- time fault detection

Received: 11 September 2012 Published: 22 January 2015

PACS:

TN911

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Wang Tianzhen
	Wu Hao
	Liu Ping
	Zhang Jian
	Tang Tianhao
	Yang Ming

Cite this article:

Wang Tianzhen,Wu Hao,Liu Ping等. Real-Time Fault Detection Model Based on Dynamic Limit under Periodic Non-Steady Condition[J]. Transactions of China Electrotechnical Society, 2014, 29(12): 95-101.

URL:

http://dgjsxb.ces-transaction.com/EN/ OR http://dgjsxb.ces-transaction.com/EN/Y2014/V29/I12/95

[1] Gallagher N B,Wise B M,Bulter S W,et al. Statistical process control tools for a semiconductor each process: improving robustness through model updating[J]. Proceeding of the ADCHEM 97,Banff,Canada,1997: 78-83.
[2] Wang Xun,Uwe Kruger,Lennox Barry,et al. Recursive partial least squares algorithms for mointoring complex industial process[J]. Control Engineering Practice,2003,11(6): 613-632.
[3] Wold S. Exponentially weighted moving principal component analysis and projection to latent stuctures. chemometrics and intelligent laboratory systems[C]. Proceedings of the 3rd Scandinavian Symposium on Chemometrics,Aprial,1994: 149-161.
[4] Weihua Li,H HenryYue,Sergio Valle_Cervantes,et al. Recursive PCA for adaptive process monitoring[J]. Journal of Process Monitoring,2000,10(5): 471-486.
[5] Lane S,Martin E B,Morrios A J,et al. Application of exponentially weighted principal component analysis for the monitoring of a polymer film manufacturing process[J]. Transactions of the Institute of Measurement and Control,2003,25(1): 17-35.
[6] Xun Wang,Uwe Krugerb,Barry Lennox. Recursive partial least squares algorithms for monitoring complex industrial processes[J]. Control Engineering Practice,2003(11): 613-632.
[7] Chen J H,Liu J L. Mixture principal component analysismodels for process monitoring[J]. Industrial and Engineering Chemistry Research,1999,38(4): 1478-1488.
[8] Ding S,Zhang P. On the Application of PCA technique to fault diagnosis[J]. Journal of Tsinghua University (Science and Technology),2010,15(2): 138-144.
[9] 文成林,胡静,王天真,陈志国. 相对主元分析及其在数据压缩和故障诊断中的应用研究[J]. 自动化学报,2008 34(9): 1129-1140. Wen Chenglin,Hu Jing,Wang Tianzhen. Relative PCA with applications of data compression and fault diagnosis[J]. Acta Automatica Sinica,2008,34(9): 1129- 1140.
[10] 王天真,汤天浩. 相对主元分析方法及其在故障检测中的应用[J]. 系统仿真学报,2007,19(13): 2889-2894. Wang Tianzhen,Tang Tianhao. Relative principal component analysis algorithm and its application in fault detection[J]. Journal of System Simulation,2007,19(13): 2889-2894.
[11] RothenhagenKai,FuchsFriedrich Wilhelm,Doubly fed induction generator model-based sensor fault detection and control loop reconfiguration[J]. IEEE Transactions on Industrial Electronics,2009,56(10): 4229-4238.
[12] Castillo Angela,Zufiria Pedro J. Fault detection schemes for continuous-time stochastic dynamical systems[J]. IEEE Transactions on Automatic Control,2009,54(8): 1820-1836.