Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes

doi:10.1016/j.cjche.2016.06.011

›› 2016, Vol. 24 ›› Issue (10): 1413-1422.DOI: 10.1016/j.cjche.2016.06.011

• Process Systems Engineering and Process Safety • 上一篇下一篇

Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes

Yuan Xu, Ying Liu, Qunxiong Zhu

College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

收稿日期:2015-10-19 修回日期:2016-02-17 出版日期:2016-10-28 发布日期:2016-11-19
通讯作者: Qunxiong Zhu,E-mail address:zhuqx@mail.buct.edu.cn.
基金资助:
Supported by the National Natural Science Foundation of China (61573051, 61472021), the Natural Science Foundation of Beijing (4142039), Open Fund of the State Key Laboratory of Software Development Environment (SKLSDE-2015KF-01), and Fundamental Research Funds for the Central Universities (PT1613-05).

Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes

Yuan Xu, Ying Liu, Qunxiong Zhu

College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

Received:2015-10-19 Revised:2016-02-17 Online:2016-10-28 Published:2016-11-19
Supported by:
Supported by the National Natural Science Foundation of China (61573051, 61472021), the Natural Science Foundation of Beijing (4142039), Open Fund of the State Key Laboratory of Software Development Environment (SKLSDE-2015KF-01), and Fundamental Research Funds for the Central Universities (PT1613-05).

摘要/Abstract

摘要： Currently, some fault prognosis technology occasionally has relatively unsatisfied performance especially for incipient faults in nonlinear processes duo to their large time delay and complex internal connection. To overcome this deficiency,multivariate time delay analysis is incorporated into the high sensitive local kernel principal component analysis. In this approach, mutual information estimation and Bayesian information criterion (BIC) are separately used to acquire the correlation degree and time delay of the process variables. Moreover, in order to achieve prediction, time series prediction by back propagation (BP) network is applied whose input is multivariate correlated time series other than the original time series. Then the multivariate time delayed series and future values obtained by time series prediction are combined to construct the input of local kernel principal component analysis (LKPCA)model for incipient fault prognosis. The newmethod has been exemplified in a simple nonlinear process and the complicated Tennessee Eastman (TE) benchmark process. The results indicate that the new method has superiority in the fault prognosis sensitivity over other traditional fault prognosis methods.

关键词: Fault prognosis, Time delay estimation, Local kernel principal component analysis

Abstract: Currently, some fault prognosis technology occasionally has relatively unsatisfied performance especially for incipient faults in nonlinear processes duo to their large time delay and complex internal connection. To overcome this deficiency,multivariate time delay analysis is incorporated into the high sensitive local kernel principal component analysis. In this approach, mutual information estimation and Bayesian information criterion (BIC) are separately used to acquire the correlation degree and time delay of the process variables. Moreover, in order to achieve prediction, time series prediction by back propagation (BP) network is applied whose input is multivariate correlated time series other than the original time series. Then the multivariate time delayed series and future values obtained by time series prediction are combined to construct the input of local kernel principal component analysis (LKPCA)model for incipient fault prognosis. The newmethod has been exemplified in a simple nonlinear process and the complicated Tennessee Eastman (TE) benchmark process. The results indicate that the new method has superiority in the fault prognosis sensitivity over other traditional fault prognosis methods.

Key words: Fault prognosis, Time delay estimation, Local kernel principal component analysis

Yuan Xu, Ying Liu, Qunxiong Zhu. Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes[J]. , 2016, 24(10): 1413-1422.

参考文献

[1] D. Bustan, N. Pariz, S.K. Hosseini Sani, Robust fault-tolerant tracking control design for spacecraft under control input saturation, ISA Trans. 53(2014) 1073-1080.
[2] S. Ahmet, J. Sarangapani, S. Can, Mahalanobis-Taguchi system as a multi-sensor based decision making prognostics tool for centrifugal pump failures, IEEE Trans. Reliab. 60(2011) 864-8708.
[3] J. Chen, H. Sheng^*, C. Li, Z. Xiong, PSTG-based multi-label optimization for multitracking, Comput. Vis. Image Underst. 144(2016) 217-227.
[4] K. Ashwani, A.P. Singh, Fuzzy classifier for fault diagnosis in analog electronic circuits, ISA Trans. 52(2013) 816-824.
[5] B. Chen, P.C.Matthews, P.J. Tavner,Wind turbine pitch faults prognosis using A-priori knowledge-based ANFIS, Expert Syst. Appl. 40(2013) 6863-6876.
[6] M. Basseville, On-board component fault detection and isolation using the statistical local approach, Automatica 34(1998) 1391-1415.
[7] H. Chang, J.H. Chen, Y.P. Ho, Batch process monitoring by wavelet transform based fractal encoding, Ind. Eng. Chem. Res. 25(2006) 3864-3879.
[8] L. Zhang, Fault prognostic algorithm based on multivariate relevance vector machine and time series iterative prediction, Procedia Eng. 29(2012) 678-686.
[9] G. Li, S.J. Qin, Y.D. Ji, D.H. Zhou, Reconstruction based fault prognosis for continuous processes, Control. Eng. Pract. 18(2010) 1211-1219.
[10] T. Jo, VTG schemes for using back propagation for multivariate time series prediction, Appl. Soft Comput. 13(2013) 2692-2702.
[11] C.H. Gao, Z.M. Zhou, J.M. Chen, Assessing the predictability for blast furnace system through nonlinear time series analysis, Ind. Eng. Chem. Res. 47(2008) 3037-3045.
[12] M.S. Roulston, Estimating the errors on measured entropy and mutual information, Phys. D 125(1999) 285-294.
[13] G. Chen, L. Xie, J.S. Zeng, J. Chu, Y. Gu, Detecting model-plant mismatch of nonlinear multivariate systems using mutual information, Ind. Eng. Chem. Res. 52(2013) 1927-1938.
[14] B. Sadeghi, HM. A BP-neural network predictor model for plastic injection molding process, J. Mater. Process. Technol. 103(2000) 411-416.
[15] W.X. Zhao, D.Z. Chen, S.X. Hu, Detection of outlier and a robust BP algorithm against outlier, Comput. Chem. Eng. 28(2004) 1403-1408.
[16] J.F. Böhme, Time delay estimation by cross-covariance maximization of quadrature sampled narrowband signals, AEU Int. J. Electron. Commun. 58(2004) 13-20.
[17] S.H. Jin, P. Lin, M. Hallett, Linear and nonlinear information flow based on timedelayed mutual information method and its application to corticomuscular interaction, Clin. Neurophysiol. 121(2010) 392-401.
[18] W.D. Penny, Comparing dynamic causal models using AIC, BIC and free energy, Neuroimage 59(2012) 319-330.
[19] M.A. Kramer, Nonlinear principal component analysis using auto-associative neural networks, AIChE J. 37(1991) 233-243.
[20] J.Wang, H.T.Wei, L.L. Cao, Q.B. Jin, Soft-transition sub-PCA fault monitoring of batch process, Ind. Eng. Chem. Res. 52(2013) 9858-9888.
[21] J.M. Lee, C.K. Yoo, S.W. Choi, P.A. Vanrolleghem, I.B. Lee,Nonlinear processmonitoring using kernel principal component analysis, Chem. Eng. Sci. 59(2004) 223-234.
[22] J.M. Lee, C. Yoo, I.B. Lee, Fault detection of batch processes using multiway kernel principal component analysis, Comput. Chem. Eng. 28(2004) 1837-1847.
[23] Z.Q. Ge, C.J. Yang, Z.H. Song, Improved kernel PCA-based monitoring approach for nonlinear processes, Chem. Eng. Sci. 64(2009) 2245-2255.
[24] U. Kruger, S. Kumar, T. Littler, Improved principal component monitoring using the local approach, Automatica 43(2007) 1532-1542.
[25] Z.Q. Ge, L. Xie, U. Kruger, Z.H. Song, Local ICA formultivariate statistical fault diagnosis in systems with unknown signal and error distributions, AIChE J. 58(2012) 2357-2372.
[26] A. Kraskov, H. Stögbauer, P. Grassberger, Estimatingmutual information, Phys. Rev. E 69(066138) (2004).
[27] S. Markus, R. Haber, U. Schmitz, Source identification of plant-wide faults based on k nearest neighbor time delay estimation, J. Process Control 22(2012) 583-598.
[28] Y. Shi, W.Q. Meeker, Bayesian methods for accelerated destructive degradation test planning, IEEE Trans. Reliab. 61(2012) 245-253.
[29] F.A. Carroll, J.M. Godinho, F.H. Quina, Development of a simple method to predict boiling points and flash points of acyclic alkenes, Ind. Eng. Chem. Res. 50(2011) 14221-14225.
[30] A. Singhal, D.E. Seborg, Evaluation of a pattern matching method for the Tennessee Eastman challenge process, J. Process Control 16(2006) 601-613.
[31] Y. Shen, S.X. Ding, A. Haghani, H.Y. Hao, P. Zhang, A comparison study of basic datadriven fault diagnosis and processmonitoringmethods on the benchmark Tennessee Eastman process, J. Process Control 22(2012) 1567-1581.
[32] R. Eslamloueyan, Designing a hierarchical neural network based on fuzzy clustering for fault diagnosis of the Tennessee-Eastman process, Appl. Soft Comput. 11(2011) 1407-1415.

Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes

Multivariate time delay analysis based local KPCA fault prognosis approach for nonlinear processes

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价