Fault diagnosis of chemical processes based on partitioning PCA and variable reasoning strategy

doi:10.1016/j.cjche.2016.04.015

Abstract

Abstract: Fault detection and identification are challenging tasks in chemical processes, the aimof which is to decide out of control samples and find fault sensors timely and effectively. This paper develops a partitioning principal component analysis (PPCA) method for process monitoring. A variable reasoning strategy is proposed and applied to recognize multiple fault variables. Compared with traditional process monitoring methods, the PPCA strategy not only reflects the local behavior of process variation in each model (each direction of principal components), but also improves the monitoring performance through the combination of local monitoring results. Then, a variable reasoning strategy is introduced to locate fault variables. Unlike the contribution plot, this method locates normal and fault variables effectively, and gives initiatory judgment for ambiguous variables. Finally, the effectiveness of the proposed process monitoring and fault variable identification schemes is verified through a numerical example and TE chemical process.

Key words: Fault detection, Fault identification, Process monitoring, Partitioning PCA, Variable reasoning strategy

摘要： Fault detection and identification are challenging tasks in chemical processes, the aimof which is to decide out of control samples and find fault sensors timely and effectively. This paper develops a partitioning principal component analysis (PPCA) method for process monitoring. A variable reasoning strategy is proposed and applied to recognize multiple fault variables. Compared with traditional process monitoring methods, the PPCA strategy not only reflects the local behavior of process variation in each model (each direction of principal components), but also improves the monitoring performance through the combination of local monitoring results. Then, a variable reasoning strategy is introduced to locate fault variables. Unlike the contribution plot, this method locates normal and fault variables effectively, and gives initiatory judgment for ambiguous variables. Finally, the effectiveness of the proposed process monitoring and fault variable identification schemes is verified through a numerical example and TE chemical process.

关键词: Fault detection, Fault identification, Process monitoring, Partitioning PCA, Variable reasoning strategy

Guozhu Wang, Jianchang Liu, Yuan Li, Cheng Zhang. Fault diagnosis of chemical processes based on partitioning PCA and variable reasoning strategy[J]. , 2016, 24(7): 869-880.

References

[1] D.C.Montgomery, Introduction to statistical quality control,Wiley, New York, 1991.
[2] J. Yu, J. Yu, Nonlinear bioprocess monitoring using multiway kernel localized fisher discriminant analysis, Ind. Eng. Chem. Res. 50(6) (2011) 3390-3402.
[3] J. Kresta, J.F. MacGregor, T.E. Marlin, Multivariate statistical monitoring of process operating performance, Can. J. Chem. Eng. 69(1) (1991) 35-47.
[4] P. Nomikos, J.F. MacGregor, Monitoring batch processes using multiway principal component analysis, AICHE J. 40(8) (1994) 1361-1375.
[5] T. Kourti, J.F.MacGregor, Process analysis,monitoring and diagnosis, usingmultivariate projection methods, Chemom. Intell. Lab. Syst. 28(95) (1995) 3-21.
[6] Y.W. Zhang, C.Ma, Fault diagnosis of nonlinear processes usingmultiscale KPCA and multiscale KPLS, Chem. Eng. Sci. 66(1) (2010) 64-72.
[7] G.Z.Wang, J.C. Liu, Y.W. Zhang, Y. Li, A novelmulti-mode data processingmethod and its application in industrial process monitoring, J. Chemom. 29(2) (2015) 126-138.
[8] Y. Yao, T. Chen, F. Gao, Multivariate statistical monitoring of two-dimensional dynamic batch processes utilizing non-Gaussian information, J. Process Control 20(10) (2011) 1188-1197.
[9] J. Wang, Q.P. He, Multivariate statistical process monitoring based on statistics pattern analysis, Ind. Eng. Chem. Res. 49(17) (2010) 7858-7869.
[10] Z.Q. Ge, C.J. Yang, Z.H. Song, Improved kernel PCA-based monitoring approach for nonlinear processes, Chem. Eng. Sci. 64(9) (2009) 2245-2255.
[11] J.Y. Guo, H.B. Chen, Y. Li, MPCA fault detection method based onmultiblock statistics for uneven-length batch processes, J. Comput. Inf. Syst. 9(18) (2013) 7181-7190.
[12] X. Wang, U. Kruger, G.W. Irwin, G. McCullough, N. McDowell, Nonlinear PCA with the local approach for diesel engine fault detection and diagnosis, IEEE Trans. Control Syst. Technol. 16(1) (2008) 122-129.
[13] Y.H. Lee, H.D. Jin, C.H. Han, On-line process state classification for adaptive monitoring, Ind. Eng. Chem. Res. 45(9) (2006) 3095-3107.
[14] X.Z. Wang, S. Medasani, F. Marhoon, H. Albazzaz, Multidimensional visualization of principal component scores for process historical data analysis, Ind. Eng. Chem. Res. 43(22) (2004) 7036-7048.
[15] M. Kano, K. Nagao, H. Hasebe, T. Hashimoto, H. Ohno, R. Strauss, B.R. Bakshi, Comparison of multivariate statistical process monitoring methods with applications to the Eastman challenge problem, Comput. Chem. Eng. 26(1) (2002) 161-174.
[16] B.R. Bakshi,Multiscale PCA with applications tomultivariate statistical process monitoring, AICHE J. 44(7) (1998) 1596-1610.
[17] J.E. Jackson, A user's guide to principal components, Wiley, New York, 1991.
[18] J.F. MacGregor, C. Jaeckle, C. Kiparissides, M. Kourtoudi, Process monitoring and diagnosis by multiblock PLS methods, AICHE J. 40(5) (1994) 826-838.
[19] J.A. Westerhuis, T. Kourti, J.F. MacGregor, Analysis of multiblock and hierarchical PCA and PLS models, J. Chemom. 12(5) (1998) 301-321.
[20] S.J. Qin, S. Valle, M.J. Piovoso, On unifying multiblock analysis with application to decentralized process monitoring, J. Chemom. 15(9) (2001) 715-742.
[21] A.K. Smilde, J.A.Westerhuis, S. DeJong, A framework for sequential multiblock component methods, J. Chemom. 17(6) (2003) 323-337.
[22] G.Z. Wang, J.C. Liu, Y. Li, L.L. Shang, Fault detection based on diffusion maps and k nearest neighbor diffusion distance of feature space, J. Chem. Eng. Jpn. 48(9) (2015) 756-765.
[23] M.A. Hussain, C.R. Che Hassan, K.S. Loh, K.W. Mah, Application of artificial intelligence technique in process fault diagnosis, J. Eng. Sci. Technol. 2(3) (2007) 260-270.
[24] H. Guo, H.G. Li, On-line batch process monitoring with improved multi-way independent component analysis, Chin. J. Chem. Eng. 21(3) (2013) 263-270.
[25] X. Deng, X. Tian, Multimode process fault detection using local neighborhood similarity analysis, Chin. J. Chem. Eng. 22(11) (2014) 1260-1267.
[26] V. Venkatasubramanian, R. Rengaswamy, K. Yin, S.N. Kavuri, A review of process fault detection and diagnosis:Part I:Quantitative model-based methods, Comput. Chem. Eng. 27(3) (2003) 293-311.
[27] V. Venkatasubramanian, R. Rengaswamy, S.N. Kavuri, A review of process fault detection and diagnosis:Part Ⅱ:Qualitative models and search strategies, Comput. Chem. Eng. 27(3) (2003) 313-326.
[28] V. Venkatasubramanian, R. Rengaswamy, S.N. Kavuri, K. Yin, A review of process fault detection and diagnosis:Part Ⅲ:Process history based methods, Comput. Chem. Eng. 27(3) (2003) 327-346.
[29] F. Yang, P. Duan, S.L. Shah, T. Chen, Capturing connectivity and causality in complex industrial processes, Springer, 2014.
[30] C.K. Lau, K. Ghosh, M.A. Hussain, C.R. Hassan, Fault diagnosis of Tennessee Eastman process with multi-scale PCA and ANFIS, Chemom. Intell. Lab. Syst. 120(2) (2013) 1-14.
[31] S.W. Choi, I.B. Lee, Multiblock PLS-based localized process diagnosis, J. Process Control 15(2005) 295-306.
[32] G.A. Cherry, S.J. Qin, Multiblock principal component analysis based on a combined index for semiconductor fault detection and diagnosis, IEEE Trans. Semicond. Manuf. 19(2) (2006) 159-172.
[33] Z.Q. Ge, Z.H. Song, Two-level multiblock statistical monitoring for plant-wide processes, Korean J. Chem. Eng. 26(6) (2009) 1467-1475.
[34] H. Yue, S.J. Qin, Reconstruction based fault identification using a combined index, Ind. Eng. Chem. Res. 20(2001) 4403-4414.
[35] T. Chen, Y. Sun, Probabilistic contribution analysis for statistical process monitoring:A missing variable approach, Control. Eng. Pract. 17(4) (2009) 469-477.
[36] V. Kariwala, P.E. Odiowei, Y. Cao, T. Chen, A branch and bound method for isolation of faulty variables through missing variable analysis, J. Process Control 20(10) (2010) 1198-1206.
[37] J.A. Westerhuis, S.P. Gurden, A.K. Smilde, Generalized contribution plots inmultivariate statistical process monitoring, Chemom. Intell. Lab. Syst. 51(2000) 95-114.
[38] T. Kourti, J.F. MacGregor, Multivariate SPC methods for process and product monitoring, J. Qual. Technol. 28(1996) 409-428.
[39] R. Dunia, S.J. Qin, Subspace approach tomultidimensional fault identification and reconstruction, AICHE J. 44(8) (1998) 1813-1831.
[40] S.J. Qin, H.H. Yue, R. Dunia, Self-validating inferential sensors with application to air emission monitoring, Ind. Eng. Chem. Res. 36(5) (1997) 1675-1685.
[41] C.F. Alcala, S.J. Qin, Reconstruction-based contribution for process monitoring, Automatica 45(7) (2009) 1593-1600.
[42] J.L. Liu, Fault diagnosis using contribution plots without smearing effect on nonfaulty variables, J. Process Control 22(9) (2012) 1609-1623.
[43] G.Z. Wang, J.C. Liu, Y. Li, Fault diagnosis using kNN reconstruction on MRI variables, J. Chemom. 29(7) (2015) 399-410.
[44] S.J. Qin, Survey on data-driven industrial process monitoring and diagnosis, Annu. Rev. Control. 36(2) (2012) 220-234.
[45] H. Xu, F. Yang, H. Ye,W. Li, P. Xu, A.K. Usadi,Weighted reconstruction-based contribution for improved fault diagnosis, Ind. Eng. Chem. Res. 52(29) (2013) 9858-9870.
[46] L.H. Chiang, E. Russell, R.D. Braatz, Fault detection and diagnosis in industrial systems, Springer Verlag, London, 2001.
[47] R.A. Johnson, D.W. Wichem, Applied multivariate statistical analysis, Prentice Hall, New Jersey, 1992.
[48] A. Alawi, S.W. Choi, E. Martin, J. Morris, Sensor fault identification using weighted combined contribution plots, Fault detection, supervision, and safety of technical processes 2007, pp. 908-913.
[49] J.L. Liu, D.S. Chen, Fault isolation using modified contribution plots, Comput. Chem. Eng. 61(3) (2014) 9-19.
[50] J.M. Lee, C.K. Yoo, S.W. Choi, P.A. Vanrolleghem, I.B. Lee, Nonlinear process monitoring using kernel principal component analysis, Chem. Eng. Sci. 59(2004) 223-234.
[51] J. Yu, S.J. Qin, Multimode process monitoring with Bayesian inference-based finite Gaussian mixture models, AICHE J. 54(7) (2008) 1811-1829.
[52] J. Lee, B. Kang, S. Kang, Integrating independent component analysis and local outlier factor for plant-wide processmonitoring, J. Process Control 21(7) (2011) 1011-1021.