Considering the huge number of variables in plant-wide process monitoring and complex relationships(linear, nonlinear, partial correlation, or independence) among these variables, multivariate statistical process monitoring(MSPM) performance may be deteriorated especially by the independent variables. Meanwhile, whether related variables keep high concordance during the variation process is still a question. Under this circumstance, a multi-block technology_x000D_ based on mathematical statistics method, Kullback-Leibler Divergence, is proposed to put the variables having similar statistical characteristics into the same block, and then build principal component analysis (PCA) models in each lowdimensional subspace. Bayesian inference is also employed to combine the monitoring results from each sub-block into the final monitoring statistics. Additionally, a novel fault diagnosis approach is developed for fault identification._x000D_ The superiority of the proposed method is demonstrated by applications on a simple simulated multivariate process and the Tennessee Eastman benchmark process.

Multi-block PCA Kullback-Leibler Divergence Bayesian Inference Plant-wide Process Monitoring

Chiang LH, Braatz RD, Russell EL, Fault detection and diagnosis in industrial systems, Springer (2001)
Venkatasubramanian V, Rengaswamy R, Kavuri SN, Yin K, Comput. Chem. Eng., 27, 3 (2003)
Kresta JV, Macgregor JF, Marlin TE, Can. J. Chem. Eng., 69, 1 (1991)
Albert S, Kinley RD, TRENDS in Biotechnol., 19, 2 (2001)
Joe Qin S, J. Chemometrics, 17, 8 (2003)
Kourti T, International Journal of Adaptive Control and Signal Processing, 19, 4 (2005)
Lee C, Lee IB, Korean J. Chem. Eng., 25(2), 203 (2008)
Jolliffe I, Principal component analysis, Wiley Online Library (2005)
Zou H, Hastienand T, Tibshirani R, Journal of Computational and Graphical Statistics, 15, 2 (2006)
Croux C, Haesbroeck G, Biometrika, 87, 3 (2000)
Han K, Park KJ, Chae H, Yoon ES, Korean J. Chem. Eng., 25(1), 13 (2008)
Hyvarinen A, Hurri J, Hoyer PO, Independent component analysis, in: Natural Image Statistics, Springer, 151 (2009)
Hyvarinen A, Oja E, Neural Networks, 13, 4 (2000)
Kim MH, Yoo CK, Korean J. Chem. Eng., 25(5), 947 (2008)
Lee JM, Yoo C, Lee IB, Journal of Process Control, 14, 5 (2004)
Ge Z, Song Z, Korean J. Chem. Eng., 26, 6 (2009)
Jia F, Martin E, Morris A, Int. J. Syst. Sci., 31, 11 (2000)
Scholz M, Kaplan F, Guy CL, Kopka J, Selbig J, Bioinformatics, 21, 20 (2005)
Ravi V, Pramodh C, Int. J. Information and Decision Sci., 2, 1 (2010)
Bakshi BR, AIChE J., 44, 7 (1998)
Qin SJ, Valle S, Piovoso MJ, J. Chemometrics, 15, 9 (2001)
Zhang Y, Ma C, Chem. Eng. Res. Design, 90, 5 (2012)
Lee DS, Vanrolleghem PA, Biotechnol. Bioeng., 82, 4 (2003)
Cherry GA, Qin SJ, Semiconductor Manufacturing, IEEE Transactions on, 19, 2 (2006)
Ge Z, Zhang M, Song Z, Journal of Process Control, 20, 5 (2010)
Tong CD, Song Y, Yan XF, Ind. Eng. Chem. Res., 52(29), 9897 (2013)
Bishop CM, Nasrabadi NM, Pattern recognition and machine learning, Springer New York (2006)
Miller P, Swanson R, Heckler CE, Applied Mathematics and Computer Science, 8 (1998)
Westerhuis JA, Gurden SP, Smilde AK, Chemometrics and Intelligent Laboratory Systems, 51, 1 (2000)
De Persis C, Isidori A, Automatic Control, IEEE Transactions on, 46, 6 (2001)
Dunia R, Joe Qin S, AIChE J., 44, 8 (1998)
Alcala CF, Qin SJ, Automatica, 45, 7 (2009)
Abdi H, Williams LJ, Wiley Interdisciplinary Reviews: Computational Statistics, 2, 4 (2010)
Kullback S, The American Statistician, 41, 4 (1987)
Burnham KP, Anderson DR, Model selection and multi-model inference: A practical information-theoretic approach, Springer (2002)
Downs JJ, Vogel EF, Comput. Chem. Eng., 17, 3 (1993)