Data-driven monitoring for stochastic systems and its application on batch process. (English) Zbl 1278.93259

Yin, Shen; Ding, Steven X.; Sari, Adel Haghani Abandan; Hao, Haiyang

Int. J. Syst. Sci. 44, No. 7, 1366-1376 (2013).

Summary: Batch processes are characterized by a prescribed processing of raw materials into final products for a finite duration and play an important role in many industrial sectors due to the low-volume and high-value products. Process dynamics and stochastic disturbances are inherent characteristics of batch processes, which cause monitoring of batch processes a challenging problem in practice. To solve this problem, a subspace-aided data-driven approach is presented in this article for batch process monitoring. The advantages of the proposed approach lie in its simple form and its abilities to deal with stochastic disturbances and process dynamics existing in the process. The kernel density estimation, which serves as a non-parametric way of estimating the probability density function, is utilized for threshold calculation. An industrial benchmark of fed-batch penicillin production is finally utilized to verify the effectiveness of the proposed approach.

MSC:

93E10	Estimation and detection in stochastic control theory
93C73	Perturbations in control/observation systems
93C55	Discrete-time control/observation systems

Keywords:

process monitoring; data-driven design approach; batch process; test statistics; kernel density estimation

References:

[1]	DOI: 10.1016/S0098-1354(02)00127-8
[2]	Blanke M, Diagnosis and Fault-Tolerant Control (2006)
[3]	DOI: 10.1214/10-AOS799 · Zbl 1200.62029
[4]	DOI: 10.1016/S0009-2509(01)00366-9
[5]	DOI: 10.1007/978-1-4615-5149-2
[6]	DOI: 10.1007/978-1-4471-0347-9
[7]	DOI: 10.1080/00207720600784486 · Zbl 1105.93058
[8]	Ding S, Model-based Fault Diagnosis Techniques (2008)
[9]	Ding S, in Proceedings of the 18th IFAC World Congress (2011)
[10]	Ding S, in Proceedings 16th IFAC World Congress (2005)
[11]	DOI: 10.1016/j.jprocont.2009.07.005
[12]	DOI: 10.1002/aic.690420810
[13]	DOI: 10.1021/ie900720w
[14]	DOI: 10.1016/S0959-1524(99)00030-X
[15]	Gertler J, Fault Detection and Diagnosis in Engineering Systems (1998)
[16]	DOI: 10.1080/00207720903513319 · Zbl 1209.93054
[17]	DOI: 10.1080/00207721003653666 · Zbl 1233.93064
[18]	DOI: 10.1109/TCST.2009.2026285
[19]	Isermann R, Fault Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance (2006)
[20]	DOI: 10.1016/j.chemolab.2010.02.004
[21]	DOI: 10.1016/S0098-1354(03)00151-0
[22]	DOI: 10.1016/j.compchemeng.2004.02.036
[23]	Ljung L, System Identification: Theory for the User (1987)
[24]	DOI: 10.1016/0959-1524(96)00010-8
[25]	DOI: 10.1016/j.jprocont.2010.06.018
[26]	DOI: 10.1002/aic.690400809
[27]	DOI: 10.1016/0169-7439(95)00043-7
[28]	DOI: 10.1007/978-1-4613-0465-4
[29]	Patton R, Issues of Fault Diagnosis for Dynamic Systems (2000)
[30]	DOI: 10.1016/j.compchemeng.2006.05.045
[31]	DOI: 10.1016/S0169-7439(98)00024-0
[32]	DOI: 10.1109/TIE.2010.2053339
[33]	DOI: 10.1109/TNN.2010.2090669
[34]	DOI: 10.1109/TCSI.2011.2112594
[35]	DOI: 10.1109/TAC.2008.930199 · Zbl 1367.93659
[36]	Silverman B, Density Estimation for Statistics and Data Analysis (1986) · Zbl 0617.62042
[37]	DOI: 10.1016/S0098-1354(02)00160-6
[38]	DOI: 10.1016/S0959-1524(02)00016-1
[39]	Wang Z, Accepted for IEEE Transactions on Automatic Control (2011)
[40]	DOI: 10.1016/j.jprocont.2010.07.002
[41]	DOI: 10.1016/j.chemolab.2004.02.002
[42]	DOI: 10.1155/2008/849546 · Zbl 05759210
[43]	Zhong MY, International Journal of Systems Science (2011)