Abstract
The control and optimization of batch processes is a challenging problem faced by (bio)chemical industry. Traditionally, (full) factorial tests are executed to investigate the effect of the manipulated variables (MV) on the (quality of the) process. Due to their nature, these tests are very time-consuming for batch processes. This paper investigates whether suitable data-driven models for batch optimization and control can be identified from a more limited set of tests.
Based on the results of two case studies, it is concluded that statistical inference models can predict the final quality of batches where the MV changes occur at time points not present in the training data, provided they fall inside of the time range used for training. Furthermore, the models provide accurate predictions for batches with multiple MV changes. This is a valuable result for industrial acceptance because it implies that fewer experiments are required for model identification.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Nomikos, P., MacGregor, J.F.: Monitoring batch processes using multiway principal component analysis. AIChE J. 40(8), 1361–1375 (1994)
Chen, J., Liu, K.-C.: On-line batch process monitoring using dynamic PCA and dynamic PLS models. Chem. Eng. Sci. 57, 63–75 (2002)
Choi, S.W., Martin, E.B., Morris, A.J., Lee, I.-B.: Fault detection based on a maximum likelihood PCA mixture. Ind. Eng. Chem. Res. 55(7), 2316–2327 (2005)
Choi, S.W., Morris, A.J., Lee, I.-B.: Dynamic model-based batch process monitoring. Chem. Eng. Sci. 63(3), 622–636 (2008)
Simoglou, A., Georgieva, P., Martin, E.B., Morris, A.J., de Azevedo, S.F.: On-line monitoring of a sugar crystallization process. Comput. Chem. Eng. 29(6), 1411–1422 (2005)
Hu, K., Yuan, J.: Multivariate statistical process control based on multiway locality preserving projections. J. Process Control 18, 797–807 (2008)
Nomikos, P., MacGregor, J.F.: Multivariate SPC charts for monitoring batch processes. Technometrics 37(1), 41–59 (1995a)
Nomikos, P., MacGregor, J.F.: Multiway partial least squares in monitoring batch processes. Chemom. Intell. Lab. Syst. 30, 97–108 (1995b)
GarcÃa-Muñoz, S., Kourti, T., MacGregor, J.F.: Model predictive monitoring for batch processes. Ind. Eng. Chem. Res. 43, 5929–5941 (2004)
Birol, G., Ündey, C., Çinar, A.: A modular simulation package for fed-batch fermentation: penicillin production. Comput. Chem. Eng. 26, 1553–1565 (2002)
Ündey, C., Ertunç, S., Çinar, A.: Online batch/fed-batch process performance monitoring, quality prediction, and variable-contribution analysis for diagnosis. Ind. Eng. Chem. Res. 42, 4645–4658 (2003)
Gins, G., Pluymers, B., Smets, I.Y., Espinosa, J., Van Impe, J.F.M.: Prediction of batch-end quality for an industrial polymerization process. In: Perner, P. (ed.) ICDM 2011. LNCS (LNAI), vol. 6870, pp. 314–328. Springer, Heidelberg (2011)
Gins, G., Van den Kerkhof, P., Van Impe, J.F.M.: Hybrid derivative dynamic time warping for online industrial batch-end quality estimation. Ind. Eng. Chem. Red. 51(17), 6071–6084 (2012)
Flores-Cerrillo, J., MacGregor, J.F.: Latent variable MPC for trajectory tracking in batch processes. J. Process Contr. 15, 651–663 (2005)
Golshan, M., MacGregor, J.F., Bruwer, M.-J., Mhaskar, P.: Latent Variable Model Predictive Control (LV-MPC) for trajectory tracking in batch processes. J. Process Control 20, 538–550 (2010)
Wan, J., Marjanovic, O., Lennox, B.: Disturbance rejection for the control of batch end-product quality using latent variable models. J. Process Control 22, 643–652 (2012)
McCready, C.: Model Predictive Multivariate Control (MPMC). In: 2nd European Conference on Process Analytics and Control Technology (EuroPACT 2011), Glasgow (United Kingdom), p. 82 (2011)
Geladi, P., Kowalski, B.R.: Partial least-squares regression: A tutorial. Anal. Chim. Acta 185, 1–17 (1986)
Arteaga, F., Ferrer, A.: Dealing with missing data in MSPC: several methods, different interpretations, some examples. J. Chemom. 16, 408–418 (2002)
Ramaker, H., Sprang, E.N.M., Westerhuis, J.A., Smilde, A.K.: Fault detection properties of global, local and time evolving models for batch process monitoring. J. Process Control 15, 799–805 (2005)
Camacho, J., Picó, J., Ferrer, A.: Bilinear modelling of batch processes. Part I: Theoretical discussion. J. Chemometr. 22, 299–308 (2008)
Faggiana, A., Faccoa, P., Doplicherb, F., Bezzoa, F., Baroloa, M.: Multivariate statistical real-time monitoring of an industrial fed-batch process for the production of specialty chemicals. Chem. Eng. Res. Des. 87, 325–334 (2009)
Gins, G., Vanlaer, J., Van Impe, J.F.M.: Online batch-end quality estimation: does laziness pay off? In: Quevedo, J., Escobet, T., Puig, V. (eds.) Proceedings of the 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Processes (SafeProcess 2009), pp. 1246–1251 (2009)
Li, B., Morris, J., Martin, E.: Model selection for partial least squares regression. Chemometr. Intell. Lab. Syst. 64, 79–89 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gins, G., Vanlaer, J., Van den Kerkhof, P., Van Impe, J.F.M. (2013). Extending Statistical Models for Batch-End Quality Prediction to Batch Control. In: Perner, P. (eds) Advances in Data Mining. Applications and Theoretical Aspects. ICDM 2013. Lecture Notes in Computer Science(), vol 7987. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39736-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-39736-3_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39735-6
Online ISBN: 978-3-642-39736-3
eBook Packages: Computer ScienceComputer Science (R0)