Abstract
This chapter deals with the modelling, simulation, and control of a separator unit used in the biodiesel industry. While mechanistic modelling provides an accurate way to describe the system dynamics, it is an iterative and computationally burdensome process that arises from the need to determine the liquid-liquid equilibria via the flash calculation. These disadvantages would preclude the use of mechanistic models for process optimization or model based control. In order to overcome this problem, an alternative strategy is here suggested. It consists of maintaining the mechanistic model structure and to approximate the iterative calculations with an artificial neural network. The general approach for dataset consideration and neural network training and validation are presented. The quality of the resulting neural network is demonstrated to be high while the computation burden is significantly reduced. Finally, the obtained grey-box model is used in order to carry out dynamic simulation and control tests of the unit.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Note that the molar fraction of the ester is linearly dependent of the molar fractions of the two other components.
References
Bambase, M., Nakamura, N., Tanaka, J., Matsumura, M.: Kinetics of hydroxide-catalyzed methanolysis of crude sunflower oil for the production of fuel-grade methyl esters. J. Chem. Technol. Biotechnol. 82(3), 273–280 (2007). doi:10.1002/jctb.1666
Bell, B.M.: CppAD: a package for C++ algorithmic differentiation. Computational Infrastructure for Operations Research COIN-OR (http://www.coin-or.org/CppAD) (2012)
Biegler, L.: Real-Time PDE-Constrained Optimization. Computational Science and Engineering. Society for Industrial and Applied Mathematics, Philadelphia (2007)
Bishop, C.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)
Brásio, A.S., Romanenko, A., Santos, L.O., Fernandes, N.C.: Modeling the effect of mixing in biodiesel production. Bioresour. Technol. 102(11), 6508–6514 (2011). doi:10.1016/j.biortech.2011.03.090
Brásio, A.S., Romanenko, A., Leal, J., Santos, L.O., Fernandes, N.C.: Nonlinear model predictive control of biodiesel production via transesterification of used vegetable oils. J. Process Control 23(10), 1471–1479 (2013). doi:10.1016/j.jprocont.2013.09.023
Chaturvedi, D.: Soft Computing: Techniques and Its Applications in Electrical Engineering. Studies in Computational Intelligence. Springer, Berlin/Heidelberg (2008)
Du, X., Liu, L., Xi, X., Yang, L., Yang, Y., Liu, Z., Zhang, X., Yu, C., Du, J.: Back pressure prediction of the direct air cooled power generating unit using the artificial neural network model. Appl. Therm. Eng. 31(14–15), 3009–3014 (2011). doi:10.1016/j.applthermaleng.2011.05.034
Fredenslund, A., Jones, R.L., Prausnitz, J.M.: Group-contribution estimation of activity coefficients in nonideal liquid mixtures. AIChE J. 21(6), 1086–1099 (1975). doi:10.1002/aic.690210607
Hagan, M., Demuth, H., Beale, M.: Neural Network Design. Electrical Engineering Series. Brooks/Cole, Boston (1996)
Lobo, L.Q., Ferreira, A.G.M.: Termodinâmica e Propriedades Termofísicas – Volume I: Termodinâmica das Fases. Imprensa da Universidade de Coimbra, Coimbra (2006)
Schmid, M.D.: A neural network package for Octave – User’s Guide (2009). http://www.plexso.com/61_octave/neuralNetworkPackageForOctaveDevelop.pdf. Consulted in March 2013
Sjöberg, J.: Neural Networks – Train and analyze neural networks to fit your data. Technical report, Wolfram Research (2005). http://media.wolfram.com/documents/NeuralNetworksDocumentation.pdf. Consulted in March 2013
Walther, A., Griewank, A.: Getting started with ADOL-C. In: Naumann, U., Schenk, O. (eds.) Combinatorial Scientific Computing. Chapman-Hall CRC Computational Science, chap. 7, pp. 181–202. CRC Press, Boca Raton (2012)
Yegnanarayana, B.: Artificial Neural Networks. Prentice-Hall Of India Pvt. Limited, New Delhi (2004)
Acknowledgements
This work had financial support from QREN through Operational Programme Mais Centro and from the European Union via FEDER under APCFAME project with reference 3509/2009, a consortium between Ciengis, SA and the University of Coimbra. The authors also express their thanks to Vitor Marques for access to his preliminary studies on equilibrium data.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Brásio, A.S.R., Romanenko, A., Fernandes, N.C.P. (2015). Development of a Numerically Efficient Biodiesel Decanter Simulator. In: Almeida, J., Oliveira, J., Pinto, A. (eds) Operational Research. CIM Series in Mathematical Sciences, vol 4. Springer, Cham. https://doi.org/10.1007/978-3-319-20328-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-20328-7_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20327-0
Online ISBN: 978-3-319-20328-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)