Abstract
The propose of this paper is to introduce a new Kalman Filter based in a Recurrent Neural Network topology (KFRNN) and a recursive Levenberg-Marquardt (L-M) algorithm. Such algorithm is able to estimate the states and parameters of a highly nonlinear continuous fermentation bioprocess in noisy environment. The control scheme is direct adaptive and also contains feedback and feedforward recurrent neural controllers. The proposed control scheme is applied for real-time identification and control of continuous stirred tank bioreactor model, taken from the literature, where a fast convergence, noise filtering and low mean squared error of reference tracking were achieved.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
References
Narendra, K.S., Parthasarathy, K.: Identification and Control of Dynamic Systems Using Neural Networks. IEEE Trans. Neural Networks 1(1), 4–27 (1990)
Hunt, K.J., Sbarbaro, D., Zbikowski, R., Gawthrop, P.J.: Neural Networks for Control Systems - A Survey. Automatica 28(6), 1083–1112 (1992)
Pao, S.A., Phillips, S.M., Sobajic, D.J.: Neural Net Computing and Intelligent Control Systems. International Journal of Control 56, 263–289 (1992)
Baruch, I.S., Escalante, S., Mariaca-Gaspar, C.R.: Identification, Filtering and Control of Nonlinear Plants by Recurrent Neural Networks Using First and Second Order Algorithms of Learning. International Journal of Dynamics of Continuous, Discrete and Impulsive Systems, Series A: Mathematical Analysis, Special Issue on Advances in Neural Networks-Theory and Applications 14 (S!), Part 2, 512–521 (2007) ISSN 1201-3390
Baruch, I.S., Mariaca-Gaspar, C.R., Barrera-Cortes, J.: Recurrent Neural Network Identification and Adaptive Neural Control of Hydrocarbon Biodegradation Processes. In: Hu, X., Balasubramaniam, P. (eds.) Recurrent Neural Networks, pp. 61–88. I-Tech/ARS Press, Croatia (2008) ISBN 978-3-902613-28-8
Asirvadam, V.S., McLoone, S.F., Irwin, G.W.: Parallel and Separable Recursive Levenberg-Marquardt Training Algorithm. In: Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing, pp. 129–138 (2002)
Ngia, L.S., Sjöberg, J., Viberg, M.: Adaptive Neural Nets Filter Using a Recursive Levenberg-Marquardt Search Direction. IEEE Signals, Systems and Computer 1, 697–701 (1998)
Ngia, L.S., Sjöberg, J.: Efficient Training of Neural Nets for Nonlinear Adaptive Filtering Using a Recursive Levenberg Marquardt Algorithm. IEEE Trans. on Signal Processing 48, 1915–1927 (2000)
Schmidt, L.D.: The Engineering of Chemical Reactions. Oxford University Press, New York (1998) ISBN 0-19-510588-5
Liu, S.-R., Yu, J.-S.: Robust Control Based on Neuro-Fuzzy Systems for a Continuous Stirred Tank Reactor. In: Proceedings of the First International Conference on Machine Learning and Cybernetics, Beijing, pp. 1483–1488 (2002)
Zhang, T., Guay, M.: Adaptive Nonlinear Control of Continuously Stirred Tank Reactor Systems. In: Proceedings of the American Control Conference, Arlington, pp. 1274–1279 (2001)
Wan, E., Beaufays, F.: Diagrammatic Method for Deriving and Relating Temporal Neural Networks Algorithms. Neural Computations 8, 182–201 (1996)
Mariaca-Gaspar, C.R.: Topologies, Learning and Stability of Hybrid Neural Networks, Applied for Nonlinear Biotechnological Processes, Ph. D. Thesis, Dept. Automatic Control, CINVESTAV-IPN. Mexico (2009)
Nava, F.R., Baruch, I.S., Poznyak, A., Nenkova, B.: Stability Proofs of Adavanced Recurrent Neural Networks Topology and Learning, Comptes Rendus. Proceedings of the Bulgarian Academy of Sciences 57(1), 27–32 (2004)
Baruch, I.S., Barrera-Cortés, J., Hernández, L.A.: A Fed-Batch Fermentation Process Identification and Direct Adaptive Neural Control with Integral Term. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds.) MICAI 2004. LNCS (LNAI), vol. 2972, pp. 764–773. Springer, Heidelberg (2004)
Baruch, I.S., Georgieva, P., Barrera-Cortes, J., Feyo de Azevedo, S.: Adaptive Recurrent Neural Network Control of Biological Wastewater Treatment. International Journal of Intelligent Systems, Special issue on Soft Computing for Modelling, Simulation and Control of Nonlinear Dynamical Systems 20(2), 173–194 (2005) ISSN 0884-8173
Baruch, I.S., Mariaca-Gaspar, C.R.: A Levenberg-Marquardt Learning Applied for Recurrent Neural Identification and Control of a Wastewater Treatment Bioprocess. International Journal of Intelligent Systems 24, 1094–1114 (2009)
Lightbody, G., Irwin, G.W.: Nonlinear Control Structures Based on Embedded Neural Systems Models. IEEE Trans. Neural Networks 8, 553–557 (1997)
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
Mariaca-Gaspar, CR., Rodríguez, JC.T., Ortiz-Rodríguez, F. (2013). Recurrent Neural Control of a Continuous Bioprocess Using First and Second Order Learning. In: Batyrshin, I., Mendoza, M.G. (eds) Advances in Computational Intelligence. MICAI 2012. Lecture Notes in Computer Science(), vol 7630. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37798-3_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-37798-3_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37797-6
Online ISBN: 978-3-642-37798-3
eBook Packages: Computer ScienceComputer Science (R0)