ArticlesNo Access

A NEW NEURAL OBSERVER FOR AN ANAEROBIC BIOREACTOR

Department of Electrical Engineering and Computer Sciences, Cinvestav del IPN, Unidad Guadalajara, Av. Científica 1145, Col El Bajío, Zapopan, Jalisco 45015, Mexico

Search for more papers by this author

S. CARLOS-HERNANDEZ

Grupo de Investigación en Recursas Naturales y Energéticos, Cinvestav del IPN, Unidad Saltillo, Carr.Saltillo-Mty Km 13, Ramos Arizpe, Coahuila 25900, Mexico

Search for more papers by this author

, and

E. N. SANCHEZ

Department of Electrical Engineering and Computer Sciences, Cinvestav del IPN, Unidad Guadalajara, Av. Científica 1145, Col El Bajío, Zapopan, Jalisco 45015, Mexico

Search for more papers by this author

https://doi.org/10.1142/S0129065710002267Cited by:12 (Source: Crossref)

Abstract

In this paper, a recurrent high order neural observer (RHONO) for anaerobic processes is proposed. The main objective is to estimate variables of methanogenesis: biomass, substrate and inorganic carbon in a completely stirred tank reactor (CSTR). The recurrent high order neural network (RHONN) structure is based on the hyperbolic tangent as activation function. The learning algorithm is based on an extended Kalman filter (EKF). The applicability of the proposed scheme is illustrated via simulation. A validation using real data from a lab scale process is included. Thus, this observer can be successfully implemented for control purposes.

Keywords:

References

K. F. Roos , Profitable alternatives for regulatory impacts on livestock waste management , National Livestock, Poultry and Aquacultural Waste Management National Workshop ( USDA Extension Service , Kansas, MI , 1991 ) . Google Scholar
S. Carlos-Hernández et al. , Modeling and analysis of the anaerobic digestion process , Proceedings of IFAC Symposium on Structures Systems and Control ( Oaxaca, Mexico , 2004 ) . Google Scholar
K. Yamuna Rani and V. S. Ramachandra Rao, Bioprocess Engineering 21, 77 (1999), DOI: 10.1007/PL00009066. Google Scholar
J. B. Van Lieret al., Water Science and Technology 43(1), 1 (2001). Medline, Web of Science, Google Scholar
V. Alcaraz-González and V. González-Álvarez, Selected Topics in Dynamics and Control of Chemical and Biological Processes (Springer Berlin, Heidelberg, 2007) pp. 119–164. Google Scholar
G. Bastin and D. Dochain , On-Line Estimation and Adaptive Control of Bioreactors ( Elsevier Science Publications , Amsterdam , 1990 ) . Google Scholar
O. Bernard and J. L. Gouzé, Journal of Process Control 4(7), 765 (2003). Google Scholar
V. Alcaraz-Gonzalezet al., Water Research 36(10), 2515 (2004), DOI: 10.1016/S0043-1354(01)00466-3. Medline, Web of Science, Google Scholar
D. Theilliolet al., Control Engineering Practice 11(9), 1007 (2003), DOI: 10.1016/S0967-0661(02)00230-7. Web of Science, Google Scholar
A. Mulleret al., Water Research 31(12), 3157 (1997), DOI: 10.1016/S0043-1354(97)00215-7. Web of Science, Google Scholar
E. Giraldo-Gomez and M. Duque , Automatic startup of a high rate anaerobic reactor using a fuzzy logic control system , Fifth Latin-American Workshop-Seminar in Wastewater Anaerobic Treatment ( Viña del Mar , Chile , 1998 ) . Google Scholar
O. Bernardet al., Water Science and Technology 43(7), 175 (2001). Medline, Web of Science, Google Scholar
A. Puñalet al., Water Science and Technology 43(7), 191 (2001). Medline, Web of Science, Google Scholar
S. Carlos-Hernándezet al., Control Engineering Practice 17, 690 (2009). Web of Science, Google Scholar
D. Urrego-Patarroyo et al. , Recurrent neural networks observer for anaerobic processes , XIII Latin-american Congress of Automatic Control ( Mérida , Venezuela , 2008 ) . Google Scholar
A. S. Poznyak et al., Differential Neural Networks for Robust Nonlinear Control, World Scientific Publishing Co. (Singapore, 2001) . Google Scholar
L. J. Ricalde and E. N. Sanchez , Inverse optimal nonlinear high order recurrent neural observer , International Joint Conference on Neural Networks ( Montreal, Canada , 2005 ) . Google Scholar
G. G. Rigatos, International Journal of Neural Systems 18(4), 305 (2008), DOI: 10.1142/S0129065708001610. Link, Web of Science, Google Scholar
G. Puscasuet al., International Journal of Neural Systems 19(2), 115 (2009), DOI: 10.1142/S0129065709001884. Link, Web of Science, Google Scholar
F. Monnet , An Introduction to Anaerobic Digestion of Organic Wastes ( Remade Scotland , 2003 ) . Google Scholar
Y. Chenet al., Bioresource Technology 99(10), 4044 (2007), DOI: 10.1016/j.biortech.2007.01.057. Medline, Web of Science, Google Scholar
S. Carlos-Hernández, Integrated intelligent control strategy for wastewater treatment plants by anaerobic digestion, in French, Ph. D. Thesis, INPG (France, 2005) . Google Scholar
V. Ottonet al., Biochemical Engineering Journal 4, 129 (2000), DOI: 10.1016/S1369-703X(99)00044-3. Web of Science, Google Scholar
A. Rozzi, Transactions Instrumentation, Modelling and Control 6(3), 153 (1984), DOI: 10.1177/014233128400600306. Google Scholar
J. F. Beteau, An industrial wastewater treatment bioprocess modelling and control, in French. Ph. D. Thesis, INPG (France, 1992) . Google Scholar
http://www.bluesens.de, visited on April 13th 2009 . Google Scholar
S. Haykin , Neural Networks: A Comprehensive Foundation , 2nd edn. ( Prentice Hall , New Jersey, USA , 1999 ) . Google Scholar
E. N. Sanchezet al., Dynamics of Continuous, Discrete and Impulsive Systems Series B (DCDIS_B) 13, 1 (2007). Web of Science, Google Scholar
B. Zhanget al., International Journal of Neural Systems 17(3), 207 (2007), DOI: 10.1142/S012906570700107X. Link, Web of Science, Google Scholar
B. Zhanget al., International Journal of Neural Systems 16(6), 473 (2006), DOI: 10.1142/S0129065706000871. Link, Web of Science, Google Scholar
M. Gao, International Journal of Neural Systems 18(3), 207 (2008), DOI: 10.1142/S0129065708001531. Link, Web of Science, Google Scholar
M. Liu and S. Zhang, International Journal of Neural Systems 18(5), 443 (2008), DOI: 10.1142/S0129065708001701. Link, Web of Science, Google Scholar
A. M. A. Haidaret al., International Journal of Neural Systems 19(6), 473 (2009), DOI: 10.1142/S0129065709002178. Link, Web of Science, Google Scholar
G. A. Rovithakis and M. A. Chistodoulou , Adaptive Control with Recurrent High-Order Neural Networks ( Springer-Verlag , Berlin, Germany , 2000 ) . Google Scholar
E. N. Sanchez and A. Y. Alanís , Neural Networks: Fundamental Concepts and Applications to Automatic Control ( Pearson Education , Madrid, Spain , 2006 ) . Google Scholar
E. N. Sanchez et al. , Discrete Time High Order Neural Control Trained with Kalman Filtering ( Springer-Verlag , Germany , 2008 ) . Google Scholar
R. J. Williams and D. Zipser, Neural Computation 1, 270 (1989), DOI: 10.1162/neco.1989.1.2.270. Web of Science, Google Scholar
C. Leunga and L. Chan, Neural Networks 16, 223 (2003). Medline, Web of Science, Google Scholar
M. D. Asaduzzamanet al., International Journal of Neural Systems 19(6), 437 (2009), DOI: 10.1142/S0129065709002130. Link, Web of Science, Google Scholar
H. T. Huynhet al., International Journal of Neural Systems 18(5), 433 (2008), DOI: 10.1142/S0129065708001695. Link, Web of Science, Google Scholar
G. Grossi, International Journal of Neural Systems 19(4), 241 (2009), DOI: 10.1142/S0129065709001999. Link, Web of Science, Google Scholar
K. A. Kramer and S. C. Stubberud, International Journal of Neural Systems 16(1), 207 (2006), DOI: 10.1142/S0129065706000457. Google Scholar
Y. Song and J. W. Grizzle, Journal of Mathematical Systems, Estimation and Control 5(1), 59 (1995). Web of Science, Google Scholar
S. Haykin , Kalman Filtering and Neural Networks ( John Wiley & Sons , N.Y., USA , 2001 ) . Google Scholar
D. G. Luenberger, IEEE Transactions on Automatic Control 16(6), 596 (1972), DOI: 10.1109/TAC.1971.1099826. Web of Science, Google Scholar