A New Neural Observer for an Anaerobic Bioreactor

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.

[1]  J. Grizzle,et al.  The Extended Kalman Filter as a Local Asymptotic Observer for Nonlinear Discrete-Time Systemsy , 1995 .

[2]  O Bernard,et al.  Advanced monitoring and control of anaerobic wastewater treatment plants: software sensors and controllers for an anaerobic digester. , 2001, Water science and technology : a journal of the International Association on Water Pollution Research.

[3]  Aini Hussain,et al.  An Intelligent Load Shedding Scheme Using Neural Networks and Neuro-Fuzzy , 2009, Int. J. Neural Syst..

[4]  J. Grizzle,et al.  The Extended Kalman Filter as a Local Asymptotic Observer for Nonlinear Discrete-Time Systems , 1992 .

[5]  Meiqin Liu,et al.  An LMI Approach to Design Hinfinity Controllers for Discrete-Time Nonlinear Systems Based on Unified Models , 2008, Int. J. Neural Syst..

[6]  Shengyuan Xu,et al.  Delay-Dependent Robust Exponential Stability for Uncertain Recurrent Neural Networks with Time-Varying Delays , 2007, Int. J. Neural Syst..

[7]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[8]  D. Dochain,et al.  On-Line Estimation and Adaptive Control of Bioreactors , 2013 .

[9]  Gerasimos G. Rigatos.  Adaptive Fuzzy Control with Output Feedback for H∞ Tracking of SISO Nonlinear Systems , 2008, Int. J. Neural Syst..

[10]  Alexandru Stancu,et al.  Nonlinear System Identification Based on Internal Recurrent Neural Networks , 2009, Int. J. Neural Syst..

[11]  Yonggwan Won,et al.  An Improvement of Extreme Learning Machine for Compact Single-Hidden-Layer Feedforward Neural Networks , 2008, Int. J. Neural Syst..

[12]  Giuliano Grossi,et al.  Adaptiveness in Monotone Pseudo-Boolean Optimization and Stochastic Neural Computation , 2009, Int. J. Neural Syst..

[13]  Xuyang Lou,et al.  Robust Exponential Stability of Markovian Jumping Neural Networks with Time-Varying Delay , 2008, Int. J. Neural Syst..

[14]  K. Yamuna Rani,et al.  Control of fermenters : a review , 1999 .

[15]  E Roca,et al.  Advanced monitoring and control of anaerobic wastewater treatment plants: diagnosis and supervision by a fuzzy-based expert system. , 2001, Water science and technology : a journal of the International Association on Water Pollution Research.

[16]  Kazuyuki Murase,et al.  Faster Training Using Fusion of Activation Functions for Feed Forward Neural Networks , 2009, Int. J. Neural Syst..

[17]  Shengyuan Xu,et al.  Relaxed Stability Conditions for Delayed Recurrent Neural Networks with Polytopic Uncertainties , 2006, Int. J. Neural Syst..

[18]  A. Rozzi,et al.  Modelling and control of anaerobic digestion processes , 1984 .

[19]  Jérôme Harmand,et al.  On-line estimation of unmeasured inputs for anaerobic wastewater treatment processes , 2003 .

[20]  J. Grizzle,et al.  The Extended Kalman Filter as a Local Asymptotic Observer for Nonlinear Discrete-Time Systems , 1992, 1992 American Control Conference.

[21]  Edgar N. Sanchez,et al.  Fuzzy observers for anaerobic WWTP: Development and implementation , 2009 .

[22]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[23]  Andrew Chi-Sing Leung,et al.  Dual extended Kalman filtering in recurrent neural networks , 2003, Neural Networks.

[24]  J Harmand,et al.  Software sensors for highly uncertain WWTPs: a new approach based on interval observers. , 2002, Water research.

[25]  F. Monnet,et al.  An Introduction to Anaerobic Digestion of Organic Wastes , 2003 .

[26]  V. Alcaraz-González,et al.  Robust Nonlinear Observers for Bioprocesses: Application to Wastewater Treatment , 2007 .

[27]  Stefano Marsili-Libelli,et al.  Fuzzy control of disturbances in a wastewater treatment process , 1997 .

[28]  A Tilche,et al.  New perspectives in anaerobic digestion. , 2001, Water science and technology : a journal of the International Association on Water Pollution Research.

[29]  D. Luenberger.  An introduction to observers , 1971 .

[30]  F. Delpech,et al.  Axial dispersion of liquid in fluidised bed with external recycling: two dynamic modelling approaches with a view to control , 2000 .

[31]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[32]  K. S. Creamer,et al.  Inhibition of anaerobic digestion process: a review. , 2008, Bioresource technology.

[33]  Alexander G. Loukianov,et al.  Discrete-Time High Order Neural Control - Trained with Kaiman Filtering , 2010, Studies in Computational Intelligence.

[34]  Kathleen A. Kramer,et al.  Analysis and Implementation of a Neural Extended Kalman Filter for Target Tracking , 2006, Int. J. Neural Syst..

[35]  Jean-Luc Gouzé,et al.  Closed loop observers bundle for uncertain biotechnological models , 2004 .

[36]  Manolis A. Christodoulou,et al.  Adaptive Control with Recurrent High-order Neural Networks , 2000, Advances in Industrial Control.

[37]  E.N. Sanchez,et al.  Inverse optimal nonlinear recurrent high order neural observer , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[38]  Alexander S. Poznyak,et al.  Differential Neural Networks for Robust Nonlinear Control , 2004, IEEE Transactions on Neural Networks.