Neuro-fuzzy control strategy for methane production in an anaerobic process

In this paper, a neuro-fuzzy control strategy composed by a neural observer and fuzzy supervisors for an anaerobic digestion process is proposed in order to maximize methane production. A nonlinear discrete-time recurrent high order neural observer (RHONO) is used to estimate biomass concentration and substrate degradation in a continuous stirred tank reactor. A Takagi-Sugeno supervisor controller based on the estimation of biomass, selects and applies the most adequate control action, allowing a smooth switching between open loop and closed loop. The control law calculates dilution rate and bicarbonate rate based on speed-gradient inverse optimal neural control. Finally, Takagi-Sugeno supervisors calculate reference trajectories for the system states, and gain scheduling for the dilution rate control law at different operating points of the process. The applicability of the proposed scheme is illustrated via simulations.

[1]  E. Sánchez,et al.  Inverse optimal control for discrete‐time nonlinear systems via passivation , 2014 .

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

[3]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[4]  N. Houbak,et al.  Technoeconomic analysis of a methanol plant based on gasification of biomass and electrolysis of water , 2010 .

[5]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Edgar N. Sánchez,et al.  A New Neural Observer for an Anaerobic Bioreactor , 2010, Int. J. Neural Syst..

[7]  Oscar Castillo,et al.  A new method for adaptive model-based control of non-linear dynamic plants using a neuro-fuzzy-fractal approach , 2001, Soft Comput..

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

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

[10]  Kazuo Tanaka,et al.  Fuzzy Control Systems Design and Analysis: A Linear Matrix Inequality Approach , 2008 .

[11]  D. Goswami,et al.  Thermodynamic optimization of biomass gasifier for hydrogen production , 2007 .

[12]  Alexander G. Loukianov,et al.  Real-Time Recurrent Neural State Estimation , 2011, IEEE Transactions on Neural Networks.

[14]  Simon A Smith,et al.  A biogas meter with adjustable resolution and minimal back-pressure. , 2008, Bioresource technology.

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

[16]  Ivan Simeonov,et al.  Parameter and State Estimation of an Anaerobic Digestion Model in Laboratory and Pilot-Scale Conditions , 2011 .

[17]  Alexander G. Loukianov,et al.  Speed-gradient inverse optimal control for discrete-time nonlinear systems , 2011, IEEE Conference on Decision and Control and European Control Conference.

[18]  Rudolf Kruse,et al.  Fuzzy Control , 2015, Handbook of Computational Intelligence.

[19]  G Herrera Ruiz,et al.  Automatic volumetric gas flow meter for monitoring biogas production from laboratory-scale anaerobic digester , 2010 .

[20]  Eric D. Larson,et al.  Methanol and hydrogen from biomass for transportation , 1995 .

[21]  C. Abdallah,et al.  Optimal discrete-time control for non-linear cascade systems , 1998 .

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

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

[24]  S. Carlos-Hernandez,et al.  Modelling and Analysis of the Anaerobic Digestion Process , 2004 .

[25]  André Faaij,et al.  Future prospects for production of methanol and hydrogen from biomass , 2002 .