Home // ADAPTIVE 2012, The Fourth International Conference on Adaptive and Self-Adaptive Systems and Applications // View article

Adaptive Control of a Biomethanation Process using Neural Networks

Authors:
Dorin Sendrescu
Elena Bunciu

Keywords: neural networks; biotechnological process; adaptive control

Abstract:
This paper deals with the design of an adaptive control scheme for the regulation of the acetate concentration in a biomethanation process with production of methane gas that takes place inside a Continuous Stirred Tank Bioreactor. The control structure is based on the nonlinear model of the process whose parameters are identified using the distributions method and the unknown reaction rates are estimated using a radial basis neural network. These estimations are then used in a nonlinear model predictive control (NMPC) scheme. Minimization of the cost function is realized using the Levenberg–Marquardt numerical optimization method. The effectiveness and performance of the proposed control strategy is illustrated by numerical simulations. The simulation results obtained with a continuous stirred tank reactor plant model confirmed the good quality of the control.

Pages: 75 to 79

Copyright: Copyright (c) IARIA, 2012

Publication date: July 22, 2012

Published in: conference

ISSN: 2308-4146

ISBN: 978-1-61208-219-6

Location: Nice, France

Dates: from July 22, 2012 to July 27, 2012