Direct adaptive control of an anaerobic depollution bioprocess using radial basis neural networks
KES'10 Proceedings of the 14th international conference on Knowledge-based and intelligent information and engineering systems: Part II
| Hi-index | 0.00 |
This paper presents the design and the analysis of some nonlinear adaptive control strategies for a class of anaerobic depollution processes that are carried out in continuous stirred tank bioreactors. The controller design is based on the input-output linearization technique. The adaptive control structure is based on the nonlinear model of the process and is combined with a state observer and a parameter estimator which play the role of the software sensors for the on-line estimation of biological states and parameter variables of interest of the bioprocess. The resulted control methods are applied in depollution control problem in the case of the anaerobic digestion bioprocess for which dynamical kinetics are strongly nonlinear and not exactly known, and not all the state variables are measurable. The effectiveness and performance of both estimation and control algorithms are illustrated by simulation results.