Experimental results in model reference adaptive estimation and control of a fermentation process

International audienceWe propose a general methodology to develop a hybrid neural model for a wide range of biotechnological processes. The hybrid neural modelling approach combines the flexibility of a neural network representation of unknown process kinetics with a global mass-balance based process description. The hybrid model is built in such a way that its trajectories keep their physical and biological meaning (mass balance, positivity of the concentrations, boundness, saturation or inhibition of kinetics) even far from the identification data conditions. We examine the constraints (a priori knowledge) that must be satisfied by the model and that provide additional conditions to be imposed on the neural network. We illustrate our approach with various biotechnological processes showing how to select the appropriate neural network architecture. The method is detailed for modelling an anaerobic wastewater treatment bioreactor using experimental data

show abstract

“…to an alcoholic fermentation process (Maher et al, 1995). to an alcoholic fermentation process (Maher et al, 1995).…”

Section: Definitions Recalls and Motivationmentioning

confidence: 99%

“…Example 4 Let us consider the example of alcoholic fermentation process (Maher et al, 1995), where the growth of the yeast Saccharomyces cerevisiae (X) is known to be enhanced by the glucose concentration (S) until saturation.…”

Section: Integration Of the Biological Knowledge In The Neural Networkmentioning

confidence: 99%