A neural‐network based model of bioreaction kinetics

Abstract

A neural-network based model of the kinetics in a fermentation process is presented. In the development and application 124

Hybrid semi-parametric modeling in process systems engineering: Past, present and future

“…for the modeling of yeast fermentations (Beluhan & Beluhan, 2000;Boareto, De Souza, Valero, & Valdman, 2007;Eslamloueyan & Setoodeh, 2011;Mazutti et al, 2010;Peres et al, 2001;Saraceno et al, 2010;Saxen & Saxen, 1996;Schubert et al, 1994aSchubert et al, , 1994b, for modeling of fungi cultivations (Chen et al, 2000;Ignova et al, 2002;Preusting et al, 1996;Silva et al, 2000Silva et al, , 2001Thibault et al, 2000;van Can et al, 1997Wang, Chen, Liu, & Pan, 2010), for modeling of bacteria cultivations (Costa, Alves, Henriques, Filho, & Lima, 1998;Gnoth et al, 2008;Henneke, Hagedorn, Budman, & Legge, 2005;Henriques et al, 1999;James et al, 2002;Jenzsch, Gnoth, Kleinschmidt, Simutis, & Luebbert, 2007;Laursen et al, 2007;Roubos et al, 2000;Thibault et al, 2000;Tholudur & Ramirez, 1999;Zuo, Cheng, Wu, & Wu, 2006;Zuo & Wu, 2000), for modeling of mammalian cell cultivations (Dors et al, , 1996Teixeira et al, 2005;Vande Wouwer et al, 2004), for modeling of insect cell cultivations (Carinhas et al, 2011), for modeling of hybridoma cell cultivations (Fu & Barford, 1995a, 1995b or for modeling the counter-ion fluxes across an ion-exchange membrane in a membrane-supported biofilm reactor …”

“…However, the corrector method is subject to certain restrictions regarding the state observability (Dochain, 2003). The underlying hybrid semi-parametric model can either rely on other at-time available measurements or solely on its own predictions (Multi-step ahead predictor), such as in Saxen and Saxen (1996). In case that the hybrid semi-parametric model is serial and uses at-time available measurements the same requirements formulated above for the soft-sensor case hold.…”

Modeling of an Industrial Full-Scale Plant for Biological Treatment of Textile Wastewaters: Application of Neural Networks

“…The neural hybrid model combines first-principles knowledge, which can be easily represented by a set of differential balance equations, with a conjunct neural network, which works as a nonparametric approximator of phenomena, which are unknown or difficult to quantify. Such a hybrid approach gives very promising results in many fields of chemical engineering, including biotechnology (e.g., see the reported work of Saxen and Saxen 6 and Anderson et al 9 ).…”

“…Such a situation, where, on one hand, a formulation of symbolic models (based on the knowledge or physical principles) is practically impossible and, on the other hand, much experimental data are available, encourages the application of empirical models. Among these types of models, the application of neural networks recently has become increasingly important as an effective and accurate tool for modeling chemical and biological processes, [6][7][8] as well as for modeling wastewater plants. [9][10][11] In this work, a neural network model of a full-scale biological treatment plant that processes textile wastewater has been elaborated and tested under different operating conditions.…”

Bayesian Symbolic Learning to Build Analytical Correlations from Rigorous Process Simulations: Application to CO2 Capture Technologies

“…Artificial neural networks (ANN), Gaussian processes, and random forest, among others, are increasingly being used in process modeling, − mostly to simulate complex unit operations hard to model based on first principles. For example, modeling bioreactors following complex kinetics is challenging and might be simplified using pure data-driven or hybrid models. − These approaches lead to mathematical models that often provide good approximations for time-constrained applications but are hard to interpret due to the absence of closed analytical expressions. Additionally, the ability to extrapolate is usually limited.…”