Modeling of an industrial process of pleuromutilin fermentation using feed-forward neural networks

Abstract

-This work investigates the use of artificial neural networks in modeling an industrial fermentation process of Pleuromutilin produced by Pleurotus mutilus in a fed-batch mode. Three feed-forward neural network models characterized by a similar structure (five neurons in the input layer, one hidden layer and one neuron in the output layer) are constructed and optimized with the aim to predict the evolution of three main bioprocess variables: biomass, substrate and product. Results show a good fit between the predicted and experimental values for each model (the root mean squared errors were 0.4624% -0.1234 g/L and 0.0016 mg/g respectively). Furthermore, the comparison between the optimized models and the unstructured kinetic models in terms of simulation results shows that neural network models gave more significant results. These results encourage further studies to integrate the mathematical formulae extracted from these models into an industrial control loop of the process.

Mathematical Modeling of Batch Antibiotic Production: Comparative Analysis between Phenomenological and Empirical Approaches

“…A wide range of studies presented in the literature report on the use of other mathematical resources, such as "intelligent" models based on neural networks, genetic algorithms, and specialist systems to analyze biosystems, such as those studied herein [19][20][21][22][23][24][25]. The advantages of the use of the models proposed in the present article lie in the fact that one, of phenomenological nature, is based on the principle of mass conservation and incorporates specific kinetic equations, making it more reliable when making interpolations and extrapolations, as compared to purely empirical models.…”

Preliminary Modeling of an Industrial Recombinant Human Erythropoietin Purification Process by Artificial Neural Networks

“…One of the most popular neural network paradigms applied to the modeling of a wide range of nonlinear systems, especially chemical and biological engineering processes, is the feed-forward back propagation neural network (Silva et al, 2000;Khaouane et al, 2013), which has been used in this paper with one hidden layer.…”

“…Since ANN have the ability to extract from experimental data the highly non-linear and complex relationships between the variables of the problem without any detailed knowledge of the system (Si-Moussa et al, 2008;Khaouane et al, 2013) and, given the great amount of available experimental data in the study, it was decided to apply this approach. In this way, it was possible to extract useful information for making decisions without the need to have a theoretical model of process behaviour.…”

Arduino Open Hardware Test Through Chemical System Simulation Under Lumped Model Dynamics

“…One example is the necessity of running an Artificial Neural Network Model toolbox with MatLab, such as in the work of Khaouane et al (2013). The toolbox provides faster developments within the computational application, since the packages are usually well documented and user friendlily, enabling its utilization by an intermediate user.…”