Inteligência computacional aplicada à modelagem matemática da produção de biossurfactantes por esterificação de ácidos graxos com açúcares

Abstract

Because of increasing demand of biosurfactants, which are more environmentally friendly than to surfactants derived from non-renewable raw materials, there is a growing need for studies proposing new processes for their production or aiming at the optimization of existing processes. In this context, the mathematical modeling of enzymatic reactors for the esterification of fatty acids with sugars in the production of biosurfactants has been a useful tool for studying and optimizing the process. In particular, artificial neural networks and fuzzy systems emerge as promising methods for developing models for those process. Thus, this work aimed at the development of hybrid-neural models and a fuzzy model for enzymatic esterification reactors associated with biosurfactant production. In the case of artificial neural networks application, the coupling of networks to reactor mass balances was considered in hybrid models to infer reactant concentrations over time. To achieve this, the classical Runge-Kutta method was employed for the integration of the material balance differential equations. Computationally, an algorithm was constructed incorporating material balances, neural reaction rates, and step-by-step numerical integration. In the case of applying fuzzy logic for modeling and optimizing the conversion of fatty acid esterification with sugars, in function of operational process parameters (such as time, temperature, molar ratio of substrates), a study was conducted based on an available set of experimental data. The aim was to compare the prediction of optimal operational conditions provided by the fuzzy model with those derived from the classical response surface methodology. All computational development was carried out using the Matlab software. In the application of hybrid-neural models, neural networks were able to predict the kinetic behavior of the xylose esterification process in biosurfactant synthesis by applying them to reactor mass balances, obtaining R2 values above 0.94, indicating a good predictive capacity. The trained fuzzy models were able to simulate the relationships between input variables and the output variable, enabling the construction of various response surface combinations and estimating the optimal operational condition at 55°C, RMS of 0:0.2, enzyme loading of 37.5 U/g, and 60 hours of reaction. The same condition was obtained when applying the particle swarm optimization algorithm, consistent with results from similar studies. Thus, this study demonstrated the capability of computational intelligence in modeling, simulation, and optimization of biosurfactant synthesis.