The objective of the present work was to apply self-organizing feature maps (SOFM) and multilayer perceptron (MLP) to evaluate the protective capacity of tert-butylhydroquinone (TBHQ), butylhydroxyanisole (BHA), and butylhydroxytoluene (BHT) antioxidants against the biodiesel oxidation reaction. For this, the antioxidant concentration and the biodiesel compliance parameters were used as continuous input variables and the type of antioxidant as a categorical. The SOFM proved to be an adequate tool for the classification of biodiesel samples containing antioxidants. The performance of the 5 most active networks of the model ranged from 89 to 99% for training, testing, and validation with an error below 1.42 × 10-4. Statistical tests applied to validate the model showed no significant difference between predicted and experimental values. The global sensitivity analysis showed that the relative protection factor (RPF) contributed with 34.89%, the antioxidant with 31.49%, the induction period with 10.69%, the water content with 6.00%, and the others all together with 16.93% in the construction of the regression models by MLP.

The simultaneous diffusion of inorganic components in the olive pulp in wet brine was modeled based on Fick’s generalized 2nd Law and simulated using the finite element method. The main and crossed diffusion coefficients, the film coefficient and the Biot number were determined, with the application of the simplex optimization method, through the minimization of the percentage errors. The errors between the simulated and experimental data were 5.35% for NaCl and 4.77% for KCl and the adjusted main diffusion coefficients were 0.4358 × 10-12 m2 s-1 for NaCl and 0.5408 × 10-12 m2 s-1 for KCl. The system developed to simulate diffusion allows the control and modulation of the salts content that diffuses through the olive pulp.

Olive samples were subjected to the salting process in brine containing 1196 mol m−3 of NaCl and 402 mol m−3 of KCl. Samples were collected during 60 h and salt concentration values were determined. With the finite element method (FEM) and the minimization of the errors percentage between the simulated and experimental values, the mass transfer coefficients in the film (hm) were obtained, being 1.0072 × 10−8 and 1.2499 × 10−8 for NaCl and KCl, respectively. The salts concentration at the olive/brine interface was simulated by FEM and analyzed via SOFM. A network with 4 × 4 topology and 10000 training epochs was used. It was observed that the influence of the stationary film formed on the surface of the olives during the salting process depends on the position, the salt involved in the diffusion and that the concentration of the salts, at each point, varies according to the immersion time.

Biodiesel is capable of replacing diesel because it has similar physicochemical properties, but this biofuel is susceptible to oxidation, which makes the application of antioxidant substances necessary. For this study, alcoholic extracts of senna leaves, hibiscus flowers, and blackberry were used. Biodiesel samples were submitted to physicochemical analysis to evaluate interference in the volume of these alcoholic extracts with antioxidant properties. The data obtained were processed using the neural network of the multilayer perceptron type (MLP). For the network’s training, 200 epochs were used. The samples were randomly divided into three groups, with 70% used for training, 15% for testing, and 15% for validation. The type of extract was considered as a categorical variable, the extract volume as a target variable, and the other ones as input variables. Among the 200 networks trained, with 5 to 20 hidden layers, the 5 with the best performance were highlighted. The Tukey test applied to the means showed no significant difference at the 5% level, between the value of the added volume and the means value predicted by the networks. The sensitive analysis showed that the most important input variable for the construction of the model was the type of extract.

The influence of the film formed during the salting of champignon mushrooms with brine containing NaCl and KCl was modeled using the finite elements method (FEM). It was verified that the film formed on the mushroom surface had a greater influence in the static salting since the diffusion of the ions was 7.5-fold smaller in this system than in the stirred salting. The application of self-organizing maps showed that the ions diffusion along the surface of the solid presented a heterogeneous occurrence and depended on the region for both static and stirred salting. A direct relation was observed among the mushroom surface morphology, the salts diffusion behavior, and the film formation. In addition, the film was not completely extinguished in the stirred system, although it has a minimal influence as the film formation is also dependent on the biosolid surface.

The NaCl and KCl diffusion in the film formed on the cheese surface during salting was simulated by the finite element method. The time and salts concentration values on the cheese surface were determined, tabulated, and presented to the multilayer perceptron neural network (MLP) for the regression modeling. The samples were divided into 70, 15 and 15% for training, testing, and validation, respectively. The networks with the best performance showed 5 to 12 hidden layers. The Tukey’s test showed that there was no significant difference, at the 5% level, between the time value used and the mean value modeled for training, testing, and validation for the NaCl. For the KCl, a significant difference was observed only for 2 training samples and 1 test sample. Sensitivity analysis showed that the discrete variable Z, which represents the static and dynamic systems, was the most important in the models’ construction.