Articles | Research in Agricultural Engineering | Agricultural Journals

This study examines the potential of applying computational intelligence modelling to describe the drying kinetics of persimmon fruit slices during vacuum drying (VD) and hot-air-drying (HAD) under different drying temperatures of 50 °C, 60 °C and 70 °C and samples thicknesses of 5 mm and 8 mm. Kinetic models were developed using selected thin layer models and computational intelligence methods including multi-layer feed-forward artificial neural network (ANN), support vector machine (SVM) and k-nearest neighbors (kNN). The statistical indicators of the coefficient of determination (R²) and root mean square error (RMSE) were used to evaluate the suitability of the models. The effective moisture diffusivity and activation energy varied between 1.417 × 10⁻⁹ m²/s and 1.925 × 10⁻⁸ m²/s and 34.1560 kJ/mol to 64.2895 kJ/mol, respectively. The thin-layer models illustrated that page and logarithmic model can adequately describe the drying kinetics of persimmon sliced samples with R² values (>0.9900) and lowest RMSE (<0.0200). The ANN, SVM and kNN models showed R² and RMSE values of 0.9994, 1.0000, 0.9327, 0.0124, 0.0004 and 0.1271, respectively. The validation results indicated good agreement between the predicted values obtained from the computational intelligence methods and the experimental moisture ratio data. Based on the study results, computational intelligence methods can reliably be used to describe the drying kinetics of persimmon fruit.

Articles | Research in Agricultural Engineering | Agricultural Journals

The mechanical behavior of Ensete ventricosum fibers, expressed as the dependency of tension force in relation to the elongation, was determined for fibers with gauge length 50 mm and transformed into general linear mathematical model describing dependency of tension stress and strain. The average rupture force (10.88 ± 1.11) N, rupture stress (390.33 ± 21.96) MPa, rupture strain (0.021 ± 2 · 10^–5), and volume energy (3.39 ± 0.22) J m⁻³ were also determined at this conducted study. Using image analyses, it was determined that the cross section of Ensete ventricosum fiber has circle shape and its dimension was specified. From the study, it implies that Ensete ventricosum fiber, with respect to its mechanical behavior under tension loading having regard to its density and to the fact that it is environmentally friendly, biodegradable and recyclable, could be used as a perspective construction material of the future. Determined model of mechanical behavior could be applied as background for further research focused on the Ensete fiber application.

Articles | Research in Agricultural Engineering | Agricultural Journals

In the present study, a Box–Behnken design of response surface methodology (RSM) was employed to optimize the processing factors (force: 100, 150, and 200 kN; speed: 3, 5, and 7 mm/min; and temperature: 40, 60, and 80 °C) for extracting pumpkin seeds oil under uniaxial compression. The design generated 15 experiments including twelve combinations of factors and three replicates at the center point. The responses: oil yield (%), oil expression efficiency (%), and energy (J) were calculated, and the regression models determined were statistically analyzed and validated. The optimum factors combination: 200 kN, 4 mm/min and 80 °C predicted the oil yield of 20.48%, oil expression efficiency of 60.90%, and energy of 848.04 J. The relaxation time of 12 min at the optimum factors increased the oil efficiency to 64.53%. The lower oil point force was determined to be 57.32 kN for estimating the maximum oil output. The tangent curve and generalized Maxwell models adequately (R² = 0.996) described the compression and relaxation processes of pumpkin seeds oil extraction. Peroxide value increased with temperatures. The study provides detailed information useful for processing different bulk oilseeds under uniaxial loading for optimizing the mechanical oil pressing in large-scale oil production.