| Summary: | A comparative approach was carried out between artificial neural networks (ANNs) and response surface methodology (RSM) to optimize the drying parameters during infrared–con- vective drying of white mulberry. The drying experiments were performed at different air temperatures (40°C, 55°C, and 70°C), air velocities (0.4, 1, and 1.6 m/s), and three levels of infrared radiation power (500, 1000, and 1500 W). RSM focuses on the maximization of effective moisture diffusivity (D eff ) and minimi- zation of specific energy consumption (SEC) in the drying pro- cess. The optimized conditions were encountered for the air temperature of 70°C, the air velocity of 0.4 m/s, and the infrared power level of 1464.57 W. The optimum values of D eff and SEC were 1.77 × 10 −9 m 2 /s and 166.554 MJ/kg, respectively, with the desirability of 0.9670. Based on the statistical indices, the results showed that the feed and cascade-forward back-Propagation neural systems with application of Levenberg-Marquardt train- ing algorithm and topologies of 3–20-20-1 and 3–10-10-1 were the best neural models to predict D eff and SEC, respectively. This finding suggests that the ANN as an intelligent method with better performance compared to the RSM can be used to pre- dict the drying parameters of the infrared-convective drying of white mulberry fruit.
|
|---|