Optimization of Caper Drying Using Response Surface Methodology and Artificial Neural Networks for Energy Efficiency Characteristics

One of the essential factors for selection drying process is energy consumption. This study intended to optimize treatment capers using convection (CD), refractive window (RWD), and vacuum (VD) combined with ultrasonic pretreatment by a comparative approach among artificial neural networks (ANN) response surface methodology (RSM) focusing on specific consumption (SEC). For this purpose, effects temperature (50, 60, 70 °C), ultrasonication time (0, 20, 40 min), method (RWD, CD, VD) SEC value (MJ/g) were tested face-centered central composite design (FCCD). RSM (R2: 0.938) determined optimum drying-temperature–ultrasonication-time values that minimize as; 50 °C-35.5 min, °C-40 min °C-24 RWD, CD VD, respectively. The conduct ANN model evidenced correlation coefficient training (0.976), testing (0.971) validation (0.972), which shows high suitability optimising