MODELING THE DRYING KINETICS OF GREEN BELL PEPPER IN A HEAT PUMP ASSISTED FLUIDIZED BED DRYER

摘要

In this research, green bell pepper was dried in a pilot plant fluidized bed dryerrnequipped with a heat pump humidifier using three temperatures of 40, 50 andrn60C and two airflow velocities of 2 and 3 m/s in constant air moisture. Threernmodeling methods including nonlinear regression technique, Fuzzy Logic andrnArtificial Neural Networks were applied to investigate drying kinetics for thernsample. Among the mathematical models, Midilli model with R = 0.9998 and rootrnmean square error (RMSE) = 0.00451 showed the best fit with experimental data.rnFeed-Forward-Back-Propagation network with Levenberg–Marquardt trainingrnalgorithm, hyperbolic tangent sigmoid transfer function, training cycle of 1,000rnepoch and 2-5-1 topology, deserving R = 0.99828 and mean square errorrn(MSE) = 5.5E-05, was determined as the best neural model. Overall, Neural Networksrnmethod was much more precise than two other methods in prediction ofrndrying kinetics and control of drying parameters for green bell pepper.