Modeling of Peach Drying Process using Infrared Dryer by Genetic Algorithm Method

Due to low energy efficiency and prolonged drying time of agricultural products by conventional methods, application of the new techniques such as infrared radiation, has been investigated. In this study, in order to dry and increase the shelf life of peach, infrared radiation (IR) method has been employed. The effect of infrared lamp power at three levels 150, 250 and 375 watts, the distance of the samples from the lamp at three levels 5, 7.5 and 10 cm and at 1 minute intervals for up to 120 minutes on drying of peach were examined. Modeling of process was carried out with genetic algorithm–artificial neural network (GA-ANN) method with 3 inputs (lamp power, distance and time) and1output (weight loss). The results of infrared drying of peach showed that by increasing the lamp power and decreasing the sample distance from the heat source, the drying rate is increased. By increasing the infrared lamp power from 150 to 375 watt, the weight loss is increased from 39.4 to 87.50 % and with increase in 250 watt lamp distance from 5 to 10 cm, the weight loss is decreased from 87.6 to 73.5 % for the sample. The GA-ANN modeling results showed that a network with 13 neurons in 1 hidden layer with using hyperbolic tangent activation function can predict the weight loss in peach drying using infrared method (R=0.9991). Sensitivity analysis results by optimum ANN showed that drying time is the most sensitive factor to control the weight loss of peach slides.