Introduction: Due to their high moisture content, cherries have a very high rate of spoilage and require the use of some post-harvest treatments in order to be effectively preserved. Drying is one of these preservation methods. Drying time can be shortened by using ultr
More
Introduction: Due to their high moisture content, cherries have a very high rate of spoilage and require the use of some post-harvest treatments in order to be effectively preserved. Drying is one of these preservation methods. Drying time can be shortened by using ultrasonic waves as a pretreatment before drying agricultural products. The genetic algorithm–artificial neural network method has a high ability to find the optimal value of a complex objective function.Materials and Methods: In this study, the effect of sonication treatment for 0, 3, 6, and 9 minutes on drying time, weight changes, and rehydration of cherries was investigated. In the next step, this process was modeled by genetic algorithm–artificial neural network method with 2 inputs (drying time and ultrasonic pretreatment time) and 1 output (weight loss percentage).Results: The results of this research showed that sonication for up to 3 min increased the rate of moisture removal from cherries and thus reduced drying time. 3-min treatment with ultrasound increased the rehydration of dried cherries; but as the treatment time increased to 6 min and 9 min, the amount of rehydration decreased. Genetic algorithm–artificial neural network modeling results showed that a network with a 1-4-2 structure in one hidden layer and using the hyperbolic tangent activation function can predict the weight loss percentage of cherries during drying with a high correlation coefficient and a low error value. According to the results of sensitivity analysis test, drying time was the most effective factor in changing the weight loss percentage of cherries during the drying process.Conclusion: In general, the best conditions for drying cherries are pretreatment with ultrasound for 3 minutes followed by drying the product with hot-air. Based on the modeling results, the genetic algorithm–artificial neural network method can also be used to predict the parameters of the cherry drying process.
Manuscript profile
