Novel Approach for Predicting Direct and Open Solar Drying Using Artificial Neural Network for Medicinal Plant

In this study, an artificial neural network (ANN) was developed to obtain a generalized model for predicting the direct and open sun drying process some medicinal plants. Since quality of experimental dataset can lead very performant model, in study collected from previously published papers divided randomly into three subsets, namely 70 %, 15 % training, testing, validation. Based on complex solar behaviour, ten parameters were considered as inputs: time, global radiation (GSR), outside temperature, inclination, emissivity, altitude, longitude, latitude, inside nutritional value, predict moisture content (MC), rate (DR). trial error method, best ANN found with topology 10-28-14-2, regression coefficient root mean square ( R = 97.044 %. RMSE 4.589 %) 99.968 1.185 MC DR, respectively. It be concluded that obtained provides method dryer modelling which any location world.