| Abstrak/Abstract |
Pneumatic conveying ring dryers (PCRD) have been designed for drying sago starch. Tofacilitate the development of further designs, an accurate prediction model is required.The objective of this research is to develop a model of artificial neural network (ANN) topredict the efficiency of drying on the sago starch dryer of PCRD type. The ANN modelconsists of 12 input neurons, hidden layers, and 1 output neuron. Hidden layer variationsare performed on the ANN model with network structure 12-5-5-1-1, 12-15-15-1-1, and12-25-25-1-1. The learning algorithm uses a trainln typebackpropagationwithlogsigactivation function. The ANN model was trained and tested using 81 data sets (54 sets oftraining data and 27 sets of test data). The test results show that the comparison betweenthe results of the prediction model of ANN with observation obtained r2train value of0.998, and r2testin0.916. The results of optimization ofthe ANN modelobtained bythemean valueof Mean Square Error (MSE) train and test (0.063 and 0.232), Root MeanSquare Error (RMSE) train and test (0.251 and 0.482), MeanAbsoluteDeviation (MAD)train and test (0.063 and 0.232), Mean Absolute Error (MAE) training and test (0.209 and0.393), and Mean Relative Error (MRE) train and test (2.414 and 4.609). The best networkstructure is 12-25-25-1-1. This shows that the ANN model is able to predict the efficiencyof drying, so it is feasible to be used for the design development on the sago starch dryerof PCRD type |
