DefinePK

Abstract

The postharvest storage process is a highly nonlinear one involving heat and mass transfer. The need to capture these nonlinearities demands the use of intelligent models. In this study a neural network model (for a potato storage process) was normalized using the standard deviation technique and optimized through different combinations of network configurations. The optimum model had a mean squared error (MSE) value of 0.8314 and a coefficient of determination (R2) value of 0.7347. In comparison to a previous study, where the network was based on the min-max method of normalization, the network provided a better representation of the storage process. The proposed model would be useful in simulation processes involving intelligent controllers.