Evaluating the Combined Effect of Temperature, Shear Rate and Water Content on Wild-Flower Honey Viscosity Using Adaptive Neural Fuzzy Inference System and Artificial Neural Networks

摘要

Handling, processing and shelf life determination of honey requires the knowledgenof rheological properties. In this study, rheological properties of eight differentnuntreated wild-flower honey samples collected in Jordan were modeled usingnthree important parameters including temperature (28–58C), water contentn(16.1–17.3%) and shear rate (2.2–47/s). Artificial neural network (ANN) (feednforward [FF] and radial basis function [RBF] ANNs) and adaptive neural fuzzyninference system (ANFIS) were used because conventional analytical models wereninsufficient. The results showed that both ANNs and ANFIS were able to modelnhoney viscosity very well. RBF-ANNs and FF-ANNs were able to model viscositynwith R2 from 0.961 to 0.986 and mean square error (MSE) of 1.43–4.71. Annimportant analysis of input variables showed that shear rate was the most influentialnfactor with 60% weight, followed by temperature (25% weight) and finallynwater content (15% weight). ANFIS was also found to adequately model honeynviscosity using three, four and five triangular and bell-shaped membership functions.nThe results showed that R2 and MSE varied between 0.953 and 0.984 andnbetween 1.41 and 4.24, respectively. ANFIS provided an extra advantage overnANNs because it presented a set of fuzzy if-then rules that can be used for predictionsnof new viscosity data. It was concluded that both ANNs and ANFIS were ablento provide an excellent alternative to conventional analytical rheological models.