Integration of artificial neural network with genetic algorithm for an optimum performance of a Chironji (Buchanania lanzan) nut decorticator

Abstract

This study has explored the integrated artificial neural network - genetic algorithm (ANN-GA) technique for the optimum performance of a Chironji (Buchanania lanzan) nut decorticator. To have desired outcomes, the performance of the decorticator was evaluated at 54 different combinations of independent variables. Those variables are six levels of moisture content of the nuts (3%, 6%, 9%, 12%, 15%, and 18% d.b.), three levels of the roller speed (400, 450, and 500 rpm), and three levels of clearance between the roller and plate (6.44, 6.95, and 7.46 mm). The optimum values found were the moisture content of 12.06% (d.b.), speed of 413 rpm, and clearance of 6.64 mm. With the optimised values, 14.69% of whole kernels, 3.45% of broken kernels, and 5.20% of un-decorticated nuts were recovered. A decorticating efficiency of 94.8% and a machine efficiency of 76.77% was recorded when the decorticator was operated at optimum conditions. The outcomes of this study will be useful for nut processing and elsewhere.