Effect of Genetic Algorithm Operators on Convergence of a Function Minimum to Predict the Hardness of a Biomaterial Extrudate

Abstract

Crossover and mutation are the main search operators of genetic algorithm, one of the most important features which distinguish it from other search algorithms like simulated annealing. A genetic algorithm adopts crossover and mutation as their main genetic operator. The present work was aimed to see the effect of crossover and mutation operators (Pc & Pm), population size (n), and number of iterations (I) on the convergence of function. A simple genetic algorithm (SGA) with a crossover and mutation operators was used in the present study. A second degree regression equation developed for the extrudate property hardness (N) of a biomaterial as a function of barrel temperature screw speed, fish content of the feed and feed moisture content was minimized. A program was developed in C language for a SGA with a rank based fitness selection method. The upper limit of population and iterations were fixed at 100. It was observed that with increase in population and iterations the convergence of function minimum improved drastically. A medium n = 50, I = 50 and Pc & Pm of = 50 % and = 0.5 % resulted in improved convergence of second order polynomial. Further the Pareto charts indicated that the effect of Pc was found to be more significant when n = 50 and Pm played a major role at low 'n' values. The function minimum of 3.82 (N) was observed for n = 60 and I = 100 and Pc & Pm of 85 % and 0.5 %.