A Case Study on Investigating the Effect of Genetic Algorithm Operators on Predicting the Global Minimum Hardness Value of Biomaterial Extrudate

Journal Article · Mon Feb 01 04:00:00 EST 2010 · International Journal of Optimization: Theory, Methods and Applications

OSTI ID:984783

Shankar, T J ^[1]; Sokhansanj, Shahabaddine ^[2]

---

1. University of British Columbia, Vancouver
2. ORNL

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 operators. The present work was aimed to see the effect of genetic algorithm operators like crossover and mutation (Pc & Pm), population size (n), and number of iterations (I) on predicting the minimum hardness (N) of the biomaterial extrudate. The second order polynomial regression equation developed for the extrudate property hardness in terms of the independent variables like barrel temperature, screw speed, fish content of the feed, and feed moisture content was used as the objective function in the GA analysis. A simple genetic algorithm (SGA) with a crossover and mutation operators was used in the present study. 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 increasing population and iterations the prediction of function minimum improved drastically. Minimum predicted hardness values were achievable with a medium population of 50, iterations of 50 and crossover and mutation probabilities of 50 % and 0.5 %. Further the Pareto charts indicated that the effect of Pc was found to be more significant when population is 50 and Pm played a major role at low population ( 10). A crossover probability of 50 % and mutation probability of 0.5 % are the threshold values for the convergence of GA to reach a global search space. A minimum predicted hardness value of 3.82 (N) was observed for n = 60 and I = 100 and Pc & Pm of 85 % and 0.5 %.

• Research Organization: Oak Ridge National Laboratory (ORNL)
• Sponsoring Organization: EE USDOE - Office of Energy Efficiency and Renewable Energy (EE)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 984783
• Journal Information: International Journal of Optimization: Theory, Methods and Applications, Journal Name: International Journal of Optimization: Theory, Methods and Applications Journal Issue: 2 Vol. 2
• Country of Publication: United States
• Language: English

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
99 GENERAL AND MISCELLANEOUS
ALGORITHMS
ANNEALING
CONVERGENCE
FORECASTING
GENETICS
HARDNESS
MOISTURE
MUTATIONS
POLYNOMIALS
PROBABILITY
VELOCITY
crossover & mutation operators
genetic algorithm
regression equation
response surface methodology