Comparison Study On Fitness Function Scaling And Operators Of Genetic Algorithm

Genetic Algorithm (GA) is a highly parallel, random and adaptive searching method based on the mechanics of natural selection and genetic. The scholars of domestic and foreign pay much attention on the research of genetic algorithm’s theory and application, and have made an amazing progress. The achievement of genetic algorithm has permeated to a lot of fields. But the theory and method of genetic algorithm haven’t been mature yet. Some insufficiencies of algorithm are also waiting for further improvement and consummation. So, this paper analyzes the mechanism of genetic algorithm, studies the fitness function scaling and genetic operators. And an improved GA is designed:combining with immune concentration adjustment mechanism to improve selection operator, replacing crossover and mutation operator with nested secondary genetic algorithm. The modified algorithm is realizes by programming with C++. Finally, the paper selects some typical multi-dimensional and high dimensional complex test functions to have a simulation test, applies the modified algorithm to the tuning of PID controller parameters, the simulations have demonstrated proposed algorithms improve the convergence speed and the probability of convergence, approved the validity and superiority compared with the simple genetic algorithm.