约束优化问题的改进遗传算法设计

遗传算子是影响遗传算法优化效果的重要因素,针对目前遗传算法研究中对约束优化问题求解的不足,提出基于退火思想的退火选择算子和加权适应度算子,并给出了退火选择算子和加权适应度算子设计方法及其计算过程.在此基础上与现有的遗传算子结合,提出一种新的改进遗传算法,分析了改进遗传算法与基于罚函数遗传算法之间在原理上的区别.最后以两个测试函数为算例对算法进行了性能测试,结果表明改进的遗传算法具有良好的优化性能,能获得更好的优化结果.

A Reformative Genetic Algorithm for Constrained Optimization

The genetic operator is an important factor in genetic algorithm. For the deficiency of genetic algorithm applied to compute the constrained optimization problem, the paper proposes the annealing selecting operator and the amending fitness operator, and the computation method is given. In combination with existing basic genetic operator, a new improved genetic algorithm is proposed, and differences between the new improved genetic algorithm and the genetic algorithm are analyzed based on the penalty function methods. At last two test functions are used to demonstrate the capability of the algorithm and the result shows that the new algorithm can achieve better optimization solution.