Abstract: A new method to handle constrained optimization is proposed in this paper, to solve the disadvantages of the methods .This method searches the solution space of the problem though the admixture crossover of feasible and infeasible solutions, and does the selection operation on feasible and infeasible populations, respectively. It avoids the difficulty of selecting the penalty factor in penalty strategy and makes the handling constrain simplify. Numerical results show that it is a general effective method.

Key words: Genetic Algorithm, Constraint handling, feasible solution, infeasible solution

摘要： 针对目前的约束处理方法中存在的问题，提出一种新的约束处理方法。该方法通过可行解和不可行解混合交叉的方法对问题的解空间进行搜索，对可行种群和不可行种群分别进行选择操作。避免了惩罚策略中选取惩罚因子的困难，使得约束处理问题简单化。实例测试结果表明，该约束处理方法的有效性。

关键词: 遗传算法, 约束处理, 可行解, 不可行解