论文部分内容阅读
为改善遗传算法局部寻优精度较差的固有缺陷,该文引入一种新的基于遗传算法的模式搜索法求解地下水管理模型。首先通过在遗传算法中引入精英保留的进化策略,提高遗传算法的收敛性,进行全局搜索得到全局近似最优解,在此基础上采用局部寻优类算法模式搜索法进一步改善优化结果,最后将该混合优化方法用于求解一个地下水管理的基准问题。计算结果表明,基于改进遗传算法的模式搜索法,改善了单一遗传算法局部寻优精度较差的缺陷,在地下水管理模型的优化求解中具有较好的应用前景。
In order to improve the inherent shortcomings of the poor local optimization of genetic algorithm, this paper introduces a new pattern search method based on genetic algorithm to solve the groundwater management model. Firstly, by introducing elitist reserved evolutionary strategy in genetic algorithm, the convergence of genetic algorithm is improved, and the global optimal solution is obtained by global search. Based on this, the local optimization algorithm is used to further improve the optimization result. At last, The hybrid optimization method is used to solve a baseline problem of groundwater management. The results show that the pattern search method based on improved genetic algorithm can improve the defect of single genetic algorithm with poor local optimization accuracy and has a good application prospect in the optimization of groundwater management model.