基于改进遗传算法的海底地层参数反演计算

为了提高对海底地层参数变量的反演计算能力,设计了一种基于双种群协同进化策略的改进遗传算法。针对标准遗传算法局部搜索能力差且易于出现早熟现象的缺点,在标准遗传算法基础上引入双种群同时进行优化搜索,两个种群分别给予不同的控制参数,实现协同进化,最终给出一个综合的最优解。通过两个算例对遗传算法的寻优能力进行测试,实验结果表明,提出的改进算法不仅提高了搜索性能,并且对遗传控制参数的依靠度大大降低,特别是对大型复合参数反演问题的求解计算更为有效。

Inversion calculation of sea bottom parameters based on improved genetic algorithm

In order to improve the inversion calculation of the sea bottom parameters variables,an improved genetic algorithm used for double populations'' co-evolutionary strategy is presented in this paper.In view of standard genetic algorithm has low efficiency in local extreme searching and might be easily premature phenomenon,the two populations are introduced to optimization based on the standard genetic algorithm,two populations are given with different control parameters to achieve co-evolution,and finally a comprehensive optimal solution is given in the text.By two examples to test the efficiency and practicability of the algorithm,the experimental results show that the proposed algorithm not only improves the search performance,but also greatly reduces the dependence on genetic control parameter,especially it is more effective to solve the large complex parameter inversion calculation problem.