论文部分内容阅读
为了有效地克服非线性、多参数、多极值的组合优化问题中遗传算法的早熟收敛现象,引入生物的小生境技术和自然界生物多种杂交方式并存、多个子群体并行以及灾变现象而提出了一种综合的快速基因搜索策略。该算法以多个子群体不同杂交方式并行搜索为主,并结合排序配对的受限交配技术和灾变算子等方法来实现快速的寻优过程。对地震资料波阻抗反演的理论模型试验表明:该算法的收敛能力和计算效率有了明显改善。
In order to effectively overcome the premature convergence of genetic algorithms in combinatorial optimization problems with nonlinear, multi-parameter and multi-extremal values, the introduction of biological niche technology and the coexistence of multiple biological hybridization in nature, the parallelism of multiple sub-groups and the catastrophe phenomenon A Comprehensive Rapid Gene Search Strategy. The algorithm is based on the parallel search of multiple sub-populations with different hybridization methods, and combined with the limited mate of ordering and pairing and catastrophic operator to achieve rapid optimization. The theoretical model test of wave impedance inversion of seismic data shows that the convergence and computational efficiency of the algorithm have been significantly improved.