遗传算法是一种模仿自然界生物进化过程中选择和遗传的机理而构造出的一种优化搜索算法．但是，简单遗传算法的收敛速度较慢，稳定性较差．针对这些问题，本文提出了一种被称为“大变异”的改善遗传算法性能的操作，在文中分别讨论了该操作的思路，实现的方法，井给出了它的有效性的数值实验证明． Genetic algorithm is a kind of optimized search algorithm which imitates the mechanism of selection and heredity in the biological evolution of nature. However, the simple genetic algorithm converges slowly and its stability is poor. In order to solve these problems, this paper presents an operation called “big mutation” to improve the performance of genetic algorithm. The paper discusses the idea of ​​the operation, the method of realization and the numerical experiment of its effectiveness .