Abstract: TSP（Traveling Salesman Problem） is one of the typical NP_hard problem in combination optimization.For solving the problem，genetic algorithm is better than traditional ones obviously，and there are also many crossover operators used to get hypo-optimization route.Based on heuristic crossover by Tanglixin，a new crossover operator is conducted.The crossover preserver the snippet of effective genes，and a moving window is used to fasten the algorithm convergence.The example shows that the new crossover operator is useful.

Key words: genetic algorithm, TSP, heuristic crossover, moving window, preserver genes snippet

摘要： 旅行商问题（TSP，Traveling Salesman Problem）是一种经典的NP组合优化问题。遗传算法在求解这类组合问题方面明显优于传统算法，同时也提出了许多求解较好路径的交叉算子。在对比分析唐立新提出的两种启发式交叉算法的基础上，提出了一种新的交叉算子。该算子通过判断父代的城市是否相邻来保存有效基因片断，通过加入一个移动的窗口来加快算法收敛。实验结果表明了该算子的有效性。

关键词: 遗传算法, TSP问题, 启发交叉算子, 移动窗口, 有效基因保留