摘要
飞行航路规划是一个大范围多目标多约束的三维规划问题。遗传算法是一种求解复杂问题的通用方法,该文在遗传算法中加入了飞行航路规划的相关知识来求解问题。首先,根据飞行航路规划中导航点属性复杂的特点,扩充导航点的模型,并在此基础上采用导航点链表形式的自由编码。第二,为加速规划的进程,同时保证充分的随机性和广泛性,初始群体构造采用端点启发初始化方法。第三,适应度函数由惩罚函数和代价函数组合计算,其中惩罚函数对应问题的约束条件,而代价函数对应问题的目标。第四,采用启发式交叉和启发式变异。最后,通过剖面优化操作实现高度维上的调整。仿真结果证明这是适于所研究问题的有效方法。
Air route planning is a three-dimensional planning problem, with wide range, many objects and many constraints. And genetic algorithm is a kind of common method resolving complex problems. This paper provides the solution to the problem by using the genetic algorithm together with associated knowledge in air route planning. Firstly, in respect of the complex attribute of navigating point in air route planning, it expands the model of navigating point and adopts free coding with the list of navigating point. Secondly, for the purpose of speeding up the process and ensuring the randomicity and universality, heuristic knowledge is added to endpoint initializing in the construction of original population. Thirdly, fitness function consists of penalty function according to the constraints of associated problem and cost function according to the objects of that. Fourthly, it pursues the heuristic cross and heuristic mutation. Lastly, it uses the operation of profile optimization to adjust the altitudinal dimension. Above all, the result of simulation proves it an effective method to resolve the problem discussed above.
出处
《计算机仿真》
CSCD
2004年第2期69-71,共3页
Computer Simulation
