基于改进NSGA⁃Ⅱ算法的航班战略冲突解脱研究

Strategic Flight Conflict Resolution Based on an Improved NSGA⁃ⅡAlgorithm

设计了一种改进的非支配排序遗传算法(Non‑dominated sorting genetic algorithmⅡ,NSGA‑Ⅱ)解决战略阶段轨迹规划大规模优化问题。在经典的NSGA‑Ⅱ的框架下,采用一种自适应交叉算子与自适应变异算子加快算法的收敛速度并提高解的质量,同时给出衡量Pareto解集优劣的评价指标。大规模四维航迹的引入不可避免地增加了问题的复杂性,本文提出了一种有效的战略冲突解脱模型,旨在最小化潜在的冲突数量和冲突解脱成本。采用中国航路网络繁忙时段1472架航班进行实例验证,并所提算法与经典的NSGA‑Ⅱ算法及MOEA/D进行对比。实验结果表明,改进的NSGA‑Ⅱ算法具有更好的优化效果,能够有效地解决航空器之间的冲突并产生较小的航空器航迹调整量。

An improved non-dominated sorting genetic algorithmⅡ(NSGA-Ⅱ)for solving the large-scale optimization problem of trajectory planning in the strategic stage is designed.Under the framework of the classic NSGA-Ⅱ,an adaptive crossover operator and an adaptive mutation operator are used to accelerate the convergence speed of the algorithm and improve the quality of the solution,and an evaluation index to measure the pros and cons of the Pareto solution set is given.Considering the introduction of large-scale fourdimensional trajectories inevitably increases the complexity of the problem,this paper proposes an effective strategic conflict resolution model,which aims to minimize the number of potential conflicts and the cost of conflict resolution.Using 1472 flights during peak hours of China’s air-route network for example verification,the proposed algorithm is compared with the classic NSGA-Ⅱalgorithm and MOEA/D.The experimental results show that the improved NSGA-Ⅱalgorithm has a better optimization effect,can effectively resolve the conflicts between aircraft and produce less trajectory amendment costs.