基于组合聚类的低空航路网络规划方法
A Low-Altitude Air Route Network Planning Method Based on Combinatorial Clustering
1.College of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China;
2. Key Laboratory of Flight Techniques and Flight Safety, CAAC, Guanghan 618307, Sichuan, China
Online published: 2025-11-18
城市低空航路结构化和网络化规划是解决低空空域资源紧张及低空运行安全的一种有效手段。本文考虑城市低空物流场景对航线和流量的实际需求,以起降场地布局和实际运行流量为输入,提出一种基于组合聚类的低空“主干-接驳”式航路网络规划方法。首先,分别基于主成分分析或数值优化确定最优主干航路方向,结合主成分分析模型或几何相似模型对聚类结果进行质量评价,形成四种差异化航路网络聚类方法。其次,构建涵盖航路网络总长度、建设成本、航路交叉点的综合评价体系,评价四种航路网络聚类方法生成结果的优劣。最后,以绍兴市为例,验证方法可行性和有效性,相比初始场景,高密度情景下网络建设总成本降低21.39%,航路交叉点数量减少34.4%;中密度情景下,网络建设总成本降低36.4%,航路交叉点数量减少16.9%。结果表明,文中所述基于“数值优化-几何相似”组合聚类方法,可以显著提升低空运行安全性和经济性,为城市低空交通系统科学化规划提供理论依据和技术支撑。
韩鹏, 曹露瑶, 曾曙, 等 . 基于组合聚类的低空航路网络规划方法[J]. 华南理工大学学报(自然科学版), 0 : 1 . DOI: 10.12141/j.issn.1000-565X.250320
The structured and networked planning of urban low-altitude air routes is an effective approach to addressing constraints on low-altitude airspace resources and enhancing operational safety. The proposed methodology is a combined clustering-based "trunk-feeder" route network planning method for urban low-altitude logistics scenarios. The incorporation of takeoff and landing site layouts, in conjunction with actual operational traffic data, serves to address the practical demands of route and traffic considerations. Initially, optimal trunk route directions are determined using either principal component analysis (PCA) or numerical optimization. The quality of clustering is evaluated through the use of PCA-based or geometric similarity models, yielding four different approaches to the clustering of route networks. Secondly, a comprehensive evaluation system encompassing the total route network length, construction costs, and route intersection points is established to assess the performance of the four clustering methods. Finally, the feasibility and effectiveness of the method were validated using Shaoxing City as a case study. In comparison with the initial scenario, the high-density scenario resulted in a 21.39% reduction in total network construction costs and a 34.4% decrease in the number of route intersections. In the medium-density scenario, total network construction costs decreased by 36.4%, and the number of route intersections decreased by 16.9%. The findings indicate that the proposed "numerical optimization-geometric similarity" combined clustering method significantly enhances low-altitude operational safety and economic efficiency, thereby providing theoretical foundations and technical support for the scientific planning of urban low-altitude traffic systems.
/
| 〈 |
|
〉 |