基于航迹点法向距离的航迹聚类研究  

Research on flight tracks clustering based on the vertical distance of track points

作　　者：徐涛[1,2] 李永祥[1] 吕宗平[2] 

机构地区：[1]中国民航大学计算机科学与技术学院,天津300300 [2]中国民航大学中国民航信息技术科研基地,天津300300

出　　处：《系统工程与电子技术》2015年第9期2198-2204,共7页Systems Engineering and Electronics

基　　金：国家自然科学基金重点项目(61139002);国家高技术研究发展计划(863计划)(2012AA063301);国家科技支撑计划(2014BAJ04B02);中国民用航空局科技项目(MHRD201006;MHRD201101);中央高校基本科研业务费专项资金(3122013P013)资助课题

摘　　要：随着民航业的飞速发展,机场噪声污染问题越来越严重,研究航迹聚类对机场噪声预防治理工作具有重要意义。现有航迹聚类算法所采用的航迹点对选取方式,无法实现所选航迹点对在空间上的对应,严重影响聚类效果。针对这一问题,提出一种基于航迹点法向距离的航迹聚类模型。该模型采用航迹点法向距离作为航迹相似性度量方法,有效地解决了因飞机速度差异引起的航迹点对选取不匹配问题。通过K-medoids聚类算法对航迹进行二维和三维聚类,使用Davies Bouldin(DB)指标、Dunn指标对聚类结果进行评价。实验表明,提出的模型能够更好地度量航迹之间的相似性,航迹聚类效果更好,从而验证了该模型的合理性和有效性。With the rapid development of the civil aviation industry, the noise pollution problem of airport is more and more serious. Research on flight tracks clustering is important for prevention and control of airport noise. The flight track point pair chose method which is the existing flight track clustering common method, could not achieve one to one match in the space, and it has a strong influence on the clustering results. In order to solve this problem, a flight track similarity measure model is proposed based on the vertical distance of track points. It can ignore the effects of flight＇s speed on flight tracks similarity. According to the daily tracks data, flight tracks can be clustered. 2D and 3D clustering of the flight tracks can be achieved by the K-medoids cluste ring algorithm. And Davies Bouldin （DB） index and the Dunn index are used to evaluate the clustering results. Experimental results show that the proposed model can measure the similarity more profitably between the tracks and the results of flight tracks clustering are better. Therefore, the rationality and availability of the model, have been verified.

关 键 词：航迹相似性 航迹聚类 K—medoids 聚类有效性评价 噪声预测 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]