摘要
针对天气现象和空中交通的不确定性,通过k-means聚类算法识别终端区对流天气相似性,将历史运行场景分类.提取相似性天气和交通特征,运用皮尔逊相关系数法选择特征,通过主成分分析进行特征降维.结合空域结构使用聚类算法确定分类,并从时空及典型日视角切入,分析不同对流天气场景对空域通行能力的影响.以广州终端区为例进行实验,结果表明,影响终端区交通情况的天气分类具有一定的合理性,能为交通流量管理措施提供指导辅助决策.
In view of the uncertainty of weather and air traffic,clustering algorithm was used to identify similar convective weather in terminal area,and the historical operational scenarios were classified into several categories.Extracted similar weather and traffic features,selected features through Pearson correlation coefficient,and used principal component analysis to reduce dimensionality.Combined with the airspacestructure,the k-means clustering algorithm was used to determine the classification,and analysis the influence of different convective weather scenarios on airspace capacity from the perspective of temporal-spatial and typical days.Conducted experiments on the Guangzhou terminal area.The results showed that the weather classification that affected the traffic in the terminal area was reasonable to provide guidance and decision-making assistance for traffic flow management measures.
作者
王洪
彭瑛
郭聪聪
陈博伟
WANG Hong;PENG Ying;GUO Cong-cong;CHEN Bo-wei(College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China)
出处
《哈尔滨商业大学学报(自然科学版)》
CAS
2021年第6期695-702,共8页
Journal of Harbin University of Commerce:Natural Sciences Edition
关键词
终端区
对流天气
聚类算法
主成分分析
皮尔逊相关系数
terminal area
convective weather
clustering algorithm
principal component analysis
Pearson correlation coefficient