Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (17): 254-257.

Previous Articles     Next Articles

Forecasting of airport congestion level based on cluster and neural network algorithms

LI Shanmei1, XU Xiaohao2, MENG Linghang1   

  1. 1.School of Computer Science and Technology, Tianjin University, Tianjin 300072, China
    2.College of Air Traffic Management, Civil Aviation University of China, Tianjin 300300, China
  • Online:2013-09-01 Published:2013-09-13



  1. 1.天津大学 计算机科学与技术学院,天津 300072
    2.中国民航大学 空中交通管理研究基地,天津 300300

Abstract: The mechanism of airport congestion is analyzed. Evaluation method of congestion level is established based on saturation from result indicators. So the five-color warning level of airport congestion is established. 5 features are extracted for depicting airport demand and airport capacity from reason indicators. Neural network classifier algorithm based on cluster is proposed. Real flight data of ATL airport is used to verify this method. The accuracy is up to 80%. The results are proved to be super to the method of BP neural network. Thus the proposed method leads to better forecasting, is applicable for the real condition.

Key words: airport congestion, airport demand, airport capacity, flight delay, neural network, cluster

摘要: 对机场拥挤机理进行分析;从后果类指标入手,提出基于饱和度的拥挤等级评价方法,建立机场拥挤5色预警等级,从原因类指标入手,提取出分别刻画机场容量和需求的5个拥挤特征指标;提出了基于聚类的神经网络分类算法;利用ATL机场实际航班数据进行实例验证,拥挤等级预测的准确度达到80%,预测效果优于BP神经网络。结果表明,提出的方法预测效果较好,具有一定的实用性。

关键词: 机场拥挤, 机场需求, 机场容量, 航班延误, 神经网络, 聚类