【摘要】 近年来航班延误日益严重,严重影响民航发展。收集国内某大型航空公司全网络中近3年来的运行数据,利用数据挖掘技术对其分析处理。首先分析各个因素(时刻、月份、机型、机场)-平均延误时间的基本特征;在延误分析的基础上,针对机场-延误关系,应用K-means聚类算法对机场繁忙程度聚类分析,使机场属性值更加精确,提高预测时效性和精确度;接着加入延误因素属性,使用CHAID决策树算法对航空公司全网络近3年数据进行训练,并使用该训练模型分类预测近半年数据。实验结果表明,模型正确率接近80%。该方法可以对延误进行精确预测,协助航空公司对延误采取针对措施。更多还原

【Abstract】 In recent years,the increasingly serious flight delay affects the development of the civil aviation.Firstly,using data mining to analyze the data of a large airline in China in recent 3 years, the relationship between various factors(including time,month,aircraft,airport) and the basic characteristics of the average delay time was analyzed.Based on delay analysis,focusing on the relationship between airport and delay,we used K-means clustering algorithm to analyze the busy degree of airports,which makes the airport property value more precise and improves prediction accuracy;then we added delay property to the airports degree property and used CHAID decision tree algorithm to train the data of an airline for nearly 3 years.The training model was used to predicate recent half a year delay.The experimental results show that the accuracy of the model is close to 80%.This method is meaningful to establish an effective model for predicating delay to help airlines take responsive measures.更多还原