J4 ›› 2014, Vol. 27 ›› Issue (3): 61-65.doi: 10.3976/j.issn.1002-4026.2014.03.012

• 交通运输专栏 • 上一篇    下一篇

基于SVM和RBF神经网络的民航不安全事件组合预测方法

单晶晶1,吴建军1,张晨2,赵芳霞1   

  1. 1.北京交通大学交通运输学院,北京 100044; 2.中国民航科学技术研究院,北京 100028
  • 收稿日期:2014-04-11 出版日期:2014-06-20 发布日期:2014-06-20
  • 作者简介:单晶晶(1990-),女,硕士研究生,研究方向为民航安全分析。Email:13120773@bjtu.edu.cn

SVM and RBF neural network based  hybrid prediction model for unsafe events of civil aviation

 SHAN Jing-Jing1, WU Jian-Jun1, ZHANG Chen2, ZHAO Fang-Xia1   

  1. 1.School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China;   2.China Academy of Civil Aviation Science and Technology, Beijing 100028, China
  • Received:2014-04-11 Online:2014-06-20 Published:2014-06-20

摘要:

        为提高航空业安全水平,预测飞行过程中存在的主要事故风险,本文基于2002年2月至2014年2月的民航事故数据统计,采用SVM和RBF神经网络加权组合模型对民航不安全事件发生原因及飞行阶段事故数量进行了预测。通过对3种典型预测方法的均方根误差比较,证明了此方法的可行性与有效性,结论可为民航安全管理提供科学依据。

关键词: 不安全事件预测, SVM, RBF神经网络

Abstract:

        This paper predicts the number of civil aviation unsafe event factors and stages with SVM and RBF neural network weighted combination model to improve the level of aviation safety and predict major flight accident risk, which is based on the accident data from Feb.2002 to Feb.2014. Its feasibility and effectiveness are proved by the comparison for the root mean square errors of three typical prediction methods. This can provide a scientific reference for the administration of civil aviation security.

Key words: prediction of unsafe events, support vector machine, RBF neural network

中图分类号: 

  • U8