中国安全科学学报 ›› 2018, Vol. 28 ›› Issue (6): 67-72.doi: 10.16265/j.cnki.issn1003-3033.2018.06.012

• 安全系统学 • 上一篇    下一篇

管制移交人误本体建模及BN诊断研究

王洁宁1,2 教授, 庾睿1,2   

  1. 1 中国民航大学 空中交通管理学院,天津 300300;
    2 中国民航大学 天津市空管运行规划与安全技术重点实验室,天津 300300
  • 收稿日期:2018-03-10 修回日期:2018-05-10 出版日期:2018-06-28 发布日期:2020-11-25
  • 作者简介:王洁宁(1966—),男,甘肃兰州人,博士,教授,硕士生导师,主要从事空管运行安全及空管系统仿真方面的研究。E-mail:wang_jiening@aliyun.com;庾睿(1993—),男,安徽马鞍山人,硕士研究生,研究方向为空管运行安全。E-mail:13072015208@163.com。
  • 基金资助:
    国家重点研发计划资助项目(2016YFB0502401)。

Research on human error ontology modeling and BN diagnosisfor handover in ATM system

WANG Jiening1,2, YU Rui1,2   

  1. 1 College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China;
    2 Tianjin Key Laboratory of Operation Programming and Safety Technology of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China
  • Received:2018-03-10 Revised:2018-05-10 Online:2018-06-28 Published:2020-11-25

摘要: 为管控人为差错导致的空中交通管制(ATM)移交风险,提高空管运行安全,基于空管人误分类模型(HERA-JANUS)构建领域本体模型,并借助BNTab插件和NeticaJ接口将领域本体转化为贝叶斯网络(BN)模型,通过软件Netica对管制移交人误进行可视化诊断;利用Netica训练美国航空安全报告系统(ASRS)中的统计数据,修正先验概率,以实际案例验证模型的有效性,并得出关键差错行为。结果表明:BN诊断可实现管制移交人误关键因素的识别,信息发送不正确、管制员误判、较晚和(或)没有发现目标等3种内部差错行为显著影响信息传输、行为选择和行为时间。

关键词: 管制移交, 人误诊断, 本体转化, 贝叶斯网络(BN), 空管人误分类模型(HERA-JANUS)

Abstract: For the purpose of controlling the risk of human error in the handover process in ATM under the influence of human error and improving the security of operation,an ATM human error ontology model was built on the basis of the model of HERA-JANUS,and a human error diagnosis BN model was extracted from the domain ontology model by means of BNTab and NeticaJ subsequently.Also,a revised prior BN was acquired by training statistical data from ASRS database,and a certain unsafe event relating to handover was used as an example to verify the effectiveness of the BN and find key errors.The results show that key factors in human errors in handover can be identified in virtue of the BN transformed from the ontology,and three kinds of internal error behaviors such as incorrect transmit information,misjudgment,late or no detection have a significant influence on information transfer,selection of action,timing of action,respectively.

Key words: handover in air traffic management(ATM), human error diagnosis, ontology extraction, Bayesian network (BN), human error in ATM technique-JANUS (HERA-JANUS) model

中图分类号: