机动区航空器速度异常检测研究
|
摘要
随着航空器起降架次的增加,机动区航空器运动过程中存在的不确定性因素增多,从而加重了塔台管制员的工作负荷。针对上述问题,提出基于SVM机动区航空器速度异常检测的方法,为管制员提供智能辅助提醒及预警,降低机场机动区的安全风险。首先对机动区航空器速度异常进行定义、分类和判定,界定出机动区航空器滑行速度异常的标准;其次对航空器ADS-B历史数据进行分析和处理,筛选出完整航迹,确定滑行路径;接着综合考虑航空器滑行位置和机型两个指标,经过统计得到航空器在跑道和滑行道滑行时的正常速度范围和异常速度范围;最后利用SVM方法建立机动区航空器速度异常检测模型,从而找出速度异常的航空器。仿真结果表明,该方法能够快速、有效的检测出航空器在滑行过程中速度异常的位置。
With the increasing in aircraft taking off and landing,the uncertainties in the movement of aircraft in the maneuvering area rise,thus increasing the workload of the tower controller. Aiming at the above problems,this paper puts forward the method of detecting the speed anomaly of the maneuvering aircraft based on SVM,and provides the intelligent auxiliary reminder and early warning for the controller to reduce the security risk of the airport maneuvering area. Firstly,the definition,classification and judgment of the aircraft speed anomaly were defined,and the standard of the aircraft sliding speed was defined. Secondly,the historical data of the aircraft ADS-B were analyzed and processed,and the complete trajectory was selected to determine the gliding path. Considering the aircraft taxiing position and type,the normal speed range and the abnormal speed range of the aircraft on the runway and the taxiway were calculated. Finally,the SVM method was used to establish the aircraft speed anomaly detection model,so as to find out the abnormal speed aircraft. The results of the simulation show that the method can detect the speed of the aircraft during the taxiing process quickly and effectively.
With the increasing in aircraft taking off and landing,the uncertainties in the movement of aircraft in the maneuvering area rise,thus increasing the workload of the tower controller. Aiming at the above problems,this paper puts forward the method of detecting the speed anomaly of the maneuvering aircraft based on SVM,and provides the intelligent auxiliary reminder and early warning for the controller to reduce the security risk of the airport maneuvering area. Firstly,the definition,classification and judgment of the aircraft speed anomaly were defined,and the standard of the aircraft sliding speed was defined. Secondly,the historical data of the aircraft ADS-B were analyzed and processed,and the complete trajectory was selected to determine the gliding path. Considering the aircraft taxiing position and type,the normal speed range and the abnormal speed range of the aircraft on the runway and the taxiway were calculated. Finally,the SVM method was used to establish the aircraft speed anomaly detection model,so as to find out the abnormal speed aircraft. The results of the simulation show that the method can detect the speed of the aircraft during the taxiing process quickly and effectively.
引文
[1]安计勇,朱猛,翟靖轩,王大阜.轨迹多因素异常集成检测[J].计算机工程与设计,2015,36(10):2700-2705.
[2]陈刚,钱猛,刘金.基于划分的高效异常轨迹检测[J/OL].计算机工程与应用,2014,50(24):127-132,172.
[3] J G Lee,J Han,X Li. Trajectory Outlier Detection:A Partitionand-Detect Framework[C]. IEEE,International Conference on Data Engineering. IEEE Computer Society,2008:140-149.
[4] P R Lei. Exploring trajectory behavior model for anomaly detection in maritime moving objects[C]. IEEE International Conference on Intelligence and Security Informatics. IEEE,2013:271-271.
[5] Guo Yuejun,et al. Trajectory Shape Analysis and Anomaly Detection Utilizing Information Theory Tools[J]. Entropy,2017,9(7):323.
[6] D Zhang,et al. i BAT:detecting anomalous taxi trajectories from GPS traces[C]. International Conference on Ubiquitous Computing. ACM,2011:99-108.
[7] S Das,et al. Anomaly detection in flight recorder data:A dynamic data-driven approach[C]. American Control Conference. IEEE,2013:2668-2673.
[8]王超,韩邦村,王飞.基于轨迹谱聚类的终端区盛行交通流识别方法[J].西南交通大学学报,2014,49(3):546-552.
[9]潘新龙,王海鹏,何友,熊伟,周伟.基于多维航迹特征的异常行为检测方法[J].航空学报,2017,38(4):254-263.
[10]姜滨,杨杰明.关于航空器异常数据检测仿真研究[J].计算机仿真,2015,32(12):72-75.
[11]任杰,韩邦村.基于划分检测模型的终端区异常轨迹检测方法[J].航空计算技术,2013,43(6):35-38.
[12]杨志民,刘广利.不确定性支持向量机—算法及应用[M].科学出版社,2012.
[13]杨洁,闫清东,梅向辉.基于支持向量机的车辆行为分析方法研究[J].南京邮电大学学报(自然科学版),2015,35(4):74-80.
[14]李楠,吕弘哲.基于场面监视数据航空器场面滑行路径确定[J].航空计算技术,2016,46(2):6-9.
[2]陈刚,钱猛,刘金.基于划分的高效异常轨迹检测[J/OL].计算机工程与应用,2014,50(24):127-132,172.
[3] J G Lee,J Han,X Li. Trajectory Outlier Detection:A Partitionand-Detect Framework[C]. IEEE,International Conference on Data Engineering. IEEE Computer Society,2008:140-149.
[4] P R Lei. Exploring trajectory behavior model for anomaly detection in maritime moving objects[C]. IEEE International Conference on Intelligence and Security Informatics. IEEE,2013:271-271.
[5] Guo Yuejun,et al. Trajectory Shape Analysis and Anomaly Detection Utilizing Information Theory Tools[J]. Entropy,2017,9(7):323.
[6] D Zhang,et al. i BAT:detecting anomalous taxi trajectories from GPS traces[C]. International Conference on Ubiquitous Computing. ACM,2011:99-108.
[7] S Das,et al. Anomaly detection in flight recorder data:A dynamic data-driven approach[C]. American Control Conference. IEEE,2013:2668-2673.
[8]王超,韩邦村,王飞.基于轨迹谱聚类的终端区盛行交通流识别方法[J].西南交通大学学报,2014,49(3):546-552.
[9]潘新龙,王海鹏,何友,熊伟,周伟.基于多维航迹特征的异常行为检测方法[J].航空学报,2017,38(4):254-263.
[10]姜滨,杨杰明.关于航空器异常数据检测仿真研究[J].计算机仿真,2015,32(12):72-75.
[11]任杰,韩邦村.基于划分检测模型的终端区异常轨迹检测方法[J].航空计算技术,2013,43(6):35-38.
[12]杨志民,刘广利.不确定性支持向量机—算法及应用[M].科学出版社,2012.
[13]杨洁,闫清东,梅向辉.基于支持向量机的车辆行为分析方法研究[J].南京邮电大学学报(自然科学版),2015,35(4):74-80.
[14]李楠,吕弘哲.基于场面监视数据航空器场面滑行路径确定[J].航空计算技术,2016,46(2):6-9.