基于相依网络和SVM的管制系统运行态势评估

doi:10.12305/j.issn.1001-506X.2021.05.16

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (5): 1287-1294.doi: 10.12305/j.issn.1001-506X.2021.05.16

基于相依网络和SVM的管制系统运行态势评估

李昂^1,²(), 聂党民^1,²(), 温祥西^1,^2,*(), 王泽坤³(), 杨诚修¹()

1. 空军工程大学空管领航学院, 陕西西安 710051
2. 国家空管防相撞技术重点实验室, 陕西西安 710051
3. 中国人民解放军32211部队，陕西榆林 719006

收稿日期:2020-06-15 出版日期:2021-05-01 发布日期:2021-04-27
通讯作者: 温祥西 E-mail:18251826766@163.com;ndm121@163.com;wxxajy@163.com;mikeyze@163.com;ycx96123@163.com
作者简介:李昂(1996—), 男, 硕士研究生, 主要研究方向为空管系统的相依网络。E-mail: 18251826766@163.com|聂党民(1966—), 男, 副教授, 硕士, 主要研究方向为空中交通管理、管制指挥与安全。E-mail: ndm121@163.com|温祥西(1984—), 男, 讲师, 博士, 主要研究方向为航空网络、冲突探测与解脱。E-mail: wxxajy@163.com|王泽坤(1995—), 男，硕士，主要研究方向为空中交通复杂性、冲突探测与解脱。E-mail: mikeyze@163.com|杨诚修(1996—), 男, 硕士研究生, 主要研究方向为航空集群。E-mail: ycx96123@163.com
基金资助:
国家自然科学基金(71801221)

Operation situation assessment of control system based on interdependent network and SVM

Ang LI^1,²(), Dangmin NIE^1,²(), Xiangxi WEN^1,^2,*(), Zekun WANG³(), Chengxiu YANG¹()

1. Air Traffic Control and Navigation College, Air Force Engineering University, Xi'an 710051, China
2. National Key Laboratory of Air Traffic Collision Prevention, Xi'an 710051, China
3. Unit 32211 of the PLA, Yulin 719006, China

Received:2020-06-15 Online:2021-05-01 Published:2021-04-27
Contact: Xiangxi WEN E-mail:18251826766@163.com;ndm121@163.com;wxxajy@163.com;mikeyze@163.com;ycx96123@163.com

摘要/Abstract

摘要：

客观准确地评估管制系统整体的运行态势, 能够帮助管制员从宏观上掌控管制系统的运行状态, 针对这一问题本文提出了一种基于相依网络和支持向量机(support vector machine, SVM)的管制系统运行态势评估方法。使用管制-飞行状态相依网络模型来代表管制系统, 充分考虑了空中航空器与地面管制员的整体状态, 采用相依网络指标描述网络运行态势。评估方法选择SVM, 将运行态势评估问题转化为分类问题, 以点到运行顺畅分类边界的距离作为指标从整体上评估管制系统的运行态势, 降低了主观因素对评估方法的影响。仿真分析与在长水机场的实例分析结果均表明: 该评估方法能够给出具体的管制系统运行态势值, 为管制员提供客观准确的态势信息。

关键词: 空中交通管制, 复杂网络, 相依网络, 支持向量机, 态势评估

Abstract:

An objective and accurate assessment of the overall operation situation of the control system can help the controller to control the operation state of the control system on the macro level. To solve the problem, an operation situation assessment method of control system based on the interdependent network and support vector machine(SVM) is proposed. The control-aircraft state interdependent network model is used to represent the control system, which fully considers the overall state of aircrafts and controllers. The interdependent network indicators are used to describe network operation situation. Choosing SVM as assessment method, the operation situation assessment problem is transformed into a classification problem. The distance from the point to the smooth operation classification boundary is used as an index to assess the operation situation of the control system, thus reducing the influence of subjective factors on the assessment method. The results of simulation analysis and an example analysis at Changshui Airport show that the assessment method can give specific operation situation values of the control system and provide objective and accurate situation information for the controllers.

Key words: air traffic control, complex network, interdependent network, support vector machine (SVM), situation assessment

中图分类号:

V355

李昂, 聂党民, 温祥西, 王泽坤, 杨诚修. 基于相依网络和SVM的管制系统运行态势评估[J]. 系统工程与电子技术, 2021, 43(5): 1287-1294.

Ang LI, Dangmin NIE, Xiangxi WEN, Zekun WANG, Chengxiu YANG. Operation situation assessment of control system based on interdependent network and SVM[J]. Systems Engineering and Electronics, 2021, 43(5): 1287-1294.

图/表 14

图1

图2

图3

表1

图4

图5

表2

图6

图7

图8

表3

图9

表4

表5

参考文献 33

1	SUN M , RAND K , FLEMING C . 4 dimensional waypoint gene-ration for conflict-free trajectory based operation[J]. Aerospace Science and Technology, 2019, 88, 350- 361. doi: 10.1016/j.ast.2019.03.035
2	ENDSLEY M R. Design and evaluation for situation awareness enhancement[C]//Proc. of the 32nd Human Factors Society Annual Meeting, 1988: 97-101.
3	ZHANG Z N , LI L T . Congestion assessment of air traffic network flow system[J]. Science Technology and Engineering, 2019, 30, 23- 31.
4	XIAO M M , ZHANG J , CAI K Q , et al. ATCEM: a synthetic model for evaluating air traffic complexity[J]. Journal of Advanced Transportation, 2016, 50 (3): 315- 325. doi: 10.1002/atr.1321
5	SKORUPSKI , JACEK . The simulation-fuzzy method of assessing the risk of air traffic accidents using the fuzzy risk matrix[J]. Safety Science, 2016, 88, 76- 87. doi: 10.1016/j.ssci.2016.04.025
6	QIU Z Y, YANG Y, ZHU Y B. A scenario-based approach to robust estimation of air traffic flow boundary[C]//Proc. of the IEEE/AIAA Digital Avionics Systems Conference, 2015.
7	KANG L , HANSEN M . Assessing the impact of tactical airport surface operations on airline schedule block time setting[J]. Transportation Research Part C: Emerging Technologies, 2018, 89 (4): 133- 147.
8	BRONSVOORT J , ZISSERMANN P , BARRY S , et al. A framework for assessing and managing the impact of ANSP actions on flight efficiency[J]. Air Traffic Control Quarterly, 2015, 23 (1): 29- 53. doi: 10.2514/atcq.23.1.29
9	TIAN Y , DONG Y L , YE B J , et al. A framework for the assessment of distributed self-separation procedures for air traffic in flow corridors[J]. IEEE Access, 2019, 8, 146- 153.
10	PIRODDI L, PRANDINI M. A geometric approach to air traffic complexity evaluation for strategic trajectory management[C]//Proc. of the IEEE Conference on Decision & Control, 2011: 213-220.
11	LEE K , FERON E , PRITCHETT A . Describing airspace complexity: airspace response to disturbances[J]. Journal of Guidance, Control and Dynamics, 2009, 32 (1): 210- 222. doi: 10.2514/1.36308
12	李昂, 聂党民, 温祥西, 等. 管制-飞行状态相依网络模型及特性分析[J]. 北京航空航天大学学报, 2020, 46 (6): 1204- 1213.
	LI A , NIE D M , WEN X X , et al. Control-aircraft state interdependent network model and the characteristic analysis[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46 (6): 1204- 1213.
13	王兴隆, 齐雁楠, 潘维煌. 基于功能脆弱性的空中交通相依网络流量分配[J]. 航空学报, 2020, 41 (4): 184- 192.
	WANG X L , QI Y N , PAN W H . Flow allocation of air traffic interdependent network based on functional vulnerability[J]. Acta Aeronautica et Astronautica Sinica, 2020, 41 (4): 184- 192.
14	GAO J X , BULDYREV , SERGEY V , et al. Networks formed from interdependent networks[J]. Nature Physics, 2012, 8, 40- 48. doi: 10.1038/nphys2180
15	HAVLIN S , KENETT D Y , BASHAN A , et al. Vulnerability of network of networks[J]. European Physical Journal Special Topics, 2014, 223, 2087- 2106. doi: 10.1140/epjst/e2014-02251-6
16	MICHAEL M D, LOUIS M S, AMIR B, et al. Vulnerability of interdependent networks and networks of networks[M]. GARASA. Interconnected Networks, Springer, 2019: 79-99.
17	HOU S , GARRIDO A , FAN N . Vulnerability analysis of interdependent network via integer programming approaches[J]. Optimization Letters, 2019, 14, 32- 38. doi: 10.1007/s11590-019-01504-y
18	BOCCALETTI S , BIANCONI G , CRIADO R , et al. The structure and dynamics of multilayer networks[J]. Physics Reports, 2014, 544 (1): 1- 122. doi: 10.1016/j.physrep.2014.07.001
19	孟光磊, 周铭哲, 朴海音, 等. 基于协同战术识别的双机编队威胁评估方法[J]. 系统工程与电子技术, 2020, 42 (10): 2285- 2293. doi: 10.3969/j.issn.1001-506X.2020.10.17
	MENG G L , ZHOU M Z , PIAO H Y , et al. Threat assessment method of dual-aircraft formation based on cooperative tactical recognition[J]. Systems Engineering and Electronics, 2020, 42 (10): 2285- 2293. doi: 10.3969/j.issn.1001-506X.2020.10.17
20	SAXENA A , CELAYA J , SAHA B , et al. Metrics for offline evaluation of prognostic performance[J]. International Journal of Prognostics and Health Management, 2010, 1 (1): 2153- 2648.
21	SHI J Y, SHI M, WANG L. Performance evaluation method of remaining useful life prediction based on pseudo life[C]//Proc. of the IEEE International Conference on Industrial Engineering & Engineering Management, 2011: 421-425.
22	SHARMA T K , YOUNG E L , SHERRY M , et al. Evaluation of a rapid, new method for detecting serum IgG antibodies to helicobacter pylori[J]. Clinical Chemistry, 1997, 43 (5): 832- 836. doi: 10.1093/clinchem/43.5.832
23	MEYER D , HAEUSSERMANN A , BARTH K , et al. Evaluation of three methods to assess the degree of milk-out in dairy cows[J]. Animal: an International Journal of Animal Bioscience, 2019, 14 (1): 1- 8.
24	LIDIA A M , MARCELA G A , ALFREDO I , et al. A multiobjective DEA model to assess the eco-efficiency of agricultural practices within the CF+DEA method[J]. Computers and Electronics in Agriculture, 2019, 161, 151- 161. doi: 10.1016/j.compag.2018.05.037
25	ANDREA A O , MASAKI T , BEATA D , et al. Freestyle gymnastic exercise can be used to assess complex coordination in a variety of sports[J]. Journal of Exercise Science & Fitness, 2020, 18 (2): 47- 56.
26	LASKOV P , GEHL C , KRUGER S , et al. Incremental support vector learning: analysis, implementation and applications[J]. Journal of Machine Learning Research, 2006, 7 (3): 234- 239.
27	MARTIN H . Predicting irregular flight operations using a binary machine learning approach based on national meteorological data[J]. Dissertations & Theses Gradworks, 2014, 8, 162- 167.
28	ASLAHI S , RAHMANI R , CHIZARI M . A hybrid method consisting of GA and SVM for intrusion detection system[J]. Neural Computing and Applications, 2016, 27 (6): 36- 40. doi: 10.1007/s00521-015-1964-2
29	LIU Y L , LIU Y , MARK H , et al. Using machine learning to analyze air traffic management actions: ground delay program case study[J]. Transportation Research Part E: Logistics and Transportation Review, 2019, 131, 80- 95. doi: 10.1016/j.tre.2019.09.012
30	吴明功, 蒋旭瑞, 温祥西, 等. 基于支持向量机的概率型飞行冲突探测算法[J]. 飞行力学, 2019, 37 (2): 56- 60.
	WU M G , JIANG X R , WEN X X , et al. A probabilistic flight conflict detection algorithm based on SVM[J]. Flight Dyna-mics, 2019, 37 (2): 56- 60.
31	韩冬, 张学军, 聂尊礼, 等. 一种基于SVM的低空飞行冲突探测算法[J]. 北京航空航天大学学报, 2018, 44 (3): 576- 582.
	HAN D , ZHANG X J , NIE Z L , et al. A conflict detection algorithm for low-altitude flights based on SVM[J]. Journal of Beijing University of Aeronautics and Astronautics, 2018, 44 (3): 576- 582.
32	SHEN K Q , ONG C J , LI X P , et al. Feature selection via sensitivity analysis of SVM probabilistic outputs[J]. Machine Learning, 2008, 70, 1- 20.
33	张进, 胡明华, 张晨, 等. 空域复杂性建模[J]. 南京航空航天大学学报, 2010, 42 (4): 454- 460. doi: 10.3969/j.issn.1005-2615.2010.04.011
	ZHANG J , HU M H , ZHANG C , et al. Airspace complexity modeling[J]. Nanjing University of Aeronautics & Astronautics, 2010, 42 (4): 454- 460. doi: 10.3969/j.issn.1005-2615.2010.04.011

m的取值范围	运行态势等级	运行态势等级解释
m≤0	高	管制系统的运行态势良好
0＜m≤1	中	管制系统的运行态势下降, 但仍较好
1＜m＜2	低	管制系统的运行态势较为严峻
m≥ 2	差	管制系统的运行态势已经非常严峻

序号	拓扑指标					标签
序号	${\bar k}$	NE	ND	${\bar s}$	${\bar C}$	标签
网络1	9.026	0.272	1.130	42.93	0.733	1
网络2	7.795	0.246	0.746	28.36	0.708	1
网络3	7.385	0.244	0.648	24.61	0.703	1
┆	┆	┆	┆	┆	┆	┆
网络28	10.469	0.270	0.949	59.780	0.821	-1
网络29	11.813	0.273	1.237	77.924	0.773	-1
网络30	11.188	0.267	0.940	59.217	0.784	-1

序号	m取值	等级	序号	m取值	等级
网络1	-1.50	高	网络16	1.89	低
网络2	-8.23	高	网络17	1.78	低
网络3	0.21	中	网络18	1.96	低
网络4	-1.80	高	网络19	1.85	低
网络5	0.28	中	网络20	2.94	差
网络6	-5.67	高	网络21	1.95	低
网络7	-7.01	高	网络22	2.14	差
网络8	-1.16	高	网络23	3.19	差
网络9	-1.37	高	网络24	2.69	差
网络10	0.56	中	网络25	3.29	差
网络11	0.84	中	网络26	2.08	差
网络12	0.04	中	网络27	2.93	差
网络13	0.67	中	网络28	2.10	差
网络14	0.12	中	网络29	2.04	差
网络15	-1.29	高	网络30	2.09	差

时刻	拓扑指标
时刻	${\bar k}$	NE	ND	${\bar s}$	${\rm{\bar k}}$C
17:00:21	11.500	0.267	1.044	65.769	0.755
17:05:22	10.271	0.266	0.882	51.156	0.759
17:10:20	9.259	0.273	0.995	52.716	0.779
17:15:22	8.776	0.258	0.608	29.198	0.716
17:20:21	8.136	0.272	0.496	21.34	0.730
17:25:23	8.410	0.241	0.890	33.80	0.688

时刻	评估值	运行态势等级
17:00:21	4.26	差
17:05:22	2.59	差
17:10:20	1.48	低
17:15:22	0.85	中
17:20:21	-5.15	高
17:25:23	-3.64	高

基于相依网络和SVM的管制系统运行态势评估

Operation situation assessment of control system based on interdependent network and SVM

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 33

相关文章 15

编辑推荐

Metrics

本文评价

[1]	薛春岭, 曹菲, 孙庆, 秦建强, 冯晓伟. 基于多特征信息融合的海面微弱目标检测[J]. 系统工程与电子技术, 2022, 44(11): 3338-3345.
[2]	王琮, 沈会良, 夏永祥, 白光晗, 方依宁. 装备保障体系关键节点分析[J]. 系统工程与电子技术, 2022, 44(10): 3134-3142.
[3]	朱峰, 蒋倩倩, 林川, 杨啸. 基于支持向量机的典型宽带电磁干扰源识别[J]. 系统工程与电子技术, 2021, 43(9): 2400-2406.
[4]	王岩韬, 杨拯. 航班运行风险网络的传播与控制改进[J]. 系统工程与电子技术, 2021, 43(9): 2544-2552.
[5]	毕可心, 吴明功, 张文斌, 温祥西, 杜坎. 基于速度障碍法的飞行冲突网络建模与分析[J]. 系统工程与电子技术, 2021, 43(8): 2163-2173.
[6]	王哲, 李建华, 康东. 网络信息体系双层异质相依网络模型鲁棒性[J]. 系统工程与电子技术, 2021, 43(4): 961-969.
[7]	王坤, 侯树贤, 王力. 基于自适应变异PSO-SVM的APU性能参数预测模型[J]. 系统工程与电子技术, 2021, 43(2): 526-536.
[8]	顾凌枫, 何明, 陈国友, 季敏惠, 刘锦涛. 无人机集群系统弹性研究[J]. 系统工程与电子技术, 2021, 43(1): 156-162.
[9]	马愈昭, 王强强, 王瑞松, 熊兴隆. 基于SVD和MPSO-SVM的光纤周界[J]. 系统工程与电子技术, 2020, 42(8): 1652-1661.
[10]	李亚兰, 金炜东, 葛鹏. 基于VMD和特征融合的辐射源信号识别[J]. 系统工程与电子技术, 2020, 42(7): 1499-1503.
[11]	王超, 郭基联, 沈安慰. 基于不对称依赖的相依网络级联故障分析[J]. 系统工程与电子技术, 2020, 42(5): 1093-1101.
[12]	李红光, 郭英, 眭萍, 齐子森, 苏令华. 基于高维特征选择的跳频电台细微特征识别[J]. 系统工程与电子技术, 2020, 42(2): 445-451.
[13]	王强, 贾希胜, 程中华, 王双川, 马云飞. 基于改进的局部保持投影的战时备件分类[J]. 系统工程与电子技术, 2020, 42(1): 133-140.
[14]	吴青, 臧博研, 祁宗仙, 张昱. 基于压缩感知的多核稀疏最小二乘支持向量机[J]. 系统工程与电子技术, 2019, 41(9): 1930-1936.
[15]	王彩云, 黄盼盼, 李晓飞, 王佳宁, 赵焕玥. 基于AEPSO-SVM算法的雷达HRRP目标识别[J]. 系统工程与电子技术, 2019, 41(9): 1984-1989.