-
摘要:
为提高机场鸟击防范管理水平，实现探鸟雷达与多种驱鸟设备联动，提出一种基于支持向量机（SVM）的机场智能驱鸟决策方法。该方法包括训练和测试两部分。训练部分利用机场鸟类探测预警与驱赶联动系统获取的大量历史鸟情信息，结合专家知识，通过数据预处理与支持向量机训练，建立驱鸟策略分类模型；测试部分根据驱鸟实时智能决策结果，对驱鸟策略分类模型进行持续修正与优化。通过某机场的实测鸟情信息数据与若干驱鸟实例，证明驱鸟策略分类模型具有较高的决策正确率，并能够通过自身修正与优化应对各种新问题。本文方法针对实时鸟情信息，实现了多种驱鸟设备的优化组合，克服了驱鸟设备长期重复运行造成的鸟类对驱鸟设备的耐受性问题，极大改善了驱鸟效果。
-
关键词:
- 支持向量机(SVM) /
- 机场 /
- 驱鸟 /
- 分类 /
- 决策
Abstract:To impove the management of bird-strike avoidance at airport and realize the linkage of avian radar with multiple bird-repelling devices, an intelligent decision making method was proposed for airport bird-repelling based on support vector machine (SVM). The method includes two steps of training and testing. In the training step, the bird-repelling strategy classification model was established by data pretreatment and SVM training, which are combined with expert knowledge and large amount of historical bird information collected by the airport linkage system for bird detection, surveillance and repelling. In the testing step, the bird-repelling strategy classification model was continuously corrected and optimized according to the real-time intelligent bird-repelling strategy results. Through the real bird information data and several bird-repelling examples of a certain airport, it is demonstrated that the decision accuracy of bird-repelling strategy classification model is relatively high, and it can solve new problems by self correction and optimization. The proposed method achieves the optimized combination of multiple bird-repelling devices against real-time bird information with great improvement of bird-repelling effect, overcoming the tolerance of birds to the bird-repelling devices due to their long-term repeated operation.
-
Key words:
- support vector machine (SVM) /
- airport /
- bird-repelling /
- classification /
- decision making
-
图 2 机场鸟类探测预警与驱赶联动系统结构
Figure 2. Architecture of airport-based linkage system for avian detection, warning and repelling
图 3 机场鸟类探测预警与驱赶联动系统外场实验
Figure 3. Outfield experimental pictures for airport-based linkage system for avian detection, warning and repelling
图 4 机场鸟类探测预警与驱赶联动系统在某机场的设备分布图
Figure 4. Equipment layout of airport-based linkage system for avian detection, warning and repelling at an airport
表 1 驱鸟策略分类与鸟情数据关联结果
Table 1. Bird-repelling strategies associated with different groups of bird information data
分类 数据总数 具体策略 1 951 将定向声波调整至飞鸟目标方向并启动，采用驱鸟音1 2 816 将定向声波调整至飞鸟目标方向并启动，采用驱鸟音2 3 505 将2部钛雷炮调整至飞鸟目标方向并启动 4 467 将1部钛雷炮调整至飞鸟目标方向并启动，同时将定向声波调整至飞鸟目标方向并启动，采用驱鸟音1 5 560 将1部钛雷炮调整至飞鸟目标方向并启动，同时将定向声波调整至飞鸟目标方向并启动，采用驱鸟音2 6 420 启动2部语音驱鸟器，选择蜂鸣声 7 816 按照与飞鸟目标的距离远近，依次启动跑道西侧的4部煤气炮 8 465 按照与飞鸟目标的距离远近，依次启动跑道东侧的4部煤气炮 
下载: 导出CSV
表 2 不同数据分配情况下的决策结果对比
Table 2. Decision making result comparison under different data assignments
% 训练数据占比 测试数据占比 决策正确率 50 50 76.2 60 40 80.1 70 30 88.6 80 20 95.5 90 10 98.9
下载: 导出CSV
表 3 实例1的驱鸟策略与驱赶效果
Table 3. Bird-repelling strategy and effect for Case 1
驱鸟策略类别 驱赶效果与数据处理 3 苍鹰目标飞离机场区域，将本数据加入训练模型
下载: 导出CSV
表 4 实例2的驱鸟策略与驱赶效果
Table 4. Bird-repelling strategy and effect for Case 2
驱鸟策略类别 驱赶效果与数据处理 1 八哥目标飞离机场区域，将本数据加入训练模型
下载: 导出CSV
表 5 实例3的驱鸟策略与驱赶效果
Table 5. Bird-repelling strategy and effect for Case 3
驱鸟策略类别 驱赶效果与数据处理 7 家燕目标飞离机场区域，将本数据加入训练模型
下载: 导出CSV
表 6 实例4的驱鸟策略与驱赶效果
Table 6. Bird-repelling strategy and effect for Case 4
驱鸟策略类别 驱赶效果与数据处理 7、8 驱鸟效果不明显，目标继续在飞行区活动，需重新设定驱鸟策略并修正训练模型
下载: 导出CSV
表 7 智能决策模型修正
Table 7. Modification of intelligent decision making model
补充策略类别 具体策略 9 启动2部语音驱鸟器，设定为超声波选项
下载: 导出CSV
-
[1] BEASON R C, NOHARA T J, WEBER P.Beware the Boojum:Caveats and strengths of avian radar[J].Human-Wildlife Interactions, 2013, 7(1):16-46. https://digitalcommons.usu.edu/hwi/vol7/iss1/4/ [2] FAA. FAA advisory circular on reporting wildlife aircraft strikes: 150/5200-32B[S]. Washington, D. C. : FAA, 2013: 1-10. [3] 李玉龙, 石霄鹏.民用飞机鸟撞研究现状[J].航空学报, 2012, 33(2):189-198. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kjysh201606020LI Y L, SHI X P.Investigation of the present status of research on bird impacting on commercial airplanes[J].Acta Aeronautica et Astronautica Sinica, 2012, 33(2):189-198(in Chinese) http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=kjysh201606020 [4] 张洁. 2015年度中国民航鸟击航空器信息分析报告: CAST001[R]. 北京: 中国民航科学技术研究院, 2016: 1-5.ZHANG J. 2015's annual report on bird-strike information analysis of China civil aviation: CAST001[R]. Beijing: China Academy of Civil Aviation Science and Technology, 2016: 1-5(in Chinese). [5] 吴雪, 杜杰, 李晓娟, 等.重庆江北机场鸟类群落结构及鸟击防范[J].生态学杂志, 2015, 34(7):2015-2024. http://www.oalib.com/paper/5136074WU X, DU J, LI X J, et al.Avian community structure and bird strike prevention measures at Jiangbei airport in Chongqing city[J].Chinese Journal of Ecology, 2015, 34(7):2015-2024(in Chinese). http://www.oalib.com/paper/5136074 [6] 王维, 孟丽娜.军民合用机场鸟击风险评价及防范措施改进研究[J].科学技术与工程, 2017, 17(2):16-21. https://www.wenkuxiazai.com/word/9190d7fb770bf78a652954b1-1.docWANG W, MENG L N.Bird strike risk assessment and improvement research of prevention suggestions of civilian-military airport[J].Science Technology and Engineering, 2017, 17(2):16-21(in Chinese). https://www.wenkuxiazai.com/word/9190d7fb770bf78a652954b1-1.doc [7] 李益得, 杨道德, 张志强, 等.湖南常德桃花源机场鸟类的时空分布与鸟击防范[J].四川动物, 2010, 29(3):446-451. http://www.cnki.com.cn/Article/CJFDTOTAL-TJSD201503040.htmLI Y D, YANG D D, ZHANG Z Q, et al.Avian spatial and temporal distribution and bird strike preventve measures at Changde Taohuayuan airport[J].Sichuan Journal of Zoology, 2010, 29(3):446-451(in Chinese). http://www.cnki.com.cn/Article/CJFDTOTAL-TJSD201503040.htm [8] 张黎明, 涂鹏, 吴炜, 等.南昌青云谱机场鸟击防范措施研究[J].西南师范大学学报(自然科学版), 2017, 42(2):141-146. https://www.wenkuxiazai.com/doc/6fd6f3174431b90d6c85c7d6.htmlZHANG L M, TU P, WU W, et al.On birdstrike disasters avoidance of Nanchang Qingyunpu airport[J].Journal of Southwest China Normal University (Natural Science Edition), 2017, 42(2):141-146(in Chinese). https://www.wenkuxiazai.com/doc/6fd6f3174431b90d6c85c7d6.html [9] NOHARA T J, BEASON R C, CLIFFORD S P. The role of radar-activated waterfowl deterrents on tailings ponds[C]//Proceedings of the International Oil Sands Tailings Conference. Edmonton: OSTRF Press, 2012, 1: 1-6. [10] 刘政强, 陈寿元, 邵增珍, 等.一种机场近跑道驱鸟系统的设计与实现[J].山东师范大学学报(自然科学版), 2017, 32(1):66-69. http://mall.cnki.net/magazine/Article/SDZK201701020.htmLIU Z Q, CHEN S Y, SHAO Z Z, et al.The design and implementation of bird driving system by the airport runway[J].Journal of Shandong Normal University (Natural Science), 2017, 32(1):66-69(in Chinese). http://mall.cnki.net/magazine/Article/SDZK201701020.htm [11] ANDERSON R. Avian radar systems[EB/OL]. Panoma: Detect Inc, 2007(2007-07-30)[2017-08-15]. http://detect-inc.com/aircraft-birdstrike-avoidance-radar/. [12] NOHARA T J, WEBER P, UNKRAINECA, et al. An overview of avian radar developments-past, present and future[C]//Proceedings of Bird Strike North American Conference. Kingston: Bird Strike Committee, 2007, 1: 1-10. https://core.ac.uk/display/17212134 [13] ROBIN. Robin Systems & Services[EB/OL]. Amsterdam: Robin Radar, 2011(2011-01-15)[2017-08-10]. https://www.robinradar.com/downloads/. [14] 陈唯实, 李敬.雷达探鸟技术发展与应用综述[J].现代雷达, 2017, 39(2):7-17. https://www.cnki.com.cn/qikan-DQWJ201205047.htmlCHEN W S, LI J.Review on development and applications of avian radar technology[J].Modern Radar, 2017, 39(2):7-17(in Chinese). https://www.cnki.com.cn/qikan-DQWJ201205047.html [15] VAPNIK V N.Statistical learning theory[M].New York:Wiley, 1998:421-426. [16] HAN J W, KAMBER M, PEI J.Data mining:Concepts and techniques[M].3rd ed.San Francisco:Morgan Kaufmann, 2011:327-330. [17] 马跃峰, 梁循, 周小平.一种基于全局代表点的快速最小二乘支持向量机稀疏化算法[J].自动化学报, 2017, 43(1):132-141. http://mall.cnki.net/magazine/magadetail/MOTO201701.htmMA Y F, LIANG X, ZHOU X P.A fast sparse algorithm for least squares support vector machine based on global representative points[J].Acta Automatica Sinca, 2017, 43(1):132-141(in Chinese). http://mall.cnki.net/magazine/magadetail/MOTO201701.htm [18] CHEN W S, NING H S, LI J.Flying bird detection and hazard assessment for avian radar system[J].Journal of Aerospace Engineering, 2012, 25(2):246-255. doi: 10.1061/(ASCE)AS.1943-5525.0000131 -
下载:
点击查看大图
计量
- 文章访问数: 790
- HTML全文浏览量: 97
- PDF下载量: 609
- 被引次数: 0
