飞机重着陆预警分析方法
|
摘要
飞机着陆垂直载荷大(重着陆)是严重的安全事件,轻则对机身结构造成伤害,严重时可能导致机毁人亡.从快速存取记录器(Quick Access Recorder, QAR)记录的飞行参数数据中挖掘规律并提前预警,对飞行安全意义重大.首先使用基于动态时间规整距离的时间序列聚类分析来确定飞行操作模式,然后研究在已知和未知飞行操作模式的情况下,重着陆预警分析的效果.对比试验表明,已知飞行操作模式的情况下,重着陆预警的召回率指标较好,可以发现更多的重着陆事件,提高安全性.
Aircraft large vertical load(hard landing) is a serious safety incident which could cause harm to the aircraft and may even lead to serious plane crash. Therefore, mining rules from Quick Access Recorder data and warning in advance is of great significance to flight safety.In this paper, the flight operation mode is determined by time series clustering analysis based on dynamic time warping distance, and then the convolution neural network is used to identify the hard landing under different flight operation modes and identify the hard landing under unclassified flight operations. The comparison of the recognition results shows that the former is better than the latter.
Aircraft large vertical load(hard landing) is a serious safety incident which could cause harm to the aircraft and may even lead to serious plane crash. Therefore, mining rules from Quick Access Recorder data and warning in advance is of great significance to flight safety.In this paper, the flight operation mode is determined by time series clustering analysis based on dynamic time warping distance, and then the convolution neural network is used to identify the hard landing under different flight operation modes and identify the hard landing under unclassified flight operations. The comparison of the recognition results shows that the former is better than the latter.
引文
[1] Boeing Commercial Airplanes. Statistical Summary of Commercial Jet Airplane Accidents[M].Seattle, WA:Boeing, 2015.
[2] Das S, Matthews B L, Srivastava A N, et al. Multiple kernel learning for heterogeneous anomalydetection:algorithm and aviation safety case study[C]//Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, July 25-28, 2010. Washington,DC, USA:ACM, 2010.
[3]许桂梅,黄圣国.应用LS-SVM的飞机重着陆诊断[J].系统工程理论与实践,2010, 30(4):763-8.
[4]聂磊,黄圣国,舒平,等.基于支持向量机(SVM)的民用飞机重着陆智能诊断研究[J].中国安全科学学报,2009, 19(7):149.
[5]曹海鹏,舒平,黄圣国.基于神经网络的民用飞机重着陆诊断技术研究[J].计算机测量与控制,2008,16(7):906-8.
[6]祁明亮,邵雪焱,池宏. QAR超限事件飞行操作风险诊断方法[J].北京航空航天大学学报,2011, 37(10):1207-10.
[7] Shao X, Qi M, Gao M. A risk analysis model of flight operations based on region partition[J].Kybernetes, 2012, 41(10):1497-508.
[8]汪磊,孙瑞山,吴昌旭,等.基于飞行QAR数据的重着陆风险定量评价模型[J].中国安全科学学报,2014,24(2):88-92.
[9]闫伟,赵杨,高原.飞行时序数据相似性挖掘算法研究[J].计算机与网络,2008, 34(21):54-7.
[10]郑磊,池宏,邵雪焱.基于QAR数据的飞行操作模式及其风险分析[J].中国管理科学,2017, 25(10):109-18.
[11]曹惠玲,张浩,王立鑫.QAR译码技术研究与自动译码系统的建立[J].航空维修与工程,2016,(05):74-7.
[12] He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, June 27-30 2015. Las Vegas, NV, USA:IEEE, 2015.
[13] Zheng Y, Liu Q, Chen E, et al. Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks[M]. London:Springer International Publishing, 2014.
[14] Zhao B, Lu H, Chen S, et al. Convolutional neural networks for time series classification[J].系统工程与电子技术(英文版),2017, 28(1):162-9.
[15] He H, Garcia E A. Learning from imbalanced data[J]. IEEE Transactions on Knowledge&Data Engineering, 2008, 21(9):1263-84.
[16] Chen C, Breiman L. Using Random Forest to Learn Imbalanced Data[R]. Berkeley, CA:University of California, 2004.
[17]叶志飞,文益民,吕宝粮.不平衡分类问题研究综述[J].智能系统学报,2009,(02):148-56.
[18] Zhou Z H, Liu X Y. Training cost-sensitive neural networks with methods addressing the class imbalance problem[J]. IEEE Transactions on Knowledge&Data Engineering, 2005, 18(1):63-77.
[19] Paulina H, David M. The Impact of Imbalanced Training Data for Convolutional Neural Networks[D]. Stockholm, Sweden:Kth Royal Institute of Technology, 2015.
[20] Ng W W Y, Zeng G, Zhang J, et al. Dual autoencoders features for imbalance classification problem[J]. Pattern Recognition, 2016, 60:875-89.
[21]杨明,尹军梅,吉根林.不平衡数据分类方法综述[J].南京师范大学学报(工程技术版),2008, 8(4):7-12.
[22]刘陶,李晓白,郎荣玲,等.飞行参数的分段线性表示及其应用[J].微计算机信息,2010(13):199-201.
[23]吴虎胜,张凤鸣,张超,等.多元时间序列的相似性匹配[J].应用科学学报,2013, 31(6):643-9.
[24]周志华.机器学习[M].北京:清华大学出版社,2016.
[25] Zeiler M D. ADADELTA:An Adaptive Learning Rate Method[J/OL] 2012, https://arxiv.org/abs/1212.5701.
[26] Krizhevsky A,Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems, December 03-06, 2012. Lake Tahoe, Nevada:ACM, 2012.
[27] Han J,Kamber M, Pei J,et al.数据挖掘:概念与技术[M].北京:机械工业出版社,2012.
[28] Lin M, Chen Q, Yan S. Network In Network:Proceedings of the International Conference on Learning Representations, Apr 14-16, 2014[C]//Banff, Canada:arXiv, 2014.
[2] Das S, Matthews B L, Srivastava A N, et al. Multiple kernel learning for heterogeneous anomalydetection:algorithm and aviation safety case study[C]//Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, July 25-28, 2010. Washington,DC, USA:ACM, 2010.
[3]许桂梅,黄圣国.应用LS-SVM的飞机重着陆诊断[J].系统工程理论与实践,2010, 30(4):763-8.
[4]聂磊,黄圣国,舒平,等.基于支持向量机(SVM)的民用飞机重着陆智能诊断研究[J].中国安全科学学报,2009, 19(7):149.
[5]曹海鹏,舒平,黄圣国.基于神经网络的民用飞机重着陆诊断技术研究[J].计算机测量与控制,2008,16(7):906-8.
[6]祁明亮,邵雪焱,池宏. QAR超限事件飞行操作风险诊断方法[J].北京航空航天大学学报,2011, 37(10):1207-10.
[7] Shao X, Qi M, Gao M. A risk analysis model of flight operations based on region partition[J].Kybernetes, 2012, 41(10):1497-508.
[8]汪磊,孙瑞山,吴昌旭,等.基于飞行QAR数据的重着陆风险定量评价模型[J].中国安全科学学报,2014,24(2):88-92.
[9]闫伟,赵杨,高原.飞行时序数据相似性挖掘算法研究[J].计算机与网络,2008, 34(21):54-7.
[10]郑磊,池宏,邵雪焱.基于QAR数据的飞行操作模式及其风险分析[J].中国管理科学,2017, 25(10):109-18.
[11]曹惠玲,张浩,王立鑫.QAR译码技术研究与自动译码系统的建立[J].航空维修与工程,2016,(05):74-7.
[12] He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, June 27-30 2015. Las Vegas, NV, USA:IEEE, 2015.
[13] Zheng Y, Liu Q, Chen E, et al. Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks[M]. London:Springer International Publishing, 2014.
[14] Zhao B, Lu H, Chen S, et al. Convolutional neural networks for time series classification[J].系统工程与电子技术(英文版),2017, 28(1):162-9.
[15] He H, Garcia E A. Learning from imbalanced data[J]. IEEE Transactions on Knowledge&Data Engineering, 2008, 21(9):1263-84.
[16] Chen C, Breiman L. Using Random Forest to Learn Imbalanced Data[R]. Berkeley, CA:University of California, 2004.
[17]叶志飞,文益民,吕宝粮.不平衡分类问题研究综述[J].智能系统学报,2009,(02):148-56.
[18] Zhou Z H, Liu X Y. Training cost-sensitive neural networks with methods addressing the class imbalance problem[J]. IEEE Transactions on Knowledge&Data Engineering, 2005, 18(1):63-77.
[19] Paulina H, David M. The Impact of Imbalanced Training Data for Convolutional Neural Networks[D]. Stockholm, Sweden:Kth Royal Institute of Technology, 2015.
[20] Ng W W Y, Zeng G, Zhang J, et al. Dual autoencoders features for imbalance classification problem[J]. Pattern Recognition, 2016, 60:875-89.
[21]杨明,尹军梅,吉根林.不平衡数据分类方法综述[J].南京师范大学学报(工程技术版),2008, 8(4):7-12.
[22]刘陶,李晓白,郎荣玲,等.飞行参数的分段线性表示及其应用[J].微计算机信息,2010(13):199-201.
[23]吴虎胜,张凤鸣,张超,等.多元时间序列的相似性匹配[J].应用科学学报,2013, 31(6):643-9.
[24]周志华.机器学习[M].北京:清华大学出版社,2016.
[25] Zeiler M D. ADADELTA:An Adaptive Learning Rate Method[J/OL] 2012, https://arxiv.org/abs/1212.5701.
[26] Krizhevsky A,Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems, December 03-06, 2012. Lake Tahoe, Nevada:ACM, 2012.
[27] Han J,Kamber M, Pei J,et al.数据挖掘:概念与技术[M].北京:机械工业出版社,2012.
[28] Lin M, Chen Q, Yan S. Network In Network:Proceedings of the International Conference on Learning Representations, Apr 14-16, 2014[C]//Banff, Canada:arXiv, 2014.