基于鸟击事故征候预测的通用航空安全研究

doi:10.3969/j.issn.1001-506X.2020.09.19

摘要/Abstract

摘要：

作为民航运输的两翼之一,通用航空安全水平直接影响民机系统的安全。目前，对通航以及鸟击事故征候进行预测的研究较少,本文根据收集到的美国从事通用航空活动发生鸟击事故征候安全状况数据,采用长短期记忆(long short-term memory, LSTM)神经网络模型对鸟击事故征候数据进行训练和预测。实验结果显示，与传统模型相比, LSTM模型具有更好的预测效果,精确度更高。基于此,提出了预测稳定性更好的LSMT-均方根误差(LSTM-root mean square error, LSTM-R)模型，为通用航空鸟击事故征候预测提供了手段和方法,加强了通用航空安全管理。

关键词: 通用航空安全, 鸟击事故征候, 事故征候预测, 长短期记忆

Abstract:

As one of the two wings of civil aviation transportation, the general aviation safety directly affects the safety of the civil aircraft systems. There are very few research on bird strike symptom prediction. According to the general aviation safety situation of the bird strike symptom in the United States, the long short-term memory (LSTM) neural network model is used to train and predict the bird strike symptom data. The experimental results show that compared with the traditional models, the LSTM model has a better fitting effect and a higher accuracy. Based on this station, an LSTM-root mean square error (LSTM-R) model with a better prediction stability is proposed, which provides a means and method for the general aviation bird strike symptom prediction, and strengthens the safety management of the general aviation.

Key words: general aviation safety, bird strike symptom, symptom prediction, long short-term memory (LSTM)

中图分类号:

熊明兰, 王华伟, 徐怡, 付强. 基于鸟击事故征候预测的通用航空安全研究[J]. 系统工程与电子技术, 2020, 42(9): 2033-2040.

Minglan XIONG, Huawei WANG, Yi XU, Qiang FU. General aviation safety research based on prediction of bird strike symptom[J]. Systems Engineering and Electronics, 2020, 42(9): 2033-2040.

图/表 12

图1

图2

图3

图4

图5

图6

表1

图7

图8

表2

图9

表3

参考文献 30

1	ANDERSONA A , CARPENTER D S , BEGIER M J , et al. Modeling the cost of bird strikes to US civil aircraft[J]. Transportation Research Part D, 2015, 38, 49- 58. doi: 10.1016/j.trd.2015.04.027
2	ROCAGONZALEZ J L, VERLOPEZ J A, BERMUDEZA G R. Organisational and costing aspects to prevent wildlife strikes on airports: a case study of Spanish airport security managers[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S0925753518314012.
3	WASHBURN B E , CISAR P J , DEVAULTA T L . Wildlife strikes to civil helicopters in the US, 1990-2011[J]. Transportation Research Part D, 2013, 24, 83- 88. doi: 10.1016/j.trd.2013.06.004
4	Federal Aviation Administration. Wildlife strikes to civil aircraft in the United States 1990-2017 [R]. Washington D.C. Federal Aviation Administration, 2019.
5	李卫东.中国民航飞机鸟击事件统计分析与研究[D].西安:西北工业大学, 2005.
	LI W D. Statistical analysis and research on bird attack events of Chinese civil aviation aircraft[D]. Xi'an: Northwestern Polytechnical University, 2005.
6	SIEMANN M H , RITT S A . Novel particle distributions for SPH bird-strike simulations[J]. Computer Methods in Applied Mechanics and Engineering, 2019, 343, 746- 766. doi: 10.1016/j.cma.2018.08.044
7	CAI J , BAO H , ZUO H F , et al. Safety evaluation of airworthiness requirement of bird-strike on aeroplane[J]. Engineering Failure Analysis, 2019, 102, 407- 416. doi: 10.1016/j.engfailanal.2019.04.042
8	KIM D H , KIM S W . Evaluation of bird strike-induced damages of helicopter composite fuel tank assembly based on fluid-structure interaction analysis[J]. Composite Structures, 2019, 201 (15): 676- 686.
9	LOPEALAGO M , CASADO R , BERMUDEZ A , et al. A predictive model for risk assessment on imminent bird strikes on airport areas[J]. Aerospace Science and Technology, 2017, 62 (62): 19- 30.
10	LIU J , LI Y , YU X C , et al. Design of aircraft structures against threat of bird strikes[J]. Chinese Journal of Aeronautics, 2018, 31 (7): 1535- 1558. doi: 10.1016/j.cja.2018.05.004
11	于思璇, 王华伟. 基于稀疏降噪自编码神经网络的通用航空风险预测[J]. 系统工程与电子技术, 2019, 41 (1): 112- 117.
	YU S X , WANG H W . Risk forecasting in general aviation based on sparse de-noising auto-encoder neural network[J]. Systems Engineering and Electronics, 2019, 41 (1): 112- 117.
12	RAO A H, MARAIS K. A state-based approach to modeling general aviation accidents[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S0951832019303424.
13	BURNS K, BONACETO C. An empirically benchmarked human reliability analysis of general aviation[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S0951832017310219.
14	刁斌.飞机风挡鸟撞有限元模拟及撞击影响分析[D].南京:南京航空航天大学, 2017.
	DIAO B. Finite element simulation and impact analysis of aircraft windshield bird collision[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2017.
15	杨盛华, 尹洋, 郭欣萌, 等. 基于多源遥感数据的净空区建筑物三维动态监测[J]. 测绘通报, 2019, (S1): 105- 109.
	YANG S H , YIN Y , GUO X M , et al. Three-dimensional dyna-mic monitoring method of clearance area buildings based on multi-source remote sensing data[J]. Bulletin of Surveying and Mapping, 2019, (S1): 105- 109.
16	OKTAY A B, KOCER A. Differential diagnosis of Parkinson and essential tremor with convolutional LSTM networks[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S1746809419302642.
17	WANG J W , CHEN R X , HE Z C . Traffic speed prediction for urban transportation network: a path based deep learning approach[J]. Transportation Research Part C: Emerging Technologies, 2019, 100, 372- 385. doi: 10.1016/j.trc.2019.02.002
18	LI P, MOHAMED A, YUAN J H. Real-time crash risk prediction on arterials based on LSTM-CNN[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S0001457519311108.
19	ERTAM F . An effective gender recognition approach using voice data via deeper LSTM networks[J]. Applied Acoustics, 2019, 156, 351- 358. doi: 10.1016/j.apacoust.2019.07.033
20	CAO J , LI Z , LI J . Financial time series forecasting model based on CEEMDAN and LSTM[J]. Physica A: Statistical Mechanics and its Applications, 2018, 519, 127- 139.
21	MAJID M, SAFABAKHSH R. Correlational convolutional LSTM for human action recognition[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S0925231219304436.
22	MUZAFFAR S , AFSHARI A . Short-term load forecasts using LSTM networks[J]. Energy Procedia, 2019, 158, 2922- 2927. doi: 10.1016/j.egypro.2019.01.952
23	XIAO C J, CHEN N C, HU C L. Short-and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S0034425719303773.
24	ZHANG Q , WANG H , DONG J Y , et al. Prediction of sea surface temperature using long short-term memory[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14 (10): 1745- 1749. doi: 10.1109/LGRS.2017.2733548
25	ZHANG B, ZHANG H W, ZHAO G M, et al. Constructing a PM 2.5 concentration prediction model by combining auto-encoder with Bi-LSTM neural networks[EB/OL]. [2019-06-03]. https://www.sciencedirect.com/science/article/pii/S1364815219300192.
26	ELSHEIKH A , YACOUT S , OUALI M S . Bidirectional handshaking LSTM for remaining useful life prediction[J]. Neurocomputing, 2019, 323, 148- 156. doi: 10.1016/j.neucom.2018.09.076
27	CABRERA D , GUAMAN A , ZHANG S H , et al. Bayesian approach and time series dimensionality reduction to LSTM-based model-building for fault diagnosis of a reciprocating compressor[J]. Neurocomputing, 2020, 380 (C): 51- 66.
28	GIANCARLO Z , KARIM R . Deep learning with TensorFlow[M]. 2nd ed (photocopy edition) Nanjing: Southeast University press, 2019: 260- 297.
29	陈强. 高级计量经济学及Stata应用[M]. 2版北京: 高等教育出版社, 2018: 246- 247.
	CHEN Q . Advanced econometrics and stata applications[M]. 2nd ed Beijing: Higher Education Press, 2018: 246- 247.
30	DAGUM E B . International encyclopedia of the social & behavioral sciences[M]. 2nd ed America: Pergamon, 2015: 347- 353.

隐藏单元	预测值标准方差	RMSE
18	6.097	4.665 7
19	7.035	5.910 4
20	5.672	4.777 8
21	7.390	6.590 2
22	5.312	5.447 8
$\underline{{\rm{23}}}$	4.652	4.355 6
24	6.008	4.725 7
25	4.731	4.537 4
26	6.792	4.976 6
27	4.978	4.754 4
28	6.770	4.903 8

预测模型	正确率/%	RMSE	时间/s
LSTM	93.24	4.384 4	2.27
LSTM(ab)	90.01	5.388 2	2.30
BP	76.55	16.89	2.12
ARIMA	84.67	7.513	2.03

预测模型	正确率/%	RMSE	时间/s
LSTM	92.65	4.918 18	2.16
LSTM(ab)	89.48	5.412 6	2.18
BP	78.07	14.312 8	2.04
ARIMA	83.94	9.452 7	1.86

[1]	聂倩, 杨丽花, 呼博, 任露露. 基扩展模型下基于LSTM神经网络的时变信道预测方法[J]. 系统工程与电子技术, 2022, 44(9): 2971-2977.
[2]	方伟, 王玉, 闫文君, 林冲. 基于神经网络的符号化飞行动作识别[J]. 系统工程与电子技术, 2022, 44(3): 737-745.
[3]	张心宇, 刘源, 宋佳凝. 基于LSTM神经网络的短期轨道预报[J]. 系统工程与电子技术, 2022, 44(3): 939-947.
[4]	蔺瑞管, 王华伟, 车畅畅, 倪晓梅, 熊明兰. 基于LSTM分类器的航空发动机预测性维护模型[J]. 系统工程与电子技术, 2022, 44(3): 1052-1059.
[5]	曾航, 张红梅, 任博, 崔利杰, 武江南. 基于改进LSTM模型的航空安全预测方法研究[J]. 系统工程与电子技术, 2022, 44(2): 569-576.
[6]	谢磊, 丁达理, 魏政磊, 汤安迪, 张鹏. AdaBoost-PSO-LSTM网络实时预测机动轨迹[J]. 系统工程与电子技术, 2021, 43(6): 1651-1658.
[7]	胡晓月, 康凯, 钱骅, 张舜卿. 基于LSTM的LEO卫星链路自适应算法[J]. 系统工程与电子技术, 2021, 43(1): 237-243.
[8]	吴子龙, 陈红, 雷迎科, 李昕, 熊颢. 基于堆栈式LSTM网络的通信辐射源个体识别[J]. 系统工程与电子技术, 2020, 42(12): 2915-2923.