Risk Index Prediction of Civil Aviation Based on Deep Neural Network

被引：0
作者：
Ni X. [1 ]
Wang H. [1 ]
Che C. [1 ]
机构：
[1] College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing
来源：
Transactions of Nanjing University of Aeronautics and Astronautics | 2019年 / 36卷 / 02期
基金：
中国国家自然科学基金;
关键词：
Denoising auto encoder; Neural network; Risk index; Unsafe events;
D O I：
10.16356/j.1005-1120.2019.02.014
中图分类号：
学科分类号：
摘要：
Safety is the foundation of sustainable development in civil aviation. Although catastrophic accidents are rare, indicators of potential incidents and unsafe events frequently materialize. Therefore, a history of unsafe data are considered in predicting safety risks. A deep learning method is adopted for extracting reactions in safety risks. The deep neural network (DNN) model for safety risk prediction is shown to extract complex data characteristics better than a shallow network model. Using extended unsafe data and monthly risk indices, hidden layers and iterations are determined. The effectiveness of DNN is also revealed in comparison with the traditional neural network. Through early risk detection using the method in the paper, airlines and the government can mitigate potential risk and take proactive measures to improve civil aviation safety. © 2019, Editorial Department of Transactions of NUAA. All right reserved.
引用
收藏
页码：313 / 319
页数：6
相关论文
共 14 条
  • [1] Janic M., An assessment of risk and safety in civil aviation, Journal of Air Transport Management, 6, 1, pp. 43-50, (2000)
  • [2] Wang H.W., Wu H.Q., Reliability evaluation model based on data fusion for aircraft engines, Transactions of Nanjing University of Aeronautics and Astronautics, 29, 4, pp. 318-324, (2012)
  • [3] Li Y.P., Jia C.L., Partial improvement of traditional grey-Markov model and its application on fault prediction, Transactions of Nanjing University of Aeronautics and Astronautics, 34, 4, pp. 449-455, (2017)
  • [4] Liu G., Wu Z.Z., Li S.Y., Study on risk index assessment method of urban accident disasters, International Conference on Reliability, pp. 1119-1123, (2014)
  • [5] Yang G.P., Yang Z.X., Research of computing the vessels' collision risk index by multiple parameters based on neural network with genetic algorithm, International Conference on Instrumentation, pp. 712-714, (2013)
  • [6] Brooker P., Experts, Bayesian belief networks, rare events and aviation risk estimates, Safety Science, 49, 8, pp. 1142-1155, (2011)
  • [7] Dalto M., Matusko J., Vasak M., Deep neural networks for ultra short term wind forecasting, IEEE International Conference on Industrial Technology, pp. 1657-1663, (2015)
  • [8] Andrei F., ICAO Doc 9859 AN/474,Safety management manual, 3, 1, pp. 129-130, (2011)
  • [9] Bengio Y., Lamblin P., Popoviei D., Et al., Greedy layer wise training of deep networks, Proc of the 12th Annual Conference on Neural Information Processing System, pp. 153-160, (2006)
  • [10] Chen Z., Deng S., Chen X., Et al., Deep neural networks-based rolling bearing fault diagnosis, Microelectronics Reliability, 3, 6, pp. 327-333, (2017)
12