Risk Index Prediction of Civil Aviation Based on Deep Neural Network

论文摘要

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.

论文目录

• 0 Introduction
• 1 Civil Aviation Safety Data System
•   1.1 Risk evaluation index
•   1.2 Unsafe events of civil aviation
•   1.3 Methods of risk prediction of aviation safety
• 2 Risk of Civil Aviation Prediction Model
•   2.1 DNN structure and learning mechanism
•     2.1.1 Auto-encoder （AE）
•     2.1.2 Denoising auto-encoder （DAE）
•   2.2 Steps of prediction model
• 3 Example
•   3.1 Data processing
•   3.2 Risk prediction of civil aviation safety
•   3.3 Comparison
• 4 Conclusions

文章来源

类型: 期刊论文

作者: NI Xiaomei,WANG Huawei,CHE Changchang

来源: Transactions of Nanjing University of Aeronautics and Astronautics 2019年02期

年度: 2019

分类: 工程科技Ⅱ辑,工程科技Ⅰ辑,信息科技

专业: 安全科学与灾害防治,航空航天科学与工程,自动化技术

单位: College of Civil Aviation,Nanjing University of Aeronautics and Astronautics

基金: supported by the Joint Funds of the National Natural Science Foundation of China (No. U1833110)

分类号: TP183;V328

DOI: 10.16356/j.1005-1120.2019.02.014

页码: 313-319

总页数: 7

文件大小: 394K

下载量: 38