Risk Management of Airfield Obstacle Free Space Based on Supervised Neural Network

2018 2nd International Workshop on Renewable Energy and Development

能源学;经济学

Wu, Peng^1 ; Chong, Xiao-Lei^1 ; Wang, Si-Jia^2

Aeronautical Engineering College, Air Force Engineering University, Xi'an

710038, China^1

Residential Environment and Construction Engineering College, Xi 'An Jiaotong University, Xi'an

710049, China^2

关键词: Aircraft trajectory;    BP neural networks;    Distribution rule;    Prediction model;    Reference values;    Simulation data;    Spatial positions;    Supervised neural networks;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/153/3/032007/pdf
DOI  :  10.1088/1755-1315/153/3/032007

来源: IOP

【 摘 要 】

In the application of current airfield clearance standard, operation differences are neglected. As a result, this paper sets up a distributional pattern of flight paths at some airfield and new obstacle limitation standards on various security target levels. It interprets and fits the flight data into actual trajectory curves and applies BP neural network to build a prediction model of the spatial position of aircrafts. Based on this theory, the model is implemented in further statistical analyses of the original and simulation data collected in this airfield, which leads to the establishment of distribution rules of aircraft trajectory. This paper proposes a fresh method to set up an airfield obstacle free space and has important reference values to improve the administration of airfield obstacle free space.