摘要
针对现有的飞行理论对中断起飞决断速度计算研究不足,并且计算方法单一的问题,利用MATLAB/Simulink仿真平台构建了中断起飞距离计算模型,通过计算不同飞行条件下不同故障速度的中断起飞距离,得到大量的训练样本。建立三层神经网络模型,以飞行条件和中断起飞需用长度为输入量,故障速度为目标量,对神经网络模型进行训练,直到均方差达到要求。将神经网络运算结果、仿真平台运算结果、手册数据进行对比,证明了提出的利用神经网络计算起飞决断速度的方法是有效的。利用神经网络,对海拔高度、飞行质量、温度、风速、跑道可用长度变化对中断起飞决断速度的影响进行了分析,给出了相关曲线。使用的神经网络方法精度较高,计算也比较便捷,可以应用到其他机型在不同条件下的中断起飞决断速度计算中,具有一定的实用价值。
Based on the problem of insufficient research and single calculation method of abort takeoff decision speed in the existing flight theory,a calculation model of abort take off distance was built by using the simulation platform of MATLAB/Simulink.By calculating the abort take off distance of different fault speeds under different conditions,a large number of training samples were obtained.A three-layer neural network model was established.Taking flight conditions and the length of abort takeoff as input and fault speed as target,the neural network model was trained until the mean square error meets the requirement.By comparing the results of neural network operation,simulation platform operation and manual data,it is proved that the method of using neural network to calculate the take-off decision speed is effective.The influence of altitude,flight quality,temperature,wind speed and runway available length on abort takeoff decision speed is analyzed by using neural network,and the relevant curves are given.The neural network method used has high accuracy and is convenient.It can be applied to the abort takeoff decision speed calculation of other aircraft under different conditions,and has certain practical value.
作者
潘军
陈柏松
华欣
PAN Jun;CHEN Bai-song;HUA Xin(Aviation University of Air Force,Aviation Operational Service College,Changchun 130022,China)
出处
《科学技术与工程》
北大核心
2019年第24期410-415,共6页
Science Technology and Engineering
