摘要
通过对飞行员多维生理信号的分析来预测飞行绩效是飞行安全的重要研究内容之一。基于细菌觅食算法(BFA)优化的广义回归神经网络(GRNN)建立飞行绩效预测模型,对飞行员多维生理信号进行训练,从而预测模拟飞行实验中的飞行绩效。通过对比模型预测结果与飞行绩效真值,验证了该方法的有效性,为飞行绩效的预测提供了一条新途径。
The prediction of flight performance via the analysis of pilots＇ multiple physiological signals is one of the most noteworthy issues in the area of aviation safety. A flight performance prediction model using Bacterial Foraging Algorithm （BFA） to optimize Generalized Regression Neural Network （GRNN） is proposed to train the pilots＇ multiple physiological signals, so as to predict the flight performance in simulated flight tests. Through the comparison between the predicted results of the model and the real value of the flight performance, the validity of the proposed method is proved, which provides a new approach to the prediction of flight performance.
作者
刘文萌
钱晨
黄丹
LIU Wen-meng;QIAN Chen;HUANG Dan(Shanghai Jiao Tong University, a. School of Aeronautics and Astronautic;b. School of Electronic Information and Electrical Engineering, Shanghai 200240, China)
出处
《电光与控制》
北大核心
2018年第4期78-82,共5页
Electronics Optics & Control
基金
国家自然科学基金(61573231)
关键词
飞行绩效预测
飞行安全
广义回归神经网络
细菌觅食算法
多维生理信号
flight performance prediction
flight safety
Generalized Regression Neural Network （GRNN）
Bacterial Foraging Algorithm （BFA）
multiple physiological signals
