航空学报 > 2017, Vol. 38 Issue (S1): 721513-721513   doi: 10.7527/S1000-6893.2017.721513

基于BP神经网络的飞行训练品质评估

姚裕盛, 徐开俊   

  1. 中国民用航空飞行学院 飞行技术学院, 广汉 618307
  • 收稿日期:2017-05-25 修回日期:2017-06-23 出版日期:2017-11-30 发布日期:2017-06-23
  • 通讯作者: 徐开俊 E-mail:k_j_xu@163.com
  • 基金资助:

    国家自然科学基金民航联合基金(U1533127);四川省科技支撑项目(2015GZ0307);中国民用航空飞行学院科技支撑项目(J2014-03);中国民用航空飞行学院创新团队支持计划(JG2016-26)

Quality assessment of flight training based on BP neural network

YAO Yusheng, XU Kaijun   

  1. Institute of Flight Technology, Civil Aviation Flight University of China, Guanghan 618307, China
  • Received:2017-05-25 Revised:2017-06-23 Online:2017-11-30 Published:2017-06-23
  • Supported by:

    The Civil Aviation Joint Funds of the National Naturl Science Foundation of China (U1533127); Sichun Province Science and Technology Support Plan Project (2015GZ0307); Science and Technology Support Plan Project of Civil Aviation Flight University of China(J2014-03);Innovation Team Support Plan Project of Civil Aviation Flight University of China(JG2016-26)

摘要:

为了弥补现有飞行训练品质评估系统存在的不足,本文提出利用飞行员生理信号和飞行操作参数来构建评估指标体系。建立了基于BP神经网络的飞行员飞行训练品质评估模型,通过已完成训练的网络的权值分布计算出各输入指标对最后评分结果的影响,并通过算例分析检验了该模型的可靠性。检验结果表明:经BP神经网络模型训练得到的结果和样本的专家评分基本吻合,选取的评价指标有效,该评估模型能够有效地将飞行员生理信号与飞行训练参数相结合,对飞行员的飞行训练品质进行评价。

关键词: 飞行训练, 品质评估模型, BP神经网络, 指标权重, 生理信号

Abstract:

To overcome the existing shortage of the model for flight training assessment, we propose in this paper the method that makes use of pilot physiological signals and flight parameters to construct the evaluation system based on the BP neural network. The influence of the input indexes on the grading result is calculated according to the weight distributions of the trained network. The reliability of this model is tested by analysis of the numerical example. The validation result shows that the result obtained according to the model proposed is consistent with the sample results of expert evaluation. The proposed model can effectively combine pilot physiological signals with flight training parameters to evaluate the quality of pilot training.

Key words: flight training, quality assessment model, BP neural network, weight value of indexes, physiological signals

中图分类号: