基于鲸鱼优化小波神经网络的飞行航迹缺失数据预测方法  

PREDICTION METHOD OF FLIGHT TRACK MISSING DATA BASED ON WHALE OPTIMIZATION WAVELET NEURAL NETWORK

作　　者：石旭东 姜鸿晔 Shi Xudong;Jiang Hongye(School of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学电子信息与自动化学院,天津300300

出　　处：《计算机应用与软件》2020年第7期200-205,共6页Computer Applications and Software

基　　金：国家自然科学基金项目(51377161);天津市高等学校创新团队培养计划项目(TD13-5071)。

摘　　要：飞行航迹数据是分析飞行状态的重要依据。针对飞行航迹缺失数据预测的问题,提出一种基于鲸鱼优化算法和小波神经网络相结合的飞行航迹缺失数据预测模型WOA-WNN。根据飞行航迹数据的非线性关系确定小波神经网络的结构;利用鲸鱼优化算优化传统小波网络的初始阈值和权值,提高收敛速度和预测精度,实现飞行航迹缺失数据的精确预测。实验结果表明:相比传统算法,WOA-WNN模型预测精度更高、预测性能更稳定,可以在输入参数较少的情况下实现航迹缺失数据的精确预测。Flight track data is an important basis for analyzing flight conditions.Aiming at the problem of missing flight track data prediction,this paper proposes a model of missing flight track data prediction based on the combination of whale optimization algorithm and wavelet neural network,WOA-WNN.It determined the structure of wavelet neural network based on the nonlinear relationship of flight track data;the whale optimization algorithm was used to optimize the initial threshold and weight of the traditional wavelet network,so as to improve the convergence speed and prediction accuracy;the accurate prediction of the flight track missing data was realized.The experimental results show that compared with the traditional algorithm,the WOA-WNN has higher prediction accuracy and more stable prediction performance.And it can accurately predict the missing track data with less input parameters.

关 键 词：数据缺失 航迹预测 鲸鱼优化 神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]