基于LS-SVM的航空器进场飞行时间预测  

Arrival Flight Time Prediction Based on LS-SVM

作　　者：李阳[1] 聂党民[1] 温祥西[1] LI Yang;NIE Dang min;WEN Xiang xi(College of Air Traffic Control and Navigation,Air Force Engineering University,Xi′an 710051,China)

机构地区：[1]空军工程大学空管领航学院,陕西西安710051

出　　处：《航空计算技术》2018年第3期74-77,共4页Aeronautical Computing Technique

基　　金：总参军训部教育训练专项项目资助(参训2015[573]号)

摘　　要：航空器预计到达时刻(ETA)的准确预测是航空器进场排序与调配的基础。基于最小二乘支持向量机方法(LS-SVM),对航空器进场飞行时间进行预测。通过对历史雷达数据进行收集,建立支持向量训练集,使用LS-SVM方法,建立航空器进场过程中的位置、高度、进场飞行速度及所需时间之间关系,预测航空器进场飞行时间。以咸阳机场为例建立仿真实验,将航空器进场飞行时间预测的均方根误差控制在11 s。仿真结果表明,可以实现对进场飞行时间的有效预测。The Estimated Time of Arrival（ ETA） is the basic of conflict allocation and prioritizing landing flights. A method of Least Square Support Vector Machine（ LS-SVM） is proposed to predict the arrival flight time. Historical radar data are collected and analysed firstly,with the LS-SVM,to establish a relationship between position,height and time,speed of flight in the process of aircraft approach,then the arrival flight time of aircraft are predicted. Taking the arrival to Xianyang International Airport as example,the simulation results indicate that,with the LS-SVM,the RMSE between predicted and actual time of arrival is controlled within 11 s. Simulation results show that what we use can effectively predict the arrival flight time.

关 键 词：预计到达时间 飞行时间预测 LS-SVM RMSE 

分 类 号：V355[航空宇航科学与技术—人机与环境工程]