论文部分内容阅读
航空器的飞行状态预测是飞行冲突探测的核心问题,也是保障飞行安全的关键所在。为了准确、高效地预测航空器的飞行状态,提出了一种HMM-BP混合模型。首先深入分析了航空器的飞行特点,从不同角度定义飞行状态并建立几何判定方法;然后通过HMM模型分别对航空器的飞行高度、航向以及速度特征进行时序建模;最后利用BP神经网络对航空器的飞行状态进行了推理预测。研究结果表明,该方法通过分析航空器在扇区内最初5min的雷达航迹数据,能够准确地预测其在扇区剩余时间的飞行状态,且计算速度快、预测效率高,可以有效协助管制员正确掌握航空器的飞行状态。
Aircraft flight status prediction is the core issue of flight conflict detection, but also the key to ensuring flight safety. In order to predict the flight status of aircraft accurately and efficiently, an HMM-BP hybrid model is proposed. Firstly, the flight characteristics of the aircraft are analyzed in depth. The flight state is defined from different angles and the geometric determination method is established. Then, the HMM model is used to time-sequence the aircraft’s flight altitude, course and velocity characteristics. Finally, BP neural network is used to predict the flight of the aircraft The state is inferred to predict. The results show that the proposed method can accurately predict the flight state of the aircraft in the remaining time of the sector by analyzing the radar track data of the first 5 min in the sector, and the method has the advantages of fast calculation speed and high prediction efficiency, which can effectively help the controller to correct Master the aircraft’s flight status.