关键词: 注意力机制(AM), 长短期记忆网络(LSTM), 飞行区, 航空器滑行, 滑行轨迹

Abstract:

In order to address the increasing risk of conflict caused by the difficulty in effectively predicting aircraft point source localization, a time series trajectory prediction model AM-LSTM based on AM and LSTM was constructed, to predict the instantaneous point source location of the aircraft in the airfield area in a short time in the future. On this basis, the contour was expanded according to the aircraft type and glide heading, the aircraft speed was used as the safety distance weight, and the ray method was used to realize the determination of the contour conflict. Urumqi Dewopu Airport was used as an example for validation, and the trained trajectory prediction model was utilized to predict aircraft taxiing trajectories in the airfield area and identified taxiing conflicts between aircraft profiles. The results show that the AM-LSTM prediction model can accurately predict the aircraft movement trajectory in the airfield area, and the average displacement error of the trajectory position prediction in the next 3 s is 1.05 m, and the accuracy of trajectory point position prediction can reach 94.37%. Therefore, it can accurately identify the risk of taxiing conflict on the basis of trajectory prediction, which is conducive to guaranteeing the safe operation of the airfield area.

Key words: attention mechanism(AM), long short term memory(LSTM), airfield area, aircraft taxiing, taxiing trajectory