考虑航段相关性的航路拥挤态势多模型 融合动态预测方法

研究航路交通拥挤状态动态实时预测问题，可为缓解航路交通拥挤，优化拥挤管控 策略提供科学的依据.首先，采用神经网络理论建立考虑航段相关性的交通流参数预测模型， 预测航段流量和航段密度参数；然后，运用多模型融合预测算法提高预测精度，基于模糊C均 值聚类算法和航段历史及预测交通流参数预测航段交通拥挤态势；最后，采用雷达实测航迹 数据验证模型的有效性.研究结果表明，本文建立的预测模型同时考虑了时间和空间因素，对 航路拥挤状态预测准确率达到82.29%，预测方法符合实际且对航路交通态势的预测具有应用 价值；同时考虑航段相关性影响和采用多模型融合预测算法能够明显提高预测精度.

Multi-model Fusion Dynamic Prediction Method of Enroute Congestion Situation with Considering the Correlation of Air Route Segment

This paper studies the dynamic real- time prediction of air route traffic congestion, which aims at providing scientific basis to alleviate air route traffic congestion and optimize control strategies. First, based on the theory of neural network, a traffic flow parameter prediction model is established, taking the correlation of air route segment into consideration. Then a multi-model fusion prediction algorithm is adopted to improve forecast accuracy, and air route segment congestion situation is predicted based on fuzzy C-means clustering algorithm and previous and predicted traffic flow parameters of air route segment. Finally, the model is verified by ATC radar data. The results demonstrate that this model takes into account the factors of both space and time, and the prediction accuracy of air route congestion is 82.29%. The model corresponds to reality and is feasible for air route traffic states prediction. Meanwhile, consideration of the correlation effects of air route segments and prediction using multi-model fusion algorithm can significantly improve forecast accuracy.