基于BIRCH聚类的航空器自主运行风险状态评价  

Risk state evaluation on autonomous operation of aircraft based on BIRCH clustering

作　　者：张洪海[1] 沈雪 瞿昕宜 张世佳 张纵驰 唐思嘉 ZHANG Honghai;SHEN Xue;QU Xinyi;ZHANG Shijia;ZHANG Zongchi;TANG Sijia(College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing Jiangsu 210000,China)

机构地区：[1]南京航空航天大学民航学院,江苏南京210000

出　　处：《中国安全生产科学技术》2024年第9期188-196,共9页Journal of Safety Science and Technology

基　　金：工业和信息化部民用飞机专项科研项目(MJZ1-7N22)。

摘　　要：为解决自主运行模式下航空器风险评价指标缺失和风险状态实时评估困难等问题,提出1种自主运行模式下航空器风险状态评价方法。从航空器冲突、气象规避区侵入、操纵裕度3个方面建立风险状态评价指标体系,运用BIRCH算法建立聚类特征树对多维航空器特征样本进行风险模型训练,引入增量式聚类的概念,更新特征树,实时评估动态目标航空器的风险状态。然后,以广州05扇区为运行场景展开仿真实验。研究结果表明:所提方法准确度达99.5%,平均计算时间约为0.0249 s。研究结果可有效支撑自主运行理念实施,提高风险预警能力,保障航空器自主运行安全。Aiming at the problems of the lack of aircraft risk evaluation indexes and the difficulty of real-time evaluation of risk status under the autonomous operation mode,a method for evaluating the risk status of aircraft under this mode was proposed.An index system of risk state evaluation was established from three aspects:aircraft conflict,weather avoidance zone intrusion,and maneuver margin.The BIRCH algorithm was used to establish a clustering feature tree,and the multi-dimensional aircraft feature samples were used to train the risk model.The concept of incremental clustering was introduced to update the feature tree,and the risk state of the dynamic target aircraft was evaluated in real time.The simulation experiment was carried out by taking Guangzhou Sector 05 as the operation scenario.The results show that the accuracy of the proposed method is as high as 99.5%,and the average computation time is 0.0249 seconds.The research results can effectively support the implementation of the idea of autonomous operation,improve the ability of risk early-warning,and guarantee the safety of autonomous operation.

关 键 词：航空运输 自主运行 风险状态指标 BIRCH聚类 

分 类 号：X949[环境科学与工程—安全科学] V355[航空宇航科学与技术—人机与环境工程]