Risk state evaluation on autonomous operation of aircraft based on BIRCH clustering
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 pro-posed.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-dimen-sional aircraft feature samples were used to train the risk model.The concept of incremental clustering was introduced to up-date 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 0.024 9 seconds.The research results can effectively sup-port the implementation of the idea of autonomous operation,improve the ability of risk early-warning,and guarantee the safety of autonomous operation.
air transportationautonomous operationrisk state indexBIRCH clustering
万方数据
维普
