A method for airspace sectorization is developed based on initial airspace configuration. The method begins with identifying Traffic Mass (TM) situations in all sectors ahead of time, especially for the sectors that e...
详细信息
ISBN:
(纸本)9789881563958
A method for airspace sectorization is developed based on initial airspace configuration. The method begins with identifying Traffic Mass (TM) situations in all sectors ahead of time, especially for the sectors that exceeds the defined controller capability to manage (called overloaded sectors) as well as for those that are under-utilized (called under-utilized sectors). Then, for the overloaded sectors, the method implements the removal of excessive Traffic Mass by moving sector boundaries from the sector with low TM to the overloaded sector in conjunction with a diffusion algorithm. Alternatively, for the under-utilized sectors, they can be combined with their neighbors using general-clustering-algorithm. The simulation demonstrates that the method not only removes excessive TM but also improves efficiency. More importantly. the designed sectors which follow the candidate boundary strategy reduce controller's cognitive difficulty, this helps to keep controllers in as much clear-headed situation as possible to ensure flight safety.
We present a neural network capable of separating inputs in an unsupervised manner. Oja's rule and Self-Organizing map principles are used to construct the network. The network is tested using 1) straight lines 2)...
详细信息
ISBN:
(纸本)9781479945030
We present a neural network capable of separating inputs in an unsupervised manner. Oja's rule and Self-Organizing map principles are used to construct the network. The network is tested using 1) straight lines 2) MNIST database. The results demonstrate that the network can operate as a general clustering algorithm, with neighboring neurons responding to geometrically similar inputs.
A method for airspace sectorization is developed based on initial airspace configuration. The method begins with identifying Traffic Mass(TM) situations in all sectors ahead of time, especially for the sectors that ex...
详细信息
A method for airspace sectorization is developed based on initial airspace configuration. The method begins with identifying Traffic Mass(TM) situations in all sectors ahead of time, especially for the sectors that exceeds the defined controller capability to manage(called overloaded sectors) as well as for those that are under-utilized(called under-utilized sectors). Then, for the overloaded sectors, the method implements the removal of excessive Traffic Mass by moving sector boundaries from the sector with low TM to the overloaded sector in conjunction with a diffusion algorithm. Alternatively, for the under-utilized sectors, they can be combined with their neighbors using general-clustering-algorithm. The simulation demonstrates that the method not only removes excessive TM but also improves efficiency. More importantly, the designed sectors which follow the candidate boundary strategy reduce controller's cognitive difficulty, this helps to keep controllers in as much clear-headed situation as possible to ensure flight safety.
暂无评论