基于SOM神经网络的民用机场分类方法

Classification method of civil airport based on SOM neural network

机场是综合交通运输的重要节点,是航空运输的重要基础设施。科学地进行机场分类研究对于机场的国家布局规划、机场自身定位和运行策略选择等都具有重要的现实与理论研究价值。利用神经网络技术中的自组织映射(SOM)网络并结合MATLAB软件进行编程对我国主要机场进行聚类分析评价,得出我国主要机场分为8层的主要结论。结果表明,自组织特征映射(SOM)能很好用于我国机场分类,是一种新颖、有效的分类方法。

Airport is an important node of comprehensive transportation and an infrastructure of air transportation. It is of practical significance for the airport classification in a scientific way to the study of national layout planning of the airport, airport positioning and running strategy selection. It presents the major airports in China by using self-organizing map （SOM） in the artificial neural network technology and Matlab software programming. Conclusions show that maior airports in China are divided into eight layers. The results show that the self-organizing map （SOM） is properly used for airports classification in China, and it is a new and effective classification method.