文档介绍：第52卷第2期 航空计算技术 Vol. wake vortex recognition framework based on mathematical morphology and K- nearest neighbor
algorithm ( KNN ). In the framework , the main work is as follows: 1) Extract the morphological characteris ­
tics of the airplane wake vortex sample according to the opening and closing operators in mathematical
morphology ;2) Introduce the pooling layer of the convolutional neural network to reduce the dimensionali ­
ty of the morphological characteristics ; 3 ) Identify the extracted wake vortex features through the KNN ma ­
chine learning model. In the experiment, Wind3D 6000 Doppler Lidar was deployed near runway 02 of
Shuangliu Airport (ZUUU) ,and the model was verified by collecting approach wind field data. The re­
sults show that the classification accuracy , precision, recall and Fl - score of the proposed model are
% ,92. 6% ,% and % Respectively.
Key words: wake vortex recognition ； neural network ； morphological operator ； Doppler Lidar
引言