Aircraft Wake Recognition and Strength Classification Based on Deep Learning

Aircraft wake is a pair of counter-rotating vortices generated behind the aircraft, which can greatly impact safety fast takeoff and landing aircraft limit improvement airport capacity. The current parameter retrieval methods cannot locate vortex's position estimate its strength level in real time. To deal with this issue, novel algorithm based on YOLOv5s deep learning network proposed. new establishes single vortex locating concept to adapt evolution at complicate background wind field conditions, proposes strength-based classification standard represent real-time hazard shorten intervals. Meanwhile, EIOU loss function introduced improve precision network. Compared state-of-the-art object detection approaches, such as Cascade R-CNN, FCOS, YOLOv5l, superiority method demonstrated terms accuracy robustness by using data from Hong Kong International Airport.