Aircraft tail vortex recognition method and system based on convolutional neural network

Abstract

The invention relates to an aircraft tail vortex recognition method and system based on a convolutional neural network. The method comprises the following steps: receiving a to-be-identified aircrafttail vortex detection image, identifying the aircraft tail vortex detection image by using a pre-trained convolutional neural network model, and outputting to obtain a probability value of identifyinga tail vortex and a probability value of not identifying the tail vortex; and if the probability value of the identified trailing vortex is greater than the probability value of the unidentified trailing vortex, identifying that the trailing vortex exists in the to-be-identified aircraft trailing vortex detection image, otherwise, identifying that the to-be-identified aircraft trailing vortex detection image does not have the trailing vortex. The method is high in recognition accuracy, whether the tail vortex exists or not under the current meteorological condition can be detected in real time, necessary auxiliary information is provided for air traffic control personnel to send out a reasonable tail vortex avoiding instruction, the current tail vortex interval can be reduced, the airspace and airport capacity is improved, and then the control efficiency is improved.

Description

technical field [0001] The invention relates to the field of aviation technology, in particular to a convolutional neural network-based aircraft wake vortex identification method and system. Background technique [0002] With the large-scale and high-speed development of my country's aviation industry, airspace and ground support resources are insufficient, and the throughput of various aviation hubs is saturated, which has brought unprecedented challenges to the safe operation of China's civil aviation. During the take-off and landing phases of the aircraft, the wake vortex generated by the front aircraft will pose a potential threat to the flight safety of the aircraft behind it, and the phases of the aircraft's take-off run, liftoff and approach landing are the most dangerous in the entire flight In the three stages, correctly identifying the wake vortex of the aircraft and reasonably avoiding the wake vortex has become an important condition to ensure the flight safety o...

AI Technical Summary

Problems solved by technology

At present, in China, the identification of aircraft wake vortex is based on the new method of classifying aircraft based on wake turbulence formulated by the FAA in 2012, which divides aircraft into three categories: heavy, medium, and light. However, the interval is too conservative, which has seriously restricted the rapid development of the aviation industry, and under different meteorological conditions, the evolution law of the wake vortex is not completely consistent, so this method wastes a lot of airspace capacity. and inefficient

Images