Search Results

When the aircraft towing operations are carried out in narrow areas such as the hangars or parking aprons, it has a high safety risk for aircraft that the wingtips may collide with the surrounding aircraft or the airport facility. A real-time trajectory prediction method for the towbarless aircraft taxiing system (TLATS) is proposed to evaluate the collision risk based on image recognition. The Yolov7 module is utilized to detect objects and extract the corresponding features. By obtaining information about the configuration of the airplane wing and obstacles in a narrow region, a Long Short-Term Memory (LSTM) encoder-decoder model is utilized to predict future motion trends. In addition, a video dataset containing the motions of various airplane wings in real traction scenarios is constructed for training and testing.

As a traditional probabilistic mid-term conflict detection algorithm, the Prandini algorithm plays an essential role in ensuring flight safety in the aircraft route area. For the issue of mutation error in the calculation results of the Prandini algorithm, this research provides an improved Prandini conflict detection algorithm. First, the integral of the standard Gaussian distribution is solved using randomization. The minimum prediction interval moment is then calculated, and the critical time points at which conflicts may exist before and after that moment are approximated separately using a bisection method. N moment values are selected uniformly within the time range formed by the two critical time points. The instantaneous conflict probabilities for these N moments are calculated and the maximum value is selected from them as a measure of the likelihood of conflict between the two aircraft over the entire route for an extreme case.

The towbarless aircraft taxiing system (TLATS) consists of the towbarless towing vehicle (TLTV) and the aircraft. The tractor realizes the towing work by fixing the nose wheel. During the towing process, the tractor driver may cause the aircraft to collide with an obstacle because of the blind spot of vision leading to the accident. The special characteristics of aircraft do not allow us to modify the structure of the aircraft to achieve collision avoidance. In this paper, three degrees of freedom (DOE) kinematic model of the tractor system is established for each of the two cases of pushing and pulling the aircraft, and the relationship between the coordinates of each danger point and the relatively articulated angle of the TLATS and the velocity of the midpoint of the rear axle is derived.