A multi-objective optimization method for flight conflict resolution

Abstract

The invention discloses a flight conflict resolution method based on multi-objective optimization. The method is based on 4DT multi-objective optimization which is achieved by means of the NSGA-II algorithm. According to the method, by establishing a flight conflict detection model and an optimized objective function and a constraint condition, conflict resolution is achieved by means of the NSGA-II algorithm in an optimized mode. The flight conflict resolution method based on the 4DT multi-objective optimization is high in operation efficiency, capable of achieving conflict resolution, reaching low average delay, and meeting requirements of conflict resolution under global optimization, more suitable for practical problems due to the adoption of the mechanism of multi-objective optimization, and stronger in feasibility.

Description

technical field [0001] The invention relates to an aircraft flight time optimization method applicable to the entire airspace, which is a strategy-level global flight conflict resolution method, and specifically refers to a multi-objective optimization flight conflict resolution method. Background technique [0002] In recent years, my country's air transport industry has developed rapidly, and it is expected that my country's civil aviation market will continue to maintain a high-speed growth trend in the next few years. At present, my country has developed into the world's second largest air transport country after the United States. However, as the flight traffic increases, the density of aircraft in the airspace also increases accordingly, making it difficult to guarantee the safe interval between aircraft, and the possibility of conflicts increases, which in turn poses a serious threat to flight safety. As one of the key technologies to ensure flight safety, the study ...

AI Technical Summary

Problems solved by technology

[0004] The flight conflict resolution problem is a complex optimization problem with multiple variables (including continuous and discrete variables), multiple objectives, multiple constraints, nonlinearity, multiple extrema, objective functions and non-analytical functions of constraints, using traditional optimization algorithms (including based on Gradient optimization algorithms and direct optimization algorithms such as Powell method) will face severe challenges, mainly in the following aspects: (1) traditional optimization algorithms cannot be directly used to deal with optimization problems with continuous / discrete mixed design variables; (2) traditional optimization algorithms It is often sensitive to the initial value, and it is easy to fall into a local optimum; (3) The single-point operation method of traditional optimization algorithms greatly limits the improvement of computational efficiency; (4) Traditional optimization algorithms often require that the objective function and constraints are continuously differentiable Analytic Functions

Images