DBN-GABP model for estimation of aircraft wake vortex parameters using Lidar data

Abstract

Aircraft wake turbulence is an inherent outcome of aircraft flight, presenting a substantial challenge to air traffic control, aviation safety and operational efficiency. Building upon data obtained from coherent Doppler Lidar detection, and combining Dynamic Bayesian Networks(DBN) with Genetic Algorithm-optimized Backpropagation Neural Networks(GA-BPNN), this paper proposes a model for the inversion of wake vortex parameters. During the wake vortex flow field simulation analysis, the wind and turbulent environment were initially superimposed onto the simulated wake velocity field. Subsequently, Lidar-detected echoes of the velocity field are simulated to obtain a data set similar to the actual situation for model training. In the case study validation, real measured data underwent preprocessing and were then input into the established model. This allowed us to construct the wake vortex characteristic parameter inversion model. The final results demonstrated that our model achieved parameter inversion with only minor errors. In a practical example, our model in this paper significantly reduced the mean square error of the inverted velocity field when compared to the traditional algorithm. This study holds significant promise for real-time monitoring of wake vortices at airports, and is proved a crucial step in developing wake vortex interval standards.