Rapid generation of re-entry landing footprint based on neural network predictive model
To address the issue of the computation of re-entry landing footprint for hypersonic vehi-cles,this paper proposed a rapid computation method based on a neural network prediction model.Firstly,on the basis of virtual target method,a neural network model was constructed and trained to predict the landing footprint quickly.This model approximated the nonlinear relationship between the down-range and cross-range of the footprint boundary under given re-entry conditions,thereby realizing fast prediction of the landing footprint.Subsequently,the predicted footprint boundary ob-tained from the fast prediction neural network model was used to optimize the initial values of the vir-tual target method's search parameters,enabling them to be distributed near the optimal solution and thereby shortening the search time for the optimal solution.Finally,the proposed method was valida-ted through simulations.The simulation results show that the method significantly improves computa-tional efficiency while maintaining optimality,indicating its feasibility and efficiency.
NETL
NSTL
万方数据
