An Online Generation Method of Terminal-Area Trajectories for Wave-Rider Using Deep Neural Networks

This paper presents a deep neural network-based online trajectory generation method for the aerodynamic characteristic description and terminal-area energy management of wave-rider aircrafts. First, flight dynamics equations in domain are linearized discretized to generate numerous aircraft samples with sequential convex optimization (SCO) methods. Then, an objective function is designed promote smoothness control variables improve similarity. Compared nonlinear programming (NLP), proposed sample more suitable training networks (DNNs). Finally, formulated trained state variables, using generated obtained samples, so that reference trajectories can be during process wave-rider’s terminal phase. Numerical simulations validate high accuracy network. Meanwhile, this enables smaller storage usage, which highly integration into on-board systems.