Integrated Morphing Strategy and Trajectory Optimization of a Morphing Waverider and Its Online Implementation Based on the Neural Network

In previous studies, a variable-sweep-wing morphing waverider was proposed and its aerodynamic performance dynamic model were provided. This can change sweep angle according to different flight scenario in order achieve an optimal performance. For the traditional fixed-geometry waverider, main objective of trajectory planning problem is find consisting time-dependent variables including attack, velocity, altitude, path so on. As for this wing changing strategy also required be calculated together with trajectory. At first, alleviate computational cost improve trajectory-planning efficiency, coefficients are approximated modeled as polynomial functions multiple Mach number, attack angle. Thereafter, offline integrated optimization both based on Gauss pseudo-spectral method investigated, which fulfill actual task requirements variable constraints. Compared four specific fixed-wing configurations, has larger downrange distance lower attack. However, real may deviate from nominal condition due uncertainties have intelligent online ability. Therefore, neural network optimization. Finally, overall examined by comparisons Monte Carlo runs.