Stochastic gradient particle swarm optimization based entry trajectory rapid planning for hypersonic glide vehicles

In this paper, a novel stochastic gradient particle swarm optimization (SGPSO) algorithm is proposed, which combines the high-efficiency of gradient search with the randomness of particle swarm search. By adjusting the stochastic gradient obtained by the best historical positions of adjacent two generations, the proposed algorithm can effectively overcome the problems of premature convergence and poor accuracy of standard particle swarm optimization (PSO). Due to the capabilities of rapidity, optimality and adaptability, the proposed algorithm is applied as a global optimization approach to rapidly generate feasible and smooth entry trajectories for hypersonic glide vehicles with highly constraints. Under the constraints of Earth's rotation and oblateness, the entry trajectory planning model is established. By parameterizing the control variables including angle of attack (AOA) and bank angle, the entry trajectory optimization problem is then converted to a multi-parameter optimization problem, which can be solved by the proposed SGPSO algorithm. Considering Common Aero Vehicle (CAV) model, the simulations show that the proposed algorithm has better performance on optimization speed, stability and solution optimality than those of the classical methods, and it can realize the rapid optimization of entry trajectory for hypersonic glide vehicles.