关键词: 零长发射, 建模仿真, SSA优化, BP神经网络, 参数寻优

Abstract:

Rocket boosted zero-length launch is an important form of UAV launch , and the selection of launch parameters such as launch angle is directly related to the success or failure of the UAV launch mission. Aiming at the launch angle, booster angle, booster thrust and other key parameters coupled to influence the launch trajectory during the zero-length launch phase of the rocket boost, it is a technical challenge to optimally select the launch parameters under the constraint envelope. In this paper, a UAV is taken as the research object, dynamics and kinematics modeling is carried out for its launching phase, a six-degree-of-freedom nonlinear model is constructed, and parametric simulation software for UAV launching trajectory is prepared based on QT/C++ software. At the same time, an optimization method for UAV launch parameters based on SSA-optimized BP neural network is proposed, and the superiority of SSA-BP for launch parameters prediction is comprehensively evaluated based on MAE, MAPE, and RMSE error evaluation methods. The results show that the UAV launch ballistic simulation and launch parameter optimization model in this paper are effective and credible, and can provide technical support for the engineering design of UAV launch subsystem.

Key words: zero-length launch, modeling and simulation, SSA optimization, back propagation neural network, parameter optimization