Online Generation Method for Interceptor Missile Launch Envelope Considering Complex Environmental Disturbances

A radial basis function (RBF) + self-attention (SA) launch envelope network model, which uses RBF neural network as the base model and is integrated with SA mechanism, is proposed to address the online calculation problem of the launch envelope when an interceptor missile intercepts a hypersonic gliding target under complex environmental disturbances. The equations of motion for the interceptor missile considering environmental disturbances such as wind and atmospheric density perturbations are established, and a launch envelope characterized by the initial positions and initial velocity direction of interceptor missile is defined based on the given target motion, interceptor missile maneuverability, and guidance strategy. Additionally, the sample data for the launch envelope are obtained offline. Then considering the strong nonlinearity of the impact of multiple environmental disturbances on the interceptor missile's launch envelope, the network-based models for the launch envelope under single disturbances (e.g., wind and atmospheric density) are established using RBF neural network, and a SA mechanism is developed to dynamically integrate the single-disturbance launch envelope base models across various combat scenarios, thus forming a launch envelope network model which has fast training speed and high accuracy under multiple environmental disturbances. The results demonstrate that the RBF + SA neural network model accurately represents the launch envelope under multiple complex environmental disturbances with high precision and achieves higher prediction accuracy using fewer samples.