Missile thermal emission flow field under the synergistic effect of deep reinforcement learning and wireless sensor network

Abstract The vehicle-mounted missile vertical thermal emission not only has excellent maneuverability, randomness, and concealment, but also a short response time, good versatility, high reliability, so it is widely used. In order to explore the gas flow field of missile, firstly, this study introduces theoretical basis deep reinforcement learning (DRL) algorithm wireless sensor network (WSN). Secondly, combining WSN DRL, technology based on DRL proposed. Finally, DRL-based applied missile. addition, simulation software employed simulate compare influence single-side double-side diversion schemes discharged by diverter open ground flat collection launcher, characteristics two are obtained. results show that in scheme, impact ablation area jet mainly appear at rear side device, launcher vehicle its tail end. While ablative site shock scheme both sides diversion, part present bottom frame inside surface tire. fields certain significance for variation launching.