Parameter Identification of a PN-Guided Incoming Missile Using an Improved Multiple-Model Mechanism

An active defense against an incoming missile requires information of it, including a guidance law parameter and first-order lateral time constant. To this end, assuming that with proportional navigation (PN) attempts to attack aerial target bang-bang evasive maneuvers, identification model based on the gated recurrent unit (GRU) neural network is built in paper. The analytic solutions for constant are derived. inputs available kinematic between aircraft missile, while outputs contain regression results parameters. increase training speed accuracy Model, output processing method called improved multiplemodel mechanism (IMMM) proposed effectiveness IMMM performance established demonstrated through numerical simulations under various engagement scenarios.