Adaptive Rocket Launcher Position AC Servo System Based on Elman Network

Considering the atrocious load property when the rocket is launched, including unbalanced torque and the disturbance from the air current impulsion, an adaptive position controller based on improved Elman network is designed. The context neurons of output layer are added to the original Elman network, and self-feedback gain coefficients are trained as connective weight. According to the load property of rocket launcher, improved Elman network could adjust the PID parameters online to minify the influence of the change of system parameters and external disturbance. Simulation and experimental results show that this method could improve the stability and anti-disturbance ability of rocket launcher position servo system effectively.