A new MRAC method based on neural network for high-precision servo system

In this paper, a novel model reference adaptive control (MRAC) scheme based on neural network (NN) is proposed for servo system tracking control to achieve high-precision position control. This scheme consists of an MRAC controller and an online NN controller in velocity-loop and a traditional PID controller in position-loop. For reducing influence which arose from modeling error, unknown model dynamics, parameter variation and disturbance acted on the velocity-loop, the NN controller is introduced to reduce the various influence mentioned above, adjust system to track the approximate velocity-loop reference model. In order to guarantee the stability of the system, updating algorithm of the weights of the NN controller and parameters of the MRAC are designed based on Lyapunov stability theory. Experiment results verify the proposed strategy can achieve high tracking precision for real-time position close-loop servo system.