Adaptive hybrid control using recurrent-neural-network for linear synchronous motor servo drive system

In this study, an adaptive hybrid control system using a recurrent-neural-network (RNN) is proposed to control a permanent magnet linear synchronous motor (PMLSM) servo drive system. In the hybrid control system, the RNN controller is the main tracking controller, which is used to mimic an optimal control law, and the compensated controller is proposed to compensate the difference between the optimal control law and the RNN controller. Moreover, an online parameter training methodology of the RNN is derived using the Lyapunov stability theorem and the backpropagation method. In addition, to relax the requirement for the bounds of minimum approximation error and Taylor high-order terms, an adaptive hybrid control system is investigated to control the PMLSM servo drive where two simple adaptive algorithms are utilized to estimate the mentioned bounds. The effectiveness of the proposed control schemes is verified by the experimental results.