Robust control of linear synchronous motor servodrive using disturbance observer and recurrent neural network compensator

Kobust control of a pcrnianent magnct (PM) lincar synchronous motor (LSM) servodrive is achieved by using a disturbance observer and a recurrent neural nctwork (RN N) compensator. An iiitcgral-proportional (IP) controller is introduccd to control tlic mover position of the LSM. The IP position controller is designed according to the cstimatcd mover parameters to match tlic timedomain command tracking specilications. A disturbance observer is implcmcnted aiid the observed disturbance force is fed forward to increase the robustness of the LSM servodrive. Moreover, to increase tlie control performance of the LSM servodrive under the occurrence of large disturbance, a KNN compensator is proposed to reduce tlic inllueiicc of parameter variations and cxtcrnal disturbances of tlic LSM servodrive system as a force controllcr. I n addition, a dynamic backpropagation algorithm is developed to train the RN N onlinc using tlie delta adaptation law. Tlic effectiveness of the proposed control schemes is deinonstratcd by some simulated and cxperimcntal results.