A New Recurrent Fuzzy Neural Network Sliding Mode Position Controller Based on Vector Control of PMLSM Using SVM

Sliding mode controller using a recurrent fuzzy neural network (RFNN) is presented, in which RFNN is utilized to estimate the real-time lumped uncertainty for the position control of permanent magnet linear synchronous motor (PMLSM) drive system, so that the control effort can be reduced. Considering the convergence rate, global feed-forward RFNN is employed instead of global feedback RFNN. Furthermore, space vector modulation (SVM) that can decrease the vector deviation is adopted. Simulation results show that the proposed new recurrent fuzzy neural network sliding mode position control scheme provides a fast and robust regulation for the mover position