Nonlinear control design of LSM drive system using adaptive modified recurrent Laguerre orthogonal polynomial NN backstepping control

The good control performance of the permanent magnet linear synchronous motor (LSM) drive system is very difficult achieved by using linear controller due to the uncertainty effects such as ending-frictious force. An adaptive modified recurrent Laguerre orthogonal polynomial neural network (NN) backstepping control system is proposed to increase the robustness of the LSM drive system. Firstly, the field-oriented mechanism is applied to formulate the dynamic equation of the LSM drive system. Secondly, a backstepping approach is proposed to control the motion of LSM drive system. With proposed backstepping cotrol system, the mover position of the LSM drive possesses the advantages of good transient control performance and robustness. Because the LSM drive system existed in much nonlinear and time-varying uncertainties, an adaptive modified recurrent Laguerre orthogonal polynomial NN uncertainty observer is proposed to estimate the lumped uncertainties in order to enhance robustness of the LSM drive system. The on-line parameter training methodology of the adaptive modified recurrent Laguerre orthogonal polynomial NN is based on Lyapunov stability theorem. Finally, the effectiveness of the proposed control system is verified by experimental results.