Clever backstepping control using two adaptive laws, a RRFNN and a compensated controller of SPCRIM drive system.

A six phase copper rotor induction motor (SPCRIM) drive system still exists in lots of nonlinear characteristics such as the added load torque, the Stribeck effect torque, the the cogging torque, the coulomb friction torque and the parameters variations. Due to some uncertainties effects, the using linear controller can not achieve better control performance for the SPCRIM drive system. To obtain better performance, a clever backstepping control system using two adaptive laws and a hitting function is proposed for controlling the SPCRIM drive system. To improve larger chattering phenomenon under uncertainties affects for aforementioned control system, the clever backstepping control system using two adaptive laws, a revised recurrent fuzzy neural network (RRFNN) and a compensated controller is proposed to estimate the required lumped uncertainty and to compensate the minimum reconstructed error of the estimated law. Furthermore, the corrected particle swarm optimization (CPSO) algorithm by using variable dynamic inertia weight and variable dynamic constriction factor with segment regulation mechanics that is the innovativeness for using the CPSO algorithm is adopted to regulate four variable learning rates of the weights in the RRFNN to speed-up parameter's convergence. Finally, comparative performances through some experimental results are verified that the clever backstepping control system using two adaptive laws, a RRFNN and a compensated controller has better control performances than those of the proposed methods for the SPCRIM drive system. [ABSTRACT FROM AUTHOR]