Adaptive second-order global terminal sliding mode direct torque control of switched reluctance motor based on RBFNN

Aiming at the problems of the parameter perturbation, the external disturbances and the torque ripple in the switched reluctance motor(SRM) speed control system, a combined control strategy of speed and torque is developed.Firstly, based on radial basis functions neural network(RBFNN), a second-order adaptive global fast terminal sliding mode(GFTSM-NN) speed controller is developed. The RBFNN is employed to compensate for the influence of unknown parameter disturbances, thereby reducing the controller's dependence on the accurate information of the system. The neural network parameters are updated according to the adaptive law that is computed using Lyapunov approach to ensure the stability of the closed-loop system. Secondly, the torque sharing function(TSF) is used to calculate the expected torque of each item, and a current controller is designed based on the Lyapunov direct method, thereby achieving the accurate current tracking and reducing the torque ripple. Finally, based on the measured data of the three phase 12/8 poles 1.5 kW SRM. comparative studies are carried out among the proposed control scheme, GFTSM control and PI control. These results demonstrate the effectiveness of the proposed method.