Research of Translational Meshing Motor Control Based on Adaptive Neuro-Fuzzy Inference System

The novel translational meshing motor (TMM) has inherent torque ripple because TMM torque is highly nonlinear relationship between rotor position and phase current. The torque ripple of TMM drive system can cause undesirable acoustic noise and vibration. In this paper, a novel controller scheme for TMM is presented. The controller is based on an adaptive neuro-fuzzy inference system (ANFIS) and combines fuzzy logic and neural networks for TMM torque ripple control. The performance of the proposed controller is investigated extensively both in simulation and in experiment. In order to prove the superiority of the controller, the results for the proposed controller are compared to those obtained by the conventional hysteresis direct torque control (HDTC) system. The comparison results demonstrate the validity of the proposed controller scheme.