State Feedback Control with ANN Based Load Torque Feedforward for PMSM Fed by 3-Level NPC Inverter with Sinusoidal Output Voltage Waveform

The approach presented in this work focuses on the full state feedback algorithm designed to control the angular velocity of the PMSM and to provide true sine wave of the 3-level neutral point clamped inverter output voltages. Artificial neural network based feedforward path was introduced into control system in order to improve dynamic behaviour of the PMSM during load changing and to reduce the effect of load torque changes. It was shown that gains of the designed controller and feedforward path are non-stationary and depends on the angular velocity. The simulation results demonstrate the advantages of the proposed approach with comparison to state feedback control system without feedforward path.