Neuro-fuzzy control of a singularly perturbed permanent magnet synchronous machine fed by a three levels inverter

In this paper, we present a control technique based on the singular perturbation technique controlled by a neuro-fuzzy regulator applied to the permanent magnet synchronous machine (PMSM). Applied to the PMSM, this technique conducts to a separation of the variables into disjoined subsets or two separated models: one having a slow dynamics, and the other a fast dynamics. To ensure certain robustness to the decoupled control system based on this technique, the control speed and the Id current are carried out by neuro-fuzzy regulators (ANFIS). A qualitative analysis of the principal variables evolution describing the behavior of the global system (PMSM-inverter with MLIControl) and its robustness is developed by several tests of digital simulation.