An experimental assessment of a stator current MRAS based on neural networks for sensorless control of induction machines

In this paper an experimental evaluation of a novel Model Reference Adaptive System (MRAS) speed observer for induction motor drives based on stator currents is presented. In this scheme the measured stator currents are used as the reference model for the MRAS observer to avoid the use of a pure integrator. A two-layer Neural Network (NN) stator current observer is used as the adaptive model which requires the rotor flux information that can be obtained from the current model. Speed estimation performance of the new MRAS scheme is studied and compared with the classical rotor flux MRAS when applied to an indirect vector control induction motor drive. Experimental results are shown for the two schemes in the low speed region of operation including tests for the regenerating mode. These results complement the simulation results presented for the proposed scheme in a recent work.