Sensorless control based on the improved VM NN SC MRAS method for high performance SPIM drives using LPF

This paper proposes a novel Stator Current Model Reference Adaptive System based scheme using neural network (NNSM_SC_MRAS) for sensorless controlled of Six-Phase Induction Motor (SPIM) drives. For this scheme, the measured stator current components are used as the reference model and a two layer linear NN stator current observer is used as an adaptive model. The voltage model (VM) rotor flux identifier with value of stator resistor is update online is used to provide the rotor flux for the adaptive model, this helps to overcome the instability problem and enhance the performance of the observer. Especially, In order to eliminate the drift problems, the pure integrator of VM is replaced with a first-order low-pass filter, and the error due to this replacement is also compensated in proposed scheme. Simulation results have demonstrated that the performance of the proposed observer is significantly improved especially at low and near zero speed range.