An MRAS Sensorless Technique based on the MCA EXIN + Neuron for High Performance Induction Motor Drives

This paper proposes a new sensorless technique for induction motor drives based on a hybrid MRAS-neural technique, which improves a previously developed neural MRAS based sensorless method. In this paper the open- -loop integration in the reference model is performed by an adaptive neural integrator, enhanced here by means of a speed-varying filter transfer function. The adaptive model is based on a more accurate discrete current model based on the modified Euler integration, with a resulting more stable behaviour in the field weakening region. The adaptive model is further trained on-line by a generalized least squares technique, the MCA EXIN + neu- ron, in which a parameterized learning algorithm is used. As a consequence, the speed estimation presents an im- proved convergence with higher accuracy and shorter settling time, because of the better transient behaviour of the neuron. A test bench has been set up to verify the methodology experimentally and the results prove its goodness at very low speeds (below 4 rad/s) and in zero-speed operation.