A CFAR-based faults detector for Induction Motors

Despite the rich literature dealing with induction motor faults detection, the automatic decision on the health operating condition has received scarce attention. This paper aims at demonstrating the usefulness of the combination of the Maximum Likelihood (ML) and the detection theory for induction motor faults detection. In particular, it proposes to use stator currents as medium for faults detection. Indeed, under faulty conditions, additional spectral components appear in the stator currents spectrum. This paper proposes to use a constant false alarm rate (CFAR) detector of these components. The objective is to decide between two hypothesis; the motor is healthy or faulty. The generalized likelihood ratio test (GLRT) is used to tackle this binary hypothesis testing problem.Monte Carlo simulations have been performed in order to evaluate the statistical performance of the proposed approach. Then, the proposed algorithm has been evaluated on experimental data for broken rotor bars fault detection.