Induction motor bearing faults diagnosis using Root-AR approach: simulation and experimental validation

The faults diagnosis of induction motors is an important area of research that has been increasingly developed in recent years. This interest is due to the development and improvement of control circuits making the induction motor very used by researchers and industrials. In this regard, several techniques are used in fault diagnosis based on the stator current analysis by applying signal processing techniques. Indeed, the periodogram technique is the most used technique but has several disadvantages associated with its low frequency resolution leading to a difficult localization of faults harmonics, even an impossible localization in some cases of incipient faults. To solve this problem, a new technique based on the auto-regressive modeling of the stator current is used in this paper, thus improving the frequency resolution at the expense of important computation time. To this end, two improvements are proposed to reduce the computation time while providing a better readability of the stator current spectrum with the use of the proposed technique. In this aim, several simulation and experimental tests are achieved in the case of bearing cage fault and rotor faults to show the effectiveness of the proposed technique.