Permanent magnet synchronous machines multiple failures identification using sequence mining

Permanent Magnet Synchronous Machines (PMSMs) are increasingly used in many industrial fields for their efficiency, robustness, reliability, and low torque inertia. Despite their widespread use, they can operate in severe conditions when faults appear in PMSM drive components such as inverters, stator windings, sensors, etc. Fault diagnosis and fault-tolerant methods are then considered to improve the stability and robustness of PMSMs. Furthermore, it is much more important to be able to identify how many faults are present in a faulty system. This task is not obvious since one fault can hide another. Consequently, it is crucial to address design phase of the system. In this paper, we show the applicability of our fault localization approach based on sequence mining to unveil PMSMs’ multiple faults presence in the models considered for their design phase.