Information Fusion With Belief Functions for Detection of Interturn Short-Circuit Faults in Electrical Machines Using External Flux Sensors

This paper proposes a diagnosis method that exploits the information delivered by external flux sensors placed in the vicinity of rotating electrical machines, in order to detect a stator interturn short circuit. This fault induces a dissymmetry in the external magnetic field that can be measured by the sensors. Sensitive harmonics are extracted from the signals delivered by a pair of sensors placed at 180 degrees from each other around the machine, and data obtained for several sensor positions are analyzed by fusion techniques using the belief function theory. The diagnosis method is applied on induction and synchronous machines with artificial stator faults. It will be shown that one can obtain high probability to detect the fault using the proposed fusion technique: on various series of measurements, the proposed approach has obtained a 90% detection rate on a considered machine.