Induction Motors Bearing Failures Detection and Diagnosis Using a RBF ANN Park Pattern Based Method

Izzet Onel (1) , Mohamed Benbouzid (2)

1 Electrical Engineering Department
2 LBMS - Laboratoire brestois de mécanique et des systèmes

This paper deals with the problem of bearing failure detection and diagnosis in induction motors. The proposed approach is a sensor-based technique using the mains current and the rotor speed measurement. The proposed approach is based on the stator current Park patterns. Induction motor stator currents are measured, recorded and used for Park patterns computation. A Radial Basis Function (RBF) Artificial Neural Network (ANN) is then used to automate the fault detection and diagnosis process. Experimental tests with artificial bearing damages results show that the proposed method can be used for accurate bearing failures detection and diagnosis in induction motors.

Mots clés: diagnosis; Park transform; neural networks; Induction motor; bearing failure

Domaines: Energie électrique

Izzet Onel, Mohamed Benbouzid. Induction Motors Bearing Failures Detection and Diagnosis Using a RBF ANN Park Pattern Based Method. International Review of Electrical Engineering, 2008, 3 (1), pp.159-165. ⟨hal-00526510⟩