Induction Motor Fault Diagnosis Using a Hilbert-Park Lissajou's Curve Analysis and Neural Network-Based Decision

Samira Bensalem (1) , Khmais Bacha (1) , Mohamed Benbouzid (2) , Abdelkader Chaari (1)

1 research unit on control, monitoring and reliability of systems
2 LBMS - Laboratoire brestois de mécanique et des systèmes

In this work we propose an original fault signature based on the Hilbert-Park Lissajou's curve analysis. The performances of the proposed signature were compared to those of the Park Lissajou's curve which is the signature most recently used. The proposed fault signature does not require a long temporal recording, and their processing is simple. This analysis offers an easy interpretation to conclude on the induction motor condition and its voltage supply state. The proposed signature shows its efficiency especially in the case of unloaded machine. The geometrical characteristic of all Hilbert-Park Lissajou's curves are calculated in order to develop the input vector necessary for the pattern recognition tools based on neural network approach with an aim of classifying automatically the various states of the induction motor. This approach was applied to a 1.1 kw induction motor under normal operation and with the following faults: unbalanced voltage, air-gap eccentricity and outer raceway bearing defect.

Mots clés: Induction motor; fault diagnosis; Lissajous curve analysis; neural network

Domaines: Energie électrique

Samira Bensalem, Khmais Bacha, Mohamed Benbouzid, Abdelkader Chaari. Induction Motor Fault Diagnosis Using a Hilbert-Park Lissajou's Curve Analysis and Neural Network-Based Decision. International Journal on Energy Conversion, 2013, 1 (3), pp.154-163. ⟨hal-01020007⟩