Back propagation neural network for classification of induction machine faults

Ammar Medoued (1) , Abdesselam Lebaroud (1) , Ahcene Boukadoum (1) , T. Boukra (1) , Guy Clerc (2)

1 Département de Génie Electrique [Skikda]
2 AMPERE - Ampère

This paper presents a new method for the classification of induction machine faults. The method is composed of two steps: feature extraction and classification. Feature extraction is based on the time-frequency representation (TFR), which is deliberately designed for maximizing the separability between classes. A distinct TFR is designed for each class. The classifier is designed with an artificial neural network. The flexibility of this method allows an accurate classification independent from the level of load. This method is validated on a 5.5-kW induction motor test bench.

Domaines: Energie électrique

Ammar Medoued, Abdesselam Lebaroud, Ahcene Boukadoum, T. Boukra, Guy Clerc. Back propagation neural network for classification of induction machine faults. 8th IEEE SDEMPED, Sep 2011, Bologne, Italy. pp.525 - 528, ⟨10.1109/DEMPED.2011.6063673⟩. ⟨hal-00734092⟩