Induction machine stator short-circuit fault detection using support vector machine

Saddam Bensaoucha; Youcef Brik; Sandrine Moreau; Sid Ahmed Bessedik; Aissa Ameur

Ayuda

Induction machine stator short-circuit fault detection using support vector machine

Saddam Bensaoucha ^[2] ; Youcef Brik ^[3] ; Sandrine Moreau ^[1] ; Sid Ahmed Bessedik ^[2] ; Aissa Ameur ^[2]
1. [1] University of Poitiers
  
  University of Poitiers
  
  Arrondissement de Poitiers, Francia
2. [2] University of Amar Telidji, Argelia
3. [3] University of M'sila, Argelia
Mostrar afiliaciones +
Localización: Compel: International journal for computation and mathematics in electrical and electronic engineering, ISSN 0332-1649, Vol. 40, Nº 3, 2021, págs. 373-389
Idioma: inglés
Enlaces
- Texto completo
Resumen
- Purpose This paper provides an effective study to detect and locate the inter-turn short-circuit faults (ITSC) in a three-phase induction motor (IM) using the support vector machine (SVM). The characteristics extracted from the analysis of the phase shifts between the stator currents and their corresponding voltages are used as inputs to train the SVM. The latter automatically decides on the IM state, either a healthy motor or a short-circuit fault on one of its three phases.
  
  Design/methodology/approach To evaluate the performance of the SVM, three supervised algorithms of machine learning, namely, multi-layer perceptron neural networks (MLPNNs), radial basis function neural networks (RBFNNs) and extreme learning machine (ELM) are used along with the SVM in this study. Thus, all classifiers (SVM, MLPNN, RBFNN and ELM) are tested and the results are compared with the same data set.
  
  Findings The obtained results showed that the SVM outperforms MLPNN, RBFNNs and ELM to diagnose the health status of the IM. Especially, this technique (SVM) provides an excellent performance because it is able to detect a fault of two short-circuited turns (early detection) when the IM is operating under a low load.
  
  Originality/value The original of this work is to use the SVM algorithm based on the phase shift between the stator currents and their voltages as inputs to detect and locate the ITSC fault.