Modified elman neural network based on-line stator winding turn fault detection for induction motors

A modified Elman neural network (MENN) based on-line stator winding turn fault detection approach for induction motors is presented in this paper. In order to detect turn fault, a MENN is employed to estimate the fault severity and the exact number of fault turns. The MENN improves the approximation accuracy by introducing a new adjustable weight between the context nodes and the output nodes. In the course of training, BP algorithm is adopted to make the MENN converging more quickly. Experiments are carried out on a special rewound laboratory induction motor, the results show that the MENN based diagnosis model determines the shorted turns exactly, and is more effective than the basic Elman neural network (BENN) based detection model under the condition of detecting a dynamically developing turn fault. 1548-7741/ Copyright © 2009 Binary Information Press.