Wound-rotor induction generator short-circuit fault classification using a new neural network based on digital data

This paper deals with a new transformation and fusion of digital input patterns used to train and test feed-forward neural network for a wound rotor three-phase induction machine winding short-circuits classification. Used input/output data have been binary coded in order to reduce the computation complexity. A new procedure, namely addition and mean of the set of same rank, has been handled to fuse binary bits to eliminate the redundancy due to the periodic character of input signals. However, this approach has a great impact on the statistical properties on the processed data in terms of richness and of statistical distribution. The proposed neural network has been trained and tested with experimental signals coming from current sensors implemented around a set-up with a prime mover and a 5.5kW wound rotor three-phase induction generator. The experimental results highlight the superiority of using this new procedure in both training and testing modes.