On-Line Determination of Salient-Pole Hydro Generator Parameters by Neural Network Estimator Using Operating Data (PEANN)

A novel application of Artificial Neural Network (ANN) to estimate and track Hydro Generator Dynamic Parameters using online disturbance measurements is presented within this paper. The data for training ANN are obtained through off-line simulation the generators modelled in a one-machine-infinite-bus environment parameters sets that representative practical data. Levenberg-Marquardt algorithm has been adopted assimilated into back-propagation learning feed-forward neural networks. inputs organized coordination with results from observability analysis synchronous generator dynamic its behaviour. collection 10 ANNs similar input patterns different outputs developed determine set parameters. trained employed real-time operational estimating acquired during conditions. tested identify disturbances. Simulation studies demonstrate ability accurately hydro-generators. also show impact test conditions on accuracy degree estimation these optimal structure determined minimize error each parameter.