Development of a neural network based saturation model for synchronous generator analysis

This paper presents a new approach to model synchronous generator saturation based on a feedforward artificial neural network (ANN) model. The machine loading conditions, excitation levels and rotor positions are all included in the modeling process. The nonlinear saturation characteristics of a three-phase salient-pole synchronous machine rated at 5 kVA and 240 V is studied using the ANN model. An appropriate selection of input/output pattern for the ANN model training based on an error back-propagation scheme is developed using the on-line small-disturbance responses and the well-known maximum-likelihood estimation algorithm. The developed ANN model is implemented in the generator dynamic transient stability study requiring only small computational alteration in saturation model representation