Development and implementation of neural network observers to estimate the state vector of a synchronous generator from on-line operating data

This paper presents a novel technique for developing and implementing artificial neural network (ANN) observers for estimating unmeasurable rotor body currents of a synchronous generator from time-domain online disturbance data. Data for training the observers are generated through off-line simulations of a 7.5 kVA machine model whose parameters are varied in accordance with previously determined online parameter estimates of the generator under consideration. Studies show that observer robustness towards noise can be improved by enhancing the size of the observer input vector. In order to increase observer robustness towards variations in the field-resistance, simulated variations representative of changes in field-resistance were introduced in the training sets. After training, the observers are tested with experimentally obtained online measurements to provide estimates of unmeasurable rotor body currents. The estimated rotor body currents are then used along with experimental measurements to estimate synchronous generator parameters.