ANN observer for on-line estimation of synchronous generator dynamic parameters

This paper presents a new method for implementing Artificial Neural Network (ANN) observers in estimating and identifying synchronous generator dynamic parameters based on one statistic feature extraction from the operating data using obtained measurements from time zone information. Required data for training the neural network observers are obtained through off-line simulations of a synchronous generator operating in a one-machine-infinite-bus environment. Optimal components of the patterns are segregated from many learning patterns based on a new method called "normalized variance". Nominal values of parameters are used as a deviance index in the machine model. Finally, neural network is tested through online simulated measurements in order to estimate and indentify synchronous generator dynamic parameters.