OUT-OF-STEP PREDICTION BASED ON ARTIFICIAL NEURAL NETWORKS

The application of artificial intelligence to power systems has result ed in an overall improvement of solutions in many generators based imp lementations. This paper presents a new approach to the prediction (de tection) of out-of-step synchronous, on artificial neural networks (AN Ns). The paper describes the ANN architecture adopted as well as the s election of input features for training the ANN. A feedforward model o f the neural network based on the stochastic back-propagation training algorithm has been used. The capabilities of the developed algorithm for the prediction of the out-of-step condition have been tested throu gh computer simulation for a typical case study. The results of using the proposed algorithm reveal a high classification performance.