Neural network transient stability assessment of a single-machine system under asymmetrical fault conditions

The authors propose a neural network approach for transient stability assessment and for critical fault clearing time estimation for a single-machine system under asymmetrical fault conditions. They describe the back-propagation neural network configurations adopted and detail the different stages in the training process of the neural networks. Results obtained by applying the neural network approach to a single-machine system show that fast and accurate assessment of transient stability boundaries can be achieved but the approach requires further improvement for use in the estimation of critical fault clearing times