The transient stability evaluation studies were mainly related to the following factors: 1) the construction parameters of the network and operating conditions of the power system. 2) the fault type and location. 3) the fault clearing time.
Application of artificial neural networks to power systems has resulted in an overall improvement of solutions in many areas. This paper presents a multi-layer feedforward perceptron type neural network (NN) for transient stability evaluation. Numerical integration and Lyapunov direct method are used to obtain the training set of the NN. The neural network architecture adopted as well as the selection of input features for training the neural networks is described: The approach is tested on a 3-generator power system using a stochastic backpropagation algorithm. The capabilities of the developed technique is tested through computer simulation for a typical case study. By comparison with the conventional methods, the proposed method can quickly estimate the transient stability of the power system at different fault locations, clearing times and load levels of the system. The results demonstrate that this approach has an excellent classification performance and simple for on-line application.