Application of minimal radial basis function neural network to distance protection

The paper presents a new approach for the protection of power transmission lines using a minimal radial basis function neural network (MRBFNN), This t ype of RBF neural network uses a sequential learning procedure to determine the optimum number of neurons in the hidden layer without resorting to tri al and error. The input data to this network comprises fundamental peak val ues of relaying point voltage and current signals, the zero-sequence compon ent of current and system operating frequency. These input variables are ob tained by Kalman filtering approach. Further, the parameters of the network are adjusted using a variant of extended Kalman filter known as locally it erated Kalman filter to produce better accuracy in the output for harmonics , de offset and noise in the input data. The number of training patterns an d the training time are drastically reduced and significant accuracy is ach ieved in different types of fault classification and location in transmissi on lines using computer simulated tests.