Fault Analysis on Transmission Lines Using Artificial Neural Network

Authors: Vishnu Malviya, Dr. Dev Kumar Rai

Certificate: View Certificate

Abstract

The transmission and distribution lines are vital links between generating units and consumers. This project focuses on detecting Fault detection on electric power transmission lines using artificial neural networks (ANN). The developed neural network is capable of detecting single line to ground and double line to ground for all the three phases Simulation results have been provided to demonstrate that artificial neural network based methods are efficient in faults detection on transmission lines and achieve satisfactory performances.

Introduction

Transmission line is the most likely element in the power scheme to be exposed especially when its physical dimension is taken into consideration. Transmission line is used to transfer power or voltage to long distance destination. Power or voltage generated from source is supplied to the load through the Transmission Line. While transmitting, Transmission Line encounters various faults due to momentary tree contact, a bird or an animal contact or due to other natural reasons such as thunderstorms or lightning. The objective of this work is to study and employ neural network (NN) method as a reliable tool to identify or detect faults in a transmission line scheme Artificial neural network (ANN) is a powerful method to be used in transmission line fault identification, isolation and classification. The parallelism inherent in neural networks (NN) enables them with faster computational time than the traditional techniques. Using this technology in transmission line fault diagnosis validates its utility and encourages engineers to use this technique in other power systems. The main objective of this paper is to develop neural network based autonomous learning scheme that acquire knowledge incrementally in real time, with as little supervision as possible and to deploy effective strategies for practical application of such scheme for fault identification and diagnosis. In protection of transmission line the fault identification, classification and location plays an important role. The number of neurons in the layers is selected to be sufficient for the provision of required problem solving quality. The number of layers is desired to be minimal in order to decrease the problem solving time. Basically, we can design and train the neural networks for solving particular problems which are difficult to solve through the human beings or the conventional computational algorithms. The computational of the training comes down to the adjustments of certain weights which are the key elements of the Artificial Neural Network. This is one of the key differences of the neural network approach to problem solving than conventional computational method. This adjustment of the weights takes place when the neural network is presented with the input data records and the corresponding target values. In the possibility of training neural networks with off-line data, they are found useful for power system. The neural network (NN) applications in transmission line protection are mainly concerned with in improvements in achieving more effective and efficient fault diagnosis and distance relaying. NN application can be used for overhead transmission lines, as well as in power distribution systems.

Conclusion

The proposed method, fault detection using artificial neural network (ANN). The fault detection in a transmission line technique have been investigated using neural network technique. The data generated is used for single phase to ground faults, double phase faults and double phase to ground faults. The results obtained for transmission line fault detection.