Abstract

Due to the increased devouring of electricity by a consumer, generating stations must provide an uninterrupted supply of electricity to load. For that intend, many steps had been taken for the detection of fault locations in overhead lines. Whenever any fault takes place in the transmission line, Fault Passage Indicators quickly detect fault and help the crew for clearing of fault as soon as possible. This will help in maintaining the constant supply of electricity to enduser equipment and increase the reliability of the load. These can be installed at different points for better operation in line. But all these traditional methods for detection of faults are time-consuming, hence with developing trends in Machine Learning and Artificial Neuron networks their concept can be used for the detection of faults in transmission lines. This report deals with the development of Ann for detection and identification a fault type in the 220kv line. As of 2020, python with Keras and Tensor Flow API is considered the best method for developing Ann models, hence a neural network is developed with them for the classification and detection of a fault utilizing Fast Fourier Transform. A Radial Basics Neural Network is formulated in MATLAB utilizing wavelet transform. A network is trained utilizing voltage sag and swell phenomena with a Resilient back propagation network in R language. At last, this report assists in understanding the nature of fault, occurring in transmission lines.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call