Thumbnail Image

Theses

Browse

20211
Reset filters
Subject: Electrical Engineering × Author: Kohli, Vikram × End date: 2021 × Type: Thesis × Thesis Type: M.Tech. ×
Reset filters

Search Results

Now showing 1 - 1 of 1
  • Thumbnail Image
    ThesisItemOpen Access
    A fault classification and location detection technique for an overhead power transmission line using an Artificial Neural Network and FFT
    (G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand), 2021-02) Kohli, Vikram; Yadav, Abhishek
    The rapidly increasing need for energy in this modern competitive era has developed an increasing demand for power supply due to which an appreciable growth of power grid can be seen all over the world. A huge number of new transmission lines and distribution networks are being installed in the system to meet the demand. The main objective of this research is to study and design a fault locator that can detect, classify, and locate faults in power transmission lines. The most important aspect of this thesis is to concentrate on the analysis of the transmission line’s phase currents and voltages during various fault conditions. The pre-processing of fault voltages and current patterns is processed using Fast Fourier Transform (FFT) tool and the output of the FFT is provided to the ANN so that they can be used to create an efficient fault locator. When considering the physical parameters and the size of the transmission line, the accuracy with which the designed system detects the fault in power system becomes very important. A fault locator with satisfactorily high accuracy can easily achieved with the help of artificial neural networks using a large amount of data set for training and the testing processes. This eliminates the need for proficiency in power systems, which is a necessity when working with expert fuzzy systems. Hence, this thesis focuses on the design of a fault locator that can be even used by people who are not experts in the field of power systems. Analysis of neural networks with various combinations of hidden layers and neurons per hidden layer has been given to validate the choice of neural networks in each stage. Simulation results have been presented to illustrate that artificial neural network based methods are successful in locating faults on transmission lines. An accuracy of 100% to classify a fault and 98.5% to locate the fault was achieved.