Open Access Open Access  Restricted Access Subscription or Fee Access

An Efficient Method of Fault Analysis using Artificial Neural Network

Vikash Kumar, Shashank Mishra

Abstract


In the power system, there are many techniques to identify and classify the faults. So, it is utmost important to choose the suitable technique. In this paper, a novel technique based on ANN have been proposed. When abnormal conditions occur in the system, the purposed method identifies and classify the fault to protect the system from the faults and stop from the big hazards. Simulation of purposed Simulink model have been tested for the system. The current waveforms are used to identify and classify the fault by using ANN in the MATLAB software. The different types of symmetrical and unsymmetrical faults such as single line to ground fault, line to line fault, double line to ground fault and three phase faults are identified and classified with the proposed model. The identification, validation of faults, check and regression plot and classification are done by the mean square error (performance), gradient and ‘Mu’ in the ANN. With the help of these parameters, identification and classification is performed.

 


Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Current Trends in Signal Processing