Abstract
In this study, fault location is implemented on an IEEE-15bus sample network using artificial neural network. The basis of this work is such that initially, in order to train the neural network, a series of specific characteristic are extracted by the relay from the observed fault signal. These characteristics are obtained by wavelet transform which properly extracts high and low frequency coefficients of the signal. Hence, since high frequencies are generated during the occurrence of the fault, signal information could be extracted using wavelet transform. After wavelet transform, the entropies of the minor components of the sequences could be obtained using statistics to extract the hidden features inside them and present them to train the neural network. Also, since the obtained inputs for the training of the neural network depend on the fault angle, resistance and location, the training data should be selected such that these differences be properly presented so the neural network does not face any issues in its identification. Therefore, selecting the signal processing function, data spectrum and subsequently, statistical parameters and their combinations are important. The simulation results show the good performance of neural network for the faults in different angles, locations, and resistances.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.