Abstract
— The proposed work investigates the application of principal component analysis (PCA) in localizing fault in a 150 km transmission line. Quarter-cycle pre-fault and half-cycle post-fault sending end noisy line currents are analyzed for faults conducted at intermediate locations with varying fault resistance. Principal component scores, so found, are further analyzed to form a planar mesh structure and smooth fit surface model, from which the distance of the test signal is predicted. Finally, the two models have been validated. The two dimension mesh and the three dimension polynomial surface model produce an average percentage error of 0.2923% and 0.2619%, respectively. The maximum Percentage Error obtained using the two methods are 2.167% and 2.033%, respectively. The high accuracy and low computational burden are achieved in presence of power system noise as well as variation of fault location and fault resistance, which indicates the robustness of the proposed localizer models. Besides, the development of the proposed algorithm using PCA only reduces the memory requirement by reducing dimensionality of a data set, enabling faster computation, especially compared to more extensively used supervised intricate analysis like neural networks, support vector machine or complex mathematical approaches like wavelet transform, fuzzy inference schemes.
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.