Intelligent busbar protection scheme based on combination of support vector machine and S‐transform. Issue 8 (29th March 2017)

• Record Type: Journal Article
• Authors: Gil, Milad; Abdoos, Ali Akbar
• Is Part Of: IET generation, transmission & distribution. Volume 11:Issue 8(2017)
• Page Start: 2056
• Page End: 2064
• Publication Date: 2017-03-29
• Subjects: busbars -- power system protection -- power system security -- support vector machines -- transforms -- power system faults -- time‐domain analysis -- frequency‐domain analysis -- power grids -- power engineering computing; intelligent busbar protection scheme -- support vector machine -- SVM -- S‐transform analysis -- signal processing technique -- time domains -- frequency domains -- differential currents -- restraint currents -- busbar differential protection scheme security -- feature space -- internal faults -- external faults -- Iranian power system grid -- Jiles‐Atherton model -- transient behaviour -- EMTDC environment -- PSCAD environment -- current transformer -- CT saturation conditions -- voltage 400 kV; Electric power production -- Periodicals; Electric power transmission -- Periodicals; Electric power distribution -- Periodicals; 621.3105
• DOI: 10.1049/iet-gtd.2016.1686
• Languages: English
• ISSNs: 1751-8687

Abstract

Abstract : Differential protection is the main protective scheme of busbar in power systems but its operation degrades during current transformer (CT) saturation conditions. In this study, the busbar differential protection scheme is improved by the addition of a new feature extracted from differential current using S‐transform analysis. S‐transform as a powerful signal processing technique gives a complete visualisation of the signal in both time and frequency domains. The new extracted feature as well as the magnitude of the differential and restraint currents are utilised to increase the security of traditional busbar differential protection scheme. With the addition of this new feature, distinctive regions are created in the feature space which can be separated by an appropriate classifier. In this study, the well‐known classifier, i.e. support vector machine is employed to effectively discriminate internal faults from external faults. To evaluate the performance of the proposed method, a part of Iranian 400‐kV power system grid is simulated in the PSCAD/EMTDC environment. The transient behaviour of CTs during saturation conditions is simulated based on the precise Jiles–Atherton model. The obtained results justify the superiority of the proposed method in terms of speed and security even in noisy conditions.