Fuzzified time-frequency method for identification and localization of power system faults

Issue title: Digital transformation through advances in artificial intelligence and machine learning

Guest editors: Hasmat Malik, Gopal Chaudhary and Smriti Srivastava

Article type: Research Article

Authors: Srikanth, Pullabhatla^{a; *} | Koley, Chiranjib^b

Affiliations: [a] EED, NIT Durgapur, West Bengal, & CCE (R&D) South, DRDO Secunderabad, India | [b] National Institute of Technology, Durgapur, West Bengal, India

Correspondence: [*] Corresponding author. Pullabhatla Srikanth, EED, NIT Durgapur, West Bengal, & CCE (R&D) South, DRDO Secunderabad, India. E-mail: [email protected].

Abstract: In this work, different types of power system faults at various distances have been identified using a novel approach based on Discrete S-Transform clubbed with a Fuzzy decision box. The area under the maximum values of the dilated Gaussian windows in the time-frequency domain has been used as the critical input values to the fuzzy machine. In this work, IEEE-9 and IEEE-14 bus systems have been considered as the test systems for validating the proposed methodology for identification and localization of Power System Faults. The proposed algorithm can identify different power system faults like Asymmetrical Phase Faults, Asymmetrical Ground Faults, and Symmetrical Phase faults, occurring at 20% to 80% of the transmission line. The study reveals that the variation in distance and type of fault creates a change in time-frequency magnitude in a unique pattern. The method can identify and locate the faulted bus with high accuracy in comparison to SVM.

Keywords: Power system faults, localization, identification, fuzzy logic, signal processing

DOI: 10.3233/JIFS-189769

Journal: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 2, pp. 1027-1039, 2022