Identification, Measurement, and Categorization of Faults in Power System Network Utilizing Advanced Fuzzy-Symbolic Strategy

Abstract

Electrical faults in power system may cause unstable power delivery and a higher risk of power outages. Consequently, precise identification, measurement, and classification of faults are crucial for efficient maintenance and optimal operation of power system to uphold uninterrupted power supply. Hence, this article presents the identification, measurement, and classification of various types of faults at different location of power system network (PSN). These different kinds of faults are measured in terms of inception angle. The performance parameters like accuracy, total harmonic distortion (THD), mean squared error (MSE) are found to be inappropriate with existing methods for identifying the faults. The existing methods also takes more data for computation and analysis. In this paper, combination of the symbolic and fuzzy logic controller (FLC) is proposed which is known as advanced fuzzy-symbolic strategy (AFSS) which surpass the issues of the existing methods. The effectiveness of the method is tested on modified IEEE 9 bus system. The computer simulation results and performance parameters like accuracy (6.55%), THD (3.02%), MSE (6.55%), are found to be better with AFSS in comparison to FLC for the identification, measurement, and classification of different kind of faults at different locations of PSN. The regression line also converges faster with AFSS in contrast to FLC.