A Probabilistic Generative Model for Fault Analysis of a Transmission Line With SFCL

The fault analysis of a transmission line (TL) are the key factors for the rapid restoration of the power network. Due to the recent expansion of the power system as well as the increased generation capacity, the magnitude of the fault current increases beyond the interruption capability of the existing circuit breaker. In this turn, the superconducting fault current limiters (SFCLs) come in handy which limits the fault current and facilitates the tripping operation without upgrading the breaker rating. Besides, the SFCLs affect the three-phase signals which, in turn, negatively affect the transmission line protection scheme. This paper proposes an unsupervised framework for fault detection and classification of a transmission line with SFCLs. The proposed scheme receives 1/2 cycle post-fault three-phase signals and hierarchically extracts the fault information for fault analyzing purposes. The effectiveness of the proposed approach is justified in terms of overall and individual accuracy. Further assessment of the model's performance against noise and measurement error is also carried out in order to confirm the high reliability of the proposed model.