An improved scheme for identifying fault zone in a series compensated transmission line using undecimated wavelet transform and Chebyshev Neural Network

摘要

Identification of fault position with respect to the compensator is an important component for a series compensated transmission line protection scheme. Based on Undecimated Discrete Wavelet Transform (UDWT) and Chebyshev Neural Network (ChNN), a new fault zone identification scheme for series compensated transmission line is proposed in this paper. The proposed technique uses only half cycle post fault data samples of three phase currents to identify the fault zone with a two-stage methodology. The performance of the proposed scheme has been compared with Discrete Wavelet Transform (DWT) and ChNN based scheme with identical fault cases comprising of all possible ten types of faults under different fault resistances, source impedances, fault inception angles and percentage compensation levels. The result demonstrates that the proposed scheme gives better performance as compared to the other methods proposed in the literature, and the DWT based technique.