Publication

Abstract : Contamination flashover of overhead line insulator is a serious problem which interrupts the power flow and affect reliability of transmission and distribution system. Therefore, timely and accurately estimation of contamination severity is a key to prevent contamination flashover henceforth enhancement of the reliability of transmission and distribution system. This paper presents an innovative and automated framework to estimate contamination level of overhead line insulator in service accurately employing surface leakage current (SLC) signal. In this framework, SLC signal procured at different contamination level has been analyzed in a joint time-frequency plane through Multisynchrosqueezing Transform. Thereafter, time-frequency spectrogram image obtained through Multisynchrosqueezing Transform has been fed to a configured CNN model for automated feature extraction and classification of SLC signals. Experimental results revealed that proposed framework is highly accurate and delivered better performance compared to other time-frequency spectrogram-based approach.