This paper proposes an advanced technique for condition assessment of outdoor insulators based on its surface leakage current through employing Detrended Fluctuation Analysis (DFA). Analysis of surface leakage current of in-service insulator can be useful for assessing its surface condition. In the proposed technique, a tracker signal has been developed based on the fundamental component of surface leakage current to extract the distortions from it which carries significant information about contamination level. DFA has then been applied on the extracted distortions of leakage current to estimate its contamination level. In order to investigate experimentally, surface leakage current of 11 kV disc insulator (contaminated at different level) has been captured at different applied voltage level. The proposed technique has been applied on the captured leakage current to estimate contamination level. Results show that, employment of the proposed technique provides satisfactory outcomes regarding assessment of insulator condition which in turn improves the reliability of power system
In this article, an efficient technique has been proposed to estimate the contamination level of overhead polymeric insulators. Deposition of contamination on polymeric insulator surface, is a serious issue as it often results in the flashover and even insulator failure. For estimating the severity of contamination level, surface leakage current (SLC) signals of a 11kV polymeric insulator with contaminated surface has been analyzed in time-frequency domain through hyperbolic window stockwell transform (HST). HST is more flexible than classical stockwell transform. Also, HST can able to handle both the low and high frequencies adequately. Considering the advantage, HST has been used here to estimate contamination degree from SLC signature. HST analysis of SLC signal returned a 2d complex time-frequency HS matrix. The complex time-frequency HS matrix has been separated into magnitude and phase spectrum. Based on the phase and magnitude spectrum, 15 statistical features, namely HST features has been extracted. Thereafter, 5 relevant HST features have been selected through least absolute shrinkage and selection operator (LASSO) feature selection technique. Finally, these relevant HST features are fed to four machine learning classifiers for estimation of contamination degree. It has also been observed that, the proposed framework method offered better classification accuracy compared to other standard time-frequency analysis and existing methods available in literature.
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.
Overhead line insulators of power systems easily get contaminated because of atmospheric pollutants and hence allow leakage current (LC) flow throughout their surfaces. On a dry contaminated insulator surface, the leakage current is quite low, however, it increases with humidity and precipitation, leading to a higher chance of flashover. Thus, it is essential to ascertain the degree of surface contamination to enable the accurate prediction of the possibility of a flashover. The levels of such surface contamination are identified by monitoring and analyzing surface leakage current (SLC). In this regard, the SLC data of a 33-kV Silicon Rubber (SiR) insulator have been experimentally acquired for various levels of insulator surface contamination and corresponding operating voltages. Further, Discrete Meyer wavelet decomposition methods have been employed to obtain statistical features from the acquired SLC signals. These feature sets can further be utilized to detect the contamination classes of the SiR insulator samples by using SLC signals with their respective degree of contamination. For this purpose, the obtained statistical features of the SLC signals have then been further utilized to train a Machine Learning (ML) classifier named Gaussian Naïve Bayes (GNB) to determine the degree of severity of SiR insulator surface contaminations.