Feature Extraction Techniques from Contaminated-Insulator Leakage Current Data for Deep Learning Applications in Condition Monitoring of High Voltage Insulators

  • Amir, Khan U.; 
  • Asif, M.; 
  • Jung, J.; 
  • Alhems, L.; 
  • Lee, B.-W.
Citations

SCOPUS

4

초록

This paper presents advanced feature extraction techniques for analyzing leakage current data from contaminated high voltage insulators, aimed at enhancing deep learning applications in condition monitoring. We extract and evaluate time-domain, frequency-domain, and wavelet domain features from leakage current signals. Using Random Forest and permutation importance, we identify key features such as temperature, relative humidity, peak-to-peak values, wavelet energy, and spectral centroid. Correlation and scatter matrix visualizations illustrate the relationships between features and their ability to distinguish pollution levels. A careful selection of features facilitates efficient training of deep learning algorithms to generalize across various contamination levels and environmental conditions. © 2024 The Korean Institute of Electrical Engineers (KIEE).

키워드

Condition Monitoring; Deep Learning; Frequency-Domain Features; High Voltage Insulators; Leakage Current; Permutation Importance; Random Forest; Wavelet Features
제목
Feature Extraction Techniques from Contaminated-Insulator Leakage Current Data for Deep Learning Applications in Condition Monitoring of High Voltage Insulators
저자
Amir, Khan U.; Asif, M.; Jung, J.; Alhems, L.; Lee, B.-W.
DOI
10.23919/CMD62064.2024.10766261
발행일
2024-12
유형
Conference Paper
저널명
2024 10th International Conference on Condition Monitoring and Diagnosis, CMD 2024
페이지
608 ~ 611