Fault detection in insulators based on ultrasonic signal processing using a hybrid deep learning technique

• Published in: IET science, measurement & technology Vol. 14; no. 10; pp. 953 - 961
• Main Authors: Frizzo Stefenon, Stéfano, Zanetti Freire, Roberto, Henrique Meyer, Luiz, Picolotto Corso, Marcelo, Sartori, Andreza, Nied, Ademir, Rodrigues Klaar, Anne Carolina, Yow, Kin-Choong
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 20.12.2020
• Subjects: autoregressive processes; classic prediction algorithms; contaminated insulator; data set acquisition; deeper LSTM layers; distribution insulators; electrical discharges; fault detection; fault diagnosis; fault prediction; feature extraction; higher surface conductivity; hybrid deep learning technique; hybrid LSTM; identifying problems; insulator contamination; irreversible failures; laboratory evaluation; learning (artificial intelligence); neural nets; possible failures; power engineering computing; power grid; recurrent neural nets; regression analysis; Research Article; system failure; time series; time series prediction; ultrasonic signal processing; voltage 13.8 kV; wavelet energy coefficient; wavelet LSTM algorithm; wavelet neural nets; wavelet energy coefficient; higher surface conductivity; fault diagnosis; time series prediction; deeper LSTM layers; regression analysis; fault detection; insulator contamination; power grid; feature extraction; contaminated insulator; wavelet neural nets; hybrid deep learning technique; voltage 13.8 kV; identifying problems; learning (artificial intelligence); irreversible failures; distribution insulators; electrical discharges; system failure; recurrent neural nets; wavelet LSTM algorithm; time series; autoregressive processes; data set acquisition; power engineering computing; laboratory evaluation; ultrasonic signal processing; classic prediction algorithms; hybrid LSTM; possible failures; fault prediction; neural nets
• ISSN: 1751-8822; 1751-8830
• DOI: 10.1049/iet-smt.2020.0083

Identifying problems in insulators is a task that requires the experience of the operator. Contaminated insulators generally do not represent a system failure, however, due to higher surface conductivity, they may suffer from electrical discharges and may result in irreversible failures. The identification of possible failures in inspections can help to forecast faults to improve reliability in the power grid. Based on this need, this article presents a study on fault prediction in distribution insulators, through a laboratory evaluation in a contaminated insulator, where 13.8 kV (root mean square) was applied considering an ultrasound detector connected to a computer for data set acquisition. In the sequence, a time series prediction, using a hybrid deep learning technique defined as wavelet long short-term memory (LSTM), was performed. The hybrid LSTM was proposed considering feature extraction through the wavelet energy coefficient. Finally, for a complete evaluation, deeper LSTM layers were included, and both the training method and the hardware configuration were evaluated. The wavelet LSTM algorithm showed interesting accuracy results when compared to classic prediction algorithms like the non-linear autoregressive exogenous model.