Fault detection in insulators based on ultrasonic signal processing using a hybrid deep learning technique. Issue 10 (4th March 2021)

• Record Type: Journal Article
• Authors: Frizzo Stefenon, Stéfano; Zanetti Freire, Roberto; Henrique Meyer, Luiz; Picolotto Corso, Marcelo; Sartori, Andreza; Nied, Ademir; Rodrigues Klaar, Anne Carolina; Yow, Kin‐Choong
• Is Part Of: IET science, measurement & technology. Volume 14:Issue 10(2020)
• Page Start: 953
• Page End: 961
• Publication Date: 2021-03-04
• Subjects: learning (artificial intelligence) -- regression analysis -- time series -- neural nets -- insulator contamination -- autoregressive processes -- fault diagnosis -- feature extraction -- power engineering computing -- recurrent neural nets -- wavelet neural nets; irreversible failures -- possible failures -- power grid -- fault prediction -- distribution insulators -- laboratory evaluation -- contaminated insulator -- data set acquisition -- time series prediction -- hybrid deep learning technique -- hybrid LSTM -- wavelet energy coefficient -- deeper LSTM layers -- wavelet LSTM algorithm -- classic prediction algorithms -- fault detection -- ultrasonic signal processing -- identifying problems -- system failure -- higher surface conductivity -- electrical discharges -- voltage 13.8 kV; Measurement -- Periodicals; Electrical engineering -- Periodicals; Electronics -- Periodicals; Nanotechnology -- Periodicals; Electromagnetism -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3
• DOI: 10.1049/iet-smt.2020.0083
• Languages: English
• ISSNs: 1751-8822

Abstract

Abstract : 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.