Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder

The reliability and health of bushings in high-voltage (HV) power transformers is essential in the power supply industry, as any unexpected failure can cause power outage leading to heavy financial losses. The challenge is to identify the point at which insulation deterioration puts the bushing at a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Imene Mitiche, Tony McGrail, Philip Boreham, Alan Nesbitt, Gordon Morison
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	transformer bushings insulation failure anomaly detection LSTM auto-encoder Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/c0f2d2102994430abf1084251180cedc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c0f2d2102994430abf1084251180cedc
record_format	dspace
spelling	oai:doaj.org-article:c0f2d2102994430abf1084251180cedc2021-11-11T19:20:24ZData-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder10.3390/s212174261424-8220https://doaj.org/article/c0f2d2102994430abf1084251180cedc2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7426https://doaj.org/toc/1424-8220The reliability and health of bushings in high-voltage (HV) power transformers is essential in the power supply industry, as any unexpected failure can cause power outage leading to heavy financial losses. The challenge is to identify the point at which insulation deterioration puts the bushing at an unacceptable risk of failure. By monitoring relevant measurements we can trace any change that occurs and may indicate an anomaly in the equipment’s condition. In this work we propose a machine-learning-based method for real-time anomaly detection in current magnitude and phase angle from three bushing taps. The proposed method is fast, self-supervised and flexible. It consists of a Long Short-Term Memory Auto-Encoder (LSTMAE) network which learns the normal current and phase measurements of the bushing and detects any point when these measurements change based on the Mean Absolute Error (MAE) metric evaluation. This approach was successfully evaluated using real-world data measured from HV transformer bushings where anomalous events have been identified.Imene MiticheTony McGrailPhilip BorehamAlan NesbittGordon MorisonMDPI AGarticletransformer bushingsinsulation failureanomaly detectionLSTMauto-encoderChemical technologyTP1-1185ENSensors, Vol 21, Iss 7426, p 7426 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	transformer bushings insulation failure anomaly detection LSTM auto-encoder Chemical technology TP1-1185
spellingShingle	transformer bushings insulation failure anomaly detection LSTM auto-encoder Chemical technology TP1-1185 Imene Mitiche Tony McGrail Philip Boreham Alan Nesbitt Gordon Morison Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder
description	The reliability and health of bushings in high-voltage (HV) power transformers is essential in the power supply industry, as any unexpected failure can cause power outage leading to heavy financial losses. The challenge is to identify the point at which insulation deterioration puts the bushing at an unacceptable risk of failure. By monitoring relevant measurements we can trace any change that occurs and may indicate an anomaly in the equipment’s condition. In this work we propose a machine-learning-based method for real-time anomaly detection in current magnitude and phase angle from three bushing taps. The proposed method is fast, self-supervised and flexible. It consists of a Long Short-Term Memory Auto-Encoder (LSTMAE) network which learns the normal current and phase measurements of the bushing and detects any point when these measurements change based on the Mean Absolute Error (MAE) metric evaluation. This approach was successfully evaluated using real-world data measured from HV transformer bushings where anomalous events have been identified.
format	article
author	Imene Mitiche Tony McGrail Philip Boreham Alan Nesbitt Gordon Morison
author_facet	Imene Mitiche Tony McGrail Philip Boreham Alan Nesbitt Gordon Morison
author_sort	Imene Mitiche
title	Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder
title_short	Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder
title_full	Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder
title_fullStr	Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder
title_full_unstemmed	Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder
title_sort	data-driven anomaly detection in high-voltage transformer bushings with lstm auto-encoder
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/c0f2d2102994430abf1084251180cedc
work_keys_str_mv	AT imenemitiche datadrivenanomalydetectioninhighvoltagetransformerbushingswithlstmautoencoder AT tonymcgrail datadrivenanomalydetectioninhighvoltagetransformerbushingswithlstmautoencoder AT philipboreham datadrivenanomalydetectioninhighvoltagetransformerbushingswithlstmautoencoder AT alannesbitt datadrivenanomalydetectioninhighvoltagetransformerbushingswithlstmautoencoder AT gordonmorison datadrivenanomalydetectioninhighvoltagetransformerbushingswithlstmautoencoder
_version_	1718431550180163584

Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM Auto-Encoder

Ejemplares similares