Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts

Wind turbines are widely installed as the new source of cleaner energy production. Dynamic and random stress imposed on the generator bearing of a wind turbine may lead to overheating and failure. In this paper, a data-driven approach for condition monitoring of generator bearings using temporal tem...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Huajin Li, Jiahao Deng, Shuang Yuan, Peng Feng, Dimuthu D. K. Arachchige
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	bearing failure condition monitoring deep belief network EWMA control chart SCADA data analysis General Works A
Acceso en línea:	https://doaj.org/article/499470d9163f4ee49543bfe6aa9e1ab9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:499470d9163f4ee49543bfe6aa9e1ab9
record_format	dspace
spelling	oai:doaj.org-article:499470d9163f4ee49543bfe6aa9e1ab92021-11-19T04:42:17ZMonitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts2296-598X10.3389/fenrg.2021.799039https://doaj.org/article/499470d9163f4ee49543bfe6aa9e1ab92021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fenrg.2021.799039/fullhttps://doaj.org/toc/2296-598XWind turbines are widely installed as the new source of cleaner energy production. Dynamic and random stress imposed on the generator bearing of a wind turbine may lead to overheating and failure. In this paper, a data-driven approach for condition monitoring of generator bearings using temporal temperature data is presented. Four algorithms, the support vector regression machine, neural network, extreme learning machine, and the deep belief network are applied to model the bearing behavior. Comparative analysis of the models has demonstrated that the deep belief network is most accurate. It has been observed that the bearing failure is preceded by a change in the prediction error of bearing temperature. An exponentially-weighted moving average (EWMA) control chart is deployed to trend the error. Then a binary vector containing the abnormal errors and the normal residuals are generated for classifying failures. LS-SVM based classification models are developed to classify the fault bearings and the normal ones. The proposed approach has been validated with the data collected from 11 wind turbines.Huajin LiHuajin LiJiahao DengShuang YuanPeng FengDimuthu D. K. ArachchigeFrontiers Media S.A.articlebearing failurecondition monitoringdeep belief networkEWMA control chartSCADA data analysisGeneral WorksAENFrontiers in Energy Research, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	bearing failure condition monitoring deep belief network EWMA control chart SCADA data analysis General Works A
spellingShingle	bearing failure condition monitoring deep belief network EWMA control chart SCADA data analysis General Works A Huajin Li Huajin Li Jiahao Deng Shuang Yuan Peng Feng Dimuthu D. K. Arachchige Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts
description	Wind turbines are widely installed as the new source of cleaner energy production. Dynamic and random stress imposed on the generator bearing of a wind turbine may lead to overheating and failure. In this paper, a data-driven approach for condition monitoring of generator bearings using temporal temperature data is presented. Four algorithms, the support vector regression machine, neural network, extreme learning machine, and the deep belief network are applied to model the bearing behavior. Comparative analysis of the models has demonstrated that the deep belief network is most accurate. It has been observed that the bearing failure is preceded by a change in the prediction error of bearing temperature. An exponentially-weighted moving average (EWMA) control chart is deployed to trend the error. Then a binary vector containing the abnormal errors and the normal residuals are generated for classifying failures. LS-SVM based classification models are developed to classify the fault bearings and the normal ones. The proposed approach has been validated with the data collected from 11 wind turbines.
format	article
author	Huajin Li Huajin Li Jiahao Deng Shuang Yuan Peng Feng Dimuthu D. K. Arachchige
author_facet	Huajin Li Huajin Li Jiahao Deng Shuang Yuan Peng Feng Dimuthu D. K. Arachchige
author_sort	Huajin Li
title	Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts
title_short	Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts
title_full	Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts
title_fullStr	Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts
title_full_unstemmed	Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts
title_sort	monitoring and identifying wind turbine generator bearing faults using deep belief network and ewma control charts
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/499470d9163f4ee49543bfe6aa9e1ab9
work_keys_str_mv	AT huajinli monitoringandidentifyingwindturbinegeneratorbearingfaultsusingdeepbeliefnetworkandewmacontrolcharts AT huajinli monitoringandidentifyingwindturbinegeneratorbearingfaultsusingdeepbeliefnetworkandewmacontrolcharts AT jiahaodeng monitoringandidentifyingwindturbinegeneratorbearingfaultsusingdeepbeliefnetworkandewmacontrolcharts AT shuangyuan monitoringandidentifyingwindturbinegeneratorbearingfaultsusingdeepbeliefnetworkandewmacontrolcharts AT pengfeng monitoringandidentifyingwindturbinegeneratorbearingfaultsusingdeepbeliefnetworkandewmacontrolcharts AT dimuthudkarachchige monitoringandidentifyingwindturbinegeneratorbearingfaultsusingdeepbeliefnetworkandewmacontrolcharts
_version_	1718420371281018880

Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts

Ejemplares similares