Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network

Due to the powerful capability of feature extraction, convolutional neural network (CNN) is increasingly applied to the fault diagnosis of key components of rotating machineries. Due to the shortcomings of traditional CNN-based fault diagnosis methods, the continuous convolution and pooling operatio...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xinghua Huang, Yuanyuan Li, Yi Chai
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	wind turbines planetary gearbox fault diagnosis convolutional neural network feature fusion wavelet transform General Works A
Acceso en línea:	https://doaj.org/article/e0d9823bd5dd49c08d17c062aa9d07a1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e0d9823bd5dd49c08d17c062aa9d07a1
record_format	dspace
spelling	oai:doaj.org-article:e0d9823bd5dd49c08d17c062aa9d07a12021-12-01T11:10:58ZIntelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network2296-598X10.3389/fenrg.2021.747622https://doaj.org/article/e0d9823bd5dd49c08d17c062aa9d07a12021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fenrg.2021.747622/fullhttps://doaj.org/toc/2296-598XDue to the powerful capability of feature extraction, convolutional neural network (CNN) is increasingly applied to the fault diagnosis of key components of rotating machineries. Due to the shortcomings of traditional CNN-based fault diagnosis methods, the continuous convolution and pooling operations result in the constant decrease of feature resolution, which may cause the loss of some subtle fault information in the samples. This paper proposes a CNN-based model with improved structure multi-scale dense fusion network (MSDFN) to realize the fault diagnosis of wind turbines planetary gearboxes under complicated working conditions. First, the continuous wavelet transform is applied to preprocess the vibration signals, and the two-dimensional wavelet time-frequency diagrams are used as the network input. Then, the multi-scale feature fusion (MSFF) module and a feature of maximum (FoM) module are used in the extraction and classification stages of fault features, respectively. Next, the multi-scale features of each network layer are fused to enhance the fault features. Finally, the high fault diagnosis accuracy is achieved by extracting the separable fusion result of fault features. The proposed method achieves more than 99% fault diagnosis average accuracy on a planetary gearbox dataset. The comparative experimental results verify the effectiveness of the proposed method and its superiority to some mainstream approaches. The ablation study further confirms that MSFF module and FoM module play the positive role in fault diagnosis.Xinghua HuangYuanyuan LiYi ChaiFrontiers Media S.A.articlewind turbines planetary gearboxfault diagnosisconvolutional neural networkfeature fusionwavelet transformGeneral WorksAENFrontiers in Energy Research, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	wind turbines planetary gearbox fault diagnosis convolutional neural network feature fusion wavelet transform General Works A
spellingShingle	wind turbines planetary gearbox fault diagnosis convolutional neural network feature fusion wavelet transform General Works A Xinghua Huang Yuanyuan Li Yi Chai Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network
description	Due to the powerful capability of feature extraction, convolutional neural network (CNN) is increasingly applied to the fault diagnosis of key components of rotating machineries. Due to the shortcomings of traditional CNN-based fault diagnosis methods, the continuous convolution and pooling operations result in the constant decrease of feature resolution, which may cause the loss of some subtle fault information in the samples. This paper proposes a CNN-based model with improved structure multi-scale dense fusion network (MSDFN) to realize the fault diagnosis of wind turbines planetary gearboxes under complicated working conditions. First, the continuous wavelet transform is applied to preprocess the vibration signals, and the two-dimensional wavelet time-frequency diagrams are used as the network input. Then, the multi-scale feature fusion (MSFF) module and a feature of maximum (FoM) module are used in the extraction and classification stages of fault features, respectively. Next, the multi-scale features of each network layer are fused to enhance the fault features. Finally, the high fault diagnosis accuracy is achieved by extracting the separable fusion result of fault features. The proposed method achieves more than 99% fault diagnosis average accuracy on a planetary gearbox dataset. The comparative experimental results verify the effectiveness of the proposed method and its superiority to some mainstream approaches. The ablation study further confirms that MSFF module and FoM module play the positive role in fault diagnosis.
format	article
author	Xinghua Huang Yuanyuan Li Yi Chai
author_facet	Xinghua Huang Yuanyuan Li Yi Chai
author_sort	Xinghua Huang
title	Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network
title_short	Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network
title_full	Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network
title_fullStr	Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network
title_full_unstemmed	Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network
title_sort	intelligent fault diagnosis method of wind turbines planetary gearboxes based on a multi-scale dense fusion network
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/e0d9823bd5dd49c08d17c062aa9d07a1
work_keys_str_mv	AT xinghuahuang intelligentfaultdiagnosismethodofwindturbinesplanetarygearboxesbasedonamultiscaledensefusionnetwork AT yuanyuanli intelligentfaultdiagnosismethodofwindturbinesplanetarygearboxesbasedonamultiscaledensefusionnetwork AT yichai intelligentfaultdiagnosismethodofwindturbinesplanetarygearboxesbasedonamultiscaledensefusionnetwork
_version_	1718405265267621888

Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network

Ejemplares similares