Virtual sensing for gearbox condition monitoring based on kernel factor analysis

Abstract Vibration and oil debris analysis are widely used in gearbox condition monitoring as the typical indirect and direct sensing techniques. However, they have their own advantages and disadvantages. To better utilize the sensing information and overcome its shortcomings, this paper presents a...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jin-Jiang Wang, Ying-Hao Zheng, Lai-Bin Zhang, Li-Xiang Duan, Rui Zhao
Formato: article
Lenguaje:EN
Publicado: KeAi Communications Co., Ltd. 2017
Materias:
Q
Acceso en línea:https://doaj.org/article/70c4e595055645dfb51c3c06a0d0e957
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:70c4e595055645dfb51c3c06a0d0e957
record_format dspace
spelling oai:doaj.org-article:70c4e595055645dfb51c3c06a0d0e9572021-12-02T08:10:22ZVirtual sensing for gearbox condition monitoring based on kernel factor analysis10.1007/s12182-017-0163-41672-51071995-8226https://doaj.org/article/70c4e595055645dfb51c3c06a0d0e9572017-05-01T00:00:00Zhttp://link.springer.com/article/10.1007/s12182-017-0163-4https://doaj.org/toc/1672-5107https://doaj.org/toc/1995-8226Abstract Vibration and oil debris analysis are widely used in gearbox condition monitoring as the typical indirect and direct sensing techniques. However, they have their own advantages and disadvantages. To better utilize the sensing information and overcome its shortcomings, this paper presents a virtual sensing technique based on artificial intelligence by fusing low-cost online vibration measurements to derive a gearbox condition indictor, and its performance is comparable to the costly offline oil debris measurements. Firstly, the representative features are extracted from the noisy vibration measurements to characterize the gearbox degradation conditions. However, the extracted features of high dimensionality present nonlinearity and uncertainty in the machinery degradation process. A new nonlinear feature selection and fusion method, named kernel factor analysis, is proposed to mitigate the aforementioned challenge. Then the virtual sensing model is constructed by incorporating the fused vibration features and offline oil debris measurements based on support vector regression. The developed virtual sensing technique is experimentally evaluated in spiral bevel gear wear tests, and the results show that the developed kernel factor analysis method outperforms the state-of-the-art feature selection techniques in terms of virtual sensing model accuracy.Jin-Jiang WangYing-Hao ZhengLai-Bin ZhangLi-Xiang DuanRui ZhaoKeAi Communications Co., Ltd.articleGearbox condition monitoringVirtual sensingFeature selection and fusionScienceQPetrologyQE420-499ENPetroleum Science, Vol 14, Iss 3, Pp 539-548 (2017)
institution DOAJ
collection DOAJ
language EN
topic Gearbox condition monitoring
Virtual sensing
Feature selection and fusion
Science
Q
Petrology
QE420-499
spellingShingle Gearbox condition monitoring
Virtual sensing
Feature selection and fusion
Science
Q
Petrology
QE420-499
Jin-Jiang Wang
Ying-Hao Zheng
Lai-Bin Zhang
Li-Xiang Duan
Rui Zhao
Virtual sensing for gearbox condition monitoring based on kernel factor analysis
description Abstract Vibration and oil debris analysis are widely used in gearbox condition monitoring as the typical indirect and direct sensing techniques. However, they have their own advantages and disadvantages. To better utilize the sensing information and overcome its shortcomings, this paper presents a virtual sensing technique based on artificial intelligence by fusing low-cost online vibration measurements to derive a gearbox condition indictor, and its performance is comparable to the costly offline oil debris measurements. Firstly, the representative features are extracted from the noisy vibration measurements to characterize the gearbox degradation conditions. However, the extracted features of high dimensionality present nonlinearity and uncertainty in the machinery degradation process. A new nonlinear feature selection and fusion method, named kernel factor analysis, is proposed to mitigate the aforementioned challenge. Then the virtual sensing model is constructed by incorporating the fused vibration features and offline oil debris measurements based on support vector regression. The developed virtual sensing technique is experimentally evaluated in spiral bevel gear wear tests, and the results show that the developed kernel factor analysis method outperforms the state-of-the-art feature selection techniques in terms of virtual sensing model accuracy.
format article
author Jin-Jiang Wang
Ying-Hao Zheng
Lai-Bin Zhang
Li-Xiang Duan
Rui Zhao
author_facet Jin-Jiang Wang
Ying-Hao Zheng
Lai-Bin Zhang
Li-Xiang Duan
Rui Zhao
author_sort Jin-Jiang Wang
title Virtual sensing for gearbox condition monitoring based on kernel factor analysis
title_short Virtual sensing for gearbox condition monitoring based on kernel factor analysis
title_full Virtual sensing for gearbox condition monitoring based on kernel factor analysis
title_fullStr Virtual sensing for gearbox condition monitoring based on kernel factor analysis
title_full_unstemmed Virtual sensing for gearbox condition monitoring based on kernel factor analysis
title_sort virtual sensing for gearbox condition monitoring based on kernel factor analysis
publisher KeAi Communications Co., Ltd.
publishDate 2017
url https://doaj.org/article/70c4e595055645dfb51c3c06a0d0e957
work_keys_str_mv AT jinjiangwang virtualsensingforgearboxconditionmonitoringbasedonkernelfactoranalysis
AT yinghaozheng virtualsensingforgearboxconditionmonitoringbasedonkernelfactoranalysis
AT laibinzhang virtualsensingforgearboxconditionmonitoringbasedonkernelfactoranalysis
AT lixiangduan virtualsensingforgearboxconditionmonitoringbasedonkernelfactoranalysis
AT ruizhao virtualsensingforgearboxconditionmonitoringbasedonkernelfactoranalysis
_version_ 1718398606750253056