Multi-layer neural network with deep belief network for gearbox fault diagnosis
Identifying gearbox damage categories, especially for early faults and combined faults, is a challenging task in gearbox fault diagnosis. This paper presents multiple classifiers based on multi-layer neural networks (MLNN) to implement vibration signals for fault diagnosis in gearbox. A MLNN-based l...
Guardado en:
Autor Principal: | |
---|---|
Formato: | Artículos |
Lenguaje: | eng |
Publicado: |
2016
|
Materias: | |
Acceso en línea: | http://repositorio.educacionsuperior.gob.ec/handle/28000/2982 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:localhost:28000-2982 |
---|---|
recordtype |
dspace |
spelling |
oai:localhost:28000-29822017-04-12T15:40:43Z Multi-layer neural network with deep belief network for gearbox fault diagnosis Li, Chuan MULTI-LAYER NEURAL NETWORK BELIEF NETWORK GEARBOX Identifying gearbox damage categories, especially for early faults and combined faults, is a challenging task in gearbox fault diagnosis. This paper presents multiple classifiers based on multi-layer neural networks (MLNN) to implement vibration signals for fault diagnosis in gearbox. A MLNN-based learning architecture using deep belief network (MLNNDBN) is proposed for gearbox fault diagnosis. Training process of the proposed learning architecture includes two stages: A deep belief network is constructed firstly, and then is trained; after a certain amount of epochs, the weights of deep belief network are used to initialize the weights of the constructed MLNN; at last, the trained MLNN is used as classifiers to classify gearbox faults. Multidimensional feature sets including time-domain, frequency-domain features are extracted to reveal gear health conditions. Experiments with different combined faults were conducted, and the vibration signals were captured under different loads and motor speeds. To confirm the superiority of MLNNDBN in fault classification, its performance is compared with other MLNN-based methods with different fine-tuning schemes and relevant vector machine. The achieved accuracy indicates that the proposed approach is highly reliable and applicable in fault diagnosis of industrial reciprocating machinery. Universidad Polit?cnica Salesiana http://connection.ebscohost.com/c/articles/109000172/multi-layer-neural-network-deep-belief-network-gearbox-fault-diagnosis 2016-11-09T16:16:24Z 2016-11-09T16:16:24Z 2015 article Chen, Zhiqiang; Li, Chuan; S?nchez, Ren?-Vinicio. (2015). Multi-layer neural network with deep belief network for gearbox fault diagnosis. Journal of Vibroengineering. Aug2015, Vol. 17 Issue 5, p2379 1392-8716 http://repositorio.educacionsuperior.gob.ec/handle/28000/2982 eng restrictedAccess p. 2379 |
institution |
SENESCYT |
collection |
Repositorio SENESCYT |
biblioteca |
Biblioteca Senescyt |
language |
eng |
format |
Artículos |
topic |
MULTI-LAYER NEURAL NETWORK BELIEF NETWORK GEARBOX |
spellingShingle |
MULTI-LAYER NEURAL NETWORK BELIEF NETWORK GEARBOX Li, Chuan Multi-layer neural network with deep belief network for gearbox fault diagnosis |
description |
Identifying gearbox damage categories, especially for early faults and combined faults, is a challenging task in gearbox fault diagnosis. This paper presents multiple classifiers based on multi-layer neural networks (MLNN) to implement vibration signals for fault diagnosis in gearbox. A MLNN-based learning architecture using deep belief network (MLNNDBN) is proposed for gearbox fault diagnosis. Training process of the proposed learning architecture includes two stages: A deep belief network is constructed firstly, and then is trained; after a certain amount of epochs, the weights of deep belief network are used to initialize the weights of the constructed MLNN; at last, the trained MLNN is used as classifiers to classify gearbox faults. Multidimensional feature sets including time-domain, frequency-domain features are extracted to reveal gear health conditions. Experiments with different combined faults were conducted, and the vibration signals were captured under different loads and motor speeds. To confirm the superiority of MLNNDBN in fault classification, its performance is compared with other MLNN-based methods with different fine-tuning schemes and relevant vector machine. The achieved accuracy indicates that the proposed approach is highly reliable and applicable in fault diagnosis of industrial reciprocating machinery. |
author |
Li, Chuan |
author_facet |
Li, Chuan |
author_sort |
Li, Chuan |
title |
Multi-layer neural network with deep belief network for gearbox fault diagnosis |
title_short |
Multi-layer neural network with deep belief network for gearbox fault diagnosis |
title_full |
Multi-layer neural network with deep belief network for gearbox fault diagnosis |
title_fullStr |
Multi-layer neural network with deep belief network for gearbox fault diagnosis |
title_full_unstemmed |
Multi-layer neural network with deep belief network for gearbox fault diagnosis |
title_sort |
multi-layer neural network with deep belief network for gearbox fault diagnosis |
publishDate |
2016 |
url |
http://repositorio.educacionsuperior.gob.ec/handle/28000/2982 |
_version_ |
1634995098090471424 |
score |
11,871979 |