Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN

Intelligent diagnosis applies deep learning algorithms to mechanical fault diagnosis, which can classify the fault forms of machines or parts efficiently. At present, the intelligent diagnosis of rolling bearings mostly adopts a single-sensor signal, and multisensor information can provide more comp...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yulin Jin, Changzheng Chen, Siyu Zhao
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Technology (General) T1-995
Acceso en línea:	https://doaj.org/article/f69df71339634749b6ca32d123f45ba3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f69df71339634749b6ca32d123f45ba3
record_format	dspace
spelling	oai:doaj.org-article:f69df71339634749b6ca32d123f45ba32021-11-22T01:11:19ZMultisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN1687-726810.1155/2021/2251530https://doaj.org/article/f69df71339634749b6ca32d123f45ba32021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/2251530https://doaj.org/toc/1687-7268Intelligent diagnosis applies deep learning algorithms to mechanical fault diagnosis, which can classify the fault forms of machines or parts efficiently. At present, the intelligent diagnosis of rolling bearings mostly adopts a single-sensor signal, and multisensor information can provide more comprehensive fault features for the deep learning model to improve the generalization ability. In order to apply multisensor information more effectively, this paper proposes a multiscale convolutional neural network model based on global average pooling. The diagnostic model introduces a multiscale convolution kernel in the feature extraction process, which improves the robustness of the model. Meanwhile, its parallel structure also makes up for the shortcomings of the multichannel input fusion method. In the multiscale fusion process, the global average pooling method is used to replace the way to reshape the feature maps into a one-dimensional feature vector in the traditional convolutional neural network, which effectively retains the spatial structure of the feature maps. The model proposed in this paper has been verified by the bearing fault data collected by the experimental platform. The experimental results show that the algorithm proposed in this paper can fuse multisensor data effectively. Compared with other data fusion algorithms, the multiscale convolutional neural network model based on global average pooling has shorter training epochs and better fault diagnosis results.Yulin JinChangzheng ChenSiyu ZhaoHindawi LimitedarticleTechnology (General)T1-995ENJournal of Sensors, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology (General) T1-995
spellingShingle	Technology (General) T1-995 Yulin Jin Changzheng Chen Siyu Zhao Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN
description	Intelligent diagnosis applies deep learning algorithms to mechanical fault diagnosis, which can classify the fault forms of machines or parts efficiently. At present, the intelligent diagnosis of rolling bearings mostly adopts a single-sensor signal, and multisensor information can provide more comprehensive fault features for the deep learning model to improve the generalization ability. In order to apply multisensor information more effectively, this paper proposes a multiscale convolutional neural network model based on global average pooling. The diagnostic model introduces a multiscale convolution kernel in the feature extraction process, which improves the robustness of the model. Meanwhile, its parallel structure also makes up for the shortcomings of the multichannel input fusion method. In the multiscale fusion process, the global average pooling method is used to replace the way to reshape the feature maps into a one-dimensional feature vector in the traditional convolutional neural network, which effectively retains the spatial structure of the feature maps. The model proposed in this paper has been verified by the bearing fault data collected by the experimental platform. The experimental results show that the algorithm proposed in this paper can fuse multisensor data effectively. Compared with other data fusion algorithms, the multiscale convolutional neural network model based on global average pooling has shorter training epochs and better fault diagnosis results.
format	article
author	Yulin Jin Changzheng Chen Siyu Zhao
author_facet	Yulin Jin Changzheng Chen Siyu Zhao
author_sort	Yulin Jin
title	Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN
title_short	Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN
title_full	Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN
title_fullStr	Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN
title_full_unstemmed	Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN
title_sort	multisource data fusion diagnosis method of rolling bearings based on improved multiscale cnn
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/f69df71339634749b6ca32d123f45ba3
work_keys_str_mv	AT yulinjin multisourcedatafusiondiagnosismethodofrollingbearingsbasedonimprovedmultiscalecnn AT changzhengchen multisourcedatafusiondiagnosismethodofrollingbearingsbasedonimprovedmultiscalecnn AT siyuzhao multisourcedatafusiondiagnosismethodofrollingbearingsbasedonimprovedmultiscalecnn
_version_	1718418316673941504

Multisource Data Fusion Diagnosis Method of Rolling Bearings Based on Improved Multiscale CNN

Ejemplares similares