Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input

Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input

Periodic vibration signals captured by the accelerometers carry rich information for bearing fault diagnosis. Existing methods mostly rely on hand-crafted time-consuming preprocessing of data to acquire suitable features. In this paper, we use an easy and effective method to transform the 1-D tempor...

Full description

Bibliographic Details
Main Authors: Zhang Wei, Peng Gaoliang, Li Chuanhao
Format: Article
Language:English
Published: EDP Sciences 2017-01-01
Series:MATEC Web of Conferences
Online Access:https://doi.org/10.1051/matecconf/20179513001
id doaj-28290c1df5af49659723136d7057ece4
record_format Article
spelling doaj-28290c1df5af49659723136d7057ece42021-02-02T08:15:09ZengEDP SciencesMATEC Web of Conferences2261-236X2017-01-01951300110.1051/matecconf/20179513001matecconf_icmme2017_13001Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as InputZhang WeiPeng GaoliangLi ChuanhaoPeriodic vibration signals captured by the accelerometers carry rich information for bearing fault diagnosis. Existing methods mostly rely on hand-crafted time-consuming preprocessing of data to acquire suitable features. In this paper, we use an easy and effective method to transform the 1-D temporal vibration signal into a 2-D image. With the signal image, convolutional Neural Network (CNN) is used to train the raw vibration data. As powerful feature extractor and classifier for image recognition, CNN can learn to acquire features most suitable for the classification task by being trained. With the image format of vibration signals, the neuron in fully-connected layer of CNN can see farther and capture the periodic feature of signals. According to the results of the experiments, when fed in enough training samples, the proposed method outperforms other common methods. The proposed method can also be applied to solve intelligent diagnosis problems of other machine systems.https://doi.org/10.1051/matecconf/20179513001
collection DOAJ
language English
format Article
sources DOAJ
author Zhang Wei
Peng Gaoliang
Li Chuanhao
spellingShingle Zhang Wei
Peng Gaoliang
Li Chuanhao
Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input
MATEC Web of Conferences
author_facet Zhang Wei
Peng Gaoliang
Li Chuanhao
author_sort Zhang Wei
title Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input
title_short Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input
title_full Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input
title_fullStr Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input
title_full_unstemmed Bearings Fault Diagnosis Based on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input
title_sort bearings fault diagnosis based on convolutional neural networks with 2-d representation of vibration signals as input
publisher EDP Sciences
series MATEC Web of Conferences
issn 2261-236X
publishDate 2017-01-01
description Periodic vibration signals captured by the accelerometers carry rich information for bearing fault diagnosis. Existing methods mostly rely on hand-crafted time-consuming preprocessing of data to acquire suitable features. In this paper, we use an easy and effective method to transform the 1-D temporal vibration signal into a 2-D image. With the signal image, convolutional Neural Network (CNN) is used to train the raw vibration data. As powerful feature extractor and classifier for image recognition, CNN can learn to acquire features most suitable for the classification task by being trained. With the image format of vibration signals, the neuron in fully-connected layer of CNN can see farther and capture the periodic feature of signals. According to the results of the experiments, when fed in enough training samples, the proposed method outperforms other common methods. The proposed method can also be applied to solve intelligent diagnosis problems of other machine systems.
url https://doi.org/10.1051/matecconf/20179513001
work_keys_str_mv AT zhangwei bearingsfaultdiagnosisbasedonconvolutionalneuralnetworkswith2drepresentationofvibrationsignalsasinput
AT penggaoliang bearingsfaultdiagnosisbasedonconvolutionalneuralnetworkswith2drepresentationofvibrationsignalsasinput
AT lichuanhao bearingsfaultdiagnosisbasedonconvolutionalneuralnetworkswith2drepresentationofvibrationsignalsasinput
_version_ 1724297557771812864

Similar Items