Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings

Traditional feature extraction and selection is a labor-intensive process requiring expert knowledge of the relevant features pertinent to the system. This knowledge is sometimes a luxury and could introduce added uncertainty and bias to the results. To address this problem a deep learning enabled f...

Full description

Saved in:
Bibliographic Details
Main Authors: David Verstraete, Andrés Ferrada, Enrique López Droguett, Viviana Meruane, Mohammad Modarres
Format: Article
Language:English
Published: Wiley 2017-01-01
Series:Shock and Vibration
Online Access:http://dx.doi.org/10.1155/2017/5067651
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849467882609573888
author David Verstraete
Andrés Ferrada
Enrique López Droguett
Viviana Meruane
Mohammad Modarres
author_facet David Verstraete
Andrés Ferrada
Enrique López Droguett
Viviana Meruane
Mohammad Modarres
author_sort David Verstraete
collection DOAJ
description Traditional feature extraction and selection is a labor-intensive process requiring expert knowledge of the relevant features pertinent to the system. This knowledge is sometimes a luxury and could introduce added uncertainty and bias to the results. To address this problem a deep learning enabled featureless methodology is proposed to automatically learn the features of the data. Time-frequency representations of the raw data are used to generate image representations of the raw signal, which are then fed into a deep convolutional neural network (CNN) architecture for classification and fault diagnosis. This methodology was applied to two public data sets of rolling element bearing vibration signals. Three time-frequency analysis methods (short-time Fourier transform, wavelet transform, and Hilbert-Huang transform) were explored for their representation effectiveness. The proposed CNN architecture achieves better results with less learnable parameters than similar architectures used for fault detection, including cases with experimental noise.
format Article
id doaj-art-e6a1f5a2d1674f71abdce3f4c9af7413
institution Kabale University
issn 1070-9622
1875-9203
language English
publishDate 2017-01-01
publisher Wiley
record_format Article
series Shock and Vibration
spelling doaj-art-e6a1f5a2d1674f71abdce3f4c9af74132025-08-20T03:26:00ZengWileyShock and Vibration1070-96221875-92032017-01-01201710.1155/2017/50676515067651Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element BearingsDavid Verstraete0Andrés Ferrada1Enrique López Droguett2Viviana Meruane3Mohammad Modarres4Department of Mechanical Engineering, University of Maryland, College Park, MD, USAComputer Science Department, University of Chile, Santiago, ChileDepartment of Mechanical Engineering, University of Maryland, College Park, MD, USAMechanical Engineering Department, University of Chile, Santiago, ChileDepartment of Mechanical Engineering, University of Maryland, College Park, MD, USATraditional feature extraction and selection is a labor-intensive process requiring expert knowledge of the relevant features pertinent to the system. This knowledge is sometimes a luxury and could introduce added uncertainty and bias to the results. To address this problem a deep learning enabled featureless methodology is proposed to automatically learn the features of the data. Time-frequency representations of the raw data are used to generate image representations of the raw signal, which are then fed into a deep convolutional neural network (CNN) architecture for classification and fault diagnosis. This methodology was applied to two public data sets of rolling element bearing vibration signals. Three time-frequency analysis methods (short-time Fourier transform, wavelet transform, and Hilbert-Huang transform) were explored for their representation effectiveness. The proposed CNN architecture achieves better results with less learnable parameters than similar architectures used for fault detection, including cases with experimental noise.http://dx.doi.org/10.1155/2017/5067651
spellingShingle David Verstraete
Andrés Ferrada
Enrique López Droguett
Viviana Meruane
Mohammad Modarres
Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings
Shock and Vibration
title Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings
title_full Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings
title_fullStr Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings
title_full_unstemmed Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings
title_short Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings
title_sort deep learning enabled fault diagnosis using time frequency image analysis of rolling element bearings
url http://dx.doi.org/10.1155/2017/5067651
work_keys_str_mv AT davidverstraete deeplearningenabledfaultdiagnosisusingtimefrequencyimageanalysisofrollingelementbearings
AT andresferrada deeplearningenabledfaultdiagnosisusingtimefrequencyimageanalysisofrollingelementbearings
AT enriquelopezdroguett deeplearningenabledfaultdiagnosisusingtimefrequencyimageanalysisofrollingelementbearings
AT vivianameruane deeplearningenabledfaultdiagnosisusingtimefrequencyimageanalysisofrollingelementbearings
AT mohammadmodarres deeplearningenabledfaultdiagnosisusingtimefrequencyimageanalysisofrollingelementbearings