A novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network

Youngji Yoo, Jun-Geol Baek

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time-frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time-frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time-frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset.

Original languageEnglish
Article number1102
JournalApplied Sciences (Switzerland)
Volume8
Issue number7
DOIs
Publication statusPublished - 2018 Jul 8

Fingerprint

Bearings (structural)
wavelet analysis
Wavelet transforms
health
Health
Neural networks
life (durability)
predictions
vibration
time signals
labor
Power spectrum
pattern recognition
learning
power spectra
Feature extraction
Fusion reactions
fusion
Personnel
Monitoring

Keywords

  • Bearings
  • Continuous wavelet transform
  • Convolutional neural network
  • Health indicator
  • Prognostics and health management
  • Remaining useful lifetime

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

@article{9cedf4651bd6436fa8d195e6b11ab6b7,
title = "A novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network",
abstract = "In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time-frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time-frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time-frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset.",
keywords = "Bearings, Continuous wavelet transform, Convolutional neural network, Health indicator, Prognostics and health management, Remaining useful lifetime",
author = "Youngji Yoo and Jun-Geol Baek",
year = "2018",
month = "7",
day = "8",
doi = "10.3390/app8071102",
language = "English",
volume = "8",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "7",

}

TY - JOUR

T1 - A novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network

AU - Yoo, Youngji

AU - Baek, Jun-Geol

PY - 2018/7/8

Y1 - 2018/7/8

N2 - In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time-frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time-frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time-frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset.

AB - In data-driven methods for prognostics, the remaining useful lifetime (RUL) is predicted based on the health indicator (HI). The HI detects the condition of equipment or components by monitoring sensor data such as vibration signals. To construct the HI, multiple features are extracted from signals using time domain, frequency domain, and time-frequency domain analyses, and which are then fused. However, the process of selecting and fusing features for the HI is very complex and labor-intensive. We propose a novel time-frequency image feature to construct HI and predict the RUL. To convert the one-dimensional vibration signals to a two-dimensional (2-D) image, the continuous wavelet transform (CWT) extracts the time-frequency image features, i.e., the wavelet power spectrum. Then, the obtained image features are fed into a 2-D convolutional neural network (CNN) to construct the HI. The estimated HI from the proposed model is used for the RUL prediction. The accuracy of the RUL prediction is improved by using the image features. The proposed method compresses the complex process including feature extraction, selection, and fusion into a single algorithm by adopting a deep learning approach. The proposed method is validated using a bearing dataset provided by PRONOSTIA. The results demonstrate that the proposed method is superior to related studies using the same dataset.

KW - Bearings

KW - Continuous wavelet transform

KW - Convolutional neural network

KW - Health indicator

KW - Prognostics and health management

KW - Remaining useful lifetime

UR - http://www.scopus.com/inward/record.url?scp=85049617363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049617363&partnerID=8YFLogxK

U2 - 10.3390/app8071102

DO - 10.3390/app8071102

M3 - Article

VL - 8

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 7

M1 - 1102

ER -