Evaluation of effectiveness of wavelet based denoising schemes using ANN and SVM for bearing condition classification

G. S. Vijay, H. S. Kumar, Pai P. Srinivasa, N. S. Sriram, Raj B.K.N. Rao

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

The wavelet based denoising has proven its ability to denoise the bearing vibration signals by improving the signal-to-noise ratio (SNR) and reducing the root-mean-square error (RMSE). In this paper seven wavelet based denoising schemes have been evaluated based on the performance of the Artificial Neural Network (ANN) and the Support Vector Machine (SVM), for the bearing condition classification. The work consists of two parts, the first part in which a synthetic signal simulating the defective bearing vibration signal with Gaussian noise was subjected to these denoising schemes. The best scheme based on the SNR and the RMSE was identified. In the second part, the vibration signals collected from a customized Rolling Element Bearing (REB) test rig for four bearing conditions were subjected to these denoising schemes. Several time and frequency domain features were extracted from the denoised signals, out of which a few sensitive features were selected using the Fisher's Criterion (FC). Extracted features were used to train and test the ANN and the SVM. The best denoising scheme identified, based on the classification performances of the ANN and the SVM, was found to be the same as the one obtained using the synthetic signal.

Original languageEnglish
Article number582453
JournalComputational Intelligence and Neuroscience
Volume2012
DOIs
Publication statusPublished - 26-12-2012

Fingerprint

Bearings (structural)
Denoising
Vibration
Support vector machines
Artificial Neural Network
Support Vector Machine
Wavelets
Vibration Signal
Signal-To-Noise Ratio
Neural networks
Evaluation
Mean square error
Signal to noise ratio
Roots
Gaussian Noise
Frequency Domain
Time Domain

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Neuroscience(all)
  • Mathematics(all)

Cite this

@article{8adac012bec44873b4c4d40c5706ccfd,
title = "Evaluation of effectiveness of wavelet based denoising schemes using ANN and SVM for bearing condition classification",
abstract = "The wavelet based denoising has proven its ability to denoise the bearing vibration signals by improving the signal-to-noise ratio (SNR) and reducing the root-mean-square error (RMSE). In this paper seven wavelet based denoising schemes have been evaluated based on the performance of the Artificial Neural Network (ANN) and the Support Vector Machine (SVM), for the bearing condition classification. The work consists of two parts, the first part in which a synthetic signal simulating the defective bearing vibration signal with Gaussian noise was subjected to these denoising schemes. The best scheme based on the SNR and the RMSE was identified. In the second part, the vibration signals collected from a customized Rolling Element Bearing (REB) test rig for four bearing conditions were subjected to these denoising schemes. Several time and frequency domain features were extracted from the denoised signals, out of which a few sensitive features were selected using the Fisher's Criterion (FC). Extracted features were used to train and test the ANN and the SVM. The best denoising scheme identified, based on the classification performances of the ANN and the SVM, was found to be the same as the one obtained using the synthetic signal.",
author = "Vijay, {G. S.} and Kumar, {H. S.} and Srinivasa, {Pai P.} and Sriram, {N. S.} and Rao, {Raj B.K.N.}",
year = "2012",
month = "12",
day = "26",
doi = "10.1155/2012/582453",
language = "English",
volume = "2012",
journal = "Computational Intelligence and Neuroscience",
issn = "1687-5265",
publisher = "Hindawi Publishing Corporation",

}

Evaluation of effectiveness of wavelet based denoising schemes using ANN and SVM for bearing condition classification. / Vijay, G. S.; Kumar, H. S.; Srinivasa, Pai P.; Sriram, N. S.; Rao, Raj B.K.N.

In: Computational Intelligence and Neuroscience, Vol. 2012, 582453, 26.12.2012.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluation of effectiveness of wavelet based denoising schemes using ANN and SVM for bearing condition classification

AU - Vijay, G. S.

AU - Kumar, H. S.

AU - Srinivasa, Pai P.

AU - Sriram, N. S.

AU - Rao, Raj B.K.N.

PY - 2012/12/26

Y1 - 2012/12/26

N2 - The wavelet based denoising has proven its ability to denoise the bearing vibration signals by improving the signal-to-noise ratio (SNR) and reducing the root-mean-square error (RMSE). In this paper seven wavelet based denoising schemes have been evaluated based on the performance of the Artificial Neural Network (ANN) and the Support Vector Machine (SVM), for the bearing condition classification. The work consists of two parts, the first part in which a synthetic signal simulating the defective bearing vibration signal with Gaussian noise was subjected to these denoising schemes. The best scheme based on the SNR and the RMSE was identified. In the second part, the vibration signals collected from a customized Rolling Element Bearing (REB) test rig for four bearing conditions were subjected to these denoising schemes. Several time and frequency domain features were extracted from the denoised signals, out of which a few sensitive features were selected using the Fisher's Criterion (FC). Extracted features were used to train and test the ANN and the SVM. The best denoising scheme identified, based on the classification performances of the ANN and the SVM, was found to be the same as the one obtained using the synthetic signal.

AB - The wavelet based denoising has proven its ability to denoise the bearing vibration signals by improving the signal-to-noise ratio (SNR) and reducing the root-mean-square error (RMSE). In this paper seven wavelet based denoising schemes have been evaluated based on the performance of the Artificial Neural Network (ANN) and the Support Vector Machine (SVM), for the bearing condition classification. The work consists of two parts, the first part in which a synthetic signal simulating the defective bearing vibration signal with Gaussian noise was subjected to these denoising schemes. The best scheme based on the SNR and the RMSE was identified. In the second part, the vibration signals collected from a customized Rolling Element Bearing (REB) test rig for four bearing conditions were subjected to these denoising schemes. Several time and frequency domain features were extracted from the denoised signals, out of which a few sensitive features were selected using the Fisher's Criterion (FC). Extracted features were used to train and test the ANN and the SVM. The best denoising scheme identified, based on the classification performances of the ANN and the SVM, was found to be the same as the one obtained using the synthetic signal.

UR - http://www.scopus.com/inward/record.url?scp=84871391949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871391949&partnerID=8YFLogxK

U2 - 10.1155/2012/582453

DO - 10.1155/2012/582453

M3 - Article

C2 - 23213323

AN - SCOPUS:84871391949

VL - 2012

JO - Computational Intelligence and Neuroscience

JF - Computational Intelligence and Neuroscience

SN - 1687-5265

M1 - 582453

ER -