Fatigue feature clustering algorithm using the morlet wavelet

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents clustering of fatigue features resulted from the segmentation of the SAESUS time series data. The segmentation process was based on the Morlet wavelet coefficient amplitude level which produces 49 segments that each has an overall fatigue damage. Observation of the fatigue damage and the wavelet coefficient was made on each segment. In the end of the process, the segments were clustered into three clusters to identify any improvements in the data scattering for fatigue data clustering prospects. This algorithm produced a more reliable and suitable method of segment by segment analysis for fatigue strain signal segmentation. According to the analysis findings, the higher Morlet wavelet coefficient presented damaging segment, otherwise, it was undamaging segment. It indicated that the relationship between the Morlet wavelet coefficient and the fatigue damage was strong and parallel.

Original languageEnglish
Title of host publicationProceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09
Pages82-87
Number of pages6
Publication statusPublished - 2009
Event2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, 2nd WSEAS International Conference on Visualization, Imaging and Simulation, VIS '09, 2nd WSEAS International Conference on Materials Science, MATERIALS '09 - Baltimore, MD
Duration: 7 Nov 20099 Nov 2009

Other

Other2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, 2nd WSEAS International Conference on Visualization, Imaging and Simulation, VIS '09, 2nd WSEAS International Conference on Materials Science, MATERIALS '09
CityBaltimore, MD
Period7/11/099/11/09

Fingerprint

Fatigue damage
Clustering algorithms
Fatigue of materials
Time series
Scattering

Keywords

  • Clustering
  • Fatigue damage
  • Fatigue strain signal
  • Morlet wavelet coefficient
  • Segmentation

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Materials Science(all)

Cite this

Putra, T. E., Abdullah, S., & Nuawi, M. Z. (2009). Fatigue feature clustering algorithm using the morlet wavelet. In Proceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09 (pp. 82-87)

Fatigue feature clustering algorithm using the morlet wavelet. / Putra, T. E.; Abdullah, Shahrum; Nuawi, Mohd. Zaki.

Proceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09. 2009. p. 82-87.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Putra, TE, Abdullah, S & Nuawi, MZ 2009, Fatigue feature clustering algorithm using the morlet wavelet. in Proceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09. pp. 82-87, 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, 2nd WSEAS International Conference on Visualization, Imaging and Simulation, VIS '09, 2nd WSEAS International Conference on Materials Science, MATERIALS '09, Baltimore, MD, 7/11/09.
Putra TE, Abdullah S, Nuawi MZ. Fatigue feature clustering algorithm using the morlet wavelet. In Proceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09. 2009. p. 82-87
Putra, T. E. ; Abdullah, Shahrum ; Nuawi, Mohd. Zaki. / Fatigue feature clustering algorithm using the morlet wavelet. Proceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09. 2009. pp. 82-87
@inproceedings{459ea573a76941adb8cbe56bbfd0506c,
title = "Fatigue feature clustering algorithm using the morlet wavelet",
abstract = "This paper presents clustering of fatigue features resulted from the segmentation of the SAESUS time series data. The segmentation process was based on the Morlet wavelet coefficient amplitude level which produces 49 segments that each has an overall fatigue damage. Observation of the fatigue damage and the wavelet coefficient was made on each segment. In the end of the process, the segments were clustered into three clusters to identify any improvements in the data scattering for fatigue data clustering prospects. This algorithm produced a more reliable and suitable method of segment by segment analysis for fatigue strain signal segmentation. According to the analysis findings, the higher Morlet wavelet coefficient presented damaging segment, otherwise, it was undamaging segment. It indicated that the relationship between the Morlet wavelet coefficient and the fatigue damage was strong and parallel.",
keywords = "Clustering, Fatigue damage, Fatigue strain signal, Morlet wavelet coefficient, Segmentation",
author = "Putra, {T. E.} and Shahrum Abdullah and Nuawi, {Mohd. Zaki}",
year = "2009",
language = "English",
isbn = "9789604741359",
pages = "82--87",
booktitle = "Proceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09",

}

TY - GEN

T1 - Fatigue feature clustering algorithm using the morlet wavelet

AU - Putra, T. E.

AU - Abdullah, Shahrum

AU - Nuawi, Mohd. Zaki

PY - 2009

Y1 - 2009

N2 - This paper presents clustering of fatigue features resulted from the segmentation of the SAESUS time series data. The segmentation process was based on the Morlet wavelet coefficient amplitude level which produces 49 segments that each has an overall fatigue damage. Observation of the fatigue damage and the wavelet coefficient was made on each segment. In the end of the process, the segments were clustered into three clusters to identify any improvements in the data scattering for fatigue data clustering prospects. This algorithm produced a more reliable and suitable method of segment by segment analysis for fatigue strain signal segmentation. According to the analysis findings, the higher Morlet wavelet coefficient presented damaging segment, otherwise, it was undamaging segment. It indicated that the relationship between the Morlet wavelet coefficient and the fatigue damage was strong and parallel.

AB - This paper presents clustering of fatigue features resulted from the segmentation of the SAESUS time series data. The segmentation process was based on the Morlet wavelet coefficient amplitude level which produces 49 segments that each has an overall fatigue damage. Observation of the fatigue damage and the wavelet coefficient was made on each segment. In the end of the process, the segments were clustered into three clusters to identify any improvements in the data scattering for fatigue data clustering prospects. This algorithm produced a more reliable and suitable method of segment by segment analysis for fatigue strain signal segmentation. According to the analysis findings, the higher Morlet wavelet coefficient presented damaging segment, otherwise, it was undamaging segment. It indicated that the relationship between the Morlet wavelet coefficient and the fatigue damage was strong and parallel.

KW - Clustering

KW - Fatigue damage

KW - Fatigue strain signal

KW - Morlet wavelet coefficient

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=78149317267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149317267&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789604741359

SP - 82

EP - 87

BT - Proceedings of the 2nd WSEAS International Conference on Sensors and Signals, SENSIG '09, Visualization, Imaging and Simulation, VIS '09, Materials Science, MATERIALS '09

ER -