Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique

Teuku Edisah Putra, Shahrum Abdullah, Dieter Schramm, Mohd. Zaki Nuawi, Tobias Bruckmann

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

Abstract

The study presents the development of a wavelet-based segmentation algorithm for fatigue life assessment. Strain data was extracted using the Morlet family. The extraction process identified damaging segments, and it was able to shorten the original signal by 74.3%, with less than 10% difference with statistical parameters. The extraction algorithm was able to retain at least 97.9% of fatigue damage. The damaging segments drawn were clustered using the k-means method to provide three groups of segments, i.e., lower, moderate, and higher groups representing statistical values. The approach was suggested as an alternative method for evaluating and clustering fatigue strain signals.

Original languageEnglish
Title of host publicationAdvanced Materials Research
PublisherTrans Tech Publications
Pages1717-1722
Number of pages6
Volume891-892
ISBN (Print)9783038350088
DOIs
Publication statusPublished - 2014
Event11th International Fatigue Congress, FATIGUE 2014 - Melbourne, VIC
Duration: 2 Mar 20147 Mar 2014

Publication series

NameAdvanced Materials Research
Volume891-892
ISSN (Print)10226680

Other

Other11th International Fatigue Congress, FATIGUE 2014
CityMelbourne, VIC
Period2/3/147/3/14

Fingerprint

Feature extraction
Fatigue of materials
Fatigue damage

Keywords

  • Data clustering
  • Fatigue data editing
  • K-means
  • Statistics
  • Wavelet

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Putra, T. E., Abdullah, S., Schramm, D., Nuawi, M. Z., & Bruckmann, T. (2014). Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique. In Advanced Materials Research (Vol. 891-892, pp. 1717-1722). (Advanced Materials Research; Vol. 891-892). Trans Tech Publications. https://doi.org/10.4028/www.scientific.net/AMR.891-892.1717

Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique. / Putra, Teuku Edisah; Abdullah, Shahrum; Schramm, Dieter; Nuawi, Mohd. Zaki; Bruckmann, Tobias.

Advanced Materials Research. Vol. 891-892 Trans Tech Publications, 2014. p. 1717-1722 (Advanced Materials Research; Vol. 891-892).

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

Putra, TE, Abdullah, S, Schramm, D, Nuawi, MZ & Bruckmann, T 2014, Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique. in Advanced Materials Research. vol. 891-892, Advanced Materials Research, vol. 891-892, Trans Tech Publications, pp. 1717-1722, 11th International Fatigue Congress, FATIGUE 2014, Melbourne, VIC, 2/3/14. https://doi.org/10.4028/www.scientific.net/AMR.891-892.1717
Putra TE, Abdullah S, Schramm D, Nuawi MZ, Bruckmann T. Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique. In Advanced Materials Research. Vol. 891-892. Trans Tech Publications. 2014. p. 1717-1722. (Advanced Materials Research). https://doi.org/10.4028/www.scientific.net/AMR.891-892.1717
Putra, Teuku Edisah ; Abdullah, Shahrum ; Schramm, Dieter ; Nuawi, Mohd. Zaki ; Bruckmann, Tobias. / Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique. Advanced Materials Research. Vol. 891-892 Trans Tech Publications, 2014. pp. 1717-1722 (Advanced Materials Research).
@inproceedings{ee5f797cf15847ce9257f2448b6fb866,
title = "Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique",
abstract = "The study presents the development of a wavelet-based segmentation algorithm for fatigue life assessment. Strain data was extracted using the Morlet family. The extraction process identified damaging segments, and it was able to shorten the original signal by 74.3{\%}, with less than 10{\%} difference with statistical parameters. The extraction algorithm was able to retain at least 97.9{\%} of fatigue damage. The damaging segments drawn were clustered using the k-means method to provide three groups of segments, i.e., lower, moderate, and higher groups representing statistical values. The approach was suggested as an alternative method for evaluating and clustering fatigue strain signals.",
keywords = "Data clustering, Fatigue data editing, K-means, Statistics, Wavelet",
author = "Putra, {Teuku Edisah} and Shahrum Abdullah and Dieter Schramm and Nuawi, {Mohd. Zaki} and Tobias Bruckmann",
year = "2014",
doi = "10.4028/www.scientific.net/AMR.891-892.1717",
language = "English",
isbn = "9783038350088",
volume = "891-892",
series = "Advanced Materials Research",
publisher = "Trans Tech Publications",
pages = "1717--1722",
booktitle = "Advanced Materials Research",

}

TY - GEN

T1 - Wavelet-based feature extraction algorithm for fatigue strain data associated with the k-means clustering technique

AU - Putra, Teuku Edisah

AU - Abdullah, Shahrum

AU - Schramm, Dieter

AU - Nuawi, Mohd. Zaki

AU - Bruckmann, Tobias

PY - 2014

Y1 - 2014

N2 - The study presents the development of a wavelet-based segmentation algorithm for fatigue life assessment. Strain data was extracted using the Morlet family. The extraction process identified damaging segments, and it was able to shorten the original signal by 74.3%, with less than 10% difference with statistical parameters. The extraction algorithm was able to retain at least 97.9% of fatigue damage. The damaging segments drawn were clustered using the k-means method to provide three groups of segments, i.e., lower, moderate, and higher groups representing statistical values. The approach was suggested as an alternative method for evaluating and clustering fatigue strain signals.

AB - The study presents the development of a wavelet-based segmentation algorithm for fatigue life assessment. Strain data was extracted using the Morlet family. The extraction process identified damaging segments, and it was able to shorten the original signal by 74.3%, with less than 10% difference with statistical parameters. The extraction algorithm was able to retain at least 97.9% of fatigue damage. The damaging segments drawn were clustered using the k-means method to provide three groups of segments, i.e., lower, moderate, and higher groups representing statistical values. The approach was suggested as an alternative method for evaluating and clustering fatigue strain signals.

KW - Data clustering

KW - Fatigue data editing

KW - K-means

KW - Statistics

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=84898850142&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898850142&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMR.891-892.1717

DO - 10.4028/www.scientific.net/AMR.891-892.1717

M3 - Conference contribution

SN - 9783038350088

VL - 891-892

T3 - Advanced Materials Research

SP - 1717

EP - 1722

BT - Advanced Materials Research

PB - Trans Tech Publications

ER -