Genetic algorithm-based fatigue data editing technique

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

Abstract

Durability testing is an essential process node in automotive component design analysis. The test associated with loading history can be accelerated if the fatigue data editing approach is considered for simplifying the given history. Even though they have been proven, unfortunately, the existing editing techniques involve complex mechanisms (e.g. abrupt detection, Fourier transformation and wavelet analysis), which are complicated in nature and which demand high computational costs. Therefore, this paper is a proposal of a simple technique that makes use of the rule-based fatigue segment classifier when deciding which parts of the history need to be removed. Rules representing the new labelling practice have been generated based on the classification data mining framework. In the context of this study, a rule set represents a group of undiscovered relationship between time domain statistical parameters and damage level. A dataset consisting of an equal length of fatigue segments trained using a multi-objective approach called the Elitist Nondominated Sorting in Genetic Algorithm (NSGA-II) for seeking several optimal sets of rules (i.e., classifiers) by maximizing predictive accuracy and comprehensibility. The number of attributes underlying the rule set is referred to for final classifier selection where the fitter solution serves as the proposed editing technique. Comparison results on strain-stress cycle properties for the edited history and the full-length version shows that the proposed technique is suitable for fatigue data editing. Moreover, it has an additional benefit that no prior requirement on the frequency or timefrequency analysis is needed, providing the damage level of fatigue segments rapidly and the discovering of linguistic knowledge as a novelty.

Original languageEnglish
Title of host publicationApplied Mechanics and Materials
PublisherTrans Tech Publications Ltd
Pages431-436
Number of pages6
Volume663
ISBN (Print)9783038352617
DOIs
Publication statusPublished - 2014
Event2nd International Conference on Recent Advances in Automotive Engineering and Mobility Research, ReCAR 2013 - Kuala Lumpur
Duration: 16 Dec 201318 Dec 2013

Publication series

NameApplied Mechanics and Materials
Volume663
ISSN (Print)16609336
ISSN (Electronic)16627482

Other

Other2nd International Conference on Recent Advances in Automotive Engineering and Mobility Research, ReCAR 2013
CityKuala Lumpur
Period16/12/1318/12/13

Fingerprint

Genetic algorithms
Fatigue of materials
Classifiers
Wavelet analysis
Sorting
Linguistics
Labeling
Data mining
Durability
Testing
Costs

Keywords

  • Fatigue data editing
  • Genetic algorithm
  • NSGA-II
  • Rule mining
  • Segmentation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Osman, M. H., Nopiah, Z. M., Mohd Nopiah, Z., Abdullah, S., Abdullah, S., & Asshaari, I. (2014). Genetic algorithm-based fatigue data editing technique. In Applied Mechanics and Materials (Vol. 663, pp. 431-436). (Applied Mechanics and Materials; Vol. 663). Trans Tech Publications Ltd. https://doi.org/10.4028/www.scientific.net/AMM.663.431

Genetic algorithm-based fatigue data editing technique. / Osman, Mohd Haniff; Nopiah, Zulkifli Mohd; Mohd Nopiah, Zulkifli; Abdullah, Shahrum; Abdullah, Shahrum; Asshaari, Izamarlina.

Applied Mechanics and Materials. Vol. 663 Trans Tech Publications Ltd, 2014. p. 431-436 (Applied Mechanics and Materials; Vol. 663).

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

Osman, MH, Nopiah, ZM, Mohd Nopiah, Z, Abdullah, S, Abdullah, S & Asshaari, I 2014, Genetic algorithm-based fatigue data editing technique. in Applied Mechanics and Materials. vol. 663, Applied Mechanics and Materials, vol. 663, Trans Tech Publications Ltd, pp. 431-436, 2nd International Conference on Recent Advances in Automotive Engineering and Mobility Research, ReCAR 2013, Kuala Lumpur, 16/12/13. https://doi.org/10.4028/www.scientific.net/AMM.663.431
Osman MH, Nopiah ZM, Mohd Nopiah Z, Abdullah S, Abdullah S, Asshaari I. Genetic algorithm-based fatigue data editing technique. In Applied Mechanics and Materials. Vol. 663. Trans Tech Publications Ltd. 2014. p. 431-436. (Applied Mechanics and Materials). https://doi.org/10.4028/www.scientific.net/AMM.663.431
Osman, Mohd Haniff ; Nopiah, Zulkifli Mohd ; Mohd Nopiah, Zulkifli ; Abdullah, Shahrum ; Abdullah, Shahrum ; Asshaari, Izamarlina. / Genetic algorithm-based fatigue data editing technique. Applied Mechanics and Materials. Vol. 663 Trans Tech Publications Ltd, 2014. pp. 431-436 (Applied Mechanics and Materials).
@inproceedings{d9a56354b326478abc36087311d4c65b,
title = "Genetic algorithm-based fatigue data editing technique",
abstract = "Durability testing is an essential process node in automotive component design analysis. The test associated with loading history can be accelerated if the fatigue data editing approach is considered for simplifying the given history. Even though they have been proven, unfortunately, the existing editing techniques involve complex mechanisms (e.g. abrupt detection, Fourier transformation and wavelet analysis), which are complicated in nature and which demand high computational costs. Therefore, this paper is a proposal of a simple technique that makes use of the rule-based fatigue segment classifier when deciding which parts of the history need to be removed. Rules representing the new labelling practice have been generated based on the classification data mining framework. In the context of this study, a rule set represents a group of undiscovered relationship between time domain statistical parameters and damage level. A dataset consisting of an equal length of fatigue segments trained using a multi-objective approach called the Elitist Nondominated Sorting in Genetic Algorithm (NSGA-II) for seeking several optimal sets of rules (i.e., classifiers) by maximizing predictive accuracy and comprehensibility. The number of attributes underlying the rule set is referred to for final classifier selection where the fitter solution serves as the proposed editing technique. Comparison results on strain-stress cycle properties for the edited history and the full-length version shows that the proposed technique is suitable for fatigue data editing. Moreover, it has an additional benefit that no prior requirement on the frequency or timefrequency analysis is needed, providing the damage level of fatigue segments rapidly and the discovering of linguistic knowledge as a novelty.",
keywords = "Fatigue data editing, Genetic algorithm, NSGA-II, Rule mining, Segmentation",
author = "Osman, {Mohd Haniff} and Nopiah, {Zulkifli Mohd} and {Mohd Nopiah}, Zulkifli and Shahrum Abdullah and Shahrum Abdullah and Izamarlina Asshaari",
year = "2014",
doi = "10.4028/www.scientific.net/AMM.663.431",
language = "English",
isbn = "9783038352617",
volume = "663",
series = "Applied Mechanics and Materials",
publisher = "Trans Tech Publications Ltd",
pages = "431--436",
booktitle = "Applied Mechanics and Materials",

}

TY - GEN

T1 - Genetic algorithm-based fatigue data editing technique

AU - Osman, Mohd Haniff

AU - Nopiah, Zulkifli Mohd

AU - Mohd Nopiah, Zulkifli

AU - Abdullah, Shahrum

AU - Abdullah, Shahrum

AU - Asshaari, Izamarlina

PY - 2014

Y1 - 2014

N2 - Durability testing is an essential process node in automotive component design analysis. The test associated with loading history can be accelerated if the fatigue data editing approach is considered for simplifying the given history. Even though they have been proven, unfortunately, the existing editing techniques involve complex mechanisms (e.g. abrupt detection, Fourier transformation and wavelet analysis), which are complicated in nature and which demand high computational costs. Therefore, this paper is a proposal of a simple technique that makes use of the rule-based fatigue segment classifier when deciding which parts of the history need to be removed. Rules representing the new labelling practice have been generated based on the classification data mining framework. In the context of this study, a rule set represents a group of undiscovered relationship between time domain statistical parameters and damage level. A dataset consisting of an equal length of fatigue segments trained using a multi-objective approach called the Elitist Nondominated Sorting in Genetic Algorithm (NSGA-II) for seeking several optimal sets of rules (i.e., classifiers) by maximizing predictive accuracy and comprehensibility. The number of attributes underlying the rule set is referred to for final classifier selection where the fitter solution serves as the proposed editing technique. Comparison results on strain-stress cycle properties for the edited history and the full-length version shows that the proposed technique is suitable for fatigue data editing. Moreover, it has an additional benefit that no prior requirement on the frequency or timefrequency analysis is needed, providing the damage level of fatigue segments rapidly and the discovering of linguistic knowledge as a novelty.

AB - Durability testing is an essential process node in automotive component design analysis. The test associated with loading history can be accelerated if the fatigue data editing approach is considered for simplifying the given history. Even though they have been proven, unfortunately, the existing editing techniques involve complex mechanisms (e.g. abrupt detection, Fourier transformation and wavelet analysis), which are complicated in nature and which demand high computational costs. Therefore, this paper is a proposal of a simple technique that makes use of the rule-based fatigue segment classifier when deciding which parts of the history need to be removed. Rules representing the new labelling practice have been generated based on the classification data mining framework. In the context of this study, a rule set represents a group of undiscovered relationship between time domain statistical parameters and damage level. A dataset consisting of an equal length of fatigue segments trained using a multi-objective approach called the Elitist Nondominated Sorting in Genetic Algorithm (NSGA-II) for seeking several optimal sets of rules (i.e., classifiers) by maximizing predictive accuracy and comprehensibility. The number of attributes underlying the rule set is referred to for final classifier selection where the fitter solution serves as the proposed editing technique. Comparison results on strain-stress cycle properties for the edited history and the full-length version shows that the proposed technique is suitable for fatigue data editing. Moreover, it has an additional benefit that no prior requirement on the frequency or timefrequency analysis is needed, providing the damage level of fatigue segments rapidly and the discovering of linguistic knowledge as a novelty.

KW - Fatigue data editing

KW - Genetic algorithm

KW - NSGA-II

KW - Rule mining

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84922022445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922022445&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMM.663.431

DO - 10.4028/www.scientific.net/AMM.663.431

M3 - Conference contribution

SN - 9783038352617

VL - 663

T3 - Applied Mechanics and Materials

SP - 431

EP - 436

BT - Applied Mechanics and Materials

PB - Trans Tech Publications Ltd

ER -