Fatigue damage monitoring using un-supervised clustering method of acoustic emission signal on SAE 1045 steel

M. Mohammad, A. Tajuddin, Shahrum Abdullah, N. Jamaluddin, B. I.S. Murat

Research output: Contribution to journalArticle

Abstract

This paper described the capability of acoustic emission (AE) technique in monitoring the fatigue damage level using unsupervised clustering technique. As fatigue damage is being a major contributing factor to component failure, it is essential to evaluate the level of damage caused by fatigue load in order to prevent the catastrophic failure of the structure. It is a concern in this study to differentiate the AE signals according to the fatigue damage stages by implementing an unsupervised clustering technique. In this study, the AE signals were collected on specimens made of medium carbon steel SAE 1045 that underwent the axial fatigue testing. The test was run at three loading values of 600, 640 and 680 MPa. The pattern behaviour of AE signals was recorded using a piezoelectric sensor in a form of time domain history signal. Later, the AE signals collected were analysed and clustered using K-means technique. Five clusters of K1, K2, K3, K4, and K5 have been found for the specimens subjected to stress value of 600-680 MPa. The optimum numbers of K clusters were determined using the smallest objective function in their group which ranges between 2.6 to 3.0. This pilot investigation shows that it may be useful to estimate the remaining life for a component before it fails.

Original languageEnglish
Pages (from-to)3584-3598
Number of pages15
JournalInternational Journal of Automotive and Mechanical Engineering
Volume13
Issue number3
DOIs
Publication statusPublished - 2016

Fingerprint

Fatigue damage
Acoustic emissions
Steel
Monitoring
Fatigue testing
Carbon steel
Fatigue of materials
Sensors

Keywords

  • AE
  • Clustering
  • Fatigue
  • K-means and medium carbon steel

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering

Cite this

Fatigue damage monitoring using un-supervised clustering method of acoustic emission signal on SAE 1045 steel. / Mohammad, M.; Tajuddin, A.; Abdullah, Shahrum; Jamaluddin, N.; Murat, B. I.S.

In: International Journal of Automotive and Mechanical Engineering, Vol. 13, No. 3, 2016, p. 3584-3598.

Research output: Contribution to journalArticle

@article{f4380cbc10224083b095d59e97a79a7b,
title = "Fatigue damage monitoring using un-supervised clustering method of acoustic emission signal on SAE 1045 steel",
abstract = "This paper described the capability of acoustic emission (AE) technique in monitoring the fatigue damage level using unsupervised clustering technique. As fatigue damage is being a major contributing factor to component failure, it is essential to evaluate the level of damage caused by fatigue load in order to prevent the catastrophic failure of the structure. It is a concern in this study to differentiate the AE signals according to the fatigue damage stages by implementing an unsupervised clustering technique. In this study, the AE signals were collected on specimens made of medium carbon steel SAE 1045 that underwent the axial fatigue testing. The test was run at three loading values of 600, 640 and 680 MPa. The pattern behaviour of AE signals was recorded using a piezoelectric sensor in a form of time domain history signal. Later, the AE signals collected were analysed and clustered using K-means technique. Five clusters of K1, K2, K3, K4, and K5 have been found for the specimens subjected to stress value of 600-680 MPa. The optimum numbers of K clusters were determined using the smallest objective function in their group which ranges between 2.6 to 3.0. This pilot investigation shows that it may be useful to estimate the remaining life for a component before it fails.",
keywords = "AE, Clustering, Fatigue, K-means and medium carbon steel",
author = "M. Mohammad and A. Tajuddin and Shahrum Abdullah and N. Jamaluddin and Murat, {B. I.S.}",
year = "2016",
doi = "10.15282/ijame.13.3.2016.5.0295",
language = "English",
volume = "13",
pages = "3584--3598",
journal = "International Journal of Automotive and Mechanical Engineering",
issn = "2229-8649",
publisher = "The Automotive Engineering Centre (AEC), Universiti Malaysia Pahang",
number = "3",

}

TY - JOUR

T1 - Fatigue damage monitoring using un-supervised clustering method of acoustic emission signal on SAE 1045 steel

AU - Mohammad, M.

AU - Tajuddin, A.

AU - Abdullah, Shahrum

AU - Jamaluddin, N.

AU - Murat, B. I.S.

PY - 2016

Y1 - 2016

N2 - This paper described the capability of acoustic emission (AE) technique in monitoring the fatigue damage level using unsupervised clustering technique. As fatigue damage is being a major contributing factor to component failure, it is essential to evaluate the level of damage caused by fatigue load in order to prevent the catastrophic failure of the structure. It is a concern in this study to differentiate the AE signals according to the fatigue damage stages by implementing an unsupervised clustering technique. In this study, the AE signals were collected on specimens made of medium carbon steel SAE 1045 that underwent the axial fatigue testing. The test was run at three loading values of 600, 640 and 680 MPa. The pattern behaviour of AE signals was recorded using a piezoelectric sensor in a form of time domain history signal. Later, the AE signals collected were analysed and clustered using K-means technique. Five clusters of K1, K2, K3, K4, and K5 have been found for the specimens subjected to stress value of 600-680 MPa. The optimum numbers of K clusters were determined using the smallest objective function in their group which ranges between 2.6 to 3.0. This pilot investigation shows that it may be useful to estimate the remaining life for a component before it fails.

AB - This paper described the capability of acoustic emission (AE) technique in monitoring the fatigue damage level using unsupervised clustering technique. As fatigue damage is being a major contributing factor to component failure, it is essential to evaluate the level of damage caused by fatigue load in order to prevent the catastrophic failure of the structure. It is a concern in this study to differentiate the AE signals according to the fatigue damage stages by implementing an unsupervised clustering technique. In this study, the AE signals were collected on specimens made of medium carbon steel SAE 1045 that underwent the axial fatigue testing. The test was run at three loading values of 600, 640 and 680 MPa. The pattern behaviour of AE signals was recorded using a piezoelectric sensor in a form of time domain history signal. Later, the AE signals collected were analysed and clustered using K-means technique. Five clusters of K1, K2, K3, K4, and K5 have been found for the specimens subjected to stress value of 600-680 MPa. The optimum numbers of K clusters were determined using the smallest objective function in their group which ranges between 2.6 to 3.0. This pilot investigation shows that it may be useful to estimate the remaining life for a component before it fails.

KW - AE

KW - Clustering

KW - Fatigue

KW - K-means and medium carbon steel

UR - http://www.scopus.com/inward/record.url?scp=85018714218&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018714218&partnerID=8YFLogxK

U2 - 10.15282/ijame.13.3.2016.5.0295

DO - 10.15282/ijame.13.3.2016.5.0295

M3 - Article

VL - 13

SP - 3584

EP - 3598

JO - International Journal of Automotive and Mechanical Engineering

JF - International Journal of Automotive and Mechanical Engineering

SN - 2229-8649

IS - 3

ER -