Cover Image

Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory

Drill string failure is a prevalent and costly problem to the oil and gas industry. This paper proposes a method for remaining useful life prediction of drill string components subjected to fatigue under combined loadings, namely axial stress, bending moment, and torsion. To accomplish this, fuzzy s...

Full description

Saved in:
Bibliographic Details
Main Authors: Lemma, T.A., Nanji, P., Gebremariam, M.A., Ahsan, S.
Format: Article
Published: Trans Tech Publications Ltd 2019
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85064378344&doi=10.4028%2fwww.scientific.net%2fKEM.796.145&partnerID=40&md5=b52a4a0ad3fa21f45d4e897c16706f42
http://eprints.utp.edu.my/23580/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.23580
record_format eprints
spelling my.utp.eprints.235802021-08-19T07:56:20Z Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory Lemma, T.A. Nanji, P. Gebremariam, M.A. Ahsan, S. Drill string failure is a prevalent and costly problem to the oil and gas industry. This paper proposes a method for remaining useful life prediction of drill string components subjected to fatigue under combined loadings, namely axial stress, bending moment, and torsion. To accomplish this, fuzzy systems are used to model the dimensionless stress intensity factor, of different API graded drill pipes. Based on the gathered database of the dimensionless stress intensity factor for various crack types, the parameter is numerically estimated using Adaptive Neuro-Fuzzy Inference System (ANFIS) in MATLAB. The fuzzy model is then incorporated into the available crack growth models (Paris Law & Walker's Law) to quantitatively evaluate the number of cycles as the crack propagates from its initial size to its critical size. The nonlinear crack propagation model is solved by Euler's Method. Finally, a parametric study is performed in order to identify the influence of load magnitudes, the variation of loadings, crack shape, and geometrical parameters on the fatigue life. The ANFIS model developed has a mean square error (MSE) of 8.3e-4, root mean square error (RMSE) of 0.0288 and R-squared error of 0.9807, thus indicating the model is highly reliable. The increase in the magnitude of stress, mean stress ratio (R) and environmental constants reduces the number of cycles to failure, thus indicating shorter RUL. © 2019 Trans Tech Publications, Switzerland Trans Tech Publications Ltd 2019 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85064378344&doi=10.4028%2fwww.scientific.net%2fKEM.796.145&partnerID=40&md5=b52a4a0ad3fa21f45d4e897c16706f42 Lemma, T.A. and Nanji, P. and Gebremariam, M.A. and Ahsan, S. (2019) Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory. Key Engineering Materials, 796 . pp. 145-154. http://eprints.utp.edu.my/23580/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Drill string failure is a prevalent and costly problem to the oil and gas industry. This paper proposes a method for remaining useful life prediction of drill string components subjected to fatigue under combined loadings, namely axial stress, bending moment, and torsion. To accomplish this, fuzzy systems are used to model the dimensionless stress intensity factor, of different API graded drill pipes. Based on the gathered database of the dimensionless stress intensity factor for various crack types, the parameter is numerically estimated using Adaptive Neuro-Fuzzy Inference System (ANFIS) in MATLAB. The fuzzy model is then incorporated into the available crack growth models (Paris Law & Walker's Law) to quantitatively evaluate the number of cycles as the crack propagates from its initial size to its critical size. The nonlinear crack propagation model is solved by Euler's Method. Finally, a parametric study is performed in order to identify the influence of load magnitudes, the variation of loadings, crack shape, and geometrical parameters on the fatigue life. The ANFIS model developed has a mean square error (MSE) of 8.3e-4, root mean square error (RMSE) of 0.0288 and R-squared error of 0.9807, thus indicating the model is highly reliable. The increase in the magnitude of stress, mean stress ratio (R) and environmental constants reduces the number of cycles to failure, thus indicating shorter RUL. © 2019 Trans Tech Publications, Switzerland
format Article
author Lemma, T.A.
Nanji, P.
Gebremariam, M.A.
Ahsan, S.
spellingShingle Lemma, T.A.
Nanji, P.
Gebremariam, M.A.
Ahsan, S.
Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory
author_facet Lemma, T.A.
Nanji, P.
Gebremariam, M.A.
Ahsan, S.
author_sort Lemma, T.A.
title Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory
title_short Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory
title_full Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory
title_fullStr Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory
title_full_unstemmed Remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory
title_sort remaining useful life prediction of drill string using fuzzy systems and cumulative damage theory
publisher Trans Tech Publications Ltd
publishDate 2019
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85064378344&doi=10.4028%2fwww.scientific.net%2fKEM.796.145&partnerID=40&md5=b52a4a0ad3fa21f45d4e897c16706f42
http://eprints.utp.edu.my/23580/
_version_ 1738656492226084864
score 13.211869

Similar Items