The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand
Buried pipes are extensively used for oil transportation from offshore platforms. Under unfavorable loading combinations, the pipe’s uplift resistance may be exceeded, which may result in excessive deformations and significant disruptions. This paper presents findings from a series of small-scale te...
Saved in:
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2021
|
Subjects: | |
Online Access: | http://eprints.um.edu.my/25879/1/25879.pdf http://eprints.um.edu.my/25879/ https://doi.org/10.3390/app11030908 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.um.eprints.25879 |
---|---|
record_format |
eprints |
spelling |
my.um.eprints.258792021-04-21T03:48:59Z http://eprints.um.edu.my/25879/ The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand Zeng, Jie Asteris, Panagiotis G. Mamou, Anna P. Mohammed, Ahmed Salih Golias, Emmanuil A. Armaghani, Danial Jahed Faizi, Koohyar Hasanipanah, Mahdi TA Engineering (General). Civil engineering (General) Buried pipes are extensively used for oil transportation from offshore platforms. Under unfavorable loading combinations, the pipe’s uplift resistance may be exceeded, which may result in excessive deformations and significant disruptions. This paper presents findings from a series of small-scale tests performed on pipes buried in geogrid-reinforced sands, with the measured peak uplift resistance being used to calibrate advanced numerical models employing neural networks. Multi-layer perceptron (MLP) and Radial Basis Function (RBF) primary structure types have been used to train two neural network models, which were then further developed using bagging and boosting ensemble techniques. Correlation coefficients in excess of 0.954 between the measured and pre-dicted peak uplift resistance have been achieved. The results show that the design of pipelines can be significantly improved using the proposed novel, reliable and robust soft computing models. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. MDPI 2021 Article PeerReviewed text en cc_by_4 http://eprints.um.edu.my/25879/1/25879.pdf Zeng, Jie and Asteris, Panagiotis G. and Mamou, Anna P. and Mohammed, Ahmed Salih and Golias, Emmanuil A. and Armaghani, Danial Jahed and Faizi, Koohyar and Hasanipanah, Mahdi (2021) The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand. Applied Sciences, 11 (3). p. 908. ISSN 2076-3417 https://doi.org/10.3390/app11030908 doi:10.3390/app11030908 |
institution |
Universiti Malaya |
building |
UM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Malaya |
content_source |
UM Research Repository |
url_provider |
http://eprints.um.edu.my/ |
language |
English |
topic |
TA Engineering (General). Civil engineering (General) |
spellingShingle |
TA Engineering (General). Civil engineering (General) Zeng, Jie Asteris, Panagiotis G. Mamou, Anna P. Mohammed, Ahmed Salih Golias, Emmanuil A. Armaghani, Danial Jahed Faizi, Koohyar Hasanipanah, Mahdi The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand |
description |
Buried pipes are extensively used for oil transportation from offshore platforms. Under unfavorable loading combinations, the pipe’s uplift resistance may be exceeded, which may result in excessive deformations and significant disruptions. This paper presents findings from a series of small-scale tests performed on pipes buried in geogrid-reinforced sands, with the measured peak uplift resistance being used to calibrate advanced numerical models employing neural networks. Multi-layer perceptron (MLP) and Radial Basis Function (RBF) primary structure types have been used to train two neural network models, which were then further developed using bagging and boosting ensemble techniques. Correlation coefficients in excess of 0.954 between the measured and pre-dicted peak uplift resistance have been achieved. The results show that the design of pipelines can be significantly improved using the proposed novel, reliable and robust soft computing models. © 2021 by the authors. Licensee MDPI, Basel, Switzerland. |
format |
Article |
author |
Zeng, Jie Asteris, Panagiotis G. Mamou, Anna P. Mohammed, Ahmed Salih Golias, Emmanuil A. Armaghani, Danial Jahed Faizi, Koohyar Hasanipanah, Mahdi |
author_facet |
Zeng, Jie Asteris, Panagiotis G. Mamou, Anna P. Mohammed, Ahmed Salih Golias, Emmanuil A. Armaghani, Danial Jahed Faizi, Koohyar Hasanipanah, Mahdi |
author_sort |
Zeng, Jie |
title |
The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand |
title_short |
The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand |
title_full |
The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand |
title_fullStr |
The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand |
title_full_unstemmed |
The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand |
title_sort |
effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand |
publisher |
MDPI |
publishDate |
2021 |
url |
http://eprints.um.edu.my/25879/1/25879.pdf http://eprints.um.edu.my/25879/ https://doi.org/10.3390/app11030908 |
_version_ |
1698697313251229696 |
score |
13.18916 |