Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art

Raheleh Jafari; Sina Razvarz; Alexander Gegov; Boriana Vatchova

doi:10.1109/IS48319.2020.9200137

Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art

Raheleh Jafari, Sina Razvarz, Alexander Gegov, Boriana Vatchova

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Pipelines have been extensively implemented to transfer oil as well as gas products at wide distances as they are safe, and suitable. However, numerous sorts of damages may happen to the pipeline, for instance erosion, cracks, and dent. Hence, if these faults are not properly refit will result in the pipeline demolitions having leak or segregation which leads to tremendously environment risks. Deep learning methods aid operators to recognize the earliest phases of threats to the pipeline, supplying them time and information in order to handle the problem efficiently. This paper illustrates fundamental implications of deep learning comprising convolutional neural networks. Furthermore the usages of deep learning approaches for hampering pipeline detriment through the earliest diagnosis of threats are introduced.

Original language	English
Title of host publication	2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings
Editors	Vassil Sgurev, Vladimir Jotsov, Rudolf Kruse, Mincho Hadjiski
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	178-182
Number of pages	5
ISBN (Electronic)	9781728154565
ISBN (Print)	9781728154572
DOIs	https://doi.org/10.1109/IS48319.2020.9200137
Publication status	Published - 18 Sept 2020
Event	10th IEEE International Conference on Intelligent Systems, IS 2020 - Sofia, Bulgaria Duration: 28 Aug 2020 → 30 Aug 2020

Publication series

Name	IEEE International Conference on Intelligent Systems
Publisher	IEEE
ISSN (Print)	1541-1672

Conference

Conference	10th IEEE International Conference on Intelligent Systems, IS 2020
Country/Territory	Bulgaria
City	Sofia
Period	28/08/20 → 30/08/20

Keywords

convolutional neural network
damage detection
deep learning

Access to Document

10.1109/IS48319.2020.9200137

Cite this

Jafari, R., Razvarz, S., Gegov, A., & Vatchova, B. (2020). Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art. In V. Sgurev, V. Jotsov, R. Kruse, & M. Hadjiski (Eds.), 2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings (pp. 178-182). (IEEE International Conference on Intelligent Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IS48319.2020.9200137

Jafari, Raheleh ; Razvarz, Sina ; Gegov, Alexander et al. / Deep learning for pipeline damage detection : an overview of the concepts and a survey of the state-of-the-art. 2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings. editor / Vassil Sgurev ; Vladimir Jotsov ; Rudolf Kruse ; Mincho Hadjiski. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 178-182 (IEEE International Conference on Intelligent Systems).

@inproceedings{171174bd70294a9aaf328b719133620c,

title = "Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art",

abstract = "Pipelines have been extensively implemented to transfer oil as well as gas products at wide distances as they are safe, and suitable. However, numerous sorts of damages may happen to the pipeline, for instance erosion, cracks, and dent. Hence, if these faults are not properly refit will result in the pipeline demolitions having leak or segregation which leads to tremendously environment risks. Deep learning methods aid operators to recognize the earliest phases of threats to the pipeline, supplying them time and information in order to handle the problem efficiently. This paper illustrates fundamental implications of deep learning comprising convolutional neural networks. Furthermore the usages of deep learning approaches for hampering pipeline detriment through the earliest diagnosis of threats are introduced.",

keywords = "convolutional neural network, damage detection, deep learning",

author = "Raheleh Jafari and Sina Razvarz and Alexander Gegov and Boriana Vatchova",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 10th IEEE International Conference on Intelligent Systems, IS 2020 ; Conference date: 28-08-2020 Through 30-08-2020",

year = "2020",

month = sep,

day = "18",

doi = "10.1109/IS48319.2020.9200137",

language = "English",

isbn = "9781728154572",

series = "IEEE International Conference on Intelligent Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "178--182",

editor = "Vassil Sgurev and Vladimir Jotsov and Rudolf Kruse and Mincho Hadjiski",

booktitle = "2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings",

address = "United States",

}

Jafari, R, Razvarz, S, Gegov, A & Vatchova, B 2020, Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art. in V Sgurev, V Jotsov, R Kruse & M Hadjiski (eds), 2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings. IEEE International Conference on Intelligent Systems, Institute of Electrical and Electronics Engineers Inc., pp. 178-182, 10th IEEE International Conference on Intelligent Systems, IS 2020, Sofia, Bulgaria, 28/08/20. https://doi.org/10.1109/IS48319.2020.9200137

Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art. / Jafari, Raheleh; Razvarz, Sina; Gegov, Alexander et al.
2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings. ed. / Vassil Sgurev; Vladimir Jotsov; Rudolf Kruse; Mincho Hadjiski. Institute of Electrical and Electronics Engineers Inc., 2020. p. 178-182 (IEEE International Conference on Intelligent Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep learning for pipeline damage detection

T2 - 10th IEEE International Conference on Intelligent Systems, IS 2020

AU - Jafari, Raheleh

AU - Razvarz, Sina

AU - Gegov, Alexander

AU - Vatchova, Boriana

PY - 2020/9/18

Y1 - 2020/9/18

N2 - Pipelines have been extensively implemented to transfer oil as well as gas products at wide distances as they are safe, and suitable. However, numerous sorts of damages may happen to the pipeline, for instance erosion, cracks, and dent. Hence, if these faults are not properly refit will result in the pipeline demolitions having leak or segregation which leads to tremendously environment risks. Deep learning methods aid operators to recognize the earliest phases of threats to the pipeline, supplying them time and information in order to handle the problem efficiently. This paper illustrates fundamental implications of deep learning comprising convolutional neural networks. Furthermore the usages of deep learning approaches for hampering pipeline detriment through the earliest diagnosis of threats are introduced.

AB - Pipelines have been extensively implemented to transfer oil as well as gas products at wide distances as they are safe, and suitable. However, numerous sorts of damages may happen to the pipeline, for instance erosion, cracks, and dent. Hence, if these faults are not properly refit will result in the pipeline demolitions having leak or segregation which leads to tremendously environment risks. Deep learning methods aid operators to recognize the earliest phases of threats to the pipeline, supplying them time and information in order to handle the problem efficiently. This paper illustrates fundamental implications of deep learning comprising convolutional neural networks. Furthermore the usages of deep learning approaches for hampering pipeline detriment through the earliest diagnosis of threats are introduced.

KW - convolutional neural network

KW - damage detection

KW - deep learning

UR - http://www.scopus.com/inward/record.url?scp=85092041757&partnerID=8YFLogxK

U2 - 10.1109/IS48319.2020.9200137

DO - 10.1109/IS48319.2020.9200137

M3 - Conference contribution

AN - SCOPUS:85092041757

SN - 9781728154572

T3 - IEEE International Conference on Intelligent Systems

SP - 178

EP - 182

BT - 2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings

A2 - Sgurev, Vassil

A2 - Jotsov, Vladimir

A2 - Kruse, Rudolf

A2 - Hadjiski, Mincho

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 28 August 2020 through 30 August 2020

ER -

Jafari R, Razvarz S, Gegov A, Vatchova B. Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art. In Sgurev V, Jotsov V, Kruse R, Hadjiski M, editors, 2020 IEEE 10th International Conference on Intelligent Systems, IS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 178-182. (IEEE International Conference on Intelligent Systems). doi: 10.1109/IS48319.2020.9200137

Deep learning for pipeline damage detection: an overview of the concepts and a survey of the state-of-the-art

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this