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.

Original document

The different versions of the original document can be found in:

• http://eprints.whiterose.ac.uk/156089/1/IS20_2_FOR_CONFIRMATION.pdf

• http://eprints.whiterose.ac.uk/156089,

https://academic.microsoft.com/#/detail/3089054406

• http://xplorestaging.ieee.org/ielx7/9199010/9199838/09200137.pdf?arnumber=9200137,

http://dx.doi.org/10.1109/is48319.2020.9200137