Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well

Accurate prediction of downhole pressure differential (surge/swab pressure gradient) in the eccentric annulus of ultra-deep wells during tripping operation is a necessity to optimize well geometry, reduction of drilling anomalies, and prevention of hazardous drilling accidents. Therefore, a new pred...

Full description

Main Authors: Krishna, S., Ridha, S., Ilyas, S.U., Campbell, S., Bhan, U., Bataee, M.
Format: Conference or Workshop Item
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.29407 /
Published: American Society of Mechanical Engineers (ASME) 2021
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85117132286&doi=10.1115%2fOMAE2021-62621&partnerID=40&md5=c9678cb470a1ae5d1d981292230c4083
http://eprints.utp.edu.my/29407/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.29407
recordtype eprints
spelling utp-eprints.294072022-03-25T01:50:52Z Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well Krishna, S. Ridha, S. Ilyas, S.U. Campbell, S. Bhan, U. Bataee, M. Accurate prediction of downhole pressure differential (surge/swab pressure gradient) in the eccentric annulus of ultra-deep wells during tripping operation is a necessity to optimize well geometry, reduction of drilling anomalies, and prevention of hazardous drilling accidents. Therefore, a new predictive model is developed to forecast surge/swab pressure gradient by using feed-forward and backpropagation deep neural networks (FFBP-DNN). A theoretical-based model is developed that follows the physical and mechanical aspects of surge/swab pressure generation in eccentric annulus during tripping operation. The data generated from this model, field data, and experimental data are used to train and test the FFBP-DNN networks. The network is developed used Keras�s deep learning framework. After testing the models, the most optimal arrangement of FFBP-DNN is the ReLU algorithm as an activation function, 4-hidden layers, the learning rate of 0.003, and 2300 of training numbers. The optimum FFBP-DNN model is validated by comparing it with field data (Wells K 470 and K 480, North Sea). It shows an excellent argument between predicted data and field data with an error range of ±7.68 . Copyright © 2021 by ASME. American Society of Mechanical Engineers (ASME) 2021 Conference or Workshop Item NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85117132286&doi=10.1115%2fOMAE2021-62621&partnerID=40&md5=c9678cb470a1ae5d1d981292230c4083 Krishna, S. and Ridha, S. and Ilyas, S.U. and Campbell, S. and Bhan, U. and Bataee, M. (2021) Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well. In: UNSPECIFIED. http://eprints.utp.edu.my/29407/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description Accurate prediction of downhole pressure differential (surge/swab pressure gradient) in the eccentric annulus of ultra-deep wells during tripping operation is a necessity to optimize well geometry, reduction of drilling anomalies, and prevention of hazardous drilling accidents. Therefore, a new predictive model is developed to forecast surge/swab pressure gradient by using feed-forward and backpropagation deep neural networks (FFBP-DNN). A theoretical-based model is developed that follows the physical and mechanical aspects of surge/swab pressure generation in eccentric annulus during tripping operation. The data generated from this model, field data, and experimental data are used to train and test the FFBP-DNN networks. The network is developed used Keras�s deep learning framework. After testing the models, the most optimal arrangement of FFBP-DNN is the ReLU algorithm as an activation function, 4-hidden layers, the learning rate of 0.003, and 2300 of training numbers. The optimum FFBP-DNN model is validated by comparing it with field data (Wells K 470 and K 480, North Sea). It shows an excellent argument between predicted data and field data with an error range of ±7.68 . Copyright © 2021 by ASME.
format Conference or Workshop Item
author Krishna, S.
Ridha, S.
Ilyas, S.U.
Campbell, S.
Bhan, U.
Bataee, M.
spellingShingle Krishna, S.
Ridha, S.
Ilyas, S.U.
Campbell, S.
Bhan, U.
Bataee, M.
Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well
author_sort Krishna, S.
title Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well
title_short Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well
title_full Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well
title_fullStr Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well
title_full_unstemmed Application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well
title_sort application of deep learning technique to predict downhole pressure differential in eccentric annulus of ultra-deep well
publisher American Society of Mechanical Engineers (ASME)
publishDate 2021
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85117132286&doi=10.1115%2fOMAE2021-62621&partnerID=40&md5=c9678cb470a1ae5d1d981292230c4083
http://eprints.utp.edu.my/29407/
_version_ 1741197237069807616
score 11.62408

Similar Items