Implementing artificial neural networks and support vector machines to predict lost circulation

Lost circulation is one of the major challenges encountered during drilling operations. The events related to the lost circulation can be responsible for losses of hundreds of millions of dollars each year. This paper presents a study on the application of artificial neural networks (ANNs) and suppo...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmed K. Abbas, Najim A. Al-haideri, Ali A. Bashikh
Format: Article
Language:English
Published: Egyptian Petroleum Research Institute 2019-12-01
Series:Egyptian Journal of Petroleum
Online Access:http://www.sciencedirect.com/science/article/pii/S1110062119301746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850253872564535296
author Ahmed K. Abbas
Najim A. Al-haideri
Ali A. Bashikh
author_facet Ahmed K. Abbas
Najim A. Al-haideri
Ali A. Bashikh
author_sort Ahmed K. Abbas
collection DOAJ
description Lost circulation is one of the major challenges encountered during drilling operations. The events related to the lost circulation can be responsible for losses of hundreds of millions of dollars each year. This paper presents a study on the application of artificial neural networks (ANNs) and support vector machine (SVM) to develop a robust system that can be used to predict the lost circulation occurrence. In the first step, field dataset, including drilling operation parameters, formation type, and lithology of the rock, as well as the drilling fluid characteristics, were collected from 385 wells drilled in southern Iraq from different fields. Then, the user-controlled parameters for ANNs (e.g., training function, number of hidden layers, transferring function, and number of neurons in each hidden layer) and SVMs (e.g., regularization factor, the type of kernel function, and its specific parameters) were optimized using the most common conventional performance criteria. Finally, the best-proposed models were examined using a few examples of real lost circulation cases from the field. The results of the analysis have revealed that both ANNs and SVM approaches can be of great use, with the SVM results being more promising. The application of the machine learning methods could assist drilling engineers in modifying drilling parameters to minimize the likelihood of lost circulation. Keywords: Lost circulation, Artificial neural networks, Support vector machine
format Article
id doaj-art-6a8a30e5a4ca4eeb984b055f9ffb523c
institution OA Journals
issn 1110-0621
language English
publishDate 2019-12-01
publisher Egyptian Petroleum Research Institute
record_format Article
series Egyptian Journal of Petroleum
spelling doaj-art-6a8a30e5a4ca4eeb984b055f9ffb523c2025-08-20T01:57:15ZengEgyptian Petroleum Research InstituteEgyptian Journal of Petroleum1110-06212019-12-0128433934710.1016/j.ejpe.2019.06.006Implementing artificial neural networks and support vector machines to predict lost circulationAhmed K. Abbas0Najim A. Al-haideri1Ali A. Bashikh2Iraqi Drilling Company, Basra 61004, Iraq; Corresponding author.Iraqi Drilling Company, Basra 61004, IraqMissan Oil Company, Missan 62001, IraqLost circulation is one of the major challenges encountered during drilling operations. The events related to the lost circulation can be responsible for losses of hundreds of millions of dollars each year. This paper presents a study on the application of artificial neural networks (ANNs) and support vector machine (SVM) to develop a robust system that can be used to predict the lost circulation occurrence. In the first step, field dataset, including drilling operation parameters, formation type, and lithology of the rock, as well as the drilling fluid characteristics, were collected from 385 wells drilled in southern Iraq from different fields. Then, the user-controlled parameters for ANNs (e.g., training function, number of hidden layers, transferring function, and number of neurons in each hidden layer) and SVMs (e.g., regularization factor, the type of kernel function, and its specific parameters) were optimized using the most common conventional performance criteria. Finally, the best-proposed models were examined using a few examples of real lost circulation cases from the field. The results of the analysis have revealed that both ANNs and SVM approaches can be of great use, with the SVM results being more promising. The application of the machine learning methods could assist drilling engineers in modifying drilling parameters to minimize the likelihood of lost circulation. Keywords: Lost circulation, Artificial neural networks, Support vector machinehttp://www.sciencedirect.com/science/article/pii/S1110062119301746
spellingShingle Ahmed K. Abbas
Najim A. Al-haideri
Ali A. Bashikh
Implementing artificial neural networks and support vector machines to predict lost circulation
Egyptian Journal of Petroleum
title Implementing artificial neural networks and support vector machines to predict lost circulation
title_full Implementing artificial neural networks and support vector machines to predict lost circulation
title_fullStr Implementing artificial neural networks and support vector machines to predict lost circulation
title_full_unstemmed Implementing artificial neural networks and support vector machines to predict lost circulation
title_short Implementing artificial neural networks and support vector machines to predict lost circulation
title_sort implementing artificial neural networks and support vector machines to predict lost circulation
url http://www.sciencedirect.com/science/article/pii/S1110062119301746
work_keys_str_mv AT ahmedkabbas implementingartificialneuralnetworksandsupportvectormachinestopredictlostcirculation
AT najimaalhaideri implementingartificialneuralnetworksandsupportvectormachinestopredictlostcirculation
AT aliabashikh implementingartificialneuralnetworksandsupportvectormachinestopredictlostcirculation