東華大學圖書館 |

Prediction of Lost Circulation Zones Using Artificial Intelligence Techniques.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Prediction of Lost Circulation Zones Using Artificial Intelligence Techniques./
作者:	Ahmed, Abdulmalek Ahmed Saif.
面頁冊數:	1 online resource (189 pages)
附註:	Source: Masters Abstracts International, Volume: 84-09.
Contained By:	Masters Abstracts International84-09.
標題:	Petroleum engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29399204click for full text (PQDT)
ISBN:	9798377638575

Prediction of Lost Circulation Zones Using Artificial Intelligence Techniques.
Ahmed, Abdulmalek Ahmed Saif.

Prediction of Lost Circulation Zones Using Artificial Intelligence Techniques. - 1 online resource (189 pages)

Source: Masters Abstracts International, Volume: 84-09.

Thesis (M.S.)--King Fahd University of Petroleum and Minerals (Saudi Arabia), 2019.

Includes bibliographical references

Drilling deep and high-pressure high-temperature wells have many challenges and problems. One of the most severe, costly and time-consuming problem in the drilling operation is the lost circulation. The drilling fluid accounts for 25-40% of the total cost of the drilling operation. Any loss of the drilling fluid will increase the total cost of the drilling operation. Uncontrolled lost circulation of the drilling fluid can result in dangerous well control problem and in some cases the loss of the well. Lost circulation or loss of return is defined as the partial or complete loss of the drilling fluid from the annulus into the formation at any depth when using overbalanced drilling technique. Lost circulation is divided into four types based on its severity: seepage, partial, severe, and total. Fluid losses can occur in different formations such as natural fracture, induced fracture, unconsolidated zones, cavernous and vugular formations, and high permeability formation.It is very difficult to cure losses, especially in workover operations. Use of conventional lost circulation material (LCM) is not successful in all the cases of lost circulation due to some limitation and disadvantages. In order to avoid loss circulation, some methods are introduced to identify the zones of losses. However, these methods are difficult to be applied due to financial issues and lack of technology. The other methods are not accurate in the prediction of the loss zones. In this thesis, five different artificial intelligence techniques namely: artificial neural networks (ANN), radial basis function (RBF), fuzzy logic (FL), support vector machine (SVM) and Functional Networks (FN) were applied to predict the zones of lost circulation using more than 4500 real filed data points in three wells based only on 6 mechanical surface drilling parameters (flow pump (FLWPMP), rate of penetration (ROP), string rotary speed (RPM), standpipe pressure (SPP), drilling torque (TORQUE) and weight on bit (WOB)). The five AI models will be trained and tested by the first well (Well A) which contains 1417 points, then the models will be validated by two unseen wells (Well B & Well C) which contain 2872 points and 1295 points respectively. In addition, a comparison between all the five AI techniques will be performed to select the optimum prediction method. The results showed that all the artificial intelligence methods can be used to predict losses zones with high accuracy (the correlation coefficient (R) is more than 0.980 and the root mean squared error (RMSE) is less than 0.088). ANN was able to predict the losses zones in the unseen well (well B) with a high performance (R = 0.958 and RMSE = 0.145). ANN also predicted the losses zones in well C which is unseen with a high correlation coefficient of (R = 0.952) and low root mean squared error of (RMSE = 0.155). Moreover, The AI techniques comparison results showed that, functional network (FN) and support vector machine (SVM) methods are considered the best tools among other AI methods in the prediction of losses zones due to their high performance (a high correlation coefficient of 0.997 and a low root mean squared error of 0.0376). However, FN has the advantage of its short time in the prediction of the losses zones. Artificial intelligence techniques have the advantage of its simplicity that represented from its prediction of losses zones of circulation from only the mechanical surface drilling parameters that are easily available in each well.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798377638575Subjects--Topical Terms:

566616
Petroleum engineering.
Subjects--Index Terms:

Artificial intelligenceIndex Terms--Genre/Form:

542853
Electronic books.

Prediction of Lost Circulation Zones Using Artificial Intelligence Techniques.
LDR:04946nmm a2200397K 4500 001 2360849
005 20231015185434.5
006 m o d
007 cr mn ---uuuuu
008 241011s2019 xx obm 000 0 eng d
020 $a 9798377638575
035 $a (MiAaPQ)AAI29399204
035 $a AAI29399204
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Ahmed, Abdulmalek Ahmed Saif. $3 3701485
245 1 0 $a Prediction of Lost Circulation Zones Using Artificial Intelligence Techniques.
264 0 $c 2019
300 $a 1 online resource (189 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-09.
500 $a Advisor: Elkatatny, Salaheldin; Abdulraheem, Abdulazeez.
502 $a Thesis (M.S.)--King Fahd University of Petroleum and Minerals (Saudi Arabia), 2019.
504 $a Includes bibliographical references
520 $a Drilling deep and high-pressure high-temperature wells have many challenges and problems. One of the most severe, costly and time-consuming problem in the drilling operation is the lost circulation. The drilling fluid accounts for 25-40% of the total cost of the drilling operation. Any loss of the drilling fluid will increase the total cost of the drilling operation. Uncontrolled lost circulation of the drilling fluid can result in dangerous well control problem and in some cases the loss of the well. Lost circulation or loss of return is defined as the partial or complete loss of the drilling fluid from the annulus into the formation at any depth when using overbalanced drilling technique. Lost circulation is divided into four types based on its severity: seepage, partial, severe, and total. Fluid losses can occur in different formations such as natural fracture, induced fracture, unconsolidated zones, cavernous and vugular formations, and high permeability formation.It is very difficult to cure losses, especially in workover operations. Use of conventional lost circulation material (LCM) is not successful in all the cases of lost circulation due to some limitation and disadvantages. In order to avoid loss circulation, some methods are introduced to identify the zones of losses. However, these methods are difficult to be applied due to financial issues and lack of technology. The other methods are not accurate in the prediction of the loss zones. In this thesis, five different artificial intelligence techniques namely: artificial neural networks (ANN), radial basis function (RBF), fuzzy logic (FL), support vector machine (SVM) and Functional Networks (FN) were applied to predict the zones of lost circulation using more than 4500 real filed data points in three wells based only on 6 mechanical surface drilling parameters (flow pump (FLWPMP), rate of penetration (ROP), string rotary speed (RPM), standpipe pressure (SPP), drilling torque (TORQUE) and weight on bit (WOB)). The five AI models will be trained and tested by the first well (Well A) which contains 1417 points, then the models will be validated by two unseen wells (Well B & Well C) which contain 2872 points and 1295 points respectively. In addition, a comparison between all the five AI techniques will be performed to select the optimum prediction method. The results showed that all the artificial intelligence methods can be used to predict losses zones with high accuracy (the correlation coefficient (R) is more than 0.980 and the root mean squared error (RMSE) is less than 0.088). ANN was able to predict the losses zones in the unseen well (well B) with a high performance (R = 0.958 and RMSE = 0.145). ANN also predicted the losses zones in well C which is unseen with a high correlation coefficient of (R = 0.952) and low root mean squared error of (RMSE = 0.155). Moreover, The AI techniques comparison results showed that, functional network (FN) and support vector machine (SVM) methods are considered the best tools among other AI methods in the prediction of losses zones due to their high performance (a high correlation coefficient of 0.997 and a low root mean squared error of 0.0376). However, FN has the advantage of its short time in the prediction of the losses zones. Artificial intelligence techniques have the advantage of its simplicity that represented from its prediction of losses zones of circulation from only the mechanical surface drilling parameters that are easily available in each well.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Petroleum engineering. $3 566616
650 4 $a Fluid mechanics. $3 528155
653 $a Artificial intelligence
653 $a Drilling deep
653 $a Neural networks
653 $a Functional networks
653 $a Fuzzy logic
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0765
690 $a 0800
690 $a 0204
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a King Fahd University of Petroleum and Minerals (Saudi Arabia). $b Petroleum Engineering Department. $3 3701427
773 0 $t Masters Abstracts International $g 84-09.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29399204 $z click for full text (PQDT)