Stuck pipe optimization using duellist algorithm

Stuck pipes are one of the most serious drilling problems, stuck pipes can cost the oil industry hundreds of millions of dollars per year. One way to avoid the risk of a stuck pipe is to predict the condition of a stuck pipe with the available drilling parameters. Throughout the years, a lot researc...

Full description

Saved in:
Bibliographic Details
Published in:IOP conference series. Earth and environmental science 2021-03, Vol.672 (1), p.12104
Main Authors: Biyanto, T R, Cordova, H, Matradji, Anggrea, T O, Suryowicaksono, H, Irawan, S
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Drill pipe
Drilling
Mudflows
Neural networks
Nodes
Oil and gas industry
Optimization
Pipes
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Stuck pipes are one of the most serious drilling problems, stuck pipes can cost the oil industry hundreds of millions of dollars per year. One way to avoid the risk of a stuck pipe is to predict the condition of a stuck pipe with the available drilling parameters. Throughout the years, a lot research has been dedicated to finding the causes that lead to stuck pipe events. But it still not reached the study in the calculation of the optimization of drilling operation costs. In this final project, Artificial Neural Network (ANN) is used for prediction stuck pipe and optimized using the Duellist Algorithm (DA). As well as Increasing fewer data that will get easier to make it in to the model. In this model, it use 1 The input layer contains 12 input nodes, 14 hidden layers trained with 1 to 30 hidden nodes, and 1 output layer in 14 hidden layers with an RMSE value of 0. At the end of the optimization, the lowest cost is USD 17300 / hour at RPM 195, 69, and mudflow 722.28 GPM. As well as constraint conditions are maintained and not stuck.
ISSN:1755-1307
1755-1315
DOI:10.1088/1755-1315/672/1/012104