Towards Machine Learning-Driven Practices for Oil and Gas Decommissioning – Introduction of a New Offshore Pipeline Dataset

2021 ◽  
Author(s):  
Pattaramon Vuttipittayamongkol ◽  
Aaron Tung ◽  
Eyad Elyan
Keyword(s):  
Machine Learning ◽  
Oil And Gas ◽  
Offshore Pipeline

Effect of Full- and Small-Scale Reeling Simulation on Mechanical Properties of Weldable 13Cr Seamless Line Pipe

2013 ◽  
Author(s):  
Hidenori Shitamoto ◽  
Nobuyuki Hisamune
Keyword(s):  
Mechanical Properties ◽  
Plastic Deformation ◽  
Oil And Gas ◽  
Small Scale ◽  
Line Pipe ◽  
Offshore Pipeline ◽  
Oil And Gas Pipelines ◽  
Before And After ◽  
Offshore Oil And Gas ◽  
Offshore Oil

There are several methods currently being used to install offshore oil and gas pipelines. The reel-lay process is fast and one of the most effective offshore pipeline installation methods for seamless, ERW, and UOE line pipes with outside diameters of 18 inches or less. In the case of the reel-laying method, line pipes are subjected to plastic deformation multiplication during reel-laying. It is thus important to understand the change of the mechanical properties of line pipes before and after reel-laying. Therefore, full-scale reeling (FSR) simulations and small-scale reeling (SSR) simulations are applied as evaluation tests for reel-laying. In this study, FSR simulations were performed to investigate the effect of cyclic deformation on the mechanical properties of weldable 13Cr seamless line pipes. Furthermore, SSR simulations were performed to compare the results obtained by FSR simulations.

Application of machine learning algorithms to predict permeability in tight sandstone formations

Nafta-Gaz ◽  
2021 ◽  
Vol 77 (5) ◽  
pp. 283-292
Author(s):  
Tomasz Topór ◽  
Keyword(s):  
Machine Learning ◽  
Oil And Gas ◽  
Learning Algorithms ◽  
Confining Pressure ◽  
Machine Learning Algorithms ◽  
Core Material ◽  
Confining Stress ◽  
Tight Sandstone ◽  
Oil And Gas Exploration ◽  
Better Than

The application of machine learning algorithms in petroleum geology has opened a new chapter in oil and gas exploration. Machine learning algorithms have been successfully used to predict crucial petrophysical properties when characterizing reservoirs. This study utilizes the concept of machine learning to predict permeability under confining stress conditions for samples from tight sandstone formations. The models were constructed using two machine learning algorithms of varying complexity (multiple linear regression [MLR] and random forests [RF]) and trained on a dataset that combined basic well information, basic petrophysical data, and rock type from a visual inspection of the core material. The RF algorithm underwent feature engineering to increase the number of predictors in the models. In order to check the training models’ robustness, 10-fold cross-validation was performed. The MLR and RF applications demonstrated that both algorithms can accurately predict permeability under constant confining pressure (R2 0.800 vs. 0.834). The RF accuracy was about 3% better than that of the MLR and about 6% better than the linear reference regression (LR) that utilized only porosity. Porosity was the most influential feature of the models’ performance. In the case of RF, the depth was also significant in the permeability predictions, which could be evidence of hidden interactions between the variables of porosity and depth. The local interpretation revealed the common features among outliers. Both the training and testing sets had moderate-low porosity (3–10%) and a lack of fractures. In the test set, calcite or quartz cementation also led to poor permeability predictions. The workflow that utilizes the tidymodels concept will be further applied in more complex examples to predict spatial petrophysical features from seismic attributes using various machine learning algorithms.

Boosting Algorithm Choice in Predictive Machine Learning Models for Fracturing Applications

2021 ◽  
Author(s):  
Abdul Muqtadir Khan
Keyword(s):  
Machine Learning ◽  
Data Science ◽  
Oil And Gas ◽  
Oil And Gas Industry ◽  
Injection Rate ◽  
Model Construction ◽  
Gradient Boosting ◽  
Light Gradient ◽  
Fracture Damage ◽  
Boosting Technique

Abstract With the advancement in machine learning (ML) applications, some recent research has been conducted to optimize fracturing treatments. There are a variety of models available using various objective functions for optimization and different mathematical techniques. There is a need to extend the ML techniques to optimize the choice of algorithm. For fracturing treatment design, the literature for comparative algorithm performance is sparse. The research predominantly shows that compared to the most commonly used regressors and classifiers, some sort of boosting technique consistently outperforms on model testing and prediction accuracy. A database was constructed for a heterogeneous reservoir. Four widely used boosting algorithms were used on the database to predict the design only from the output of a short injection/falloff test. Feature importance analysis was done on eight output parameters from the falloff analysis, and six were finalized for the model construction. The outputs selected for prediction were fracturing fluid efficiency, proppant mass, maximum proppant concentration, and injection rate. Extreme gradient boost (XGBoost), categorical boost (CatBoost), adaptive boost (AdaBoost), and light gradient boosting machine (LGBM) were the algorithms finalized for the comparative study. The sensitivity was done for a different number of classes (four, five, and six) to establish a balance between accuracy and prediction granularity. The results showed that the best algorithm choice was between XGBoost and CatBoost for the predicted parameters under certain model construction conditions. The accuracy for all outputs for the holdout sets varied between 80 and 92%, showing robust significance for a wider utilization of these models. Data science has contributed to various oil and gas industry domains and has tremendous applications in the stimulation domain. The research and review conducted in this paper add a valuable resource for the user to build digital databases and use the appropriate algorithm without much trial and error. Implementing this model reduced the complexity of the proppant fracturing treatment redesign process, enhanced operational efficiency, and reduced fracture damage by eliminating minifrac steps with crosslinked gel.

Local Buckling in end Expansion of Subsea Pipelines

2014 ◽  
Vol 69 (7) ◽  
Author(s):  
Jaswar Koto ◽  
Abd. Khair Junaidi ◽  
M. H. Hashim
Keyword(s):  
Crude Oil ◽  
Axial Force ◽  
Oil And Gas ◽  
Local Buckling ◽  
Offshore Platform ◽  
Offshore Pipeline ◽  
Specific Rule ◽  
Subsea Pipelines ◽  
Study Development

Offshore pipeline is mainly to transport crude oil and gas from offshore to onshore. It is also used to transport crude oil and gas from well to offshore platform and from platform to another platform. The crude oil and gas horizontally flows on the seabed, and then vertically flows inside the riser to the offshore platform. One of current issues of the oil and gas transportation system is an end expansion caused by the axial force. If the end expansion occurs over it limit can cause overstress to riser. This paper explores the effect of axial force toward local buckling in end expansion. In the study, development of programming in visual basic 2010 firstly was constructed using empirical equation. The programming code, then, was validated by comparing simulation result with actual data from company. As case study, the end expansion for various thicknesses of pipes was simulated. In this programming, DNV regulation is included for checking either design complied or not with regulation. However, DNV regulation doesn’t have specific rule regarding the end expansion but it is evaluated under load displacement control under strain condition.

Dynamic Response Interaction of Vibrating Offshore Pipeline on Moving Seabed

2006 ◽  
Vol 129 (2) ◽  
pp. 107-119 ◽  
Author(s):  
Vincent O. S. Olunloyo ◽  
Charles A. Osheku ◽  
Ayo A. Oyediran
Keyword(s):  
Dynamic Response ◽  
Oil And Gas ◽  
Fluid Velocity ◽  
Gas Industry ◽  
Offshore Pipeline ◽  
Internal Fluid ◽  
Geomechanical Property ◽  
Sediment Cover ◽  
The Subject ◽  
Oil Gas

The dynamic response interaction of a vibrating offshore pipeline on a moving seabed is herein investigated where the pipeline is idealized as a beam vibrating on an elastic foundation. This problem is of relevance in offshore exploration where pipelines are laid either on or buried in the seabed. When such pipes carry oil and gas, the undulating topography of the sea floor and the internal motion of the fluid subject the entire structure to vibration due to bending forces and form the subject of our study. Our analysis revealed that in general, the seabed acts either as a damper or as a spring and in particular when we have sedimentation, the seabed geology permits the geomechanical property of the sediment cover to act only as a damper. As expected, external excitation will increase the response of these pipes for which an amplification factor has been derived. For soft beds, high transverse vibrations were dampened by increasing the internal fluid velocity whereas they became amplified for hard beds. These results are of contemporary interest in the oil/gas industry where deep sea exploration is now receiving significant attention.

Correlating geologic and seismic data with unconventional resource production curves using machine learning

Geophysics ◽  
2019 ◽  
Vol 84 (2) ◽  
pp. O39-O47 ◽  
Author(s):  
Ryan Smith ◽  
Tapan Mukerji ◽  
Tony Lupo
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Oil And Gas ◽  
Principal Component ◽  
Functional Principal Component Analysis ◽  
Full Time ◽  
Data Types ◽  
Production Time ◽  
Well Production ◽  
Unconventional Resource

Predicting well production in unconventional oil and gas settings is challenging due to the combined influence of engineering, geologic, and geophysical inputs on well productivity. We have developed a machine-learning workflow that incorporates geophysical and geologic data, as well as engineering completion parameters, into a model for predicting well production. The study area is in southwest Texas in the lower Eagle Ford Group. We make use of a time-series method known as functional principal component analysis to summarize the well-production time series. Next, we use random forests, a machine-learning regression technique, in combination with our summarized well data to predict the full time series of well production. The inputs to this model are geologic, geophysical, and engineering data. We are then able to predict the well-production time series, with 65%–76% accuracy. This method incorporates disparate data types into a robust, predictive model that predicts well production in unconventional resources.

scholarly journals Discovering Business Processes from Email Logs using fastText and Process Mining

2020 ◽  
Author(s):  
Yaghoub rashnavadi ◽  
Sina Behzadifard ◽  
Reza Farzadnia ◽  
sina zamani
Keyword(s):  
Machine Learning ◽  
Business Processes ◽  
Oil And Gas ◽  
Process Mining ◽  
The Body ◽  
Process Models ◽  
Supervised Machine Learning ◽  
Implicit Information ◽  
Oil And Gas Sector

<p>Communication has never been more accessible than today. With the help of Instant messengers and Email Services, millions of people can transfer information with ease, and this trend has affected organizations as well. There are billions of organizational emails sent or received daily, and their main goal is to facilitate the daily operation of organizations. Behind this vast corpus of human-generated content, there is much implicit information that can be mined and used to improve or optimize the organizations’ operations. Business processes are one of those implicit knowledge areas that can be discovered from Email logs of an Organization, as most of the communications are followed inside Emails. The purpose of this research is to propose an approach to discover the process models in the Email log. In this approach, we combine two tools, supervised machine learning and process mining. With the help of supervised machine learning, fastText classifier, we classify the body text of emails to the activity-related. Then the generated log will be mined with process mining techniques to find process models. We illustrate the approach with a case study company from the oil and gas sector.</p>

Sign in / Sign up

Export Citation Format

Share Document