Prediction of dog-leg severity by using artificial neural network

Kaymak, Sinem
As technology growth, complexity of the drilling wells has been increasing. Directional wells have been drilling in order to deviate the well through planned targets which are at distant location from wellhead. One of the most important preliminary studies before drilling of any directional well is the prediction of Dog-leg severity. High and inconsistent Dog-leg severities can lead to high tortuosity, which may bring in high bottom torque, downhole tool failures, stuck pipe, target miss, inabilities to run casings, casing stuck and even side-track operations. Therefore, estimation of Dog-leg severity is vital for any directional wells. There are many variables affecting to DLS severity, which increases the complexity of estimation. Artificial Neural Networks (ANN) has become useful application for drilling industry since it is able to simulate highly non-linear relationships with large data sets. It is a statistical learning model inspired by biological neurons that connected and sending signals to each other. There are many Artificial Neural Network structures available. The most common one is “Feed-Forward Back Propagation Artificial Neural Network” known as; most accurate network due to generation of low error. This thesis is about estimation of Dog-leg severity of directional wells by Feed-Forward Back Propagation Artificial Neural Network. The study consists of two vi separate field drilling data, first one is an oil field located at Southeast of Turkey in Diyarbakir that has carbonates formation. Second one is a geothermal field located at the West of the Turkey in Manisa which has sandstone and claystone formation originated from metamorphic rocks. Two different ANN models have been created by considering 4290 individual drilling data of 12 wells for their 8 ½” hole sections in Diyarbakir Field and 1100 individual drilling data of 7 wells for their 12 ¼” hole sections in Manisa Field. Data sets have been prepared by dividing into 30m depth intervals. Parameters that affects Dog-leg severity are taken into account as input variables which are Sleeve Stabilizer Outer Diameter, String Stabilizer Outer Diameter, Downhole Motor Bent Angle, Rate of Penetration for bit wear effect, Depth, Inclination of the Wellbore, Tool Face Orientation, Weight on Bit, Bottom Revolution per Minute and Sliding Percentage. There are total 10 input variables drives 1 output variable which is Dog-leg Severity. Several sensitivity analyses have been made to decide network structure to obtain accurate, low error driven ANN model. It has been found that ANN Model is a proven tool for the estimation of DLS. Satisfactory results have been obtained with low Mean Squared Errors (MSE). MSE of Diyarbakir Field is 0.056 and, it is 0.057 for Manisa Field.


Analysis of finite element method solution of sinusoidal buckling behaviour of drill string in vertical, directional, and horizontal wellbores and comparison with analytical solutions
Cebeci, Mehmet; Kök, Mustafa Verşan; Gücüyener, İ. Hakkı; Department of Petroleum and Natural Gas Engineering (2017)
The buckling of drill string in oil, gas and geothermal wells is a critical problem that has been of interest to many researchers in the industry. Prevention of buckling of drill string is important since it may negatively affect the drilling operations. When buckling of drill string occurs, it may cause deviation control problems while drilling, inefficient load transfer to the bit, excessive torque values, even pipe failures due to fatigue. The first rigorous treatment of stability of drill strings for ve...
Candidate selection process for polymer gel application by using artificial neural networks
Örs, Oytun; Sınayuç, Çağlar; Department of Petroleum and Natural Gas Engineering (2017)
Rapid increase in water-oil ratio has been one of the most important challenges of the oil companies that are producing from the mature oil fields. For this reason, various studies have been conducted to diminish the excessive water production. One of the most widely used chemical shutoff technique, polymer gel treatment, involves injection of different polymers into the production wells in order to plug the easy flow pathways of the excessive water. For the successful application of the polymer gel treatme...
Review of natural gas discovery and production from conventional resources in Turkey
Keskin, Hakan; Mehmetoğlu, Mustafa Tanju; Department of Petroleum and Natural Gas Engineering (2007)
Oil and natural gas are the most strategic raw materials to meet the expanding energy requirement in today’s world. They have great impact on issues such as economy, national security, development, competition, and political consistency. Being a developing country, Turkey’s natural gas requirement is increasing rapidly. However, the production is far from covering the demand. Recent assumptions point out that natural gas demand of Turkey will reach 44 billion cubic meters in 2010 with a financial burden of ...
Optimization of CO₂ EOR and storage design under uncertainity
Bender, Serdar; Akın, Serhat; Department of Petroleum and Natural Gas Engineering (2016)
The combination of CO₂ enhanced oil recovery (EOR) and permanent CO₂ storage in mature oil reservoirs have the potential to provide a critical near-term solution for reducing greenhouse gas emissions. In the literature, although there are many studies about CO₂ storage and EOR, only a few studies have focused on maximizing both the oil recovery and the CO₂ storage. Moreover, these studies are either experimental or conducted using synthetic reservoir models. Typically, pure CO₂ has the property of mixing wi...
ARIMA forecasting of primary energy demand by fuel in Turkey
Ediger, Volkan S.; Akar, Sertac (2007-03-01)
Forecasting of energy demand in emerging markets is one of the most important policy tools used by the decision makers all over the world. In Turkey, most of the early studies used include various forms of econometric modeling. However, since the estimated economic and demographic parameters usually deviate from the realizations, time-series forecasting appears to give better results. In this study, we used the Autoregressive Integrated Moving Average (ARIMA) and seasonal ARIMA (SARIMA) methods to estimate ...
Citation Formats
S. Kaymak, “Prediction of dog-leg severity by using artificial neural network,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Petroleum and Natural Gas Engineering., Middle East Technical University, 2019.