Akademik Veri Yönetim Sistemi
Tezin Türü: Yüksek Lisans
Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Petrol ve Doğal Gaz Mühendisliği Bölümü, Türkiye
Tezin Onay Tarihi: 2018
Öğrenci: TUNÇ BURAK
Danışman: SERHAT AKIN
Özet:Drilling directionally through naturally fractured geothermal reservoirs is a challenging task due to unexpected changes in inclination and azimuth of the well axis, which causes inefficient weight on bit transfer, decrease in penetration rate, increasing the risk of stuck pipe and problems in while running casings. To predict the sudden changes in inclination while drilling, a back propagation, feed forwarded multi layered artificial neural network (ANN) model, which uses drilling data collected from 12 J-type directionally drilled geothermal wells from Büyük Menderes Graben was developed. The training dataset consisted of 7600 individual drilling data. During the training process, effects of each drilling parameter on inclination were investigated with different scenarios for different hole sizes. Moreover, inclination predictions were carried out for a field case in which kick off point to the target depth with 30 meters survey intervals and results were compared. It has been found that developed ANN model provided satisfactory results based on the mean-square-error (MSE) value which was measured to check accuracy and quality of each training. The MSE of the training data set is 0.42% and the neural networks predicts the testing data with 1.19% MSE value. According to the sensitivity analysis, it has been found out that as WOB, Bit Revolution Per Minute (RPM) and Stand Pipe Pressure (SPP) increase, inclination increases. On the other hand, increment in flow rate leads to drop in inclination. Moreover, the result of the case study was 0.59% MSE which concludes that network is not memorizing the data. In addition, different ANN’s were created by omitting some drilling parameters to analyze individual effects of each parameter on network accuracy. The results indicated that, Total Flow Area (TFA), International Association of Drilling Contractors (IADC) code and Weight on Bit (WOB) have the highest impact on network dataset when compared to other drilling parameters.