|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
Summary There is a great deal of interest in the oil and gas industry (OGI) in seeking ways to implement machine learning (ML) to provide valuable insights for increased profitability. With buzzwords such as data analytics, ML, artificial intelligence (AI), and so forth, the curiosity of typical drilling practitioners and researchers is piqued. While a few review papers summarize the application of ML in the OGI, such as Noshi and Schubert (2018), they only provide simple summaries of ML applications without detailed and practical steps that benefit OGI practitioners interested in incorporating ML into their workflow. This paper addresses this gap by systematically reviewing a variety of recent publications to identify the problems posed by oil and gas practitioners and researchers in drilling operations. Analyses are also performed to determine which algorithms are most widely used and in which area of oilwell-drilling operations these algorithms are being used. Deep dives are performed into representative case studies that use ML techniques to address the challenges of oilwell drilling. This study summarizes what ML techniques are used to resolve the challenges faced, and what input parameters are needed for these ML algorithms. The optimal size of the data set necessary is included, and in some cases where to obtain the data set for efficient implementation is also included. Thus, we break down the ML workflow into the three phases commonly used in the input/process/output model. Simplifying the ML applications into this model is expected to help define the appropriate tools to be used for different problems. In this work, data on the required input, appropriate ML method, and the desired output are extracted from representative case studies in the literature of the last decade. The results show that artificial neural networks (ANNs), support vector machines (SVMs), and regression are the most used ML algorithms in drilling, accounting for 18, 17, and 13%, respectively, of all the cases analyzed in this paper. Of the representative case studies, 60% implemented these and other ML techniques to predict the rate of penetration (ROP), differential pipe sticking (DPS), drillstring vibration, or other drilling events. Prediction of rheological properties of drilling fluids and estimation of the formation properties was performed in 22% of the publications reviewed. Some other aspects of drilling in which ML was applied were well planning (5%), pressure management (3%), and well placement (3%). From the results, the top ML algorithms used in the drilling industry are versatile algorithms that are easily applicable in almost any situation. The presentation of the ML workflow in different aspects of drilling is expected to help both drilling practitioners and researchers. Several step-by-step guidelines available in the publications reviewed here will guide the implementation of these algorithms in the resolution of drilling challenges.
Abstract Rate of Penetration referrers to the speed of breaking the rock under the bit. It measures the speed or the progress of the bit when it drills the formation. It has been reported in the industry that high percentage of the well budget is spent on the drilling phase, thus many drilling operators pay close attention to this factor and try to optimize it as much as possible. However, it is very challenging to capture the effect of each individual parameter since most of them are interconnected, and changing one parameter affects the other. As a result, many companies maintain a data for the drilling performance per field and set certain benchmarks to gauge the speed of any newly drilled well. To date, no solid or reliable model exists because of the complexity of the drilling process, and one cannot capture every factor to predict the rate of penetration. Therefore, the utilization of artificial intelligence (AI) in the drilling applications will be a game changer since most of the unknown parameters are accounted for during the modeling or training process. The objective of this paper is to develop a rate of penetration model using artificial neural network (ANN) with the least possible number of inputs. Actual field data of more than 4,500 data points were used to build the model. The inputs were pumping rate, weight on bit, rotation speed, torque, stand pipe pressure and unconfined compressive strength. Well-A was used to train and test the model with 70/30 data ratio. Then two unseen data which are well-B and well-C were used to test the model. ANN was used in this study, with many sensitivity analyses to achieve the best combination of parameters. The obtained results showed that ANN can be used effectively to predict the rate of penetration with average correlation coefficient of 0.94 and average absolute percentage error of 8.6%, which shows 22% improvement over the current published methods. The best ANN model was achieved using 1 layer, 12 neurons and a linear transfer function. The developed ANN-ROP model proved to be successful using only six inputs and having a total of two wells with unseen data.
Mahmoud, Ahmed Abdulhamid (King Fahd University of Petroleum & Minerals) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals) | Al-AbdulJabbar, Ahmad (King Fahd University of Petroleum & Minerals) | Moussa, Tamer (King Fahd University of Petroleum & Minerals) | Gamal, Hany (King Fahd University of Petroleum & Minerals) | Shehri, Dhafer Al (King Fahd University of Petroleum & Minerals)
ABSTRACT This study introduces an empirical equation for estimation of the rate of penetration (ROP) while horizontally drilling carbonate formations based on the surface measurable drilling parameters, well log data, and the extracted weights and biases of an optimized artificial neural networks (ANN) model. The ANN model was trained using 3000 datasets of different surface measurable drilling parameters including the torque, rotation speed, and weight-on-bit, with the conventional well log data of the deep resistivity, gamma-ray, and formation bulk density, and their corresponding ROP, the self-adaptive differential evolution algorithm was applied to optimize the ANN model's design parameters. For the training dataset, the ROP was predicted with the optimized ANN model with an average absolute percentage error (AAPE) and a correlation coefficient (R) of 5.12% and 0.960, respectively. The developed empirical equation was tested on another unseen dataset (531 data points) collected from the same training well; where it predicted the ROP with AAPE of 5.80% and R of 0.951. 1. INTRODUCTION The total cost of drilling a hydrocarbon well is time-dependent (Lyons and Plisga, 2004). Rig time, which is affected by many factors, such as rate of penetration (ROP), is considered the most critical parameter for determining the total cost of drilling. Optimizing ROP has a significant impact on reducing the total cost (Barbosa et al., 2019). ROP is affected by several parameters, which can be categorized into controllable and uncontrollable parameters (Hossain and Al-Majed, 2015). The controllable parameters include weight-on-bit (WOB), rotation speed (RPM), pumping rate (GPM), torque (T), and standpipe pressure (SPP) (Eren and Ozbayoglu, 2010; Payette et al., 2017). All abbreviations are listed in Appendix A. The uncontrollable parameters include bit size and drilling fluid type, density, and rheological properties. The uncontrollable parameters affect each other, which complicates the quantification of their effect on ROP (Osgouei, 2007).
Gamal, Hany (King Fahd University of Petroleum & Minerals, Dhahran, Eastern Province, Saudi Arabia) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals, Dhahran, Eastern Province, Saudi Arabia) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals, Dhahran, Eastern Province, Saudi Arabia)
The fourth industrial revolution and its vision for developing and governing the technologies supported artificial intelligence (AI) applications in the different petroleum industry disciplines. Therefore, the objective of this paper is to use the artificial neural network (ANN) to build a model for the rate of penetration (ROP) that considers the effect of drilling parameters,formation lithology, and drill bit design on the ROP performance. The novelty in this study is addressing the influence of poly diamond crystalline (PDC) bit design as the number of blades and cutter size, bit nozzle total flowing area (TFA),and combined different drilled formations on the penetration rate. The well drilling data covered the 8-3/8" phase with more than 1000 readings for each input.The input data are the weight on bit (WOB),revolution per minute (RPM), torque (T), standpipe pressure (SPP),and mudflow rate (Q), mud weight (MWin), gamma-ray (GR), bit design codes as the number of blades and cutter size, bit nozzle, and total flowing area (TFA).The data training to testing ratio was 70: 30%. Another data set from the same filed was used to validate the model and the results showed high accuracy for the ANN-ROP model. The model provides a high performance and accuracy level with correlation coefficient (R) of 0.99, 0.98, and 0.98 and an average absolute percentage error (AAPE) of 4.36 %, 7.06 %, and 8.14 % for training, testing, and validating respectively.
Mahmoud, Ahmed Abdulhamid (King Fahd University of Petroleum & Minerals) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals) | Alsabaa, Ahmed (King Fahd University of Petroleum & Minerals) | Shehri, Dhafer Al (King Fahd University of Petroleum & Minerals)
ABSTRACT This study is aimed to develop a functional neural networks (FNN) model to estimate Estatic for sandstone formations as a function of the conventional well log data of the bulk formation density, compressional time, and shear time. 355 well log datasets from Well-A were used to train the FNN model which was then tested on another 237 datasets from Well-A and validated on 38 data points from Well-B. The developed FNN-based model predicted the Estatic for the training dataset with a very low average absolute percentage error (AAPE) of 0.78%, a very high correlation coefficient (R) of 0.9995, and a coefficient of determination (R) of 0.999. For the testing dataset, the Estatic was predicted with AAPE, R, and R of 0.85%, 0.9993, and 0.999, respectively. The optimized FNN model predicted the Estatic for the validation data with AAPE of 2.54%, R of 0.997, and R of 0.995. The obtained results confirmed the high accuracy of the developed FNN model in estimating the Estatic. 1. INTRODUCTION Young's modulus is a mechanical parameter that indicates the hardness of the rock samples when exposed to a uniaxial load (Fjaer et al., 2008). Static Young's modulus (Estatic) is a critical variable needed to build the earth geomechanical model (Chang et al., 2006), it is also used for fractures designing and mapping (Gatens et al., 1990; Meyer and Jacot, 2001). While drilling hydrocarbon wells, Estatic is also needed with other mechanical and petrophysical properties to make a full description of the in-situ stresses to ensure wellbore stability (Nes et al., 2012). Estatic varies significantly with the change in lithology (Howard and Fast, 1970; Fjaer et al., 2008). Estatic for shale is ranging from 0.1 to 1.0 MPsi, for limestone is between 8 to 12 MPsi, and for sandstone is between 2 to 10 MPsi (Howard and Fast, 1970). These ranges confirm the wide difference in Estatic from formation type to another and the huge change within the same lithology, therefore, it is necessary to estimate Estatic along the whole drilled hydrocarbon well.