Gowida, Ahmed (King Fahd University of Petroleum & Minerals) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals)
Formation density plays a central role to identify the types of downhole formations. It is measured in the field using density logging tool either via logging while drilling (LWD) or more commonly by wireline logging, after the formations have been drilled, because of operational limitations during the drilling process that prevent the immediate acquisition of formation density.
The objective of this study is to develop a predictive tool for estimating the formation bulk density (RHOB) while drilling using artificial neural networks (ANN). The ANN model uses the drilling mechanical parameters as inputs and petrophysical well-log data for RHOB as outputs. These drilling mechanical parameters including the rate of penetration (ROP), weight on bit (WOB), torque (T), standpipe pressure (SPP) and rotating speed (RPM), are measured in real time during drilling operation and significantly affected by the formation types. A dataset of 2,400 data points obtained from horizontal wells was used for training the ANN model. The obtained dataset has been divided into a 70:30 ratio for training and testing the model, respectively.
The results showed a high match with a correlation coefficient (R) between the predicted and the measured RHOB of 0.95 and an average absolute percentage error (AAPE) of 0.71%. These results demonstrated the ability of the developed ANN model to predict RHOB while drilling based on the drilling mechanical parameters using an accurate and low-cost tool. The black-box mode of the developed ANN model was converted into white-box mode by extracting a new ANN-based correlation to calculate RHOB directly without the need to run the ANN model. The new model can help geologists to identify the formations while drilling. Also, by tracking the RHOB trends obtained from the model it helps drilling engineers avoid many interrupting problems by detecting hazardous formations, such as overpressured zones, and identifying the well path, especially while drilling horizontal sections. In addition, the continuous profile of RHOB obtained from the developed ANN model can be used as a reference to solve the problem of missing and false logging data.
Tariq, Zeeshan (King Fahd University of Petroleum & Minerals) | Mahmoud, Mohamed (King Fahd University of Petroleum & Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals)
Carbonate rocks have a very complex pore system due to the presence of interparticle and intra-particle porosities. This makes the acquisition and analysis of the petrophysical data, and the characterization of carbonate rocks a big challenge. In this study, functional network tool is used to develop a model to predict water saturation using petrophysical well logs as input data and the dean-stark measured water saturation as an output parameter. The data comprised of more than 200 well log points corresponding to available core data. The developed FN model was optimized by using several optimization algorithms such as differential evolution (DE), particle swarm optimization (PSO), and covariance matrix adaptation evolution strategy (CMAES). FN model optimized with PSO found to be the most robust artificial intelligence (AI) model to predict water saturation in carbonate rocks. The results showed that the proposed model predicted the water saturation with an accuracy of 97% when related to the experimental core values. In this study in addition to the development of optimized FN model, an explicit empirical correlation is also extracted from the optimized FN model. To validate the proposed correlation, three most commonly applied water saturation models (Simandoux, Bardon and Pied model, Fertl and Hammack Model, Waxman-Smits, and Indonesian) from literature were selected and subjected to same well log data as the AI model to estimate water saturation. The estimated water saturation values for AI and other saturation models were then compared with experimental values of testing data and the results showed that AI model was able to predict water saturation with an error of less than 5% while the saturation models did the same with lesser accuracy of error up to 50%. This work clearly shows that computer-based machine learning techniques can determine water saturation with a high precision and the developed correlation works extremely well in prediction mode.
Ahmed S, Abdulmalek (King Fahd University of Petroleum & Minerals) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals) | Ali, Abdulwahab Z (King Fahd University of Petroleum & Minerals) | Mahmoud, Mohamed (King Fahd University of Petroleum & Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals)
Rate of Penetration (ROP) means how fast the drilling bit is drilling through the formations. It is known that in the oil and gas industry, most of the well cost is taken by the drilling operations. So, it is very crucial to drill carefully and improve the drilling processes. Nevertheless, it is hard to know the influence of every single parameter because most of the drilling parameters depend on each other, and altering an individual parameter will have an impact on the other. Due to the difficulty of the drilling operations, up to the present time, there is no dependable model that can estimate the ROP correctly. Consequently, using the artificial intelligence (AI) in the drilling is becoming more and more applicable because it can consider all the unknown parameters in building the model. In this work, a real filed data that contain the real time surface drilling parameters and the drilling fluid properties were utilized by fuzzy logic (FL) to estimate the rate of penetration. The achieved results proved that fuzzy logic technique can be applied effectively to estimate the rate of penetration accurately with R 0.97 and AAPE 7.3%, which outperformed the other ROP models. The developed AI models also have the advantage of using less input parameters than the previous ROP models.
Ahmed S., Abdulmalek (King Fahd University of Petroleum & Minerals) | Mahmoud, Ahmed Abdulhamid (King Fahd University of Petroleum & Minerals) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals) | Mahmoud, Mohamed (King Fahd University of Petroleum & Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals)
Pore and fracture pressures are a critical formation condition that affects efficiency and economy of drilling operations. The knowledge of the pore and fracture pressures is significant to control the well. It will assist in avoiding problems associated with drilling operation and decreasing the cost of drilling operation. It is essential to predict pore and fracture pressures accurately prior to drilling process to prevent various issues for example fluid loss, kicks, fracture the formation, differential pipe sticking, heaving shale and blowouts. Many models are used to estimate the pore and fracture pressures either from log information, drilling parameters or formation strengths. However, these models have some limitations such as some of the models can only be used in clean shales, applicable only for the pressure generated by under-compaction mechanism and some of them are not applicable in unloading formations. Few papers used artificial intelligence (AI) to estimate the pore and fracture pressures. In this work, a real filed data that contain the log data and real time surface drilling parameters were utilized by support vector machine (SVM) to predict the pore and fracture pressures.
Mustafa, Ayyaz (King Fahd University of Petroleum and Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum and Minerals) | Abouelresh, Mohamed Ibrahim (King Fahd University of Petroleum and Minerals) | Sahin, Ali (King Fahd University of Petroleum and Minerals)
The lower Silurian Qusaiba Shale is one of the major source rocks for Paleozoic petroleum reservoirs in Saudi Arabia and is considered a potential shale gas resource. The study aims to evaluate the prospectivity and improve the production potential of Qusaiba shale by defining the lithofacies and mineralogy as controlling factors for brittleness and other mechanical parameters.
The continuous 30 feet subsurface cores and log data of Qusaiba Shale from Rub’ Al-Khali Basin were utilized for the study. Geological characteristics on the core were fully demonstrated in terms of size, mineralogy, color, primary structures and diagenetic features to identify lithofacies. In addition, 30 thin sections were used to study micro scale geological characteristics. The powder X-ray diffraction (XRD) was used to determined the mineralogical compositions. Surface morphology visualization and elemental analysis were performed using the scanning electron microscope supplemented with energy dispersive spectroscopy (SEM-EDS). Acoustic velocity measurements and compressive strength tests were performed on 15 core plugs (5 from each lithofacies).
Based on the above-mentioned analyses, three lithofacies were identified: (1) Micaceous laminated organic-rich mudstone facies (Lithofacies-I), (2) Laminated clay-rich mudstone facies (Lithofacies-II), and (3) Massive siliceous mudstone facies (Lithofacies-III). Mineralogical composition resulted in variable amounts of quartz ranging from 39 to 40, 45-55 and 60 to 78% for Lithofacies-I, II and III, respectively. Lithofacies-I having relatively lower quartz and higher clay percentage and total organic content (12% by volume) exhibited low stiffness. Mineralogy- and elastic parameters-based brittleness indices exhibited ductile behavior of this lithofacies. Lithofacies-II with relatively higher quartz (45 to 55%) and lower clay contents and TOC (3-5%) than Lithofacies-I resulted in relatively higher stiffness and brittleness. The brittleness index exhibited brittle behavior for silica rich Lithofacies-III (low TOC< 3%) as reflected by Young's modulus (average 32 GPa) and low Poisson's ratio (average 0.25). Hence, it is concluded that mineralogy and geological characteristics are the main controlling factors on mechanical properties and brittleness. The integration of three essential disciplines i.e. geology, mineralogy and geomechanics, plays the key role to better evaluate the production potential by highlighting the sweet spots within the heterogeneous shale gas reservoirs.
Young's modulus and Poisson's ratio describe the elastic behavior of rock. It is extremely important to determine these parameters in order to minimize the risk associated with the oil and gas well engineering. The estimation helps in several areas of drilling and production such as well placement optimization, design of completions, mud weight calculations, and hydraulic fracture geometry. Each one of these factors play a part in maximizing the recovery of hydrocarbons and in taking crucial decisions for an appropriate field development strategy.
Poisson's ratio is second most important parameter in understanding the elastic behavior of the rock and plays a critical role in almost all processes such as drilling, reservoir simulation, and production. It is an essential component in geomechanical earth model (GEM).
The Poisson's ratio is estimated based on empirical models and artificial intelligence models. These models are construction from data that has different types of uncertainties. This paper presents an Artificial Neural Network (ANN) as well as Fuzzy Logic Type-2 (FLT2) approach for prediction of static Poisson's ratio. FLT2 is able to incorporate the uncertainties in measurements and still give a robust solution to a given problem. Well log data is used as input and laboratory determined static Poisson's ratio is used as output in the artificial intelligence (AI) tool. The data were collected from a range of experiments conducted on carbonate rocks covering a wide range of input and output values.
The model takes care of uncertainties in the input and output data and is therefore a better approach in establishing a relationship between them and in predicting static Poisson's ratio for new input data.
Ahmed S, Abdulmalek (King Fahd University of Petroleum & Minerals) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals) | Ali, Abdulwahab Z (King Fahd University of Petroleum & Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals) | Mahmoud, Mohamed (King Fahd University of Petroleum & Minerals)
Fracture pressure is a critical formation condition that affects efficiency and economy of drilling operations. The knowledge of the fracture pressure is significant to control the well. It will assist in avoiding problems associated with drilling operation and decreasing the cost of drilling operation. It is essential to predict fracture pressure accurately prior to drilling process to prevent various issues for example fluid loss, kicks, fracture the formation, differential pipe sticking, heaving shale and blowouts.
Many models are used to estimate the fracture pressure either from log information or formation strengths. However, these models have some limitations such as some of the models can only be used in clean shales, applicable only for the pressure generated by under-compaction mechanism and some of them are not applicable in unloading formations. Few papers used artificial intelligence (AI) to estimate the fracture pressure. In this work, a real filed data that contain only the real time surface drilling parameters were utilized by artificial neural network (ANN) to predict the fracture pressure.
The results indicated that artificial neural network (ANN) predicted the fracture pressures with an excellent precision where the coefficient of determination (R2) is greater than 0.99. In addition, the artificial neural network (ANN) was compared with other fracture pressure models such as Matthews and Kelly model, which is one of the most used models in the prediction of the fracture pressure in the field. Artificial neural network (ANN) model outperformed the fracture models by a high margin and by its simple prediction of fracture pressure where it can predict the fracture pressure from only the real time surface drilling parameters, which are easily available.
Tariq, Zeeshan (King Fahd University of Petroleum and Minerals) | Mahmoud, Mohamed (King Fahd University of Petroleum and Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum and Minerals) | Al-Nakhli, Ayman (Saudi Aramco) | Bataweel, Mohammed (Saudi Aramco)
The enormous resources of hydrocarbons hold by unconventional reservoirs across the world along with the growing oil demand make their contributions to be most imperative to the world economy. However, one of the major challenges faced by oil companies to produce from the unconventional reservoirs is to ensure economical production of oil. Unconventional reservoirs need extensive fracturing treatments to produce commercially viable hydrocarbons. One way to produce from these reservoirs is by drilling horizontal well and conduct multistage fracturing to increase stimulated reservoir volume (SRV), but this method of increasing SRV is involved with higher equipment, material, and operating costs.
To overcome operational and technical challenges involved in horizontal wells multistage fracturing, the alternative way to increase SRV is by creating multiple radial fractures by performing pulse fracturing. Pulse fracturing is a relatively new technique, can serve as an alternative to conventional hydraulic fracturing in many cases such as to stimulate naturally fractured reservoirs to connect with pre-existing fractures, to stimulate heavy oil with cold heavy oil production technique, to remove condensate banking nearby wellbore region, and when to avoid formation damage near the vicinity of the wellbore originated due to perforation. Pulse fracturing is not involved with injecting pressurized fluids into the reservoir, so it is also a relatively cheaper technique.
The purpose of this paper is to present a general overview of the pulse fracturing treatment. This paper will give general idea of the different techniques and mechanisms involved in the application of pulse fracturing technique. The focus of this review will be on the comparison of different fracturing techniques implemented normally in the industry. This study also covers the models developed and applied to the simulation of complex fractures originated due to pulse fracturing.
Elhaj, Murtada (Memorial University of Newfoundland) | Abdullatif, Osman (King Fahd University of Petroleum and Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum and Minerals) | Hassan, Amjed (King Fahd University of Petroleum and Minerals) | Sultan, Abdullah (King Fahd University of Petroleum and Minerals)
The science of Acoustics deals with the propagation of mechanical waves in the three phases of materials, solids, liquids, and gases. In exploration and reservoir engineering, acoustic wave velocities play an essential role in reservoir description. The primary challenge in the initial evaluation and characterization of reservoirs is related to the understanding of its geology, petrophysics, and geomechanics. Therefore, an accurate estimation of acoustic wave velocities and rock porosity is essential for better reservoir description and performance as well as a better forecast of seismic properties. In this reseach, the primary objective is to analyze the texture, mineralogy, porosity and permeability data of outcrop carbonate rock samples to study the impact of confining pressure on wave velocities. Furthermore, an empirical correlation is proposed for relating porosity with acoustic properties.
Ninety outcrops samples are collected from Dam Formation in Al-Lidam area in Eastern Province, Saudi Arabia to develop a correlation. The carbonate samples varies from mudstone to grainstone facies. The samples are collected, prepared, and tested for this experimental study based on API standards. Compressional and shear wave velocities of carbonate rocks are measured under dry and fully brine-saturated conditions for 5 to 25 MPa effective confining pressures at room temperature. Moreover, porosity and permeability are measured using three different techniques, viz., AP-608 Automated Porosimeter-Permeameter, Helium Porosimeter, and thin section technique. Finally, the results are compared with those from other studies related to the same area.
A state-of-the-art review is presented on seismic properties, relationship with porosity and acoustics in addition to the current trend and the future challenges in the area. The laboratory investigations for this study reveals that Al-Lidam area has different types of facies. The results also show that both compressional and shear wave velocities increase as the confining pressure on the dry samples increase. However, the compressional wave velocities increased and the shear wave velocities decreased with confining pressure under fully saturated conditions. A new correlation is presented for carbonate rocks to predict porosity from acoustic wave velocities.
This study will help in improving the exploration efforts as well as give a better explanation for reservoir characterization, facies recognition, geophysical interpretation, and engineering calculations. This attempt will open a new research area for engineers and scientists to study the effect of variation in different properties on wave velocities.
Khan, Mohammad Rasheed (King Fahd University of Petroleum & Minerals) | Alnuaim, Sami (ARAMCO) | Tariq, Zeeshan (King Fahd University of Petroleum & Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals)
Well production rate is one of the most critical parameters for reservoir/production engineers to evaluate performance of the system. Given this importance, however, monitoring of production rates is not usually carried out in real time. Some cases flowmeters are used which are known to carry their own inherent uncertainties. The industry, thus, relies on the use of correlations to allocate production to wells. Over time, it has been realized that the generally used correlations are not effective enough due to multiple technical and economic issues.
The focus of this work is to utilize machine learning (ML) algorithms to develop a correlation that can accurately predict oil rate in artificial gas lift wells. The reason for using these algorithms is to provide a solution that is simple, easy to use and universally applicable. Various intelligent algorithms are employed, namely; Artificial Neuro Fuzzy Inference Systems (ANFIS), and Support Vector Machines (SVM), along with the development of Artificial Neural Network providing a usable equation to be applied on any field, hence demystifying the black-box reputation of artificial intelligence. In addition, non-linear regression is also performed to compare the results with ML methods.
Data cleansing and data-reduction were carried out on the dataset comprising of 1500 separator test points. This practice yielded in only the common wellhead parameters to be used as input for the model. All ML models were compared with the non-linear regression model and with previously derived empirical models to gauge the effectiveness of the work. The newly developed model using ANN shows that it can predict the flow-rate with 99% accuracy. This is an interesting outcome, as such accuracy has not been reported in literature usually.
The results of this study show that the correlation developed using ANN outperforms all the current empirical correlations, moreover, it also performs multiple times better in comparison to previously developed AI models. In addition, this work provides a functional equation that can be used by anyone on their field data, thereby removing any ambiguities or confusion related to the concept of artificial intelligence expertise and software. This effort puts forth an industrial insight into the role of data-driven computational models for the production reconnaissance scheme, not only to validate the well tests but also as an effective tool to reduce qualms in production provisions.