Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
fuzzy logic
A Data Driven Machine Learning Approach to Predict the Nuclear Magnetic Resonance Porosity of the Carbonate Reservoir
Ayyaz Mustafa, Ayyaz (King Fahd University of Petroleum and minerals) | Zeeshan Tariq, Zeeshan (King Fahd University of Petroleum and minerals) | Mohamed Mahmoud, Mohamed (King Fahd University of Petroleum and minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum and minerals)
Abstract 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. Neutron porosity log and sonic porosity logs are usually considered as less accurate compared to the NMR porosity. Neutron-density porosity depends on parameters related to rock matrix which cause the inaccurate estimation of the porosity in special cases suchlike dolomitized and fractured zone. Whereas NMR porosity is based on the amount of hydrogen nuclei in the pore spaces and is independent of the rock minerals and is related to the pore spaces only. In this study, different machine learning algorithms are used to predict the Nuclear Magnetic Resonance (NMR) porosity. Conventional well logs such as Gamma ray, neutron porosity, deep and shallow resistivity logs, sonic traveltime, and photoelectric logs were used as an input parameter while NMR porosity log was set as an output parameter. More than 3500 data points were collected from several wells drilled in a giant carbonate reservoir of the middle eastern oil reservoir. Extensive data exploratory techniques were used to perform the data quality checks and remove the outliers and extreme values. Machine learning techniques such as random forest, deep neural networks, functional networks, and adaptive decision trees were explored and trained. The tuning of hyper parameters was performed using grid search and evolutionary algorithms approach. To optimize further the results of machine learning models, k-fold cross validation criterion was used. The evaluation of machine learning models was assessed by average absolute percentage error (AAPE), root mean square error (RMSE), and coefficient of correlation (R). The results showed that deep neural network performed better than the other investigated machine learning techniques based on lowest errors and highest R. The results showed that the proposed model predicted the NMR porosity with an accuracy of 94% when related to the actual values. In this study in addition to the development of optimized DNN model, an explicit empirical correlation is also extracted from the optimized model. The validation of the proposed model was performed by testing the model on other wells, the data of other wells were not used in the training. This work clearly shows that computer-based machine learning techniques can determine NMR porosity with a high precision and the developed correlation works extremely well in prediction mode.
- Geology > Mineral (0.50)
- Geology > Rock Type > Sedimentary Rock > Carbonate Rock (0.46)
- Geology > Geological Subdiscipline > Economic Geology > Petroleum Geology (0.34)
Data Driven Intelligent Modeling to Estimate Adsorption of Methane Gas in Shales
Kalam, Shams (King Fahd University of Petroleum and Minerals) | Abu-Khamsin, Sidqi A. (King Fahd University of Petroleum and Minerals) | Khan, Mohammad Rasheed (Schlumberger) | Abbasi, Asiya (Halliburton) | Asad, Abdul (Sprint Oil & Gas Services) | Khan, Rizwan Ahmed (King Fahd University of Petroleum and Minerals)
Abstract Artificial intelligence is a smart tool widely used in Petroleum engineering. Adaptive Neuro-Fuzzy Inference System (ANFIS) is an artificial intelligence technique that is a hybrid between Artificial Neural Networks (ANN) and fuzzy logic. In this paper, both ANN and ANFIS were applied to propose a new methodology based on intelligent algorithms to predict adsorption of methane gas in shale. Feed-Forward Neural Network and subtractive clustering were applied to correlate adsorption with several parameters. These include temperature, pressure, moisture content, and total organic content (TOC). A real data set collected from the literature, which includes about 350 data points, was used in the development of a new empirical correlation. The set was divided into a 70:30 ratio for training and testing, respectively. The average absolute percentage error, correlation coefficient, and mean squared error were considered in the error metrics to obtain the best possible model. The results show that methane adsorption can be efficiently correlated with the inputs using both machine learning tools. Using ANN, the correlation coefficient for both testing and training data was more than 99%. A detailed sensitivity analysis for the ANN model is also provided in this paper.
- Research Report > New Finding (0.49)
- Research Report > Experimental Study (0.48)
- Asia > China > Sichuan > Sichuan Basin (0.99)
- South America > Brazil > Brazil > South Atlantic Ocean (0.91)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Fuzzy Logic (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
Virtual Multiphase Flowmetering Using Adaptive Neuro-Fuzzy Inference System (ANFIS): A Case Study of Hai Thach-Moc Tinh Field, Offshore Vietnam
Trung, Tran Ngoc (Bien Dong Petroleum Operating Company) | Truong, Trieu Hung (Ha Noi University of Mining and Geology) | Tung, Tran Vu (Bien Dong Petroleum Operating Company (Corresponding author)) | Hai, Ngo Huu (Bien Dong Petroleum Operating Company) | Khoa, Dao Quang (Bien Dong Petroleum Operating Company) | Tinh, Nguyen Thanh (Bien Dong Petroleum Operating Company) | Son, Hoang Ky (Bien Dong Petroleum Operating Company)
Summary For any oil and gas company, well-testing and performance-monitoring programs are expensive because of the cost of equipment and personnel. In addition, it may not be possible to obtain all of the necessary data for a reservoir for a period of time because of production demand constraints or changes in surface process conditions. To overcome these challenges, there are many studies on the implementation and value of virtual flowmetering (VFM) for real-time well performance prediction without any need for a comprehensive well-testing program. This paper presents the VFM model using an adaptive neuro-fuzzy inference system (ANFIS) at Hai Thach-Moc Tinh (HT-MT) gas-condensate field, offshore Vietnam. The ANFIS prediction model can tune all its membership functions (MFs) and consequent parameters to formulate the given inputs to the desired output with minimum error. In addition, ANFIS is a successful technique used to process large amounts of complex time series data and multiple nonlinear inputs-outputs (Salleh et al. 2017), thereby enhancing predictability. The authors have built ANFIS models combined with large data sets, data smoothing, and k-fold cross-validation methods based on the actual historical surface parameters such as choke valve opening, surface pressure, temperature, the inlet pressure of the gas processing system, etc. The prediction results indicate that the local regression โloessโ data smoothing method reduces the processing time and gives both clustering algorithms the best results among the different data preprocessing techniques [highest value of R and lowest value of mean squared error (MSE), error mean, and error standard deviation]. The k-fold cross-validation technique demonstrates the capability to avoid the overfitting phenomenon and enhance prediction accuracy for the ANFIS subtractive clustering model. The fuzzy C-mean (FCM) model in the present study can predict the gas condensate production with the smallest root MSE (RMSE) of 0.0645 and 0.0733; the highest coefficient of determination () of 0.9482 and 0.9337; and the highest variance account of 0.9482 and 0.9334 for training and testing data, respectively. Applied at the HT-MT field, the model allows the rate estimation of the gas and condensate production and facilitates the virtual flowmeter workflow using the ANFIS model.
- Asia > Vietnam (1.00)
- North America > United States > Texas (0.68)
Application of Artificial Intelligence To Predict Time-Dependent Mud-Weight Windows in Real Time
Phan, Dung T. (Aramco Americas: Aramco Research CenterโHouston) | Liu, Chao (Aramco Americas: Aramco Research CenterโHouston) | AlTammar, Murtadha J. (Saudi Aramco) | Han, Yanhui (Aramco Americas: Aramco Research CenterโHouston) | Abousleiman, Younane N. (University of Oklahoma)
Summary Selection of a safe mud weight is crucial in drilling operations to reduce costly wellbore-instability problems. Advanced physics models and their analytical solutions for mud-weight-window computation are available but still demanding in terms of central-processing-unit (CPU) time. This paper presents an artificial-intelligence (AI) solution for predicting time-dependent safe mud-weight windows and very refined polar charts in real time. The AI agents are trained and tested on data generated from a time-dependent coupled analytical solution (poroelastic) because numerical solutions are prohibitively slow. Different AI techniques, including linear regression, decision tree, random forest, extra trees, adaptive neuro fuzzy inference system (ANFIS), and neural networks are evaluated to select the most suitable one. The results show that neural networks have the best performances and are capable of predicting time-dependent mud-weight windows and polar charts as accurately as the analytical solution, with 1/1,000 of the computer time needed, making them very applicable to real-time drilling operations. The trained neural networks achieve a mean squared error (MSE) of 0.0352 and a coefficient of determination (R) of 0.9984 for collapse mud weights, and an MSE of 0.0072 and an R of 0.9998 for fracturing mud weights on test data sets. The neural networks are statistically guaranteed to predict mud weights that are within 5% and 10% of the analytical solutions with probability up to 0.986 and 0.997, respectively, for collapse mud weights, and up to 0.9992 and 0.9998, respectively, for fracturing mud weights. Their time performances are significantly faster and less demanding in computing capacity than the analytical solution, consistently showing three-orders-of-magnitude speedups in computational speed tests. The AI solution is integrated into a deployed wellbore-stability analyzer, which is used to demonstrate the AIโs performances and advantages through three case studies.
- Asia > Middle East > Saudi Arabia (0.46)
- North America > United States > California (0.46)
- North America > Canada > Alberta (0.28)
- North America > United States > Texas (0.28)
- Research Report > New Finding (0.48)
- Research Report > Experimental Study (0.34)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > ร sgard Formation (0.99)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > Svarte Formation (0.99)
- Europe > Norway > North Sea > Central North Sea > South Viking Graben > PL 046 > Block 15/9 > Volve Field > Shetland Group > Sleipner Formation (0.99)
- (17 more...)
Efficiency and Effectiveness - A Fine Balance: An Integrated System to Improve Decisions in Real-Time Hydraulic Fracturing Operations
Mondal, Somnath (Shell Exploration & Production Co.) | Garusinghe, Ashan (Shell Canada Ltd.) | Ziman, Sebastian (Shell Global Solutions International B.V.) | Abdul-Hameed, Muhammed (Shell Global Solutions International B.V.) | Paleja, Rakesh (Shell Global Solutions International B.V.) | Jones, Matthew (Shell Global Solutions International B.V.) | Limbeck, Jan (Shell Global Solutions International B.V.) | Bartmann, Bryce (Shell Global Solutions International B.V.) | Young, Jeremy (Ely & Associates) | Shanley, Kent (Ely & Associates) | Cardwell, Bonner (Ely & Associates) | Klobodu, Humphrey (Ely & Associates) | Huckabee, Paul (Shell Exploration & Production Co.) | Ugueto, Gustavo (Shell Exploration & Production Co.) | Ledet, Christopher (Shell Exploration & Production Co.)
Abstract Hydraulic fracturing is a key driver of well productivity and field development planning, in addition to being the most significant portion of capex in shales. Recent breakthroughs in connectivity and digital technologies have enabled the monitoring and analyses of frac operations in real-time. However, most of the digitalization effort to date has been focused on increasing operational efficiency to reduce cost. Without an equal consideration for creating effective fracture geometries, this may lead to poor resource recovery and leave significant value behind. In this paper, we - 1) demonstrate the need to balance between optimizing fracture efficiency and effectiveness; 2) present an integrated system for frac optimization using real-time, historical data along with organizational knowledge; and 3) discuss the challenges of setting up such a system and key considerations, along with examples of large, untapped potential that can be unlocked with data science to deliver real value. Currently, several service providers exist to stream frac data with interactive analytics dashboards. While they offer some customizability, most do not provide a true frac optimization platform that goes beyond frac monitoring and analytics geared towards efficiency and cost indicators. We are still dependent on an individual operator's experience and rules of thumb to make job decisions during a frac stage. In this paper, a real-time optimization workflow is presented that uses advanced data science and statistical techniques to interpret and predict time-series treatment data, integrate historical and contextual information, and honor basin-specific knowledge that has been gathered and tested over the years. Examples are presented from diagnostic pads that highlight the need for balancing stimulation effectiveness with efficiency. We demonstrate a platform to host and execute an ensemble of models and visualizations that communicate actionable insights to an operator within minutes of identifying an event, gather feedback, and learn. Results from field testing show that our system accelerates the learning curve, enables consistent decision making by operators, and can generate significant cost savings. Finally, we share learnings from our digitalization journey. Completion and stimulation expenses account for approximately half of an unconventional well cost. Automated decision making for real-time fracture treatment is the holy grail of digital completions in shales. However, a blind pursuit of efficiency may lead to sub-par fracture treatments and significant value erosion for shale assets. We present an integrated framework that connects real-time data and organizational knowledge to guide an operator to pump the best frac stage while reacting to formation response within a set of constraints. To the best of our knowledge, this is the first paper to describe the general architecture and demonstrate the viability of such a system that relies only on standard wellhead measurements during fracturing.
- North America > United States (1.00)
- North America > Canada > Alberta (0.28)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Architecture > Real Time Systems (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Fuzzy Logic (0.68)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.46)
Integrated spatial geotechnical and geophysical evaluation tool for engineering projects: A 3D example at a challenging urban environment in the city of Athens, Greece (Sixth International Conference on Engineering Geophysics, Virtual, 25โ28 October 2021)
Orfanos, Christos (National Technical University of Athens) | Leontarakis, Konstantinos (National Technical University of Athens) | Apostolopoulos, George (National Technical University of Athens) | Zevgolis, Ioannis (National Technical University of Athens)
A novel Integrated Spatial Geophysical & Geotechnical evaluation algorithm (I.S.G.E) has been developed for the estimation of geotechnical parameters spatial distribution using high-resolution geophysical methods. The proposed algorithm is based on fuzzy logic and the final output is the prediction of the 2D or 3D distribution of a geotechnical parameter in a survey area. The main advantage of the developed I.S.G.E tool is that itcan propagate the geotechnical sparse or even point information from 1D to 2D or even 3D spacethrough a fully automatic unbiased statistical procedure. In this study, the I.S.G.E is implementedand evaluated at a challenging urban area before the rehabilitation of an existing building in the city of Athens, Greece. The automatic derived 3D models depicting the spatial distribution of specific geotechnical parameters, even under the existing building, providing engineers with an additional interpretation tool for a better understanding of subsurface conditions of the survey area.
- Geophysics > Seismic Surveying > Surface Seismic Acquisition (0.70)
- Geophysics > Seismic Surveying > Seismic Processing (0.48)
Artificial intelligence (AI) is transforming the way we live, work, and interact. From our personal lifestyles through our social engagements to the way we conduct our private and corporate businesses, AI is altering our methodologies and changing the landscape of end products. From the age-old medical expert systems and intelligent search engines to intelligent chatbots and predictive models, the enthusiasm for AI practice is growing rapidly. This article starts with a brief overview of AI, the key elements, and its recent advancements. It concludes with a few suggestions for getting started.
- Information Technology > Artificial Intelligence > Natural Language (1.00)
- Information Technology > Artificial Intelligence > Machine Learning (1.00)
- Information Technology > Data Science > Data Mining (0.90)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Fuzzy Logic (0.48)
Deterministic Modeling to Predict the Natural Gas Density Using Artificial Neural Networks
Shreif, Mariam (Lebanese American University) | Kalam, Shams (King Fahd University of Petroleum & Minerals) | Khan, Mohammad Rasheed (Schlumberger) | Khan, Rizwan Ahmed (King Fahd University of Petroleum & Minerals)
Abstract During the past decades, several research studies have been made to unfold the immense and diversified benefits of the innovative applications of machine learning (ML) techniques in the petroleum industry. For instance, machine learning algorithms were applied to estimate the various physical properties of natural gas. Natural gas density is considered an indispensable metric that influences the determination of several variables necessary for analyzing natural gas systems. In this work, the Artificial neural network (ANN), a machine learning technique, was applied to estimate natural gas density incorporating the influencing factors. The ANN model was also compared with another ML technique, namely the Adaptive Neuro-Fuzzy Inference System (ANFIS). A mathematical form has been also presented using ANN. A real data set was taken from the literature, comprised of about 4500 data points assimilating three influencing input variables, including pseudo-reduced pressure (PPr), pseudo-reduced temperature (TPr), and molecular weight (Mw). The PPr and TPr are obtained by calculating the averages of the sample gas critical pressures and critical temperatures. A complicated nonlinear relationship exists between the three influencing variables and the gas density. The data set was divided into a 70:30 ratio for training and testing the model, respectively. Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANN) were applied to train and test the model. Absolute average percentage error (AAPE), coefficient of determination (R), and root mean squared error (RMSE) were considered in the error metrics to acquire the best possible model. LevenbergโMarquardt backpropagation algorithm was employed for ANN, while subtractive clustering was used for ANFIS. Results showed that natural gas density can be well correlated with numerous inputs using machine learning tools (ANN and ANFIS). The input parameters include Ppr, Tpr, and Mw, as mentioned above. ANN performed better than ANFIS. The network was adjusted against the training sub-set to set-up weights and biases covering each node. R for both testing and training data was more than 99%, while AAPE was around 4% for both cases. Moreover, a detailed mathematical scheme for the ANN model is also provided in this paper.
- Research Report > New Finding (0.48)
- Overview > Innovation (0.48)
- North America > United States > Louisiana > Grand Bay Field (0.99)
- North America > United States > Texas > Fort Worth Basin > Katz Field (0.93)
Abstract This investigation presents a powerful predictive model to determine crude oil formation volume factor (FVF) using state-of-the-art artificial intelligence (AI) techniques. FVF is a vital pressure-volume-temperature (PVT) parameter used to characterize hydrocarbon systems and is pivotal to reserves calculation and reservoir engineering studies. Ideally, FVF is measured at the laboratory scale; however, prognostic tools to evaluate this parameter can optimize time and cost estimates. The database utilized in this study is obtained from open literature and covers statistics of crude oils of the Middle East region. Multiple AI algorithms are considered, including Artificial Neural Networks (ANN) and Artificial Neural Fuzzy Inference Systems (ANFIS). Models are developed utilizing an optimization strategy for various parameters/hyper-parameters of the respective algorithms. Unique permutations and combinations for the number of perceptron and their resident layers is investigated to reach a solution that provides the most optimum output. These intelligent models are produced as a function of the parameters intrinsically affecting FVF; reservoir temperature, solution GOR, gas specific gravity, bubble point pressure, and crude oil API gravity. Comparative analysis of developed AI models is performed using visualization/statistical analysis, and the best model is pointed out. Finally, the mathematical equation extraction to determine FVF is accomplished with the respective weights and bias for the model presented. Graphical analysis is used to evaluate the performance of developed AI models. The results of scatter plots showed most of the points are lying on the 45 degree line. Moreover, during this study, an error metric is developed comprising of multiple analysis parameters; Average absolute percentage error (AAPE), Root Mean Squared Error (RMSE), coefficient of determination (R). All models investigated are tested on an unseen dataset to prevent a biased model's development. Performance of the established AI models is gauged based on this error metric, demonstrating that ANN outperforms ANFIS with error within 1% of the measured PVT values. A computationally derived intelligent model provides the strongest predictive capabilities as it maps complex non-linear interactions between various input parameters leading to FVF.
A Fuzzy Method to Quantitatively Evaluate the Effect of Foam Deliquification in Gas Wells
Jia, Min (PetroChina RIPED) | Zhang, Jianjun (PetroChina RIPED) | Han, Xiuling (PetroChina RIPED) | Shi, Junfeng (PetroChina RIPED) | Guo, Donghong (PetroChina RIPED) | Cao, Guangqiang (PetroChina RIPED) | Li, Jun (PetroChina RIPED) | Li, Nan (PetroChina RIPED) | Wang, Haoyu (PetroChina RIPED) | Zhang, Yi (PetroChina RIPED) | Liu, Yan (PetroChina RIPED)
Abstract Deliquification is the primary technique for stabilizing gas production and improving gas recovery in gas fields producing water, and foam deliquification is the key subject of research for the purpose of enhancing gas production and cutting down cost. However, there is no systematic method to evaluate and compare the effects of foam deliquification in gas wells in various conditions. Aiming at the above problem, a new fuzzy quantitative evaluation method for foam deliquification is proposed. The method focus on four indicators, namely, rate of change in daily gas production, rate of change in daily water production, rate of change in the difference between tubing and casing pressures, and rate of change in daily injection cost. The evaluation results are calculated by the linear analysis, hierarchy analysis and fuzzy relation synthesis operator. The method has been applied to 30 foam deliquification wells in Sulige gas field and Chongqing gas field, and the comprehensive index of foam deliquification effect is calculated. The advantage of this method is that the technical and economic factors affecting foam deliquifiction, the membership relationships of various indicators, as well as the weight coefficients of the indicators are integratedly considered. It can be used for comprehensive evaluation and quantitative comparison of foam deliquification effects in gas wells in various conditions, assisting in determining candidate wells for foam deliquification, and guiding the selection of foaming agents.
- Asia > China > Inner Mongolia (0.26)
- Asia > China > Chongqing Province > Chongqing (0.26)
- Asia > China > Sichuan > Sichuan Basin > Zhongba Field (0.99)
- Asia > China > Qinghai > Qaidam Basin > Sebei Field (0.99)
- Asia > China > Inner Mongolia > Ordos Basin > Sulige Field > Ordos Formation (0.99)
- (2 more...)