Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Abstract One of the biggest challenges facing oil and gas companies is to lower the cost of drilling operations. The most critical parameter affecting drilling cost is the rate of penetration (ROP). Improving the ROP and reducing the drilling cycle can be significant for companies to reduce drilling costs and risks, thus enhancing market competitiveness. In the present study, we evaluate the accuracy and effectiveness of different machine learning algorithms for directional wells. We collect many field drilling datasets such as bit type, bit drilling time, revolutions per minute (RPM), weight on bit, torque, formation type, rock properties, and hydraulic and drilling mud properties. We input these data to the machine learning model to be trained, validated, and tested for predicting ROP. The machine learning models we used include linear regression, Artificial Neural Networks (ANN), Support Vector Machine (SVM), and Random Forest (RF) algorithms. In this study, we implement the Genetic Algorithm (GA) to optimize the hyper-parameters of the five machine learning algorithms. We also apply Savitzky-Golay (SG) smoothing filter to reduce the noise in the original dataset. We use accuracy metrics such as root mean square error, mean absolute error, and regression coefficient (R) to compare the accuracy of several machine learning models. At last, we select the best-performing algorithm as the prediction tool for ROP. We conduct 50 cases for each machine learning model, where we evaluate the performance of the models and measure the time required for the models to be trained for the prediction tasks. The comparative study shows that implementing the GA optimization algorithm increased the accuracy of individual ROP models. We find that optimizing only a few hyper-parameters can significantly improve the machine modelsโ accuracy. We also compare the results from the model trained by the data processed with the SG smoothing filter with those trained by the original data. The study demonstrates that the SG algorithm effectively improves the accuracy of the machine learning models. Among the four machine learning models, ANN has the highest accuracy after GA optimization, reaching 97% on average. The overall training time for all four algorithms is between two and four minutes, considered a reasonable time frame for a real-time training and prediction task. We compare several machine learning methodsโ accuracies in predicting ROP in real-time. We find that ML-based prediction models, especially ANN with hyper-parameters optimized by Genetic Algorithm, can accurately predict ROP in real-time and provide the operator with suggestions for appropriate measures.
- Research Report > New Finding (0.35)
- Research Report > Experimental Study (0.34)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Regression (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Support Vector Machines (0.72)
A Machine Learning Approach for Gas Kick Identification
Obi, C. E. (Texas A&M University (Corresponding author)) | Falola, Y. (Texas A&M University) | Manikonda, K. (Texas A&M University) | Hasan, A. R. (Texas A&M University) | Hassan, I. G. (Texas A&M University Qatar) | Rahman, M. A. (Texas A&M University Qatar)
Summary Warning signs of a possible kick during drilling operations can either be primary (flow rate increase and pit gain) or secondary (drilling break and pump pressure decrease). Drillers rely on pressure data at the surface to determine in-situ downhole conditions while drilling. The surface pressure reading is always available and accessible. However, understanding or interpretation of this data is often ambiguous. This study analyzes significant kick symptoms in the wellbore annulus both under static (shut in) and dynamic (drilling/circulating) conditions. We used both supervised and unsupervised learning techniques for flow regime identification and kick prognosis. These include an artificial neural network (ANN), support vector machine (SVM), K-nearest neighbor (KNN), decision trees, K-means clustering, and agglomerative clustering. We trained these machine learning models to detect kick symptoms from the gas evolution data collected between the point of kick initiation and the wellhead. All the machine learning techniques used in this work made excellent predictions with accuracy greater than or equal to 90%. For the supervised learning, the decision tree gave the overall best results, with an accuracy of 96% for air influx cases and 98% for carbon dioxide influx cases in both static and dynamic scenarios. For unsupervised learning, K-means clustering was the best, with Silhouette scores ranging from about 0.4 to 0.8. The mass rate per hydraulic diameter and the mixture viscosity yielded the best types of clusters. This is because they account for the fluid properties, flow rate, and flow geometry. Although computationally demanding, the machine learning models can use the surface/downhole pressure data to relay annular flow patterns while drilling. There have been several recent advances in drilling automation. However, this is still limited to gas kick identification and handling. This work provides an alternative and easily accessible primary kick detection tool for drillers based on data at the surface. It also relates this surface data to certain annular flow regime patterns to better tell the downhole story while drilling.
- Europe (1.00)
- Asia > Middle East (0.93)
- North America > United States > Texas (0.46)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Support Vector Machines (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Clustering (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
Machine Learning for Determining Remaining Oil Saturation Based on C/O Spectral Logging in Multilayer String Cased Well
Qiu, Fei (School of Geosciences, China University of Petroleum) | Zhang, Feng (School of Geosciences, China University of Petroleum) | Liu, Zhiyuan (School of Geosciences, China University of Petroleum (East China)) | Xiao, Guiping (School of Geosciences, China University of Petroleum) | Fang, Qunwei (School of Geosciences, China University of Petroleum (East China))
Abstract Dynamic monitoring of reservoir can reflect the physical response of fluid underground and clarify the oil and water distribution of the production, which is important for the production management in the later stage of oil field. C/O logging plays an important role in downhole fluid dynamic monitoring, which can accurately determine the oil saturation of the formation. However, due to the limitations of neutron generator yield and measuring speed, the statistical fluctuation in low and medium pore formation are large, masking the difference of spectrum measured and C/O response in oil and water formations; meanwhile, complex borehole and string combinations as well as lithology cause high uncertainty of oil-bearing saturation interpretation by conventional C/O interpretation methods. To improve the signal-to-noise ratio of measurements and the accuracy of oil-bearing saturation interpretation under complex borehole and formation conditions, machine learning methods for spectrum noise reduction and formation saturation prediction of C/O logging are introduced in this paper. Based on numerical simulation methods and calibration well measurements, the standard spectrum and the corresponding noise-add spectrum are constructed under different string and formation conditions. The main components in the noise-add spectrum are extracted and recovered using stacked autoencoder networks to realize the noise reduction process. Utilizing the ensemble learning method, artificial neural network and random forest method are integrated to construct the oil saturation prediction model, and the window counts of C, O, Si, Ca and Fe and the count ratios of C/O, Si/Ca and Si/Fe are obtained from the noise reduction spectrum, which are used as input features together with the string, mineral content, formation porosity, shale content and other bare-hole well data for oil content prediction of the formation saturation prediction. More than 5000 simulated data were calculated covering different string, formation lithology, porosity, and oil saturation; meanwhile, Wells with different string and lithology conditions were used as machine learning training samples to jointly construct the saturation prediction model. The model was validated by establishing simulated data under new parameters of different bole hole and formation conditions. The results showed that the autoencoder method improved the signal-to-noise ratio (SNR) of spectrum compared with Savitzky-Golay method, and the absolute error of saturation prediction from simulations and wells in the formation with porosity at 10 % is less than 10 %. This study improves the accuracy of C/O logging in determining the oil saturation of a formation under complex borehole and formation conditions.
- Asia > China (0.50)
- Europe > Norway > Norwegian Sea (0.24)
- Geology > Rock Type > Sedimentary Rock > Clastic Rock (0.68)
- Geology > Mineral > Silicate > Phyllosilicate (0.47)
- Asia > Japan > Honshu Island > Akita Prefecture > Yurihara Field (0.99)
- Asia > China > Bohai Bay > Bohai Basin > Jidong Nanpu Field (0.99)
- Reservoir Description and Dynamics > Reservoir Characterization > Exploration, development, structural geology (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Open hole/cased hole log analysis (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Neural networks (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
Abstract Water Saturation (Sw) is a critical input to reserves estimation and reservoir modeling workflows which ultimately informs effective reservoir management and decision-making. Without laboratory analysis on expensive core data, Sw is estimated using traditional correlationsโcommonly Archie's equation. However, using such a correlation in routine petrophysical analysis for estimating reservoir properties on a case-by-case basis is challenging and time-consuming. This study employs a data-driven approach to model Sw in Niger Delta sandstone reservoirs using readily available geophysical well logs. We evaluate the performance of several generic and ensemble machine learning (ML) algorithms for predicting Archie's computed Sw. ML techniques such as unsupervised anomaly detection and multivariate single imputation were used for preprocessing the data and feature engineering was used to improve the predictive quality of the input well logs. The generalization ability of the ML models was assessed on the individual training wells as well as a held-out test well. Model hyperparameters were tuned using Bayesian Optimization in the cross-validation process to achieve a high rate of success. Several evaluation metrics and graphical methods such as learning curves, convergence plots, and partial dependence plots (PDPs) were then used to assess the predictive performance of the models and explain their behavior. This revealed the Tree Boosting ensembles as the top performers. The superior performance of the Tree Boosting ensembles over the benchmark linear model reveals that the relationship between the transformed logs and Sw is complex and better modeled in the nonlinear domain. Based on the results obtained in this research, we propose the Tree Boosting ensembles as potential models for rapidly estimating Sw for reservoir characterization. A broader field application of the proposed methodologies is expected to provide greater insight into subsurface fluid distribution thereby improving hydrocarbon recovery.
- Europe (1.00)
- Asia > Middle East (1.00)
- Africa > Nigeria > Niger Delta (1.00)
- (2 more...)
- Energy > Oil & Gas > Upstream (1.00)
- Government > Regional Government > North America Government > United States Government (0.46)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (26 more...)
- Reservoir Description and Dynamics > Reservoir Simulation (1.00)
- Reservoir Description and Dynamics > Reservoir Characterization (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Open hole/cased hole log analysis (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
Machine Learning Approach to Improve Calculated Bottom-hole Pressure
Eltahan, Esmail (University of Texas at Austin) | Ganjdanesh, Reza (University of Texas at Austin) | Yu, Wei (SimTech LLC) | Sepehrnoori, Kamy (University of Texas at Austin) | Williams, Ryan (EP Energy) | Nohavitsa, Jack (EP Energy)
Abstract Resulting from their relatively expensive installation cost, a large portion of oil- and gas-production wells have no bottom-hole-flowing-pressure (BHFP) gauges. Operators typically rely on empirical correlations from literature to convert flowing pressure readings at the surface into BHFP estimates. The estimated BHFP consistently over- or under-estimate the actual flowing pressure at the sandface, often by hundreds of psi. In this work, we utilize data obtained from 11 producing horizontal wells in the Uinta basin that have downhole real-time pressure readings measured by gauges installed near the bottom hole. Our objective is to use the typically available data to train a machine-learning (ML) model to correct the pressure estimated by the empirical correlations, such that those corrections can be applied to other wells in the area of interest, where down-hole readings are unavailable. We propose that the actual BHFP is larger than the empirical estimate by some correction factor, and as such, the ML model is seeded with an input array and trained on the data to predict the correction factor. The input array includes (1) surface production rates: oil, water, and gas, (2) production ratios: gas/oil ratio, water/oil ratio, gas/liquid ratio, (3) pressure data: surface flowing pressure and the empirical BHFP estimate, and (4) gas-lift-injection rate (if applicable). The ML model predictions are tested on one well at a time, while being trained on the remaining 10 wells. We design a cross-validation technique that we use to test multiple configurations of ML architectures using linear regression, support-vector regression (SVR), and random forest (RF). The results show promising potential for ML methods to assist reservoir engineers and increase the confidence in the BHFP estimates for the wells. We present three best candidate ML models to predict the BHFP, as well as provide an uncertainty model to place lower and upper bounds on the predictions. The best performance was achieved by the RF model which reduces the root mean square error (RMSE) in the pressure gradient by 29.7% on average over all the test wells. This reduction in error, and the quantified uncertainty, have profound impact on the reservoir-engineering studies that rely on BHFP information.
- North America > United States > Texas > Travis County > Austin (0.28)
- North America > United States > Texas > Harris County > Houston (0.28)
- Research Report > New Finding (0.48)
- Research Report > Experimental Study (0.34)
- North America > United States > Wyoming > Uinta Basin (0.99)
- North America > United States > Utah > Uinta Basin (0.99)
- North America > United States > Colorado > Uinta Basin (0.99)
- Reservoir Description and Dynamics > Unconventional and Complex Reservoirs (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management > Drillstem/well testing (1.00)
- Production and Well Operations > Well & Reservoir Surveillance and Monitoring > Downhole and wellsite flow metering (1.00)
- (2 more...)