Artificial neural network based production forecasting for a hydrocarbon reservoir under water injection

Negash, Berihun Mamo; Yaw, Atta Dennis

doi:10.1016/s1876-3804(20)60055-6

Cited by 83 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advances in data analysis, the DOE has become a powerful tool to assess experimental data. Its results can even be enhanced using techniques such as artificial neural networks, 39 and some solid approaches can also be used to reconstruct if there is missing information. 40 In this research, Box–Behnken experimental design was adopted to evaluate the effects of independent variables on the CH 4 adsorption in Marcellus shale.…”

Section: Resultsmentioning

confidence: 99%

Synergetic Effect of Surfactant Concentration, Salinity, and Pressure on Adsorbed Methane in Shale at Low Pressure: An Experimental and Modeling Study

et al. 2020

Self Cite

View full text Add to dashboard Cite

The influence of an anionic surfactant, a cationic surfactant, and salinity on adsorbed methane (CH 4 ) in shale was assessed and modeled in a series of systematically designed experiments. Two cases were investigated. In case 1, the crushed Marcellus shale samples were allowed to react with anionic sodium dodecyl sulfate (SDS) and brine. In case 2, another set of crushed Marcellus shale samples were treated with cetyltrimethylammonium bromide (CTAB) and brine. The surfactant concentration and salinity of brine were varied following the Box–Behnken experimental design. CH 4 adsorption was then assessed volumetrically in the treated shale at varying pressures (1–50 bar) and a constant temperature of 30 °C using a pressure equilibrium cell. Mathematical analysis of the experimental data yielded two separate models, which expressed the amount of adsorbed CH 4 as a function of SDS/CTAB concentration, salinity, and pressure. In case 1, the highest amount of adsorbed CH 4 was about 1 mmol/g. Such an amount was achieved at 50 bar, provided that the SDS concentration is kept close to its critical micelle concentration (CMC), which is 0.2 wt %, and salinity is in the range of 0.1–20 ppt. However, in case 2, the maximum amount of adsorbed CH 4 was just 0.3 mmol/g. This value was obtained at 50 bar and high salinity (∼75 ppt) when the CTAB concentration was above the CMC (>0.029 wt %). The findings provide researchers with insights that can help in optimizing the ratio of salinity and surfactant concentration used in shale gas fracturing fluid.

show abstract

Section: Resultsmentioning

confidence: 99%

Synergetic Effect of Surfactant Concentration, Salinity, and Pressure on Adsorbed Methane in Shale at Low Pressure: An Experimental and Modeling Study

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The MATLAB Deep Learning Toolbox advice to use "Levenberg-Marquardt" algorithm as default for the ANN training; however, the obtained data had noise, and the ANN could yield to a low mapping performance. The authors of Reference [87] suggested using the Bayesian regularization, which is an appropriate training algorithm since it also endorses over-fitting prevention. An iteration in the training consists in Equation (12), where the vector Wb contains the current weights and bias, g k is the current gradient, and α is the learning rate.…”

Section: Neural Network Compensation Detailedmentioning

confidence: 99%

High-Performance Tracking for Piezoelectric Actuators Using Super-Twisting Algorithm Based on Artificial Neural Networks

et al. 2021

View full text Add to dashboard Cite

Piezoelectric actuators (PEA) are frequently employed in applications where nano-Micr-odisplacement is required because of their high-precision performance. However, the positioning is affected substantially by the hysteresis which resembles in an nonlinear effect. In addition, hysteresis mathematical models own deficiencies that can influence on the reference following performance. The objective of this study was to enhance the tracking accuracy of a commercial PEA stack actuator with the implementation of a novel approach which consists in the use of a Super-Twisting Algorithm (STA) combined with artificial neural networks (ANN). A Lyapunov stability proof is bestowed to explain the theoretical solution. Experimental results of the proposed method were compared with a proportional-integral-derivative (PID) controller. The outcomes in a real PEA reported that the novel structure is stable as it was proved theoretically, and the experiments provided a significant error reduction in contrast with the PID.

show abstract

“…In addition, optimization of the well location is normally conducted first and well control settings are optimized as a fixed well location [88]. Contract theory can be used to jointly optimize the well placement optimization problem and well control optimization problem [49]. Again, a comprehensive sensitivity analysis is important.…”

Section: Limitations Of the Studymentioning

confidence: 99%

A Modified Niching Crow Search Approach to Well Placement Optimization

et al. 2021

Self Cite

View full text Add to dashboard Cite

Well placement optimization is considered a non-convex and highly multimodal optimization problem. In this article, a modified crow search algorithm is proposed to tackle the well placement optimization problem. This article proposes modifications based on local search and niching techniques in the crow search algorithm (CSA). At first, the suggested approach is verified by experimenting with the benchmark functions. For test functions, the results of the proposed approach demonstrated a higher convergence rate and a better solution. Again, the performance of the proposed technique is evaluated with well placement optimization problem and compared with particle swarm optimization (PSO), the Gravitational Search Algorithm (GSA), and the Crow search algorithm (CSA). The outcomes of the study revealed that the niching crow search algorithm is the most efficient and effective compared to the other techniques.

show abstract

Artificial neural network based production forecasting for a hydrocarbon reservoir under water injection

Cited by 83 publications

References 28 publications

Synergetic Effect of Surfactant Concentration, Salinity, and Pressure on Adsorbed Methane in Shale at Low Pressure: An Experimental and Modeling Study

Synergetic Effect of Surfactant Concentration, Salinity, and Pressure on Adsorbed Methane in Shale at Low Pressure: An Experimental and Modeling Study

High-Performance Tracking for Piezoelectric Actuators Using Super-Twisting Algorithm Based on Artificial Neural Networks

A Modified Niching Crow Search Approach to Well Placement Optimization

Contact Info

Product

Resources

About