Simulation of Two-Phase Flowback Phenomena in Shale Gas Wells

The gas-water two-phaseflow occurring as a result of fracturingfluidflowback phenomena is known to impact significantly the productivity of shale gas well.In this work,this two-phaseflow has been simulated in the framework of a hybrid approach partially relying on the embedded discrete fracture model(EDFM).This model assumes the region outside the stimulated reservoir volume(SRV)as a single-medium while the SRV region itself is described using a double-medium strategy which can account for thefluid exchange between the matrix and the micro-fractures.The shale gas adsorption,desorption,diffusion,gas slippage effect,fracture stress sensitivity,and capillary imbibition have been considered.The shale gas production,pore pressure distribution and water saturation distribution in the reservoir have been simulated.The influences of hydraulic fracture geometry and nonorthogonal hydraulic fractures on gas production have been determined and discussed accordingly.The simulation results show that the daily gas production has an upward and downward trend due to the presence of a large amount of fracturingfluid in the reservoir around the hydraulic fracture.The smaller the angle between the hydraulic fracture and the wellbore,the faster the daily production of shale gas wells decreases,and the lower the cumulative production.Nonplanar fractures can increase the control volume of hydraulic fractures and improve the production of shale gas wells.

Bottom hole pressure prediction based on hybrid neural networks and Bayesian optimization

Many scholars have focused on applying machine learning models in bottom hole pressure (BHP) prediction. However, the complex and uncertain conditions in deep wells make it difficult to capture spatial and temporal correlations of measurement while drilling (MWD) data with traditional intelligent models. In this work, we develop a novel hybrid neural network, which integrates the Convolution Neural Network (CNN) and the Gate Recurrent Unit (GRU) for predicting BHP fluctuations more accurately. The CNN structure is used to analyze spatial local dependency patterns and the GRU structure is used to discover depth variation trends of MWD data. To further improve the prediction accuracy, we explore two types of GRU-based structure: skip-GRU and attention-GRU, which can capture more long-term potential periodic correlation in drilling data. Then, the different model structures tuned by the Bayesian optimization (BO) algorithm are compared and analyzed. Results indicate that the hybrid models can extract spatial-temporal information of data effectively and predict more accurately than random forests, extreme gradient boosting, back propagation neural network, CNN and GRU. The CNN-attention-GRU model with BO algorithm shows great superiority in prediction accuracy and robustness due to the hybrid network structure and attention mechanism, having the lowest mean absolute percentage error of 0.025%. This study provides a reference for solving the problem of extracting spatial and temporal characteristics and guidance for managed pressure drilling in complex formations.

Intelligent Drilling and Completion:A Review

The application of artificial intelligence(AI)has become inevitable in the petroleum industry.In drilling and completion engineering,AI is regarded as a transformative technology that can lower costs and significantly improve drilling efficiency(DE),In recent years,numerous studies have focused on intelligent algorithms and their application.Advanced technologies,such as digital twins and physics-guided neural networks,are expected to play roles in drilling and completion engineering.However,many challenges remain to be addressed,such as the automatic processing of multi-source and multi-scale data.Additionally,in intelligent drilling and completion,methods for the fusion of data-driven and physicsbased models,few-sample learning,uncertainty modeling,and the interpretability and transferability of intelligent algorithms are research frontiers.Based on intelligent application scenarios,this study comprehensively reviews the research status of intelligent drilling and completion and discusses key research areas in the future.This study aims to enhance the berthing of AI techniques in drilling and completion engineering.

Settling behavior of non-spherical particles in power-law fluids:Experimental study and model development

Solid-particle settling occurs in many natural and industrial processes, such as in the transportation of drilling cuttings and fracturing proppant. Knowledge of the drag coefficient and settling velocity of cuttings and proppant is of significance to hydraulics design, wellbore cleanout, and fracture optimization. We conducted 553 tests to investigate the settling characteristics of spherical and non-spherical particles in power-law fluids. Three major particle shapes (spherical, cubic, and cylindrical) and eight different particle sphericities were used to simulate cuttings and proppant, and power-law fluids were applied to simulate drilling and fracturing fluids. Based on the data analysis, a new drag coefficient-particle Reynolds number correlation was developed to determine the drag coefficient in a power-law fluid for spherical and non-spherical particles. The drag coefficient increases as the sphericity decreases for the same particle Reynolds number. For a specific particle shape, the drag coefficient decreases as the particle Reynolds number increases, but the decreasing trend is reduced at high particle Reynolds number conditions. An explicit settling-velocity equation was proposed to calculate the settling velocity of spherical and non-spherical particles in power-law fluids by considering the effect of sphericity. A suitable range for the proposed model is 0.0001 < Re <200, 0.471 <φ< 1, and 0.505 < n < 1. An illustrative example is presented to show how to calculate the drag coefficient and settling velocity in power-law fluids with given particle and fluid properties.

Settling behavior of spherical particles in vertical annulus:Experimental study and model development

Coiled tubing(CT)drilling technology offers significant advantages in terms of cost and efficiency for exploitations of unconventional oil and gas resources.However,the development of CT drilling technol-ogy is restricted by cuttings accumulation in the wellbore due to non-rotation of the drill string and limited circulating capacity.Cuttings cleaning becomes more difficult with the wall resistance of pipe-wellbore annulus on the cutting transport.Accurate description of particle transport process in the pipe-wellbore annulus is,therefore,important for improving the wellbore cleanliness.In this study,high-speed cam-era is used to record and analyze the settling process of particles in the transparent annulus filled with power-law fluids.A total of 540 tests were carried out,involving dimensionless diameters of 0.10-0.95 and particle Reynolds Numbers of 0.01-12.97,revealing the effect of the dimensionless diameter and particle Reynolds number on the annulus wall effect,and the wall factor model with an average relative error of2.75%was established.In addition,a dimensionless parameter,Archimedes number,independent of the settling velocity,was introduced to establish an explicit model of the settling velocity of spherical particles in the vertical annulus,with the average relative error of 7.89%.Finally,a calculation example was provided to show how to use the explicit model of settling velocity in annulus.The results of this study are expected to provide guidance for field engineers to improve the wellbore cleanliness of coiled tubing drilling.

Predicting wall drag coefficient and settling velocity of particle in parallel plates filled with Newtonian fluids

The hindrance of boundary to particle transport exists widely in various industrial applications.In this study,the wall drag force of parallel plates on settling particles was revealed through settling experiment.High-speed camera was used to record and analyze the settling process of particles in parallel plates that are filled with Newtonian fluids.A total of 600 experiments were carried out,involving the range of relative diameter and particle Reynolds number of 0.01-0.95 and 0.004-14.30,respectively.The wall drag coefficient was defined to quantitatively analyze the wall drag force of the parallel plates.The influence of relative diameter,particle properties,rheological properties,and the settling dynamic process on the wall drag coefficient was revealed,and the wall drag coefficient model with mean relative error of 5.90% was established.Furthermore,an explicit settling velocity model with mean relative error of 8.96% for the particle in parallel plates was developed by introducing a dimensionless variable independent of settling velocity,the Archimedes number.Finally,a calculation example was provided to clarify the using process of the explicit model.This research is expected to provide guidance for optimizing water hydraulic fracturing in the oil and gas industry.