Evaluation of hydraulic fracturing of horizontal wells in tight reservoirs based on the deep neural network with physical constraints

Accurate diagnosis of fracture geometry and conductivity is of great challenge due to the complex morphology of volumetric fracture network. In this study, a DNN (deep neural network) model was proposed to predict fracture parameters for the evaluation of the fracturing effects. Field experience and the law of fracture volume conservation were incorporated as physical constraints to improve the prediction accuracy due to small amount of data. A combined neural network was adopted to input both static geological and dynamic fracturing data. The structure of the DNN was optimized and the model was validated through k-fold cross-validation. Results indicate that this DNN model is capable of predicting the fracture parameters accurately with a low relative error of under 10% and good generalization ability. The adoptions of the combined neural network, physical constraints, and k-fold cross-validation improve the model performance. Specifically, the root-mean-square error (RMSE) of the model decreases by 71.9% and 56% respectively with the combined neural network as the input model and the consideration of physical constraints. The mean square error (MRE) of fracture parameters reduces by 75% because the k-fold cross-validation improves the rationality of data set dividing. The model based on the DNN with physical constraints proposed in this study provides foundations for the optimization of fracturing design and improves the efficiency of fracture diagnosis in tight oil and gas reservoirs.

A numerical investigation of hydraulic fracturing on coal seam permeability based on PFC‑COMSOL coupling method

Hydraulic fracturing and permeability enhancement are effective methods to improve low-permeability coal seams.However,few studies focused on methods to increase permeability,and there are no suitable prediction methods for engineering applications.In this work,PFC2D software was used to simulate coal seam hydraulic fracturing.The results were used in a coupled mathematical model of the interaction between coal seam deformation and gas flow.The results show that the displacement and velocity of particles increase in the direction of minimum principal stress,and the cracks propagate in the direction of maximum principal stress.The gas pressure drop rate and permeability increase rate of the fracture model are higher than that of the non-fracture model.Both parameters decrease rapidly with an increase in the drainage time and approach 0.The longer the hydraulic fracturing time,the more complex the fracture network is,and the faster the gas pressure drops.However,the impact of fracturing on the gas drainage effect declines over time.As the fracturing time increases,the difference between the horizontal and vertical permeability increases.However,this difference decreases as the gas drainage time increases.The higher the initial void pressure,the faster the gas pressure drops,and the greater the permeability increase is.However,the influence of the initial void pressure on the permeability declines over time.The research results provide guidance for predicting the anti-reflection effect of hydraulic fracturing in underground coal mines.

Investigating microscopic seepage characteristics and fracture effectiveness of tight sandstones:a digital core approach

Microscopic seepage characteristics are critical for the evaluation of tight sandstone reservoirs.In this study,a digital core approach integrating microscopic seepage simulation and CT scanning was developed to characterize microscopic seepage and fracture effectiveness(the ratio of micro-fractures that contributes to fluid flow)of tight sandstones.Numerical simulations were carried out for characterizations of tight sandstones.The results show that the axial permeability of the investigated cylindrical tight sandstone from Junggar Basin in China is 0.460μm~2,while the radial permeability is 0.3723μm~2,and the axial and radial effective fracture ratios are 0.4387 and 0.4806,respectively,indicating that cracks are not fully developed and the connectivity between micro-cracks is poor.Directional permeability that is difficult to measure by laboratory experiments can be obtained readily using the proposed method in this paper.The results provide important information for improving the exploration and development of tight sandstone reservoirs.

An evaluation method of volume fracturing effects for vertical wells in low permeability reservoirs

To evaluate the fracturing effect and dynamic change process after volume fracturing with vertical wells in low permeability oil reservoirs, an oil-water two-phase flow model and a well model are built. On this basis, an evaluation method of fracturing effect based on production data and fracturing fluid backflow data is established, and the method is used to analyze some field cases. The vicinity area of main fracture after fracturing is divided into different stimulated regions. The permeability and area of different regions are used to characterize the stimulation strength and scale of the fracture network. The conductivity of stimulated region is defined as the product of the permeability and area of the stimulated region. Through parameter sensitivity analysis, it is found that half-length of the fracture and the permeability of the core area mainly affect the flow law near the well, that is, the early stage of production;while matrix permeability mainly affects the flow law at the far end of the fracture. Taking a typical old well in Changqing Oilfield as an example, the fracturing effect and its changes after two rounds of volume fracturing in this well are evaluated. It is found that with the increase of production time after the first volume fracturing, the permeability and conductivity of stimulated area gradually decreased, and the fracturing effect gradually decreased until disappeared;after the second volume fracturing, the permeability and conductivity of stimulated area increased significantly again.

Hydraulic Fracture Parameter Inversion Method for Shale GasWells Based on Transient Pressure-Drop Analysis during Hydraulic Fracturing Shut-in Period

Horizontal well drilling and multi-stage hydraulic fracturing are key technologies for the development of shale gas reservoirs.Instantaneous acquisition of hydraulic fracture parameters is crucial for evaluating fracturing effectiveness,optimizing processes,and predicting gas productivity.This paper establishes a transient flow model for shale gas wells based on the boundary element method,achieving the characterization of stimulated reservoir volume for a single stage.By integrating pressure monitoring data following the pumping shut-in period of hydraulic fracturing for well testing interpretation,a workflow for inverting fracture parameters of shale gas wells is established.This new method eliminates the need for prolonged production testing and can interpret parameters of individual hydraulic fracture segments,offering significant advantages over the conventional pressure transient analysismethod.The practical application of thismethodology was conducted on 10 shale gaswellswithin the Changning shale gas block of Sichuan,China.The results show a high correlation between the interpreted single-stage total length and surface area of hydraulic fractures and the outcomes of gas production profile tests.Additionally,significant correlations are observed between these parameters and cluster number,horizontal stress difference,and natural fracture density.This demonstrates the effectiveness of the proposed fracture parameter inversion method and the feasibility of field application.The findings of this study aim to provide solutions and references for the inversion of fracture parameters in shale gas wells.

Fluid identification and effective fracture prediction based on frequency-dependent AVOAz inversion for fractured reservoirs

Fluid and effective fracture identification in reservoirs is a crucial part of reservoir prediction.The frequency-dependent AVO inversion algorithms have proven to be effective for identifying fluid through its dispersion property.However,the conventional frequency-dependent AVO inversion algorithms based on Smith&Gidlow and Aki&Richards approximations do not consider the acquisition azimuth of seismic data and neglect the effect of seismic anisotropic dispersion in the actual medium.The aligned fractures in the subsurface medium induce anisotropy.The seismic anisotropy should be considered while accounting for the seismic dispersion properties through fluid-saturated fractured reservoirs.Anisotropy in such reservoirs is frequency-related due to wave-induced fluid-flow(WIFF)between interconnected fractures and pores.It can be used to identify fluid and effective fractures(fluid-saturated)by using azimuthal seismic data via anisotropic dispersion properties.In this paper,based on Rüger’s equation,we derived an analytical expression in the frequency domain for the frequencydependent AVOAz inversion in terms of fracture orientation,dispersion gradient of isotropic background rock,anisotropic dispersion gradient,and the dispersion at a normal incident angle.The frequency-dependent AVOAz equation utilizes azimuthal seismic data and considers the effect of both isotropic and anisotropic dispersion.Reassigned Gabor Transform(RGT)is used to achieve highresolution frequency division data.We then propose the frequency-dependent AVOAz inversion method to identify fluid and characterize effective fractures in fractured porous reservoirs.Through application to high-qualified seismic data of dolomite and carbonate reservoirs,the results show that the method is useful for identifying fluid and effective fractures in fluid-saturated fractured rocks.

The influencing factors and mechanisms of the electromagnetic radiation during rock fracture

Based on the laboratory experiments this paper presented that the primary influence factors about the electromagnetic radiation during rock fracture are the rock mechanics characters and mineral components. The brittle samples and samples contained quartz, pyrite, chalopyrite produce electromagnetic radiation easily. There are three fracture radiation effects. The crystal fracture effect produces the high frequency electromagnetic signals, the piezoelectric effect produces low frequency signals and the natural semiconductor effect produces middle frequency signals possessed distinct wave shapes.

Dynamic fracture toughness of high strength metals under impact loading:increase or decrease

An elusive phenomenon is observed in previous investigations on dynamic fracture that the dynamic fracture toughness （DFT） of high strength metals always increases with the loading rate on the order of TPa.m1/2.s-1. For the purpose of verification, variation of DFT with the loading rate for two high strength steels commonly used in the aviation industry, 30CrMnSiA and 40Cr, is studied in this work. Results of the experiments are compared, which were conducted on the modified split Hopkinson pressure bar （SHPB） apparatus, with striker velocities ranging from 9.2 to 24.1 m/s and a constant value of 16.3 m/s for 30CrMnSiA and 40Cr, respectively. It is observed that for 30CrMnSiA, the crack tip loading rate increases with the increase of the striker velocity, while the fracture initiation time and the DFT simultaneously decrease. However, in the tests of 40Cr, there is also an increasing tendency of DFT, similar to other reports. Through an in-depth investigation on the relationship between the dynamic stress intensity factor （DSIF） and the loading rate, it is concluded that the generally increasing tendency in previous studies could be false, which is induced from a limited striker velocity domain and the errors existing in the experimental and numerical processes. To disclose the real dependency of DFT on the loading rate, experimentsneed to be performed in a comparatively large striker velocity range.

SEM in-situ Fracture Observation and the Reinforcing Effect of Composite SiC_p/ZA22

The strengthening effect of a Zn alloy reinforced by SiC particulate was examined. Based on the results of SEM in-situ fracture observation and stress field analysis by finite element method, it is believed that the reinforcing effect of this composite is due to the combination of strain and stress hardening in the matrix.

Test evaluation for vertical fracture wells in low permeability reservoir

As flow environment is poor in low permeability reservoirs, wells are always fractured in order to gain better economic benefits. Well testing analysis is very necessary for fracturing wells. However, available test analysis methods are of slow fitting speed and low fitting precision. In this paper, we first use a comprehensive evaluation method of analytical well testing, numerical well testing and well testing design. Many dynamic parameters such as fracture length, fracture conductivity, skin factor, etc are obtained. An example to illustrate accurate results of this method is given.

CO_2 permeability of fractured coal subject to confining pressures and elevated temperature: Experiments and modeling

The CO_2 permeability of fractured coal is of great significance to both coalbed gas extraction and CO_2 storage in coal seams, but the effects of high confining pressure, high injection pressure and elevated temperature on the CO_2 permeability of fractured coal with different fracture extents have not been investigated thoroughly. In this paper, the CO_2 permeability of fractured coals sampled from a Pingdingshan coal mine in China and artificially fractured to a certain extent is investigated through undrained triaxial tests. The CO_2 permeability is measured under the confining pressure with a range of 10–25 MPa, injection pressure with a range of 6–12 MPa and elevated temperature with a range of 25–70°C. A mechanistic model is then proposed to characterize the CO_2 permeability of the fractured coals. The effects of thermal expansion, temperature-induced reduction of adsorption capacity, and thermal micro-cracking on the CO_2 permeability are explored. The test results show that the CO_2 permeability of naturally fractured coal saliently increases with increasing injection pressure. The increase of confining pressure reduces the permeability of both naturally fractured coal and secondarily fractured coal. It is also observed that initial fracturing by external loads can enhance the permeability, but further fracturing reduces the permeability. The CO_2 permeability decreases with the elevation of temperature if the temperature is lower than 44°C, but the permeability increases with temperature once the temperature is beyond 44°C. The mechanistic model well describes these compaction mechanisms induced by confining pressure, injection pressure and the complex effects induced by elevated temperature.

Physical simulation experiment and numerical inversion of the full life cycle of shale gas well

The ultra-low porosity and permeability,as well as complex occurrence and transport state of shale reservoir make it possess special L-type production characteristic curve and complicated shale gas flow mechanism.To solve the difficulty of collecting complete production data due to short production time and operation discontinuity,a full-diameter core physical simulation experiment on the full lifecycle production process of shale gas well depletion is conducted with the purpose of obtaining many important production data including complete pressure and daily gas output in the simulated production process of shale gas well.The experimental results show the production characteristic from simulation is consistent with those from gas well.Based on the simulation data,the critical desorption pressure(12 MPa)of core,free gas production(3820.8 mL),adsorbed gas production(2151.2 mL),the proportion of the daily gas production between free and absorbed gas under different time and formation pressure,as well as the production time and final recovery rate corresponding to abandoned pressure,can be determined accurately.Numerical inversion is carried out to calculate the production performance curve of shale gas well and predict the development effect of gas well based on well testing and similarity analysis of the dimensionless time between core experiment and gas well production.Finally,the permeability and the fracturing effect(fracture network density)as the keys to the effective development of shale gas reservoirs are proposed.The permeability is the fundamental factor and the fracturing technology is the major means.

Shear response of β-SiC bulk dependent on temperature and strain rate

The shear responses of β-SiC are investigated using molecular dynamics simulation with the Tersoff interatomic potential. Results show a clear decreasing trend in critical stress,fracture strain and shear modulus as temperature increases. Above a critical temperature, β-SiC bulk just fractures after the elastic deformation. However, below the critical temperature, an interesting pattern in β-SiC bulk emerges due to the elongation of Si-C bonds before fracture. Additionally, the shear deformation of β-SiC at room temperature is found to be dependent on the strain rate. This study may shed light on the deformation mechanism dependent on temperature and strain rate.