Multi-fractured Horizontal Wells Research Articles

Modeling the Transient Flow Behavior of Multi-Stage Fractured Horizontal Wells in the Inter-Salt Shale Oil Reservoir, Considering Stress Sensitivity

Oil flow in inter-salt shale oil reservoirs is different from that of other oil fields due to its high salt content. Dissolution and diffusion occur when the salt minerals meet the water-based working fluid, resulting in drastic changes in the shale’s permeability. In addition, ignoring the stress-sensitive effect will cause significant errors in naturally fractured reservoirs for a large number of the natural fractures developed in shales. This study presents a transient pressure behavior model for a multi-stage fractured horizontal well (MFHW) in inter-salt shale oil reservoirs, considering the dissolution of salt and the stress sensitivity mentioned above. The analytical solution of our model was obtained by applying the methods of Pedrosa’s linearization, the perturbation technique and Laplace transformation. The transient pressure of a multi-stage fractured horizontal well in an inter-salt shale oil reservoir was obtained in real space by using the method of Stehfest’s numerical inversion. The bi-logarithmic-type curves thus obtained reflected the characteristics of the transient pressure behavior of a MFHW for the inter-salt shale oil reservoirs, and eight flow periods were recognized in the type curves. The effects of salt dissolution, stress sensitivity, the storativity ratio and other parameters on the type curves were analyzed thoroughly, which is of great significance for understanding the transient flow behavior of inter-salt shale oil reservoirs.

A productivity prediction method for multi-fractured horizontal wells in tight oil reservoirs considering fracture closure

The closure fracture phenomenon increases the complexity of well testing and reduces the accuracy of productivity forecasts when tight oil reservoirs are exploited. However, most existing productivity models tend to ignore this. Therefore, a productivity prediction model for multi-fractured horizontal wells in tight oil reservoirs considering fracture closure has been developed by considering the stress sensitivity in the formation and combining the physical parameters of actual production. The model is solved by the Laplace transform, perturbation transform, Pedrosa transform, and Stehfest numerical inversion. Drawing productivity impact curves and discussing productivity influence factors based on the model results from this study show that the model is reasonable. In the actual production process, the hydraulic fracture parameter values are not as high as possible, and they have a reasonable range of values. The fracture closure pressure has a significant impact on the production of tight oil reservoirs. The higher the fracture closure pressure is, the greater the fracture conductivity decreases sharply, and the larger the proppant elastic modulus is, the stronger the fracture conductivity. The influence of fracture conductivity on the production in tight oil reservoirs has an obvious point, and when the value is less than the point, the production effect is good. Improved production can be achieved by balancing the relationship between fracture parameters. The findings of this study can help to better understand the influence of fracture parameters on productivity and contribute to increasing well production and improved development of tight oil reservoirs.

Productivity Prediction of Multistage Fractured Horizontal Wells in Tight Oil Reservoirs with Fully Coupled Flow and Geomechanics

Productivity Prediction of Multistage Fractured Horizontal Wells in Tight Oil Reservoirs with Fully Coupled Flow and Geomechanics

Effects of a Multistage Fractured Horizontal Well on Stimulation Characteristics of a Clayey Silt Hydrate Reservoir.

The gas production from clayey silt natural gas hydrate (NGH) reservoir in the South China Sea faces the problem of low connectivity between the reservoir and the production well, which seriously reduces the gas production rate. Multistage fractured horizontal well (MFHW) is regarded as an effective technical means to improve gas production for an unconventional reservoir with low permeability. In this paper, a three-dimensional numerical simulation model was built to study the promotion effects of MFHW technology on gas production from a clayey silt NGH reservoir. The temporal and spatial evolution characteristics of the NGH reservoir with and without multiple fractures were compared and analyzed in detail. In addition, the influences of the fracture number, permeability, and morphology on the stimulation effect on gas production through MFHW technology were discussed. The results indicated that the fractures with high conductivity provided a fast channel for gas and water flow and increased the contact area between the horizontal well and the NGH reservoir, which had a positive effect on increasing gas production from the clayey silt NGH reservoir. Increasing fracture number, fracture permeability, and the area of fracture morphology effectively improved the gas production rate and total gas production, but the stage of the high gas production rate only lasted for a short time. This study demonstrated the production behavior of MFHW technology in the clayey silt NGH reservoir, which was helpful for understanding this technology’s stimulation effect.

Study on flow model of multi-stage fracturing horizontal well in stress-denpendent dual medium reservoir

Often with abundant of natural fracture, Carbonate reservoirs are characterized with the stress sensitive and dual media. Mostly, its flow model solved by numerical method. In this paper, the semi-analytical solution for this problem is presented: firstly, the point source function considering stress sensitivity in infinite dual medium reservoir is obtained in Laplace space by Perturbation Transformation and Laplace Transformation; Secondly, the Laplace space solution of multi-stage fracturing horizontal well in infinite plate reservoir is obtained by Image Principle and Superposition Principle; Finally, the spacial solution of multi-stage fracturing horizontal well is obtained by Stehfest numerical inversion and perturbation inverse transformation. The calculation results show that the flow regime of multi-stage fracturing horizontal well can be divided into six stages: Ⅰ- linear flow, Ⅱ-first radial flow, Ⅲ-double radial flow, Ⅳ-radial flow of natural fracture system, Ⅴ-channeling flow regime and Ⅵ-radial flow of the whole system. The impact of stress sensitivity of formation permeability on linear flow is lower, and mainly affecting the last five flow regimes, and the dimensionless pressure drop derivative curve tends to rise in the later stage of development, showing the characteristics of closed boundary. In this paper, when the reservoir stress sensitivity is not considered, the calculation results will produce a large error, and the wrong well test interpretation will be obtained.

Rate-transient analysis for estimating the linear flow parameters of communicating wells using the dynamic drainage area (DDA) concept

Development of unconventional reservoirs using multi-fractured horizontal wells (MFHWs) has led to closer well and hydraulic fracture spacing. Tighter placement of MFHWs has consequently led to increased instances of well interference, particularly through hydraulic fractures. In addition to possible problems posed for development, fracture communication that persists during production complicates rate-transient analysis (RTA) because models/methods for RTA have mostly been developed for single-well analysis. Availability of RTA methods specifically developed for communicating wells can reduce errors associated with hydraulic fracture and reservoir characterization and can lead to improved decision making.A semi-analytical method for history matching MFHWs communicating through hydraulic fractures has recently been developed using the dynamic drainage area (DDA) concept. In the current work, the DDA concept is employed to develop a new straight-line analysis (SLA) method for the transient linear flow regime that can be applied to two communicating MFHWs. The change in the drainage area of a single well due to communication challenges the use of the DDA concept. However, when the second well comes on production, reinitialization of the calculations for the first well helps to facilitate the implementation of the DDA concept.The new DDA-corrected RTA (SLA) method for communicating wells is verified against the results of numerical simulation. Several synthetic cases are generated using numerical simulation to verify the accuracy of the developed method using various reservoir/fracture properties. The new method applied to the simulated cases allows the fracture half-length (xf) to be estimated within 10% of simulation model input. The DDA-corrected RTA method has also been applied to a field dataset, previously analyzed by the authors using the DDA approach to history match well production data. This dataset consists of six wells, drilled into two separate reservoir layers (three wells per layer) and from two adjacent pads, which exhibit strong well-pair communication. For this dataset, the calculated linear flow parameters for these wells are compared. The results demonstrate that there is a difference between the linear flow parameters of wells completed in the upper layer and lower layers, which could be attributed to either differences in effective fracture area or permeability.This new approach can help practitioners quickly and accurately estimate reservoir and fracture properties in these scenarios. The method can therefore be used to improve hydraulic fracture design, well forecasting and development planning where persistent well communication through hydraulic fractures is occurring.

Publisher’s Note

In-situ conversion of oil shale process has been appealing from economic and energy security perspectives. Conventional in-situ upgrading techniques use electric heaters to heat oil shale, not shale oil. However, the efficiency of electrical heating method is very slow which requires preheating more than a year. Most conventional heating technologies focused on using different heat injection methods converting the shale oil reservoirs. As shale is a poor heat conductor, many of attempts are still in the laboratory stage. The shale oil matrix is very tight and the pore scale ranges from micro to nano-meter. In this paper, we propose to inject air into hydraulically fractured horizontal wells to create in-situ combustion of shale oil in ultra-low permeability formations. Heat is introduced into the formation through multistage fractured horizontal wells, which enhances the contact area of exposed kerogen. This process uses combustion reactants as fuel feed stock to generate perpetual heating. Firstly, we used the laboratory tube combustion of shale oil results to validate the simulation model. Then, we upscale the simulation model to investigate the well productivity performance by in-situ upgrading of shale oil by air injection. The main objective of this work is to determine the technical feasibility of recovering shale oil resources by air injection. It involves the application of hydraulic fracturing technology to enhance the kerogen exposure to oxygen. Heat flows from the fracture into shale oil formation, gradually converting the solid kerogen into mobile oil and gas which can be produced via fractures to the production wells. Our simulation results in this paper have shown the potential of in-situ combustion process to improved oil recovery in shale oil reservoirs. Simulation result indicates that the key parameters controlling the well productivity include air injection rate, injected gas composition and fracture spacing. The available literature provides limited studies on the applicability of in-situ combustion of shale oil in very low permeability formations. The paper provides a comprehensive model that allows kerogen to undergo thermal cracking and oxidation process. The results of this study indicate that the developed kinetic model is feasible to model the kerogen in-situ conversion process induced by air injection.

Machine-learning-based well production prediction under geological and hydraulic fracture parameters uncertainty for unconventional shale gas reservoirs

Shale gas production prediction under history-matching-based geomodel is crucial to achieve reliable assessment and economic management of unconventional shale resources, however, conventional history matching is generally performed through repeatedly running high-fidelity reservoir simulations and therefore presents intensive computation-cost in practical applications. Without the need of history matching step, this work presents an efficient and robust post-history production forecasting framework using a latent-space learning-based direct forecast approach, e.g., referred to as LS-LDFA. A novel dimensionality reduction method, e.g., convolutional autoencoder, is employed to regularize the multi-well time-series data by low-order representation within a latent space. Once the machine-learning proxy is trained offline, the online post-history production forecast can be efficiently achieved by input history data. This paper presents some comparative studies between LS-LDFA and model-based history matching. This approach is tested on two examples with an increasing complexity, e.g., a multi-fractured horizontal well and a naturally fractured reservoir model with multi-well-pad-production based on synthetic shale formation. The results confirm that the method achieves high robustness and computational efficiency simultaneously in comparison with the conventional history matching. The application of learning-based direct forecast approach can effectively fuse information from history data and thus support reliable decision-making and risk assessment.

Transient analysis of horizontal wells with multiple fractures in sour gas reservoirs

Due to the decrease of reservoir pressure, the elemental sulfur deposits in sour gas reservoirs, leading to the reduction in the reservoir porosity and permeability. It can also impact the transient pressure and rate behavior of gas wells, which is always reflected in pressure and flow rate type curves. However, few studies focus on transient analysis of multi-fractured horizontal wells affected by sulfur deposition. Therefore, the objective of this work is to develop a comprehensive model to analyze the transient pressure and flow rate of multi-fractured horizontal wells in sour gas reservoirs. Pseudo-time function and pseudo-pressure function are derived and the point source method is applied in this model. Then the proposed model is validated against analytical solutions and real production data. Furthermore, sensitivity analysis for pressure and rate type curves was conducted. Results show that the pressure type curves can be divided into six stages. The reservoir with higher H2S concentration will result in more sulfur deposition, which requires larger pressure difference to maintain a constant rate in the late time. Fracture properties impact flow rate in the early production time, and increasing fracture conductivity and fracture number is helpful to reduce the generation of sulfur deposition. For a smaller reservoir, larger pressure difference is essential to stabilize constant production rate, which means more sulfur deposition will be produced in the reservoir. During the development of sour gas reservoir, it is important to control flow rate to reduce pressure depletion for decrease amount of sulfur deposition. This paper reveals the impacts of sulfur deposition on type curves and provides a comprehensive transient analysis for multi-fractured horizontal wells in the development of sour gas reservoirs.

Analysis of seepage mechanism and productivity model of multi-stage fractured horizontal well in tight sandstone gas reservoir

During synchronous fracturing of horizontal well clusters, the induced stresses generated by multiple wells affect the formation of complex fractures. By using linear superposition and vector representation, the productivity model for the horizontal stress field between wells was constructed. The results demonstrated simultaneous fracturing can produce stronger and a wider range of stress interference variable impact on induced stress field, the most influential factor is the row spacing, accounting for 32.09% and the engineering factors with the least impact is fracture conductivity, with weight of 0.08%. The research results were used to YA gas field. After the preliminary implementation in the field, the initial production of a well in the reservoir increased by 20.48%, the decline rate slowed down by 13.16% and the output of well increased by 43.75% in the stable production period. In addition, these results might also provide an acceptable explanation for the high productivity of synchronous fracturing operations in horizontal well clusters. Generally speaking, a clear understanding of changes in induced stress fields in horizontal clusters might provide are liable foundation for the determination of optimal well spacing and a fracturing program for horizontal well clusters to develop unconventional formations.

Formation damage simulation of a multi-fractured horizontal well in a tight gas/shale oil formation

Formation damage in drilling comes from drilling fluid invasion due to high differential pressure between a wellbore and the formation. This mechanism happens with fracture fluid invasion of multi-fractured horizontal wells in tight formations. Some multi-fractured wells show production rates and cumulative productions far lower than expected. Those damaged wells may sustain further impact such as well shutting due to unexpected events such as the COVID-19 outbreak and then experience a further reduction in cumulative production. This paper focuses on the root causes of formation damage of fractured wells and provides possible solutions to improve production. A simulation study was conducted using Computer Modelling Group software to simulate formation damage due to fracture fluid invasion and well shut-in. Simulation results revealed that the decrease in cumulative hydrocarbon production due to leak-off and shut-in of the simulated well could range from 20 to 41%, depending on different conditions. The results showed that the main causes are high critical water saturation of tight formations, low drawdown, and low residual proppant permeability under formation closure stress. The sensitivity analysis suggests two feasible solutions to mitigate formation damage: optimizing drawdown during production and optimized proppant pack permeability of the hydraulic fracturing process. Optimizing pressure drawdown is effective in fixing leak-off damage, but it does not mitigate shut-in damage. Formation damage due to shut-in should be prevented in advance by using an appropriate proppant permeability. These key findings enhance productivity and improve the economics of tight gas and shale oil formations.

A comparative study on outlier detection techniques for noisy production data from unconventional shale reservoirs

Decline curve analyses (DCA) and rate transient analyses (RTA) are widely used to characterize the fluid flow through porous media and forecast future production. Oil and gas production data are routinely analyzed for history matching and optimizing the well stimulation methods in hydrocarbon exploration and production lifecycle. However, outliers add significant uncertainty and non-uniqueness to results from production data analysis. This study provides a structured and comprehensive overview of five widely used outlier detection (OD) techniques for identifying and removing outliers in production data. Each OD technique measures deviation differently and, therefore, has a different outcome even when applied to the same dataset, creating the need to test several methods and find the optimal technique for identifying and removing outliers from production data. First, we generated production data from a typical multi-fractured horizontal well using a numerical reservoir simulator and added random noise to the data. Then, we used five different OD techniques to identify the prelabeled outliers from the synthetic production data. Finally, we identified the best-performing OD algorithm by comparing the various evaluation metrics such as the mean absolute error (MAE), precision, sensitivity, and F1 score. Results showed that the angle-based OD (ABOD) had the best MAE, precision, sensitivity, and F1 score of 8%, 85%, 98%, and 0.90, respectively. The next best-performing OD technique was distance-based OD (DBOD), with MAE, precision, sensitivity, and F1 score of 16%, 71%, 100%, and 0.83, respectively. We tested the ABOD method on several field production datasets by assuming different outlier thresholds (fraction of the data points likely to be outliers). Visual inspection of the processed data showed that the ABOD method effectively identified and removed the outliers from a relatively clean dataset (outlier threshold of 20%) and a highly noisy dataset (outlier threshold of 80%). This algorithm is intuitive and can effectively identify and remove outliers from the field production data to improve production forecasting, reserves estimation, and rate transient analysis for multi-fractured horizontal oil and gas reservoirs.

Pressure transient behavior modeling of a multi-horizontal well pad with damaged fracture in shale gas

Multi-fractured horizontal wells significantly promoted the development of shale gas, and multi-well pads are applied generally in field application. The interference between adjacent wells attributed to the close well spacing becomes an issue that must be considered. Also, with the proppant accumulation in near-wellbore, fracture damage with low permeability and strong stress sensitivity usually occurs in far from wellbore fracture section. A semi-analytical model of multi-horizontal well pad with damaged fractures is established for the first time with a method that can deal with non-uniform fractures. Based on numerical inversion, the type curve is obtained and eight regimes are identified by the characteristics of the pressure derivative curve. Good agreement with the numerical simulation manifests the correctness of our model. Afterward, the influences of crucial parameters on pressure transient are studied. Considering the influence of adjacent wells, the pressure derivative curve elevates since well interference regime and finally maintains at a value of ∑0.5qwDi during whole system radial flow. Well spacing has an impact on the appearance time of the well interference regime. The pressure transient type curve since well interference regime moves up with higher production rate of adjacent wells. The damaged fracture section influences the early time pressure transient. With the increase of damaged fracture length, the early time pressure drop is enhanced. With consideration of stress sensitivity, ‘hump’ would be identified in the pressure derivative curve. Compared with undamaged fracture section, the ‘hump’ caused by the stress-sensitive damaged fracture section appears earlier due to a sharper conductivity decline. The model reveals the flow mechanism of stress-sensitive partially propped fractures and provides some new insights on pressure transient analysis of multi-horizontal well pad in shale gas.

Gas–Water Two-Phase Flow Characteristics and Flowback Evaluation for Shale Gas Wells

The dynamic characteristics of shale gas wells are complexly affected by the gas–water two-phase flow. Based on the special flow mechanism of gas–water two-phase flow in shale gas reservoir, this paper establishes a mathematical model for gas–water two-phase flow in shale gas multi-stage fractured horizontal wells, introduces the eigenvalue method and orthogonal transformation, and obtains the analytical solution of the two-phase flow model. The gas–water two-phase flow rules and main influence factors of shale gas wells were identified, further combined with the flowback test characteristics and data of the shale gas wells in southern Sichuan, the characteristic parameters for the evaluation of the gas well flowback effect were determined, and an index system was established for the evaluation of shale gas well flowback. The analysis result shows that the shale gas well flowback effect has a good relationship with its production capacity, which is mainly reflected in the flowback characteristic parameters such as gas breakthrough time, gas breakthrough flowback rate, 30 d flowback rate, and maximum production flowback rate. The shale gas wells with lower flowback factors have a better production capacity than those with higher flowback factors. The flowback evaluation index system can accurately forecast the shale gas well production capacity in its initial stage, and furthermore offer guidance to promptly ascertaining the block development potential and formulating the development schemes.

A Machine Learning Approach to Benchmarking Operators Performance: A New Perspective Utilizing Factor Contribution Analysis

Summary This study explains how production performance of the multifractured horizontal wells can be divided into two key contributing components: geographical location and completion strategy. Furthermore, we show how to quantify the contribution of these two independent components to production and to understand the variations in key performance drivers across the evaluated field. Being able to differentiate these contributions allows us to compare well performance in a consistent manner and identify potential upside opportunities, such as refracturing candidates, infill well development, and operator benchmarking. Further analysis uses multiple benchmarks to evaluate operator performance and assess how underperforming operators can optimize their completion strategies. We use a novel machine learning approach—a combination of XGBoost and Factor Contribution Analysis (FCA)—that not only allows for fieldwide well evaluations, but also provides a quantifiable contribution of each feature to production. Our approach generates a production prediction model and accounts for the completion parameters and geological information for each well. The final model can be used to either predict future performance of a field/well or to understand reservoir and completion characteristics. This study focuses on the latter and provides an approach to understand the main influencing factors behind well performance as a result of location and completion strategies. Our study is conducted on three major unconventional plays (Haynesville, Eagle Ford, and Bakken), where we demonstrate how different completion features (e.g. lateral length, proppant volume, and fluid volume) affect production data and what we could expect in terms of production should the well have been completed differently. We show how to combine the effect of individual controlling factors (e.g. location, depth, lateral length, proppant volume, fluid volume, and well spacing) to appropriately characterize the performance of each well in terms of two key components: location and completion. This enables us to quantify what portion of the production is a result of rock quality and how much is due to its completion strategy. This technique also allows us to quantify and relate each of these features, and highlight areas with desirable geological features, as well as good candidates for refracturing jobs. Moreover, we benchmark different operators’ performance as it relates to changing rock quality and completion strategies.

Numerical Simulation of Choke Size Optimization in a Shale Gas Well

To optimize the flowback system of shale gas horizontal wells after fracturing and to maximize the production capacity of gas wells, pipe flow and flowback models of shale gas multistage fractured horizontal wells were established based on the actual geological engineering conditions and the fracture parameters inverted from automatic history matching by combining experimental and numerical simulation methods. Optimization of the maximum choke size, reasonable opening choke size, replacement stages, and choke replacement frequency were studied. The research results show that the larger the production pressure difference in the early period, the higher the initial gas production rate but the easier the migration of proppant and the higher its stress sensitivity, which increases the permeability damage and weakens the reservoir recovery ability. Thus, the fracture conductivity gets worse and the later gas production rate and liquid production rate get lower. Specifically, the research results mainly include the following: (1) The laboratory experiment results show that the effective stress exceeding 19 MPa caused a proppant breakage and embedding phenomenon, leading to difficult recovery from reservoir permeability damage. Therefore, the maximum production pressure difference corresponding to the single-well maximum choke size shall not exceed 19 MPa. (2) A small opening choke size of a shale gas well is superior to the large one, and according to the numerical simulation, the choke size of 3 mm is recommended to be the reasonable opening choke size. (3) Under the drainage and production systems of replacing the choke size from small to large, the simulation results indicate that the production effect under the drainage and production systems of increasing the choke size incrementally stage by stage with an increase in amplitude of 1 mm is much better than that under the drainage and production systems of increasing the choke size by skipping the stage. (4) When the choke size is increased stage by stage, the research results indicate that the optimal duration of each grade of choke size is 3 days, beyond which, the increase of EUR will not be remarkable. The application of the proposed fine choke system research method in Well-CN001 indicates that the influence amplitude of the reasonable choke system on the daily gas production of Well-CN001 is in the range of 65.96%–121.67% and that on single-well EUR increase amplitude in 20 years is in the range of 5.2%–22.27%. The research results provide technical support for understanding the influence of different choke systems on the productivity of shale gas wells and optimizing the reasonable drainage and production systems of shale gas wells after fracturing.

Pressure Drawdown Management Strategies for Multifractured Horizontal Wells in Shale Gas Reservoirs: A Review.

The flow capacity of shale gas reservoirs is easily impaired during the depletion process due to strong stress sensitivity. Thereby, an adequate production system, namely, the managed pressure drop method, has been widely introduced to the industrial practice application by decelerating the wellbore pressure drop rate and ultimately improving the long-term production process. This work presents a review of the pressure drawdown management mechanisms for shale gas formations. However, clarifying the water–shale interaction physical chemistry process and developing a mathematical model that accurately describes the water–shale interaction mechanism remain a challenge. Moreover, different classifications of the managed production simulation research approaches are discussed in detail. Each approach has its own merits and demerits. Among them, numerical simulations are commonly seen in cognizance of characterizing the managed pressure drawdown production period but are found to be relatively time-consuming and also computationally expensive. An optimized theoretical model is therefore essential because it can lead to a precise estimation of the ultimate long-term production and capture instantaneously the actual shale gas reservoir depletion phenomenon with various production systems compared to other available methods. The key influence of managed pressured production for single wells in shale reservoirs is elaborated as well. As observed from the current review, an accurate description of the pressure drop management mechanism is crucial for the theoretical model of the pressure control production process for shale gas wells. The influence of water–rock interaction on the managed pressure drawdown mechanism cannot be ignored. There have thus been works to improve and enhance it for use in theoretical models for shale formations. On the other hand, the advancement of theoretical models presents an opportunity for better representation of the managed pressure drop production process.

Surrogate-assisted hydraulic fracture optimization workflow with applications for shale gas reservoir development: a comparative study of machine learning models

Unconventional reservoirs have become the main alternative for increasing oil and gas reserves around the world. Owing to their ultralow permeability properties and special pore structure, hydraulic fracturing technology is necessary to realize the efficient development and economic management of unconventional resources. To maximize the production capacity of wells, several fracture parameters, including fracture number, length, width, conductivity, and spacing, need to be optimized effectively. The optimization of hydraulic fracture parameters in shale gas reservoirs generally demands intensive computations owing to the necessity of numerous physicalmodel simulations. This study proposes a machine learning (ML)–assisted global optimization framework to rapidly obtain optimal fracture parameters. We employed three supervised ML models, including the radialbasis function, K-nearest neighbor, and multilayer perceptron, to emulate the relationship between fracture parameters and shale gas productivity for multistage fractured horizontal wells. Firstly, several forward shale gas simulations with embedded discrete fracture models generate training samples. Then, the samples are divided into training and testing samples to train these ML models and optimize network hyper parameters, respectively. Finally, the trained ML models are combined with an intelligent differential evolution algorithm to optimize the fracture parameters. This novel method has been applied to a naturally fractured reservoir model based on the real-field Barnett shale formation. The obtained results are compared with those of conventional optimizations with high-fidelity models. The results confirm the superiority of the proposed method owing to its very low computational cost. The use of ML modeling technology and an intelligent optimization algorithm could greatly contribute to simulation optimization and design, prompting progress in the intelligent development of unconventional oil and gas reservoirs in China.

Semi-analytical modeling of transient pressure behaviour for a multifractured horizontal well in a gas reservoir with a complex fracture network by considering effects of slippage, stress-sensitivity, and gas adsorption/desorption

A semi-analytical technique has been developed, validated, and applied to quantify the pressure behaviour of a multifractured horizontal well (MFHW) in a gas reservoir with discrete fracture networks and an arbitrary boundary. Considering stress-sensitivity and the slippage effect in the matrix subsystem, a pseudo-pressure is incorporated into the gas flow equations. To weaken the strong nonlinearity from such a combined effect, the dual-reciprocity boundary element method (DRBEM) is applied to efficiently and effectively linearize the governing equations by replacing the nonlinear function with a series of particular solutions. Comparing with the boundary element method (BEM), not only can the DRBEM be used to obtain the accurate solution in any space and time domains, but also it is flexible to deal with the nonlinearity restriction in the governing equations. The finite volume method (FVM) is then adopted to simulate gas flow behaviour in the fracture subsystem with different fracture geometries. Not only can the proposed model be applied to a complex fracture network and operating schedules, but also capture complex gas flow behaviour including the Langmuir sorption, slippage effect, and stress-sensitive effect in a gas reservoir with a discrete fracture network and an arbitrary boundary. The mathematical formulations have been validated and then extended to field applications. A strong stress-sensitive effect is found to result in a large pressure drop and offset the permeability-enhancing effect from the slippage effect. In addition, a decrease in pressure drop derived from gas desorption would restrict the stress-sensitive effect. Furthermore, it can be found that each individual factor imposes a significant impact on the linear flow and boundary dominated flow regimes. On the basis of a mutual interference, the combined effect (i.e., stress-sensitivity, slippage effect, and gas adsorption/desorption) may be weaker than that of each individual factor. In the late boundary-dominated flow regime, the effect of boundary shape becomes more obvious on the pressure distribution curves since the pressure wave would reach the boundaries near fractures within a relatively short time.

Fully coupled fluid-solid productivity numerical simulation of multistage fractured horizontal well in tight oil reservoirs

A mathematical model, fully coupling multiple porous media deformation and fluid flow, was established based on the elastic theory of porous media and fluid-solid coupling mechanism in tight oil reservoirs. The finite element method was used to determine the numerical solution and the accuracy of the model was verified. On this basis, the model was used to simulate productivity of multistage fractured horizontal wells in tight oil reservoirs. The results show that during the production of tight oil wells, the reservoir region close to artificial fractures deteriorated in physical properties significantly, e.g. the aperture and conductivity of artificial fractures dropped by 52.12% and 89.02% respectively. The simulations of 3000-day production of a horizontal well in tight oil reservoir showed that the predicted productivity by the uncoupled model had an error of 38.30% from that by the fully-coupled model. Apparently, ignoring the influence of fluid-solid interaction effect led to serious deviations of the productivity prediction results. The productivity of horizontal well in tight oil reservoir was most sensitive to the start-up pressure gradient, and second most sensitive to the opening of artificial fractures. Enhancing the initial conductivity of artificial fractures was helpful to improve the productivity of tight oil wells. The influence of conductivity, spacing, number and length of artificial fractures should be considered comprehensively in fracturing design. Increasing the number of artificial fractures unilaterally could not achieve the expected increase in production.