Finite Element and Neural Network Models to Forecast Gas Well Inflow Performance of Shale Reservoirs

Azim, Reda Abdel; Aljehani, Abdulrahman S.

doi:10.3390/pr10122602

Cited by 2 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finite-element method (FEM) is a numerical technique for solving approximate solutions of boundary value problems [23,24]. Because of the diversity and flexibility, FEM has been expanded and applied in many fields to obtain approximate solutions of various engineering problems [25].…”

Section: Finite-element Methodsmentioning

confidence: 99%

Synthetic Minority Oversampling Enhanced FEM for Tool Wear Condition Monitoring

Zhou

Ye²,

Huang³

et al. 2023

Processes

View full text Add to dashboard Cite

Recent advances in artificial intelligence (AI) technology have led to increasing interest in the development of AI-based tool wear condition monitoring methods, heavily relying on large training samples. However, the high cost of tool wear experiment and the uncertainty of tool wear change in the machining process lead to the problems of sample missing and insufficiency in the model training stage, which seriously affects the identification accuracy of many AI models. In this paper, a novel identification method based on finite-element modeling (FEM) and the synthetic minority oversampling technique (SMOTE) is proposed to overcome the problem of sample missing and sample insufficiency. Firstly, a few tool wear monitoring experiments are carried out to obtain experimental samples with low cost. Then, a FEM model based on the Johnson–Cook constitutive model was established and verified according to the experimental samples. Based on the verified FEM model, the simulated missing sample in the experiments can be supplemented to compose a complete training set. Finally, the SMOTE is employed to expand the sample size to construct a perfect training set to train the SVM classification model. End milling tool wear monitoring experiments demonstrate that the proposed FEM-SMOTE method can obtain 98.7% identification accuracy, which is 30% higher than that based on experimental samples. The proposed method provides an effective approach for tool wear condition monitoring with low experimental cost.

show abstract

Section: Finite-element Methodsmentioning

confidence: 99%

Synthetic Minority Oversampling Enhanced FEM for Tool Wear Condition Monitoring

Zhou

Ye²,

Huang³

et al. 2023

Processes

View full text Add to dashboard Cite

show abstract

“…The established finite element model in this study was validated in Part I of this study [9] using the data provided in Table 2 with one horizontal hydraulic fracture in the presented shale reservoir simulation model. Figure 6 shows the 2-D model used with pressure and stress distribution around the wellbore.…”

Section: Validation Using a Numerical Simulation Modelmentioning

confidence: 99%

“…The performance of shale gas reservoirs depends on various reservoir rock properties that include flow absorption, desorption, reservoir complexities, and natural fracture apertures. In addition, the subsurface natural gas stored as free and adsorbed gas that makes up to 85% of the total gas reserve and the remaining volume are dissolved in formation water [9]. Unlike conventional gas reservoirs, the flow of shale gas reservoirs has a unique and complex flow behavior where different states of gas coexist in the pore spaces such as free gas in matrix and fracture systems; adsorbed gas mainly occurs in the organic matrix, and dissolved gas occurs in formation water and in organic-rich matter.…”

Section: Introductionmentioning

confidence: 99%

“…The volumetric method for estimating gas in place is based on the log and core analysis data of the reservoir: pressure, average reservoir porosity, average fluid saturation, reservoir thickness, and the initial gas formation volume factor. For shale gas reservoirs, the parameters of gas adsorption characteristics to calculate the adsorbed gas volume are also required [9]. The volume of gas adsorption in shale reservoirs is controlled by total organic carbon, clay mineral components, and shale thermal maturity [18].…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, it can be concluded that the existing MBE's either ignores some of the important shale gas reservoir parameters (such as stress sensitivity, matrix shrinkage, and critical desorption pressure) or it includes such important parameters but with an iterative calculation process. Therefore, this study is a continuation of work that was presented by (Azim et al, 2022) [9] to propose a modified material balance equation for estimating the shale gas reserves by taking into account stress sensitivity during the production process of shale and porosity variation as well as the critical desorption pressure using a simple linear relationship between reservoir expansion and production terms without any need of a complex and iterative calculation process. The proposed material balance equation was derived and validated against production data that were collected from gas wells in a certain shale gas reservoir located in Australia.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Estimation of Shale Gas Reserves: A Modified Material Balance Equation and Numerical Simulation Study

2023

Self Cite

View full text Add to dashboard Cite

This study presents a comprehensive material balance equation (MBE) to estimate the reserve of shale gas reservoirs including free and adsorbed gas volume. The presented material balance equation takes into account the effect of stress change, matrix shrinkage, water volume production and influx, and critical desorption pressure. The material balance equation is converted into a linear relationship between the reservoir production and expansion parameters used during the derivation procedures that include rock-fluid properties and production history data. The proposed straight line reserve evaluation technique yields a slope of original free and absorbed gas in organic matrix, while the y-intercept yields the volume of original free gas in the in-organic matrix. A field case study of shale gas located in Australia is presented. Results show that the proposed MBE and the corresponding straight line reserve evaluation technique are rational and competent in estimating the free gas and adsorbed gas volumes accurately with error less than 6% compared to the numerical simulation model presented in this study using an in-house simulator based on finite element technique and FORTRAN language. Hence, the presented technique in this study can be used as a quick and easy to use tool to accurately estimate the free and adsorbed gas reserves and to improve the development of the production strategies of shale gas reservoirs.

show abstract

Finite Element and Neural Network Models to Forecast Gas Well Inflow Performance of Shale Reservoirs

Cited by 2 publications

References 33 publications

Synthetic Minority Oversampling Enhanced FEM for Tool Wear Condition Monitoring

Synthetic Minority Oversampling Enhanced FEM for Tool Wear Condition Monitoring

Estimation of Shale Gas Reserves: A Modified Material Balance Equation and Numerical Simulation Study

Contact Info

Product

Resources

About