Artificial intelligence(AI)methods and applications have recently gained a great deal of attention in many areas,including fields of mathematics,neuroscience,economics,engineering,linguistics,gaming,and many others.Th...Artificial intelligence(AI)methods and applications have recently gained a great deal of attention in many areas,including fields of mathematics,neuroscience,economics,engineering,linguistics,gaming,and many others.This is due to the surge of innovative and sophisticated AI techniques applications to highly complex problems as well as the powerful new developments in high speed computing.Various applications of AI in everyday life include machine learning,pattern recognition,robotics,data processing and analysis,etc.The oil and gas industry is not behind either,in fact,AI techniques have recently been applied to estimate PVT properties,optimize production,predict recoverable hydrocarbons,optimize well placement using pattern recognition,optimize hydraulic fracture design,and to aid in reservoir characterization efforts.In this study,three different AI models are trained and used to forecast hydrocarbon production from hydraulically fractured wells.Two vastly used artificial intelligence methods,namely the Least Square Support Vector Machine(LSSVM)and the Artificial Neural Networks(ANN),are compared to a traditional curve fitting method known as Response Surface Model(RSM)using second order polynomial equations to determine production from shales.The objective of this work is to further explore the potential of AI in the oil and gas industry.Eight parameters are considered as input factors to build the model:reservoir permeability,initial dissolved gas-oil ratio,rock compressibility,gas relative permeability,slope of gas oil ratio,initial reservoir pressure,flowing bottom hole pressure,and hydraulic fracture spacing.The range of values used for these parameters resemble real field scenarios from prolific shale plays such as the Eagle Ford,Bakken,and the Niobrara in the United States.Production data consists of oil recovery factor and produced gas-oil ratio(GOR)generated from a generic hydraulically fractured reservoir model using a commercial simulator.The Box-Behnken experiment design was used to minimize the number of simulations for this study.Five time-based models(for production periods of 90 days,1 year,5 years,10 years,and 15 years)and one rate-based model(when oil rate drops to 5 bbl/day/fracture)were considered.Particle Swarm Optimization(PSO)routine is used in all three surrogate models to obtain the associated model parameters.Models were trained using 80%of all data generated through simulation while 20%was used for testing of the models.All models were evaluated by measuring the goodness of fit through the coefficient of determination(R2)and the Normalized Root Mean Square Error(NRMSE).Results show that RSM and LSSVM have very accurate oil recovery forecasting capabilities while LSSVM shows the best performance for complex GOR behavior.Furthermore,all surrogate models are shown to serve as reliable proxy reservoir models useful for fast fluid recovery forecasts and sensitivity analyses.展开更多
Production from unconventional formations,such as shales,has significantly increased in recent years by stimulating large portions of a reservoir through the application of horizontal drilling and hydraulic fracturing...Production from unconventional formations,such as shales,has significantly increased in recent years by stimulating large portions of a reservoir through the application of horizontal drilling and hydraulic fracturing.Although oil shales are heavily dependent on oil prices,production forecasts remain positive in the North-American region.Due to the complexity of hydraulically fractured tight formations,reservoir numerical simulation has become the standard tool to assess and predict production performance from these unconventional resources.Many of these unconventional fields are immense,consisting of multistage and multiwell projects,which results in impractical simulation run times.Hence,simplification of large-scale simulation models is now common both in the industry and academia.Typical simplified models such as the“single fracture”approach do not often capture the physics of large-scale projects which results in inaccurate results.In this paper we present a simple,yet rigorous workflow that generates simplified representative models in order to achieve low simulation run times while capturing physical phenomena which is fundamental for accurate calculations.The proposed workflow is based on consideration of representative portions of a large-scale model followed by postprocess scaling to obtain desired full model results.The simplified models that result from the application of the proposed workflow for a single well and a multiwell case are compared to full-scale models and the“single fracture”model.Comparison of fluid rates and cumulative production show that accurate results are possible for simplified models if all important components for a particular case are taken into account.Finally,application of the workflow is shown for a heterogeneous field case where prediction studies can be carried out.展开更多
Borehole thermal energy storage(BTES)systems have garnered significant attention owing to their efficacy in storing thermal energy for heating and cooling applications.Accurate modeling is paramount for ensuring the p...Borehole thermal energy storage(BTES)systems have garnered significant attention owing to their efficacy in storing thermal energy for heating and cooling applications.Accurate modeling is paramount for ensuring the precise design and operation of BTES systems.This study conducts a sensitivity analysis of BTES modeling by employing a comparative investigation of five distinct parameters on a wedge-shaped model,with implications extendable to a cylindrical configuration.The parameters examined included two design factors(well spacing and grout thermal conductivity),two operational variables(charging and discharging rates),and one geological attribute(soil thermal conductivity).Finite element simulations were carried out for the sensitivity analysis to evaluate the round-trip efficiency,both on a per-cycle basis and cumulatively over three years of operation,serving as performance metrics.The results showed varying degrees of sensitivity across different models to changes in these parameters.In particular,the round-trip efficiency exhibited a greater sensitivity to changes in spacing and volumetric flow rate.Furthermore,this study underscores the importance of considering the impact of the soil and grout-material thermal conductivities on the BTES-system performance over time.An optimized scenario is modelled and compared with the base case,over a comparative assessment based on a 10-year simulation.The analysis revealed that,at the end of the 10-year period,the optimized BTES model achieved a cycle efficiency of 83.4%.This sensitivity analysis provides valuable insights into the merits and constraints of diverse BTES modeling methodologies,aiding in the selection of appropriate modeling tools for BTES system design and operation.展开更多
文摘Artificial intelligence(AI)methods and applications have recently gained a great deal of attention in many areas,including fields of mathematics,neuroscience,economics,engineering,linguistics,gaming,and many others.This is due to the surge of innovative and sophisticated AI techniques applications to highly complex problems as well as the powerful new developments in high speed computing.Various applications of AI in everyday life include machine learning,pattern recognition,robotics,data processing and analysis,etc.The oil and gas industry is not behind either,in fact,AI techniques have recently been applied to estimate PVT properties,optimize production,predict recoverable hydrocarbons,optimize well placement using pattern recognition,optimize hydraulic fracture design,and to aid in reservoir characterization efforts.In this study,three different AI models are trained and used to forecast hydrocarbon production from hydraulically fractured wells.Two vastly used artificial intelligence methods,namely the Least Square Support Vector Machine(LSSVM)and the Artificial Neural Networks(ANN),are compared to a traditional curve fitting method known as Response Surface Model(RSM)using second order polynomial equations to determine production from shales.The objective of this work is to further explore the potential of AI in the oil and gas industry.Eight parameters are considered as input factors to build the model:reservoir permeability,initial dissolved gas-oil ratio,rock compressibility,gas relative permeability,slope of gas oil ratio,initial reservoir pressure,flowing bottom hole pressure,and hydraulic fracture spacing.The range of values used for these parameters resemble real field scenarios from prolific shale plays such as the Eagle Ford,Bakken,and the Niobrara in the United States.Production data consists of oil recovery factor and produced gas-oil ratio(GOR)generated from a generic hydraulically fractured reservoir model using a commercial simulator.The Box-Behnken experiment design was used to minimize the number of simulations for this study.Five time-based models(for production periods of 90 days,1 year,5 years,10 years,and 15 years)and one rate-based model(when oil rate drops to 5 bbl/day/fracture)were considered.Particle Swarm Optimization(PSO)routine is used in all three surrogate models to obtain the associated model parameters.Models were trained using 80%of all data generated through simulation while 20%was used for testing of the models.All models were evaluated by measuring the goodness of fit through the coefficient of determination(R2)and the Normalized Root Mean Square Error(NRMSE).Results show that RSM and LSSVM have very accurate oil recovery forecasting capabilities while LSSVM shows the best performance for complex GOR behavior.Furthermore,all surrogate models are shown to serve as reliable proxy reservoir models useful for fast fluid recovery forecasts and sensitivity analyses.
文摘Production from unconventional formations,such as shales,has significantly increased in recent years by stimulating large portions of a reservoir through the application of horizontal drilling and hydraulic fracturing.Although oil shales are heavily dependent on oil prices,production forecasts remain positive in the North-American region.Due to the complexity of hydraulically fractured tight formations,reservoir numerical simulation has become the standard tool to assess and predict production performance from these unconventional resources.Many of these unconventional fields are immense,consisting of multistage and multiwell projects,which results in impractical simulation run times.Hence,simplification of large-scale simulation models is now common both in the industry and academia.Typical simplified models such as the“single fracture”approach do not often capture the physics of large-scale projects which results in inaccurate results.In this paper we present a simple,yet rigorous workflow that generates simplified representative models in order to achieve low simulation run times while capturing physical phenomena which is fundamental for accurate calculations.The proposed workflow is based on consideration of representative portions of a large-scale model followed by postprocess scaling to obtain desired full model results.The simplified models that result from the application of the proposed workflow for a single well and a multiwell case are compared to full-scale models and the“single fracture”model.Comparison of fluid rates and cumulative production show that accurate results are possible for simplified models if all important components for a particular case are taken into account.Finally,application of the workflow is shown for a heterogeneous field case where prediction studies can be carried out.
文摘Borehole thermal energy storage(BTES)systems have garnered significant attention owing to their efficacy in storing thermal energy for heating and cooling applications.Accurate modeling is paramount for ensuring the precise design and operation of BTES systems.This study conducts a sensitivity analysis of BTES modeling by employing a comparative investigation of five distinct parameters on a wedge-shaped model,with implications extendable to a cylindrical configuration.The parameters examined included two design factors(well spacing and grout thermal conductivity),two operational variables(charging and discharging rates),and one geological attribute(soil thermal conductivity).Finite element simulations were carried out for the sensitivity analysis to evaluate the round-trip efficiency,both on a per-cycle basis and cumulatively over three years of operation,serving as performance metrics.The results showed varying degrees of sensitivity across different models to changes in these parameters.In particular,the round-trip efficiency exhibited a greater sensitivity to changes in spacing and volumetric flow rate.Furthermore,this study underscores the importance of considering the impact of the soil and grout-material thermal conductivities on the BTES-system performance over time.An optimized scenario is modelled and compared with the base case,over a comparative assessment based on a 10-year simulation.The analysis revealed that,at the end of the 10-year period,the optimized BTES model achieved a cycle efficiency of 83.4%.This sensitivity analysis provides valuable insights into the merits and constraints of diverse BTES modeling methodologies,aiding in the selection of appropriate modeling tools for BTES system design and operation.