Accelerating flash calculations in unconventional reservoirs considering capillary pressure using an optimized deep learning algorithm

Tao, Zhang; Li, Yiteng; Sun, Shuyu; Bai, Hua

doi:10.1016/j.petrol.2020.107886

Cited by 56 publications

(29 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be easily referred that the two-phase region has been extended if capillarity is taken into account, while a higher temperature is needed for the mixture entering the single (vapor) phase region. This finding meets exactly the conclusion in [37] that the bubble point curve is suppressed with capillarity while the dew point curve is expanded outward with dew point pressure decreasing (and increasing) in the lower (and upper) branch of the dew point curve in the phase envelop. Thus, the proposed TINN configuration is proven to be effective in both phase equilibrium predictions and study on the effect capillary pressures.…”

Section: Scheme Verificationsupporting

confidence: 90%

“…However, the effect of capillarity was not taken into consideration, which limited the adaption in unconventional studies. Capillarity was considered in [37], but an implicit constraint was implied in that scheme as the pore size was assumed to be constant. In recent years, a number of publications have been reported to handle various phase equilibrium problems [38][39][40], and the concept of deep learning and artificial neural network has also been sorted [41].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure

Tao

Sun

2021

Energies

Self Cite

View full text Add to dashboard Cite

The thermodynamic properties of fluid mixtures play a crucial role in designing physically meaningful models and robust algorithms for simulating multi-component multi-phase flow in subsurface, which is needed for many subsurface applications. In this context, the equation-of-state-based flash calculation used to predict the equilibrium properties of each phase for a given fluid mixture going through phase splitting is a crucial component, and often a bottleneck, of multi-phase flow simulations. In this paper, a capillarity-wise Thermodynamics-Informed Neural Network is developed for the first time to propose a fast, accurate and robust approach calculating phase equilibrium properties for unconventional reservoirs. The trained model performs well in both phase stability tests and phase splitting calculations in a large range of reservoir conditions, which enables further multi-component multi-phase flow simulations with a strong thermodynamic basis.

show abstract

Section: Scheme Verificationsupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure

Tao

Sun

2021

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wang et al [45] introduced an ANN model for stability testing that predicts the saturation pressure. Similar works have been presented by various authors [46][47][48][49]. Recently Gaganis et al [50] presented a method, based on simple cubic splines, that produces k-values for depletion and water flooding production schemes where k-values depend mostly on pressure and temperature rather than on composition.…”

Section: Introductionmentioning

confidence: 60%

Application of Machine Learning to Accelerate Gas Condensate Reservoir Simulation

2022

View full text Add to dashboard Cite

According to the roadmap toward clean energy, natural gas has been pronounced as the perfect transition fuel. Unlike usual dry gas reservoirs, gas condensates yield liquid which remains trapped in reservoir pores due to high capillarity, leading to the loss of an economically valuable product. To compensate, the gas produced on the surface is stripped from its heavy components and reinjected back to the reservoir as dry gas thus causing revaporization of the trapped condensate. To optimize this gas recycling process compositional reservoir simulation is utilized, which, however, takes very long to complete due to the complexity of the governing differential equations implicated. The calculations determining the prevailing k-values at every grid block and at each time step account for a great part of total CPU time. In this work machine learning (ML) is employed to accelerate thermodynamic calculations by providing the prevailing k-values in a tiny fraction of the time required by conventional methods. Regression tools such as artificial neural networks (ANNs) are trained against k-values that have been obtained beforehand by running sample simulations on small domains. Subsequently, the trained regression tools are embedded in the simulators acting thus as proxy models. The prediction error achieved is shown to be negligible for the needs of a real-world gas condensate reservoir simulation. The CPU time gain is at least one order of magnitude, thus rendering the proposed approach as yet another successful step toward the implementation of ML in the clean energy field.

show abstract

“…Phase transition is not preferred in practical pipeline dispatching, as it may cause unsafe heat production, hydrate blockage and surface corrosion [16,17]. The accelerated phase equilibrium calculations using the thermodynamics-informed neural network (TINN) have been investigated thoroughly in [18][19][20]. Thus, it is meaningful to incorporate the flash calculation network and the pipeline dispatching network in order to construct a coupled deep neural network and the related deep learning algorithm to evaluate the safety performance in the natural gas pipeline dispatching.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Natural Gas and Hydrogen Pipeline Dispatching Using the Coupled Thermodynamics-Informed Neural Network and Compressor Boolean Neural Network

Tao

Bai²,

Sun

2022

Processes

Self Cite

View full text Add to dashboard Cite

Natural gas pipelines have attracted increasing attention in the energy industry thanks to the current demand for green energy and the advantages of pipeline transportation. A novel deep learning method is proposed in this paper, using a coupled network structure incorporating the thermodynamics-informed neural network and the compressor Boolean neural network, to incorporate both functions of pipeline transportation safety check and energy supply predictions. The deep learning model is uniformed for the coupled network structure, and the prediction efficiency and accuracy are validated by a number of numerical tests simulating various engineering scenarios, including hydrogen gas pipelines. The trained model can provide dispatchers with suggestions about the number of phases existing during the transportation as an index showing safety, while the effects of operation temperature, pressure and compositional purity are investigated to suggest the optimized productions.

show abstract

Accelerating flash calculations in unconventional reservoirs considering capillary pressure using an optimized deep learning algorithm

Cited by 56 publications

References 58 publications

Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure

Thermodynamics-Informed Neural Network (TINN) for Phase Equilibrium Calculations Considering Capillary Pressure

Application of Machine Learning to Accelerate Gas Condensate Reservoir Simulation

Intelligent Natural Gas and Hydrogen Pipeline Dispatching Using the Coupled Thermodynamics-Informed Neural Network and Compressor Boolean Neural Network

Contact Info

Product

Resources

About