Landmark Graphics Corporation

Halliburton Energy Services, Inc.

Jianxin Lu

Andrey V Filippov

Vitaly Khoriakov

Dale E Jamison

Michael Thomas Pelletier

Li Gao

Srinath Madasu

Keshava Prasad Rangarajan

Avinash Wesley

Arash Haghshenas

Feifei Zhang

Vitaly Anatolievich Khoriakov

System and methods for training neural network models for real-time flow simulations are provided. Input data is acquired. The input data includes values for a plurality of input parameters associated with a multiphase fluid flow. The multiphase fluid flow is simulated using a complex fluid dynamics (CFD) model, based on the acquired input data. The CFD model represents a three-dimensional (3D) domain for the simulation. An area of interest is selected within the 3D domain represented by the CFD model. A two-dimensional (2D) mesh of the selected area of interest is generated. The 2D mesh represents results of the simulation for the selected area of interest. A neural network is then trained based on the simulation results represented by the generated 2D mesh.

Effective representation of complex three-dimensional simulation results for real-time operations

Gas bubble migration can be managed in liquids. In one example, a system can execute wellbore-simulation software to simulate changes in gas dissolution in a liquid over time. This may involve dividing the wellbore into segments spanning from the well surface to the downhole location, each segment spanning a respective depth increment between the well surface and the downhole location. Next, for each time, the system can determine a respective multiphase-flow regime associated with each segment of the plurality of segments based on a simulated pressure level, a simulated temperature, a simulated pipe eccentricity, and a simulated fluid velocity at the segment. The system can also determine how much of the gas is dissolved in the liquid at each segment based on the respective multiphase-flow regime at the segment. The system can display a graphical user interface representing the gas dissolution in the liquid over time.

Managing gas bubble migration in a downhole liquid

A system includes a processor. The processor estimates a pattern of a flow of a mixture of drilling fluid and cuttings in an annulus of a wellbore. The flow is estimated as a stationary bed flow, a dispersed flow, or a transitional flow relative to the stationary bed and dispersed flows. The processor estimates parameters based on the estimated pattern of the flow, and determines a plurality of dimensionless parameters including a first dimensionless parameter corresponding to an effect of turbulence on the flow and a second dimensionless parameter corresponding to an effect of gravity on the flow, based on the estimated parameters. The processor characterizes the pattern of the flow as the stationary bed flow, the dispersed flow, or the transitional flow, based on the dimensionless parameters, and models the flow based on the estimated pattern if it is determined that the characterized pattern matches the estimated pattern.

Method and device for hole cleaning and drilling hydraulic design

An estimated gas leak flow rate can be determined using a teaching set of concentration profiles, a regression model implemented by a machine-learning subsystem, and a subset of attributes measured within an environment. The teaching set of concentration profiles can include gas flow rates associated with relevant attributes. The regression model can be transformed into a gas leak flow regression model via the machine-learning subsystem using the teaching set. The subset of attributes measured within the environment can be applied to the gas leak flow regression model to determine other attributes absent from the subset of attributes and an estimated gas flow rate for the environment. A gas leak attenuation action can be performed in response to the estimated gas flow rate.

Determining gas leak flow rate in a wellbore environment

System and methods for controlling suspended particle redistribution during stimulation treatments. Fluid flow in a wellbore is simulated for a stimulation treatment to be performed along a section of the wellbore within a subterranean formation, based on a flow model associated with the wellbore. Based on the simulation, dimensionless parameters characterizing a flow of suspended particles within a treatment fluid to a fractured area of the formation via at least one perforation along the section of the wellbore are calculated. A collection efficiency of the suspended particles within the fluid is determined, based on the dimensionless parameters. The collection efficiency is used to calculate a flow rate of the suspended particles to the fractured area of the formation via the perforation. The flow rate is used to estimate an amount of the suspended particles to be injected into the wellbore during the stimulation treatment along the wellbore section.

Controlling redistribution of suspended particles in non-Newtonian fluids during stimulation treatments

The disclosed embodiments include a method, apparatus, and computer program product for determining optimal flow control device (FCD) properties that would yield to a prescribed shape of the injection flow rate profile. For example, in one embodiment, a computer implemented method is configured to perform the steps of: determining a reference location along a production length of the injection well; determining a reference value equal to the injection flow rate profile at the reference location along the production length of the injection well; defining a target injection profile using the reference value; determining a pressure distribution along the production length of the injection well based on the target injection profile; determining a FCD distribution profile using the target injection profile and the pressure distribution; and determining FCD properties that yields the target injection profile based on the FCD distribution profile.

Optimizing flow control device properties for a liquid injection well using a coupled wellbore-reservoir model

The disclosed embodiments include a computer implemented method, apparatus, and computer program product that includes executable instructions that when executed performs operations for determining flow control device properties for an injection well that would yield to a prescribed uniform or non-uniform accumulated injection profile along a production well.

Optimizing flow control device properties for accumulated liquid injection

A computer implemented method, system, and computer program product are provided for determining flow control device (FCD) properties for a gas injection well that would yield a prescribed shape of a gas injection front according to a target gas injection profile. An FCD distribution function is adjusted based on the results of a simulation of injected gas flow distribution in the gas injection well over a period of time. The simulation and resulting adjustment of the FCD distribution function is repeated until a convergence between a shape of a displaced oil volume front obtained using the adjusted flow control device distribution function and a target gas injection profile is reached within a predetermined convergence range. The FCD properties are then determined based on the adjusted FCD distribution function.

Growing community of inventors

Bellaire, TX, United States of America

Jianxin Lu