# US 11,308,413 B2 · Intelligent optimization of flow control devices > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,413 B2 - Document ID: US11308413B2 - Status: Granted - Kind: B2 - Application number: 16/258,335 - Filed: 2019-01-25 - Published: 2020-07-30 - Granted: 2022-04-19 - Earliest claimed: 2019-01-25 - Assignees: Baker Hughes Oilfield Operations LLC - Applicants: Alireza Shahkarami; Guoxiang Liu; Naresh Sundaram Iyer; Hayley Stephenson; Atul Kshirsagar; Tushar Patil; Colin Cranfield - Inventors: Alireza Shahkarami; Guoxiang Liu; Naresh Sundaram Iyer; Hayley Stephenson; Atul Kshirsagar; Tushar Patil; Colin Cranfield - Web page: https://patentgrep.com/patent/US11308413B2 ## CPC - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/00: Machine learning - E21B 43/12: Methods or apparatus for controlling the flow of the obtained fluid to or in wells (E21B43/25 takes precedence; valve arrangements E21B34/00) - E21B 43/14: Obtaining from a multiple-zone well - G06F 30/18: Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling (circuit design at the physical level G06F30/39; network planning tools for wireless communication networks H04W16/18) - G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) - G06F 30/28: using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD] - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - E21B 2200/22: Fuzzy logic, artificial intelligence, neural networks or the like - G01V 20/00: Geomodelling in general - G06F 2111/08: Probabilistic or stochastic CAD - G06F 2111/10: Numerical modelling - G06F 2113/14: Pipes - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02) ## Abstract A method for generating a well completion plan includes: evaluating a plurality of different well completion plans using a reservoir simulator to calculate dynamic flows of fluid through a subsurface formation, each well completion plan having a flow control device with location and associated flow setting or rating, and optionally a packer and location to provide output data for each well completion plan evaluation; developing a surrogate reservoir model using the output data and input data for each well completion plan evaluation; using intelligent sequential sampling of the output and input data for each well completion plan evaluation to provide intelligent sequential sampling data in response to the surrogate reservoir model not meeting a validation criterion; updating the surrogate reservoir model using the intelligent sequential sampling data; and iterating the using and the updating using a latest surrogate reservoir model until the latest surrogate reservoir model meets the validation criterion. ## Claims ### Claim 1 A method for generating a well completion plan and design that meets or converges to a selected objective for a well penetrating a subsurface formation having a reservoir of a hydrocarbon fluid or a geothermal reservoir, the method comprising: evaluating with a processor a plurality of different well completion plans and designs for the well using a reservoir simulator that includes a detailed model of the subsurface formation to calculate dynamic flows of fluid through the subsurface formation, each well completion plan and design in the plurality comprising a flow control device, a location of the flow control device, an adjustment setting or rating of the flow control device related to fluid flow through the flow control device and into or out of tubing disposed in the well, and optionally a packer and location of the packer to provide output data for each well completion plan and design evaluation resulting in a plurality of output data sets, the plurality of output data sets comprising a first data set comprising first evaluation output data corresponding to first input data and a second data set comprising second evaluation output data corresponding to second input data, the second data set being different from the first data set; developing with the processor a surrogate reservoir model using at least some of the first data set; using intelligent sequential sampling of the first data set for with the processor to provide intelligent sequential sampling data in response to the surrogate reservoir model not meeting a validation criterion based on the second data set; updating with the processor the surrogate reservoir model using the intelligent sequential sampling data; iterating with the processor the using and the updating using a latest surrogate reservoir model until the latest surrogate reservoir model meets the validation criterion; calculating with the processor an objective function using the latest surrogate reservoir model and a proposed well completion plan and design; modifying with the processor the proposed well completion plan and design in response to the calculated objective function not meeting the selected objective; iterating with the processor the calculating and the modifying until the latest calculated objective function meets the selected objective; and presenting the modified proposed completion plan and design in which the latest calculated objective function meets the selected objective to a user using a user interface. ### Claim 2 (depends on 1) The method according to claim 1, further comprising implementing the modified completion plan and design in which the latest calculated objective function meets or converges to the selected objective using a rig/platform. ### Claim 3 (depends on 1) The method according to claim 1, wherein the objective function comprises at least one of an amount of oil that can be produced, an amount of money to be made from produced oil, and a return on investment. ### Claim 4 (depends on 1) The method according to claim 1, wherein the flow control device comprises an inflow control device (ICD), an autonomous inflow control device (AICD), an interval control valve (ICV), and/or an outflow control device. ### Claim 5 (depends on 1) The method according claim 1, wherein developing a surrogate reservoir model comprises applying regression to the output data for each well completion plan evaluation using Gaussian Processes that characterize an unknown function in terms of a Gaussian distribution over functions, specified by a mean value and a correlation structure on sampling input space. ### Claim 6 (depends on 5) The method according to claim 5, further comprising using intelligent sequential sampling to obtain locations in the sampling input space to obtain samples to which the Gaussian Processes are applied. ### Claim 7 (depends on 1) The method according to claim 1, wherein intelligent sequential sampling comprises sampling iteratively one sample at a time, modeling an output response for each sample, and exploiting the output response to determine where in input space to sample a subsequent sample. ### Claim 8 (depends on 7) The method according to claim 7, wherein the intelligent sequential sampling comprises selecting a sequential sampling point based on the sampling point having a maximum value of an acquisition function. ### Claim 9 (depends on 1) The method according to claim 1, further comprising evaluating another different well completion plan using the reservoir simulator based on the intelligent sequential sampling data to provide another output data corresponding to the another different well completion plan. ### Claim 10 (depends on 1) The method according to claim 1, further comprising: defining a region of competence for the latest surrogate reservoir model; determining if the latest calculated objective function is within the region of competence for the latest surrogate reservoir model; iterating the intelligent sequential sampling based on the latest calculated objective function not being within the region of competence for the latest surrogate reservoir model in order to update the surrogate reservoir model; and proceeding to implement the optimized well completion plan and design based on the latest calculated objective function being within the region of competence for the latest surrogate reservoir model. ### Claim 11 A system for generating a well completion plan and design that meets a selected objective for a well penetrating a subsurface formation having a reservoir of a hydrocarbon fluid or a geothermal reservoir, the system comprising: a processor; a memory comprising instructions executable by the processor, the instructions being configured to: evaluate a plurality of different well completion plans and designs for the well using a reservoir simulator that includes a detailed model of the subsurface formation to calculate dynamic flows of fluid through the subsurface formation, each well completion plan and design in the plurality comprising a flow control device, an adjustment setting of the flow control device related to fluid flow through the flow control device and into or out of tubing disposed in the well, and optionally a packer and location of the packer to provide output data for each well completion plan and design evaluation resulting in a plurality of output data sets, the plurality of output data sets comprising a first data set comprising first evaluation output data corresponding to first input data and a second data set comprising second evaluation output data corresponding to second input data, the second data set being different from the first data set; develop a surrogate reservoir model using at least some of the first data set; use intelligent sequential sampling of the first data set with the processor to provide intelligent sequential sampling data in response to the surrogate reservoir model not meeting a validation criterion based on the second data set; update the surrogate reservoir model using the intelligent sequential sampling data; iterate the using and the updating using the latest surrogate reservoir model until the latest surrogate reservoir model meets the validation criterion; calculate an objective function using the latest surrogate reservoir model and a proposed well completion plan; modify the proposed well completion plan and design in response to the calculated objective function not meeting the selected objective; and iterate the calculating, and the modifying until the latest calculated objective function meets the selected objective; a user interface configured to present the modified proposed completion plan and design in which the latest calculated objective function meets the selected objective to a user. ### Claim 12 (depends on 11) The system according to claim 11, further comprising a rig/platform configured to implement the modified completion plan and design in which the latest calculated objective function meets or converges to the selected objective. ### Claim 13 (depends on 11) The system according to claim 11, wherein the objective function comprises at least one of an amount of oil that can be produced, an amount of money to be made from produced oil, and a return on investment. ### Claim 14 (depends on 11) The system according to claim 11, wherein in order to develop the surrogate reservoir model the instructions are further configured to apply regression to the output data for each well completion plan evaluation using Gaussian Processes that characterize an unknown function in terms of a Gaussian distribution over functions, specified by a mean value and a correlation structure on sampling input space. ### Claim 15 (depends on 14) The system according to claim 14, wherein the instructions are further configured to use intelligent sequential sampling to obtain locations in the sampling input space to obtain samples to which the Gaussian Processes are applied. ### Claim 16 (depends on 11) The system according to claim 11, wherein intelligent sequential sampling comprises sampling iteratively one sample at a time, modeling an output response for each sample, and exploiting the output response to determine where in input space to sample a subsequent sample. ### Claim 17 (depends on 16) The system according to claim 16, wherein the intelligent sequential sampling comprises selecting a sequential sampling point based on the sampling point having a maximum value of an acquisition function. ### Claim 18 (depends on 11) The system according to claim 11, wherein the instructions are further configured to evaluate another different well completion plan and design using the reservoir simulator based on the intelligent sequential sampling data to provide another output data corresponding to the another different well completion plan and design. ### Claim 19 (depends on 11) The system according to claim 11, wherein the instructions are further configured to: define a region of competence for the latest surrogate reservoir model; determine if the latest calculated objective function is within the region of competence for the latest surrogate reservoir model; iterate the intelligent sequential sampling based on the latest calculated objective function not being within the region of competence for the latest surrogate reservoir model in order to update the surrogate reservoir model; and provide the latest proposed well completion plan and design as the optimized well completion plan and design based on the latest calculated objective function being within the region of competence for the latest surrogate reservoir model. ### Claim 20 (depends on 11) The system according to claim 11, wherein the flow control device comprises an inflow control device (ICD), an autonomous inflow control device (AICD), an interval control valve (ICV), and/or an outflow control device.