• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    A system and method for adjusting a gas supply for gas extraction from a production well uses Bayesian optimization. A computer device controls a gas supply for injecting gas into one or more wells. The computing device receives reservoir data associated with an underground reservoir into which the wells are to enter and can simulate production using reservoir data and using a physics-based model, a machine learning model, or a hybrid physics-based machine learning model representing the underground reservoir. Production simulation can provide production data. We can perform a Bayesian optimization of an objective function of production data subject to gas injection constraints to generate gas extraction parameters. The gas extraction settings can be applied to the gas supply to adjust the gas injection into the wellbore (s). Figure for the abstract: Figure 1
    公开号:FR3084905A1
    申请号:FR1907578
    申请日:2019-07-08
    公开日:2020-02-14
    发明作者:Srinath Madasu；Terry Wong；Keshava Prasad Rangarajan；Steven Ward；Zhixiang Jiang
    申请人:Landmark Graphics Corp；
    IPC主号:
    专利说明:

    Description
    Title of the invention: OPTIMIZATION OF GAS EXTRACTION IN A WELLBORE Technical field [0001] The present invention relates generally to the use of artificial gas extraction to facilitate production in well systems. More specifically, but not limited to, the present invention relates to the optimized real-time adjustment of gas extraction parameters during production from a wellbore.
    PRIOR ART A well may include a wellbore drilled through an underground formation. The underground formation may include a rock matrix impregnated with the oil to be extracted. The oil distributed through the rock matrix can be called a "reservoir". Reservoirs are often modeled using standard statistical techniques to forecast or determine parameter values that can be used in drilling or production to maximize yield. For example, partial differential equations called "black oil" equations can be used to model a reservoir based on production rates and other production data.
    One method of increasing oil production from a reservoir is to use artificial gas extraction. Artificial gas extraction consists of injecting gas into the production train, also called "production tubing", to reduce the density of the fluid, and thus reduce the hydrostatic charge, in order to allow the tank pressure to act more favorably on the oil which is extracted towards the surface. This gas injection can be achieved by pumping or forcing the gas into the annular space between the production casing and the well casing, and then into the production casing. The gas bubbles mix with the tank fluids, reducing the overall density of the mixture and improving extraction.
    Brief description of the drawings [0004] [fig. 1] Ligure 1 is a side sectional view of an example of a reservoir with a well cluster which includes a system for creating an artificial gas extraction in production wells in certain aspects.
    [Fig.2] Ligure 2 is a block diagram of a computer device for adjusting the parameters of gas extraction according to certain aspects.
    [Fig.3] Ligure 3 is a flow diagram illustrating a process for controlling a gas extraction system in certain aspects.
    [Fig. 4] Ligure 4 is a graphical representation of the pressure contours along the fractures of a reservoir as modeled in certain aspects.
    [Fig.5A-5B] Ligure 5A and Ligure 5B are, respectively, a schematic representation of the pressure contours of Ligure 4 and a detailed graphical representation of part of this schematic representation.
    [Fig. 6] Ligure 6 is a curve representing the production efficiency as a function of the injection flow rate for gas extraction for an example of a well and reservoir according to certain aspects.
    Description of the embodiments Certain aspects and certain characteristics relate to a system which improves, and makes more efficient, the prediction of optimized values for the adjustable parameters of the artificial gas extraction, such as the injection flow rate for the extraction and size of nozzle. Adjustable parameters can be calculated taking into account reservoir data and a physics or machine learning based reservoir model, or a physics and machine learning based hybrid reservoir model. The parameters can be used for real-time adjustment and automation in a gas extraction system to maximize production efficiency.
    The system according to certain examples described here can ensure the optimization of gas extraction by means of a simulation of production in tanks to formulate an objective function based on the quantity of oil produced and the flow rate of gas injected for ensure artificial extraction. Optimized gas extraction parameters can be predicted using Bayesian optimization (OB). The objective function can be based on simulated production data, generated from the physics-based or machine-learning reservoir model, or from the physics-based and machine learning hybrid reservoir model. The reservoir model can be used to generate the data necessary for optimization. The examples combine the reservoir model with gas extraction parameters and input minimization using Bayesian optimization. Bayesian optimization can provide the gas extraction parameters for field optimization with multiple wells in a cluster of wells drilled in the same reservoir.
    In some examples, a system includes a gas supply arrangement for injecting gas into one or more boreholes and a computer device in communication with the gas supply arrangement. The computing device includes a memory device with instructions executable by the computing device to cause the computing device to receive reservoir data associated with an underground reservoir into which the wells are to enter and to simulate production using the reservoir data and using a physics or machine learning model, or a hybrid physics and machine learning model representing the underground reservoir. The production simulation provides the production data. We carry out a Bayesian optimization of an objective function of the production data subject to gas injection constraints to generate gas extraction parameters in response to the satisfaction of the convergence criteria. The gas extraction parameters are applied to the gas supply to adjust the gas injection into the wellbore (s).
    Ligure 1 is a sectional view of an example of underground formation 100 with a reservoir 102 operated by means of a cluster of wells comprising wells defined by the cluster boreholes 103 and 104. The system 105 includes a computer device 140 disposed on the surface 106 of the underground formation 100, as well as a gas source 108 which, in this example, is connected to flow measurement and regulation devices 110. The gas source may comprise a compressor (not shown). The gas source 108 and a flow measurement and control device 110 work together to supply gas to a well and may be referred to herein as "gas supply system", "gas supply arrangement" or "supply in gas ”. The flow measurement and regulation devices 110 can be connected to or form part of a distribution system provided with several gas outlets (not shown). The production tubing train 112 is disposed in the wellbore 103. The production casing train 114 is disposed in the wellbore 104. It should be noted that although the wellbore 103 and 104 are shown as vertical drilling wells, one of these drilling wells, or these two drilling wells, may in addition or as a variant comprise a substantially horizontal section.
    During operation of the system 105 in Ligure 1, the gas flows to the well bottom from the gas supply and enters the production tubing 112 through the injection port 150. The gas enters also in the production tubing 114 through the injection port 152. The gas returns to the surface 106 and can be captured in the gas storage device 160 to be stored, for other uses, or to be recycled. The gas storage device 160 may include a storage tank.
    Still with reference to Ligure 1, the computing device 140 is connected to the gas source 108 and to the flow measurement and regulation devices 110 for adjusting the gas supply to the wells 103 and 104. The computerized device can also receive and store reservoir data for use in production simulations. Tank data can be received through production trains by means of sensors (not shown) which transmit signals to computing device 140, from stored files generated from previous tank monitoring, or even by through user input. The data may include characteristics of the reservoir 102 such as viscosity, speed and pressure of the fluid, as these values vary in space. The data associated with the underground reservoir are used to model the reservoir and simulate production in the computer device 140 according to the aspects described here.
    Figure 2 shows an example of a computing device 140. The computing device 140 includes a processing device 202, a bus 204, a communication interface 206, a memory device 208, a user input device 224 and a display device 226. In certain examples, all or part of the components shown in FIG. 2 can be integrated into a single structure, such as a single housing. In other examples, all or part of the components shown in Figure 2 can be distributed (in separate housings) and in communication with each other. The processing device 202 can execute one or more operations to optimize the gas extraction. The processing device 202 can execute instructions stored in the memory device 208 to perform these operations. The processing device 202 may include a processing device or more than one processing device. Nonlimiting examples of the processing device 202 include a programmable door network ("FPGA"), an application-specific integrated circuit ("ASIC"), a microprocessor device, etc.
    The processing device 202 shown in Figure 2 is coupled in communication to the memory device 208 via the bus 204. The non-transient memory device 208 may include any type of memory device which retains the information stored when it's off. Nonlimiting examples of the memory device 208 include an electrically erasable and programmable read-only memory (“EEPROM”), a flash memory or any other type of non-volatile memory. In some examples, at least a portion of the memory device 208 may include a non-transient computer readable medium from which the processing device 202 can read instructions. A computer readable medium may include electronic, optical, magnetic or other storage devices capable of providing the processing device 202 with computer readable instructions or other program code. Non-limiting examples of computer readable media include (but are not limited to) magnetic disks, memory chips, read only memory (ROM), random access memory ("RAM"), ASIC, processing device configured, optical storage, or any other medium from which a computer processing device can read instructions. The instructions may include the processing of device-specific instructions, generated by a compiler or interpreter from code written in any suitable computer programming language, including C, C ++, C #, etc.
    Still referring to the example of Ligure 2, the memory device 208 includes values stored for constraints 220 to be used in the optimization of adjustable gas extraction parameters. The maximum gas extraction capacity of the system is an example of a constraint. The memory device 208 includes computer program code instructions 209 for adjusting the gas supply to the wells of a well cluster. The instructions for adjusting the gas supply may include a control unit giving an action proportional to the error, its integral and its derivative (PID). The memory device 208 in this example comprises a model 212 of the reservoir 102 based on physics or on machine learning, or a hybrid model 212 of the reservoir 102 based on physics and on machine learning. The reservoir data 219 are also stored in the memory device 208 and can be used with the model 212 based on physics or on machine learning, or with the hybrid model 212 based on physics and on machine learning, to run a production simulation. The production simulation program code instructions 218 are stored in the memory device 208. The production simulation generates production data 214, which is also stored in the memory device 208. The memory device 208 in this example includes an optimizer 210. The optimizer may be, for example, computer program code instructions for implementing Bayesian optimization of an objective function of production data to generate optimal values for the extraction parameters gas adjustable. The results from the optimizer can be stored as adjustable output values 222 in the memory device 208. The optimizer 210 can optimize the objective function subject to convergence criteria 216 to generate the output values 222.
    In some examples, the computing device 140 includes a communication interface 206. The communication interface 206 may represent one or more components which facilitate a network connection or otherwise facilitate communication between electronic devices. Examples include, but are not limited to, wired interfaces such as Ethernet, USB, IEEE 1394 and / or wireless interfaces such as IEEE 802.11, Bluetooth, near field communication (NFC) interfaces, RFID interfaces or radio interfaces for access to cellular telephone networks (for example, transceiver / antenna to access a CDMA, GSM, UMTS or other mobile communication network).
    In some examples, the computing device 140 includes a user input device 224. The user input device 224 can represent one or more components used to enter data. Examples of the user input device 224 may include a keyboard, mouse, touchpad, button or touch screen, etc. In some examples, the computer device 140 includes a display device 226. Examples of the display device 226 can include a liquid crystal display (LCD), a television, a computer screen, a touch screen, etc. In some examples, the user input device 224 and the display device 226 may be one and the same device, such as a touch screen display.
    Figure 3 is a flow diagram illustrating a process 300 for controlling a gas extraction system according to certain aspects. In block 302, the reservoir data 219 is received by the computer device 140. In block 304, the processing device 202 simulates the production using reservoir data 219 and the model 212 based on physics or on machine learning, or the hybrid model 212 based on physics and machine learning, with reservoir data, to provide production data 214. At block 306, processing device 202 performs Bayesian optimization of a function objective of the production data 214 subject to the gas injection constraints 220 and to the convergence criteria 216. The processing device in this example performs Bayesian optimization using the optimizer 210. As examples, convergence criteria can include a maximum number of iterations of the optimizer, convergence within a specified tolerance with respect to the maximum production throughput al, convergence within a specified range of a minimum friction value for the production casing, or a combination of all or some of these criteria. If the convergence criteria are satisfied in block 308, the processing device generates and stores the gas extraction parameters in block 310 as output values 222. If the convergence criteria are not satisfied in block 308, the Bayesian optimization iterations continue at block 306. Gas extraction parameters are applied to the gas source at block 312 to adjust the injection of gas into the wellbore. In some examples, the gas extraction parameters include the gas injection rate, the nozzle size, or both.
    The process 300 of Figure 3 uses Bayesian optimization to model the production with optimal parameters of artificial gas extraction. The production is a function of the gas injection rate, which can be constant or a function of time. The optimal gas injection rate is considered here as the rate necessary to maximize production and minimize friction in the production tubing. The optimal nozzle size for the purposes of the examples described here is the size necessary to avoid back pressure at a gas storage point, for example, at the gas storage device 160 in Figure L [0023 ] The example process shown in Figure 3 can be used to predict the gas extraction parameters that maximize efficiency, in that the predicted parameters are the values that should maximize production while minimizing input. Since the oil produced determines revenues and the gas used is a variable cost, these values can be considered, at least to some extent, as values that maximize profits. For example, profits can be calculated as follows:
    [Math.l]
    Q * price * (fraction of revenue retained) - (gas flow rate) * (gas price) The fraction of revenue retained from a given cluster of wells would be the residual fraction of revenue after payment of leases and operating costs. Q is the oil production rate, which is a function of the length and width of the fracture, as well as the conductivity of the reservoir as modeled. These relationships provide the objective function used for the Bayesian optimization described here. An objective function is sometimes also called an "economic function".
    The example process described here was used for a well with a reservoir model comprising 12 layers having a permeability of 0.002 mD, a porosity of 25%, an initial water saturation of 0.2, an initial pressure 3,500 psia, 23 hydraulic fractures with a half-length of 500 feet, an opening of 0.1 inch, a conductivity of 3 mD at the level of a perforation and a porosity of 30%. Figure 4 is a graphic representation 400 of the pressure contours along the 23 fractures, obtained with the Nexus® reservoir simulation software. Figure 5A is a schematic representation 500 of the fractures and Figure 5B is a close-up view of part of Figure 5A showing an unstructured superimposed grid. The optimal gas injection rate expected in this case using the example process described here was 517.55 Mscf / day. Bayesian optimization predicted optimal parameters with nine observations. The Bayesian optimization predicted a maximum efficiency which would generate a profit of 337.44 million dollars for an optimal gas injection rate of 517.55 Mscf / day.
    Figure 6 is a curve 600 representing the actual production rate as a function of the gas injection rate for the tank modeled as described above. Efficiency is shown on the y-axis and gas extraction injection rate is shown on the x-axis. The curve 602 illustrates the real production increased by gas extraction and the point 604 is where the maximum efficiency is reached. The forecast using Bayesian optimization is very close to the best real gas injection rate.
    Unless otherwise indicated, it is understood that, throughout this description, terms such as "treatment", "calculation", "determination", "operations" or other similar terms denote the actions or processes of '' a computer device, such as the control unit or the processing device described here, which can manipulate or transform data represented in the form of electronic or magnetic physical values in memories, registers or other devices information storage, transmission devices or display devices. The order of the processing blocks presented in the examples above can be modified; for example, blocks can be reordered, combined or broken down into sub-blocks. Certain blocks or processes can be executed in parallel. As used here, the term "configured for" is intended to be open and inclusive, in the sense that it does not exclude that devices are configured to perform additional tasks or steps. In addition, as used here, the expression "based on" is meant to be open and inclusive, in the sense that a process, a step, a calculation or other action "based on" a or several conditions or values mentioned may, in practice, be based on conditions or values other than those mentioned. Items described as "related" or "connectable", or described in similar terms, can be linked directly or through intermediaries.
    As used below, any reference to a series of examples should be understood as a reference to each of these examples taken in isolation (for example, "Examples 1 to 4" should be understood as "Example 1, 2, 3 or 4 ”).
    Example 1. A system comprises a gas supply arrangement for injecting gas into at least one wellbore near the production casing for the at least one wellbore and a computer device in communication with the gas supply arrangement. The computing device includes a non-transient memory device including instructions executable by the computing device to cause the computing device to perform operations. The operations include receiving reservoir data associated with an underground reservoir into which at least one borehole is to enter, simulating production using reservoir data associated with the underground reservoir and using '' a physics-based model, a machine learning model, or a physics-based hybrid machine learning model representing the underground reservoir, to provide production data, achieving optimization an objective function of production data subject to gas injection constraints and convergence criteria to generate gas extraction parameters and the application of gas extraction parameters to the layout of gas supply in response to meeting the convergence criteria to adjust the gas injection into the at least one well age.
    Example 2. The system according to Example 1, wherein the at least one wellbore comprises several cluster wells. The system further includes a production tubing train disposed in at least one of the plurality of cluster wells, an injection port connected to the production tubing train for injecting downhole gas into the production tubing train, and a gas storage device connected to the production tubing train.
    Example 3. The system according to Examples 1 to 2, in which the gas extraction parameters include the gas injection rate and the nozzle size.
    Example 4. The system according to Examples 1 to 3, in which the gas injection rate is constant.
    Example 5. The system according to Examples 1 to 4, in which the gas injection rate is a function of time.
    Example 6. The system according to Examples 1 to 5, in which the convergence criteria include a maximum number of iterations.
    Example 7. The system according to Examples 1 to 6, wherein the convergence criteria include convergence within a specified tolerance with respect to a maximum production flow and a minimum friction value for the production casing.
    Example 8. LJn method comprises receiving, by a processing device, reservoir data associated with an underground reservoir into which must penetrate at least one wellbore, the simulation, by the processing device, of the production using reservoir data associated with the underground reservoir and using a physics-based model, a machine learning model, or a hybrid physics-based machine learning model representing the underground reservoir, in order to provide the production data, the realization, by the processing device, of a Bayesian optimization of an objective function of the production data subject to gas injection constraints and to convergence criteria for generating gas extraction parameters and applying, by the processing device, gas extraction parameters to a supply arrangement gas specification in response to meeting the convergence criteria to adjust the gas injection into the at least one wellbore.
    Example 9. The method according to Example 8, wherein the at least one wellbore comprises several cluster wells. At least one of the wells includes a production casing train. The method further includes injecting downhole gas into the production tubing train, and capturing the gas at a gas storage device connected to the production tubing train.
    Example 10. The method according to Examples 8 to 9, in which the gas extraction parameters include the gas injection rate and the nozzle size.
    Example 11. The method according to Examples 8 to 10, in which the gas injection rate is constant.
    Example 12. The method according to Examples 8 to 11, in which the gas injection rate is a function of time.
    Example 13. The method according to Examples 8 to 12, in which the convergence criteria include a maximum number of iterations.
    Example 14. The method according to Examples 8 to 13, in which the convergence criteria include convergence within a specified tolerance with respect to a maximum production rate and a minimum friction value for the production casing.
    Example 15. A non-transient computer-readable medium comprises instructions which can be executed by a processing device to cause the processing device to execute a method. The method includes receiving reservoir data associated with an underground reservoir into which a wellbore cluster is to enter, simulating production using reservoir data associated with the underground reservoir and using a physics-based model, a machine learning model, or a physics-based hybrid machine learning model representing the underground reservoir, in order to provide production data, achieving Bayesian optimization of '' an objective function of production data subject to gas injection constraints and convergence criteria to generate gas extraction parameters and the application of gas extraction parameters to a gas supply arrangement gas in response to meeting the convergence criteria to adjust the injection of gas into at least one borehole in the gra borehole ppe.
    Example 16. The non-transient computer-readable medium according to Example 15, in which the gas extraction parameters include the gas injection rate and the nozzle size.
    Example 17. The non-transient computer-readable medium according to Examples 15 to 16, in which the gas injection rate is constant.
    Example 18. The non-transient computer-readable medium according to Examples 15 to
    17, in which the gas injection rate is a function of time.
    Example 19. The non-transient computer-readable medium according to Examples 15 to 18 further comprises instructions which can be executed by a processing device to cause the processing device to inject gas at the bottom of the well in a train. production tubing and capturing the gas at a gas storage device connected to the production tubing train.
    Example 20. Non-transient computer-readable medium according to Examples 15 to 19, in which the convergence criteria include at least one of a maximum number of iterations, of convergence within a specified tolerance with respect to maximum production flow and minimum friction value for production tubing.
    The foregoing description of certain examples, including the illustrated examples, has been presented only for purposes of illustration and description and is not intended to be exhaustive or to limit the invention to the forms specific described. Many modifications, adaptations and uses of these will appear to the specialist in the field without departing from the scope of the invention.
    权利要求:
    Claims (1)
    [1" id="c-fr-0001]
    claims [Claim 1] System comprising:a gas supply arrangement for injecting gas into at least one wellbore near the production casing for the at least one wellbore; anda computing device in communication with the gas supply arrangement, the computing device comprising a non-transient memory device comprising instructions executable by the computing device to cause the computing device to carry out operations comprising:receiving reservoir data associated with an underground reservoir into which at least one borehole is to enter;simulation of production using reservoir data associated with the underground reservoir and using a physics-based model, a machine learning model, or a hybrid machine learning model based on physics representing the underground reservoir, to provide production data;carrying out a Bayesian optimization of an objective function of production data subject to gas injection constraints and convergence criteria to generate gas extraction parameters; andapplying the gas extraction parameters to the gas supply arrangement in response to meeting the convergence criteria to adjust the gas injection into the at least one wellbore. [Claim 2] The system of claim 1, wherein the at least one wellbore comprises a plurality of cluster wells, the system further comprising:a production tubing train disposed in at least one of the plurality of cluster wells;an injection port connected to the production tubing train for injecting downhole gas into the production tubing train; and a gas storage device connected to the production tubing train. [Claim 3] The system of claim 1 or claim 2, wherein the gas extraction parameters include the gas injection rate and the nozzle size. [Claim 4] The system of claim 3, wherein the gas injection rate
    is constant. [Claim 5] The system of claim 3, wherein the gas injection rate is a function of time. [Claim 6] The system of claim 1 or claim 2, wherein the convergence criteria include a maximum number of iterations. [Claim 7] The system of claim 1 or claim 2, wherein the convergence criteria include convergence within a specified tolerance with respect to a maximum production rate and a minimum friction value for the production casing. [Claim 8] Process comprising:receiving, by a processing device, reservoir data associated with an underground reservoir into which at least one borehole is to penetrate;the simulation, by the processing device, of production using reservoir data associated with the underground reservoir and using a physics-based model, a machine learning model, or a hybrid physics-based machine learning model representing the underground reservoir to provide production data;the realization, by the processing device, of a Bayesian optimization of an objective function of the production data subject to gas injection constraints and to convergence criteria to generate gas extraction parameters; and applying, by the processing device, gas extraction parameters to a gas supply arrangement in response to meeting the convergence criteria for adjusting the injection of gas into the at least one well. drilling. [Claim 9] The method of claim 8, wherein the at least one wellbore comprises a plurality of cluster wells, at least one of the plurality of cluster wells comprising a production casing train, the method further comprising: injecting downhole gas into the production tubing train; andgas capture at a gas storage device connected to the production tubing train. [Claim 10] The method of claim 8 or claim 9, wherein the gas extraction parameters include the gas injection rate and the nozzle size.
    [Claim 11] [Claim 12] [Claim 13] [Claim 14] [Claim 15]
    The method of claim 10, wherein the gas injection rate is constant.
    The method of claim 10, wherein the gas injection rate is a function of time.
    The method of claim 8 or claim 9, wherein the convergence criteria include a maximum number of iterations.
    The method of claim 8 or claim 9, wherein the convergence criteria include convergence within a specified tolerance with respect to a maximum production rate and a minimum friction value for the production casing.
    A non-transient computer readable medium which includes instructions which are executable by a processing device to cause the processing device to perform the method of claim 8 or claim 9.
    类似技术:
    公开号 | 公开日 | 专利标题
    US9104823B2|2015-08-11|Optimization with a control mechanism using a mixed-integer nonlinear formulation
    Bredehoeft2002|The water budget myth revisited: why hydrogeologists model
    FR3084905A1|2020-02-14|OPTIMIZATION OF GAS EXTRACTION IN A WELLBORE
    FR2961844A1|2011-12-30|MULTIPHASE FLOW IN A WELLBORE AND CONNECTED HYDRAULIC FRACTURE
    JP2019523515A|2019-08-22|Many water resource management tools
    EP2426630A1|2012-03-07|Method for optimising the positioning of wells in an oil deposit
    Deng et al.2020|Machine-learning-assisted closed-loop reservoir management using echo state network for mature fields under waterflood
    Deng et al.2021|Data-driven proxy model for waterflood performance prediction and optimization using Echo State Network with Teacher Forcing in mature fields
    Castineira et al.2018|Augmented AI Solutions for Heavy Oil Reservoirs: Innovative Workflows That Build from Smart Analytics, Machine Learning And Expert-Based Systems
    Saputra et al.2021|Generalized extreme value statistics, physical scaling and forecasts of gas production in the Haynesville shale
    WO2017143326A1|2017-08-24|System and method for generating a schedule to extract a resource fluid from a reservoir
    US20150149089A1|2015-05-28|Determining reserves of a reservoir
    US9376905B2|2016-06-28|Expert systems for well completion using Bayesian probabilities, open hole gravel pack types, gravel pack design details, open hole gravel packs, and completion types
    FR3086321A1|2020-03-27|WELL OPERATIONS INVOLVING A SYNTHETIC INJECTION FRACTURE TEST
    US9262561B2|2016-02-16|Modeling of non-newtonian fluids in subterranean reservoirs
    FR3086779A1|2020-04-03|MATCHING AN AUTOMATED PRODUCTION HISTORY USING BAYESIAN OPTIMIZATION
    Shahkarami et al.2017|Performance Forecast and Optimization Workflow for Horizontal Wells: A Case Study on Utica-Point Pleasant Shale Play
    FR2926591A1|2009-07-24|IMPROVING PRODUCTION BY DISTRIBUTING REAL LOSS
    Gladkov et al.2017|Application of CRM for production and remaining oil reserves reservoir allocation in mature west Siberian waterflood field
    Molina et al.2020|Artificial Intelligence for Production Optimization in Unconventional Reservoirs
    Liu et al.2016|Assessment model for estimating CO2 commercial storage capacity in saline formations: A case study in Taiwan
    Naufal et al.2021|A Digital Oilfield Comprehensive Study: Automated Intelligent Production Network Optimization
    FR3032222A1|2016-08-05|PRIORI UNCERTAINTY PARAMETER ARCHITECTURE INTEGRATED IN SIMULATION MODEL CREATION
    FR3037683B1|2019-08-02|AUTOMATED CHARACTERIZATION OF PVT AND FLOW MEASUREMENT
    FR3084906A1|2020-02-14|OPERATION OF A WELLBORE EQUIPMENT USING A DISTRIBUTED DECISION-MAKING FRAMEWORK
    同族专利:
    公开号 | 公开日
    US20210404302A1|2021-12-30|
    GB202018658D0|2021-01-13|
    NO20201425A1|2020-12-22|
    CA3100491A1|2020-02-13|
    GB2588322A|2021-04-21|
    WO2020032949A1|2020-02-13|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    US9280517B2|2011-06-23|2016-03-08|University Of Southern California|System and method for failure detection for artificial lift systems|
    US9157308B2|2011-12-29|2015-10-13|Chevron U.S.A. Inc.|System and method for prioritizing artificial lift system failure alerts|
    WO2013188090A1|2012-06-15|2013-12-19|Landmark Graphics Corporation|Methods and systems for gas lift rate management|
    US10138724B2|2012-07-31|2018-11-27|Landmark Graphics Corporation|Monitoring, diagnosing and optimizing gas lift operations by presenting one or more actions recommended to achieve a GL system performance|
    US10012059B2|2014-08-21|2018-07-03|Exxonmobil Upstream Research Company|Gas lift optimization employing data obtained from surface mounted sensors|US20210372259A1|2020-05-26|2021-12-02|Landmark Graphics Corporation|Real-time wellbore drilling with data quality control|
    WO2021251981A1|2020-06-12|2021-12-16|Landmark Graphics Corporation|Shale field wellbore configuration system|
    法律状态:
    2021-04-09| ST| Notification of lapse|Effective date: 20210306 |
    优先权:
    申请号 | 申请日 | 专利标题
    PCT/US2018/045949|WO2020032949A1|2018-08-09|2018-08-09|Wellbore gas lift optimization|
    IBPCT/US2018/045949|2018-08-09|
    [返回顶部]