Method and device for splitting production of multi-layer commingled gas well

Abstract

This invention provides a method and apparatus for dividing the production of multi-layer syndicated gas wells, relating to the field of oil and gas reservoir productivity evaluation technology. The method includes: acquiring static parameters and initial dynamic parameters of each gas reservoir layer; inputting the static parameters and initial dynamic parameters of each gas reservoir layer into a daily gas production prediction model to determine the initial daily gas production of each gas well layer; determining the productivity index of each gas well layer based on the initial daily gas production and the gas productivity equation; determining the total gas production of all gas well layers within the production cycle based on the productivity index of each gas well layer, the gas productivity equation corrected using a production correction coefficient, the dynamic reserves of each gas reservoir layer, and the material balance equation; setting the minimum deviation between the total gas production and historical measured gas production as the optimization objective, and optimizing the production correction coefficient; and calculating the daily gas production of each gas well layer within the production cycle based on the gas productivity equation corrected using the optimized production correction coefficient.

Description

Technical Field

[0001] This invention relates to the field of oil and gas reservoir productivity evaluation technology, and more particularly to a method and apparatus for dividing the production of multi-layered syngas wells. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] Due to the influence of diagenesis and sedimentary environment, multi-layered gas reservoirs have complex reservoir structures, with differences in reservoir porosity, permeability, and thickness among the various layers. Furthermore, the extraction methods for each layer differ, resulting in varying production rates for each well during extraction. To formulate development adjustment strategies for multi-layered gas reservoirs, it is necessary to accurately analyze the production rates of wells in multiple layers and determine the production patterns of each well. Current technologies typically use geological parameter methods to calculate the gas production of each well, but this method has significant errors and therefore cannot guide the formulation of development strategies for multi-layered gas reservoirs. Summary of the Invention

[0004] This invention proposes a method for dividing the production of multi-layer syngas wells, which improves the accuracy of calculating the gas production of each well layer and ensures the reliability of production division in multi-layer syngas wells. This method can guide the formulation of development strategies for multi-layer gas reservoirs, including:

[0005] Obtain the static parameters and initial dynamic parameters of each gas reservoir;

[0006] The static parameters and initial dynamic parameters of each gas reservoir are input into the daily gas production prediction model to determine the initial daily gas production of each gas well. The daily gas production prediction model is obtained by training a machine learning model based on the static parameters and initial dynamic parameters of historical gas reservoirs and the corresponding historical daily gas production.

[0007] Based on the initial daily gas production and gas production capacity equation of each gas production well, the production capacity index of each gas production well is determined.

[0008] Based on the production capacity index of each gas well, the gas production capacity equation corrected by the production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation, the total gas production of all gas wells in all layers during the production cycle is determined. The optimization target is set as minimizing the deviation between the total gas production and the historical measured gas production. The production correction coefficient is optimized according to the optimization target. The production correction coefficient is used to improve the calculation accuracy of the gas production capacity equation.

[0009] Based on the optimized production correction coefficient, the gas production capacity equation, the dynamic reserves of each gas reservoir, and the material balance equation, the daily gas production of each gas well during the production cycle is calculated.

[0010] This invention proposes a multi-layer syngas well production splitting device to improve the accuracy of gas production calculation for each well layer, ensuring the reliability of multi-layer syngas well production splitting. This device can guide the formulation of development strategies for multi-layer gas reservoirs, including:

[0011] The parameter acquisition module is used to acquire the static parameters and initial dynamic parameters of each gas reservoir.

[0012] The daily gas production prediction module is used to input the static parameters and initial dynamic parameters of each gas reservoir into the daily gas production prediction model to determine the initial daily gas production of each gas well. The daily gas production prediction model is obtained by training a machine learning model based on the static parameters and initial dynamic parameters of historical gas reservoirs and the corresponding historical daily gas production.

[0013] The production capacity index determination module is used to determine the production capacity index of each gas production well based on the initial daily gas production and gas production capacity equation of each gas production well.

[0014] The optimization and correction module is used to determine the total gas production of all gas wells in all layers during the production cycle based on the production capacity index of each gas well, the gas production capacity equation corrected by the production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation. The optimization target is to minimize the deviation between the total gas production and the historical measured gas production. The production correction coefficient is optimized according to the optimization target. The production correction coefficient is used to improve the calculation accuracy of the gas production capacity equation.

[0015] The daily gas production calculation module is used to calculate the daily gas production of each gas well during the production cycle based on the gas production capacity equation corrected by the optimized production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation.

[0016] An embodiment of the present invention proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for splitting the production of multi-layer syngas wells.

[0017] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a method for splitting the production of multi-layered syngas wells.

[0018] This invention provides a computer program product, which includes a computer program that, when executed by a processor, implements a method for splitting the production of multi-layered syngas wells.

[0019] The horizontal well coordinated cold production method and device proposed in this invention can solve the problem that the existing technology has large errors in calculating the gas production of each gas production well, which cannot guide the formulation of development strategies for multi-layer gas reservoirs. This invention obtains the static parameters and initial dynamic parameters of each gas reservoir; inputs these parameters into a daily gas production prediction model to determine the initial daily gas production of each gas production well; wherein, the daily gas production prediction model is obtained by training a machine learning model based on the historical static parameters and initial dynamic parameters of the gas reservoir, and the corresponding historical daily gas production; based on the initial daily gas production of each gas production well and the gas production rate... The process involves determining the production capacity index of each gas production well layer; based on the production capacity index of each gas production well layer, the gas production capacity equation corrected using a production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation, determining the total gas production of all gas production wells within the production cycle; minimizing the deviation between the total gas production and historical measured gas production is set as the optimization objective; and the production correction coefficient is optimized based on the optimization objective; the production correction coefficient is used to improve the calculation accuracy of the gas production capacity equation; and based on the optimized production correction coefficient, the gas production capacity equation corrected by the gas correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation, the daily gas production of each gas production well within the production cycle is calculated. This embodiment of the invention can optimize the production correction coefficient, improve the calculation accuracy of the gas production of each gas production well layer, ensure the reliability of production allocation for multi-layer syndicated gas wells, and guide the formulation of development strategies for multi-layer gas reservoirs. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the method for splitting the production of multi-layer commingled gas wells in an embodiment of the present invention.

[0022] Figure 2 This is a specific example diagram of the method for splitting the production of multi-layer commingled gas wells in this invention.

[0023] Figure 3 This is a specific example diagram of the method for splitting the production of multi-layer commingled gas wells in this invention.

[0024] Figure 4This is a specific example diagram of the method for splitting the production of multi-layer commingled gas wells in this invention.

[0025] Figure 5 This is a specific example diagram of the method for splitting the production of multi-layer commingled gas wells in this invention.

[0026] Figure 6 This is a specific example diagram of the method for splitting the production of multi-layer commingled gas wells in this invention.

[0027] Figure 7 This is a schematic diagram of the multi-layer commingled gas well production splitting device in an embodiment of the present invention;

[0028] Figure 8 This is a schematic diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0030] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0031] In the description of this specification, the terms "comprising," "including," "having," and "containing" are open-ended terms, meaning that they include but are not limited to. The terms "an embodiment," "a specific embodiment," "some embodiments," and "for example," etc., refer to specific features, structures, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. The order of steps involved in the various embodiments is used to illustrate the implementation of this application, and the order of steps is not limited and can be adjusted appropriately as needed.

[0032] The principles and spirit of the present invention will be explained in detail below with reference to several representative embodiments.

[0033] Figure 1This is a schematic flowchart of the method for splitting the production of multi-layered syngas wells according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0034] Step 101: Obtain the static parameters and initial dynamic parameters of each gas reservoir layer;

[0035] Step 102: Input the static parameters and initial dynamic parameters of each gas reservoir into the daily gas production prediction model to determine the initial daily gas production of each gas well. The daily gas production prediction model is obtained by training a machine learning model based on the static parameters and initial dynamic parameters of historical gas reservoirs and the corresponding historical daily gas production.

[0036] Step 103: Determine the production capacity index of each gas production well based on the initial daily gas production and gas production capacity equation of each gas production well.

[0037] Step 104: Based on the production capacity index of each gas well, the gas production capacity equation corrected by the production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation, determine the total gas production of all gas wells in the production cycle. Set the minimum deviation between the total gas production and the historical measured gas production as the optimization target, and optimize the production correction coefficient according to the optimization target. The production correction coefficient is used to improve the calculation accuracy of the gas production capacity equation.

[0038] Step 105: Calculate the daily gas production of each gas well during the production cycle based on the gas production capacity equation corrected by the optimized production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation.

[0039] Depend on Figure 1As shown in the process, this embodiment of the invention obtains the static parameters and initial dynamic parameters of each gas reservoir; inputs the static parameters and initial dynamic parameters of each gas reservoir into the daily gas production prediction model to determine the initial daily gas production of each gas well; wherein, the daily gas production prediction model is obtained by training a machine learning model based on the static parameters and initial dynamic parameters of historical gas reservoirs and the corresponding historical daily gas production; based on the initial daily gas production of each gas well and the gas production capacity equation, the production capacity index of each gas well is determined; based on the production capacity index of each gas well... This invention utilizes a production correction coefficient to correct the gas production capacity equation, the dynamic reserves of each gas reservoir, and the material balance equation to determine the total gas production of all wells in all reservoirs during the production cycle. The optimization objective is to minimize the deviation between the total gas production and historical measured gas production. The production correction coefficient is then optimized based on this objective. This production correction coefficient improves the accuracy of the gas production capacity equation calculation. Based on the optimized production correction coefficient, the daily gas production of each well in the production cycle is calculated using the corrected gas production capacity equation, the dynamic reserves of each gas reservoir, and the material balance equation. This embodiment of the invention optimizes the production correction coefficient, improving the accuracy of gas production calculation for each well, ensuring the reliability of production allocation for multi-layered syndicated gas wells, and guiding the development strategy for multi-layered gas reservoirs.

[0040] To provide a clearer explanation of the above-mentioned method for splitting the production of multi-layered syngas wells, a detailed explanation of each step is provided below.

[0041] In one embodiment of the present invention, the static parameters of the gas reservoir include any one or more of the following: reservoir burial depth, effective reservoir thickness, clay content, reservoir porosity, reservoir permeability, and gas saturation; the initial dynamic parameters include: initial formation pressure and initial bottomhole flowing pressure.

[0042] In one embodiment of the present invention, for step 102, the static parameters and initial dynamic parameters of each gas reservoir are input into the daily gas production prediction model to determine the initial daily gas production of each gas well; wherein, the daily gas production prediction model is obtained by training a machine learning model based on the static parameters and initial dynamic parameters of historical gas reservoirs and the corresponding historical daily gas production.

[0043] In practice, correlation analysis is used to obtain parameters related to the daily production of a single gas well from the reservoir depth, effective reservoir thickness, clay content, reservoir porosity, reservoir permeability, gas saturation, initial formation pressure, and initial bottom-hole flowing pressure of gas field A. These parameters are used as characteristic parameter data. For example, the characteristic parameter data for gas field A are effective reservoir thickness, reservoir porosity, reservoir permeability, gas saturation, initial formation pressure, and initial bottom-hole flowing pressure. Five machine learning models are established: support vector machine, random forest, progressive gradient regression tree, extreme gradient regression tree, and BP neural network. The obtained static parameters and initial dynamic parameters of the gas reservoir, along with the corresponding daily gas production of the single gas well, are divided into training and test sets in a 7:3 ratio. The training set is trained using 5-fold cross-validation to obtain five trained machine learning models. The accuracy of the five trained machine learning models on the test set is compared, and the machine learning model with the highest accuracy on the test set is selected as the daily gas production prediction model. The machine learning model with the highest accuracy on the test set is the progressive gradient regression tree model.

[0044] In one embodiment of the present invention, the machine learning model is an asymptotic gradient regression tree model.

[0045] In one embodiment of the present invention, for step 103, the production capacity index of each gas production well is determined based on the initial daily gas production of each gas production well and the gas production capacity equation; wherein, the production capacity index is used to measure the daily gas production of each gas production well.

[0046] In practice, the daily gas production of each production well in Gas Field A is predicted based on the daily gas production prediction model, assuming that each production well is producing independently. The production capacity index of each production well is then calculated using the gas production capacity equation, which is as follows:

[0047]

[0048] Where, j j P represents the production capacity index of the j-th gas production well; i P represents the initial formation pressure of the gas reservoir. wf0 q represents the initial bottom hole flowing pressure; j This represents the daily gas production of the j-th gas well; n represents the number of gas well layers.

[0049] Figure 2 This is a specific example diagram of the method for splitting the production of multi-layered syngas wells in an embodiment of the present invention.

[0050] In one embodiment of the present invention, reference is made to Figure 2 Based on the production capacity index of each gas well, the gas production capacity equation corrected using the production correction factor, the dynamic reserves of each gas reservoir, and the material balance equation, the total gas production of all gas wells in all reservoirs during the production cycle is determined, including:

[0051] The following steps are repeated for each gas production well until the end of the production cycle. Based on the daily gas production of each gas production well during the production cycle, the total gas production of all gas production wells during the production cycle is determined:

[0052] Step 201: Determine the daily gas production of each well based on the production capacity index of each gas production well, the gas production capacity equation corrected by the production correction coefficient, the formation pressure of each gas reservoir on the same day, and the bottom hole flowing pressure on the same day.

[0053] Step 202: Determine the cumulative daily gas production value of each gas production well based on the daily gas production of each gas production well on the current day and the daily gas production of each day before the current day.

[0054] Step 203: Based on the cumulative daily gas production of each gas well, the initial formation pressure, the dynamic reserves of each gas reservoir, and the material balance equation, determine the formation pressure of each gas reservoir after gas production, and set the formation pressure of each gas reservoir after gas production as the formation pressure for the next day.

[0055] Step 204: Adjust the dynamic reserves of each gas reservoir based on the cumulative daily gas production of each well.

[0056] Step 205: Obtain the bottom hole flowing pressure after gas production and determine the bottom hole flowing pressure for the next day.

[0057] In one embodiment of the present invention, minimizing the deviation between the total gas production and the historical measured gas production is set as the optimization objective. The production correction coefficient is then optimized based on this objective, including:

[0058] Repeat the following steps until the deviation between the total gas production and the historical measured gas production is minimized:

[0059] Adjust the production correction coefficient, and determine the total gas production of all gas wells in the production cycle based on the production capacity index of each gas well, the gas production capacity equation corrected by the adjusted production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation.

[0060] In practice, the gas production capacity equation and the material balance equation, which are modified by the adjusted production correction coefficient, are iteratively obtained to obtain the formation pressure of each gas reservoir and the daily gas production of each gas well in each production cycle. The dynamic reserves and production correction coefficient of each gas reservoir are adjusted by an automatic fitting algorithm to fit the daily gas production of each gas well. The goal is to find the best fit between the calculated total gas production of all gas wells in the production cycle and the historical measured gas production, so that the deviation is minimized and the optimal fitting effect is achieved.

[0061] In one embodiment of the present invention, the gas production capacity equation corrected using the production correction factor is as follows:

[0062]

[0063] Among them, P rj P represents the formation pressure of the j-th gas reservoir; wf Indicates bottomhole flowing pressure; m represents production correction factor; n represents the number of gas production wells; j j Q represents the production capacity index of the j-th gas production well; scj This represents the daily gas production of the j-th gas well during its production cycle. The initial value of the given production correction coefficient is 1.

[0064] In one embodiment of the present invention, the mass balance equation is as follows:

[0065]

[0066] Among them, P rj P represents the formation pressure of the j-th gas reservoir; i Z represents the initial formation pressure of the gas reservoir. j Z represents the deviation coefficient of the j-th gas reservoir; i G represents the deviation coefficient of the initial state. j G represents the dynamic reserves of the j-th gas reservoir; pj This represents the cumulative daily gas production of the j-th gas well; n represents the number of gas wells. Wherein, the dynamic reserves G of the j-th gas reservoir are given. j The initial value is the ratio of the dynamic reserves of the gas reservoir to the number of syngas layers.

[0067] In practice, the total daily gas production Q of all gas production wells in all layers during the production cycle is calculated as the sum of the daily gas production Q of all gas production wells in all layers. sc The cumulative daily gas production value G of the gas production of the j-th gas well and the gas production of the j-th gas well pj Among them, the sum of the daily gas production of all gas production wells in all layers, Q sc G represents the sum of the daily gas production of wells from layer 1 to layer n during the production cycle, and the cumulative daily gas production of well j is given by G. pj Let Q be the daily gas production of the j-th gas well during its production cycle. scj The accumulation of.

[0068] Using the method provided by this invention, an example test on 18 multi-layer syngas wells shows that the output results of the multi-layer syngas well production splitting method provided by this invention are significantly more accurate than the results calculated by existing methods, and are closer to the gas production profile test results.

[0069] Figure 3 , Figure 4This is a specific example diagram of the method for splitting the production of multi-layered syngas wells in an embodiment of the present invention.

[0070] Unlike the multi-layer syngas well production splitting method provided by this invention, the gas production profile testing method uses logging instruments to test the gas production profile. The testing cost is expensive, and it can only measure the instantaneous production contribution rate at a certain point in time. It cannot reflect the change law of production throughout the entire production cycle of the gas well, and it interferes with the normal production of the gas well.

[0071] In one embodiment of the present invention, the daily gas production fitting calculation results for well Shuangxx-1 in gas field A are as follows: Figure 3 As shown. The production contribution rate represents the production breakdown of the double xx-1 well, which is the percentage of the daily gas production of the j-th layer well to the total daily gas production of all layers. For example... Figure 4 As shown, the evaluation results of the production splitting method for four multi-layer syndicated gas wells in Shuangxx-1 on October 27, 2017, November 19, 2018, June 12, 2020, and July 22, 2021, compared with the results of the gas production profile testing method, show average errors of 8.91%, 5.58%, 3.53%, 7.16%, and 6.95% for He7, He8, Shan1, Shan2, and B gas fields, respectively.

[0072] Figure 5 , Figure 6 This is a specific example diagram of the method for splitting the production of multi-layered syngas wells in an embodiment of the present invention.

[0073] In another embodiment of the present invention, the fitting calculation results of the daily gas production of well Shuangxx-2 are as follows: Figure 5 As shown, the evaluation results of the production splitting method for three multi-layer syngas production wells in well Shuangxx-2 on August 3, 2020, February 7, 2021, and August 1, 2021, are compared with the gas production profile test results. For example... Figure 6 As shown, the average errors for gas fields 8, 1, 2, and B are 4.18%, 9.56%, 5.98%, and 4.73%, respectively. This invention achieves production splitting across the entire production cycle of multi-layer commingled gas wells, reducing investment in related dynamic monitoring projects, saving costs, and minimizing disruption to gas well production. The production splitting method for multi-layer commingled gas wells provided by this invention is beneficial for widespread adoption.

[0074] It should be noted that although the operation of the method of the present invention has been described in a specific order in the above embodiments and figures, this does not require or imply that the operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0075] The implementation of the multi-layered syngas well production splitting device can refer to the implementation of the above method, and the repeated parts will not be described again. The term "module" or "unit" used below can be a combination of software and / or hardware to achieve a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0076] Based on the same inventive concept, this invention also proposes a multi-layer syngas well production splitting device, such as... Figure 7 As shown, the device includes:

[0077] The parameter acquisition module 701 is used to acquire the static parameters and initial dynamic parameters of each gas reservoir layer;

[0078] The daily gas production prediction module 702 is used to input the static parameters and initial dynamic parameters of each gas reservoir into the daily gas production prediction model to determine the initial daily gas production of each gas well. The daily gas production prediction model is obtained by training a machine learning model based on the static parameters and initial dynamic parameters of historical gas reservoirs and the corresponding historical daily gas production.

[0079] The production capacity index determination module 703 is used to determine the production capacity index of each gas production well based on the initial daily gas production and gas production capacity equation of each gas production well.

[0080] The optimization and correction module 704 is used to determine the total gas production of all gas wells in the production cycle based on the production capacity index of each gas well, the gas production capacity equation corrected by the production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation. The optimization target is to minimize the deviation between the total gas production and the historical measured gas production. The production correction coefficient is optimized according to the optimization target. The production correction coefficient is used to improve the calculation accuracy of the gas production capacity equation.

[0081] The daily gas production calculation module 705 is used to calculate the daily gas production of each gas well during the production cycle based on the gas production capacity equation corrected by the optimized production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation.

[0082] In one embodiment of the present invention, the static parameters of the gas reservoir include any one or more of the following: reservoir burial depth, effective reservoir thickness, clay content, reservoir porosity, reservoir permeability, and gas saturation.

[0083] Initial dynamic parameters include: initial formation pressure and initial bottom hole flowing pressure.

[0084] In one embodiment of the present invention, the machine learning model is an asymptotic gradient regression tree model.

[0085] In one embodiment of the present invention, the optimization and correction module 704 is specifically used for:

[0086] The following steps are repeated for each gas production well until the end of the production cycle. Based on the daily gas production of each gas production well during the production cycle, the total gas production of all gas production wells during the production cycle is determined:

[0087] The daily gas production of each well is determined based on the production capacity index of each well, the gas production capacity equation corrected by the production correction coefficient, the formation pressure of each gas reservoir on the same day, and the bottom hole flowing pressure on the same day.

[0088] The cumulative daily gas production value of each gas production well is determined based on the daily gas production of each gas production well on the current day and the daily gas production of each day prior to the current day.

[0089] Based on the cumulative daily gas production of each well, the initial formation pressure, the dynamic reserves of each gas reservoir, and the material balance equation, the formation pressure after gas production in each gas reservoir is determined, and the formation pressure after gas production in each gas reservoir is determined as the formation pressure for the next day.

[0090] The dynamic reserves of each gas reservoir are adjusted based on the cumulative daily gas production of each well.

[0091] Obtain the bottom hole flowing pressure after gas production and determine it as the bottom hole flowing pressure for the next day.

[0092] In one embodiment of the present invention, the optimization and correction module 704 is specifically used for:

[0093] Repeat the following steps until the deviation between the total gas production and the historical measured gas production is minimized:

[0094] Adjust the production correction coefficient, and determine the total gas production of all gas wells in the production cycle based on the production capacity index of each gas well, the gas production capacity equation corrected by the adjusted production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation.

[0095] In one embodiment of the present invention, the gas production capacity equation corrected using the production correction factor is as follows:

[0096]

[0097] Among them, P rj P represents the formation pressure of the j-th gas reservoir; wf Indicates bottomhole flowing pressure; m represents production correction factor; n represents the number of gas production wells; j j Q represents the production capacity index of the j-th gas production well; scj This represents the daily gas production of the j-th gas well during its production cycle.

[0098] In one embodiment of the present invention, the mass balance equation is as follows:

[0099]

[0100] Among them, P rj P represents the formation pressure of the j-th gas reservoir; i Z represents the initial formation pressure of the gas reservoir. j Z represents the deviation coefficient of the j-th gas reservoir; i G represents the deviation coefficient of the initial state. j G represents the dynamic reserves of the j-th gas reservoir; pj This represents the cumulative daily gas production of the j-th gas well; n represents the number of gas well layers.

[0101] It should be noted that although several modules of the multi-layer syngas well production splitting device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0102] Based on the aforementioned inventive concept, such as Figure 8 As shown, the present invention also proposes a computer device 800, including a memory 801, a processor 802, and a computer program 803 stored in the memory 801 and executable on the processor 802. When the processor 802 executes the computer program 803, it implements the aforementioned method for splitting the production of multi-layered gas wells.

[0103] Based on the aforementioned inventive concept, this invention proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for splitting the production output of multi-layered syngas wells.

[0104] Based on the aforementioned inventive concept, this invention proposes a computer program product, which includes a computer program that, when executed by a processor, implements a method for splitting the production output of multi-layered syngas wells.

[0105] The horizontal well coordinated cold production method and device proposed in this invention can solve the problem that the existing technology has large errors in calculating the gas production of each gas production well, which cannot guide the formulation of development strategies for multi-layer gas reservoirs. This invention obtains the static parameters and initial dynamic parameters of each gas reservoir; inputs these parameters into a daily gas production prediction model to determine the initial daily gas production of each gas production well; wherein, the daily gas production prediction model is obtained by training a machine learning model based on the historical static parameters and initial dynamic parameters of the gas reservoir, and the corresponding historical daily gas production; based on the initial daily gas production of each gas production well and the gas production rate... The process involves determining the production capacity index of each gas well layer; based on the production capacity index of each gas well layer, the gas production capacity equation corrected using a production correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation, determining the total gas production of all gas well layers within the production cycle; minimizing the deviation between the total gas production and historical measured gas production is set as the optimization objective; and the production correction coefficient is optimized based on the optimization objective; the production correction coefficient is used to improve the calculation accuracy of the gas production capacity equation; based on the optimized production correction coefficient, the gas production capacity equation corrected by the gas correction coefficient, the dynamic reserves of each gas reservoir, and the material balance equation, the daily gas production of each gas well layer within the production cycle is calculated. This invention can optimize the production correction coefficient, improve the calculation accuracy of the gas production of each gas well layer, ensure the reliability of production allocation for multi-layer syngas wells, and guide the formulation of development strategies for multi-layer gas reservoirs. The multi-layer syngas well production allocation method provided by this invention saves costs and does not interfere with gas well production, reducing the impact on gas well production and facilitating its widespread use.

[0106] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0107] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0108] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0109] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0110] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for splitting production in a multilayer commingled gas well, characterized by, The method comprises the following steps: obtaining static parameters and initial dynamic parameters of each layer of the gas reservoir; inputting the static parameters and the initial dynamic parameters of each layer of the gas reservoir into a daily gas production prediction model to determine the initial daily gas production of each layer of the gas production well; wherein the daily gas production prediction model is obtained by training a machine learning model according to the static parameters and the initial dynamic parameters of a historical gas reservoir and the corresponding historical daily gas production; determining the deliverability index of each layer of the gas production well according to the initial daily gas production of each layer of the gas production well and the gas deliverability equation; determining the total gas production of the gas production well of all layers in the production cycle according to the deliverability index of each layer of the gas production well, the gas deliverability equation corrected by the production correction coefficient, the dynamic reserves of each layer of the gas reservoir, and the material balance equation, setting the minimum deviation of the total gas production from the historical measured gas production as an optimization target, and optimizing the production correction coefficient according to the optimization target; wherein the production correction coefficient is used to improve the calculation accuracy of the gas deliverability equation; calculating the daily gas production of each layer of the gas production well in the production cycle according to the gas deliverability equation corrected by the optimized production correction coefficient, the dynamic reserves of each layer of the gas reservoir, and the material balance equation; determining the total gas production of the gas production well of all layers in the production cycle according to the deliverability index of each layer of the gas production well, the gas deliverability equation corrected by the production correction coefficient, the dynamic reserves of each layer of the gas reservoir, and the material balance equation, comprising: cyclically executing the following steps for each layer of the gas production well until the end of the production cycle, determining the total gas production of the gas production well of all layers in the production cycle according to the daily gas production of each layer of the gas production well in the production cycle: determining the daily gas production of each layer of the gas production well on the current day according to the deliverability index of each layer of the gas production well, the gas deliverability equation corrected by the production correction coefficient, the formation pressure of each layer of the gas reservoir on the current day, and the bottom-hole flowing pressure on the current day; determining the daily gas production accumulation value of each layer of the gas production well according to the daily gas production of each layer of the gas production well on the current day and the daily gas production of each layer of the gas production well on each previous day; determining the formation pressure of each layer of the gas reservoir after gas production according to the daily gas production accumulation value of each layer of the gas production well, the initial formation pressure, the dynamic reserves of each layer of the gas reservoir, and the material balance equation, and determining the formation pressure of each layer of the gas reservoir after gas production as the formation pressure of the next day; adjusting the dynamic reserves of each layer of the gas reservoir according to the daily gas production accumulation value of each layer of the gas production well; obtaining the bottom-hole flowing pressure after gas production and determining the bottom-hole flowing pressure after gas production as the bottom-hole flowing pressure of the next day.

2. The method of claim 1, wherein, The static parameters of the gas reservoir include any one or more of the following: reservoir burial depth, reservoir effective thickness, shale content, reservoir porosity, reservoir permeability, and gas saturation; The initial dynamic parameters include the initial formation pressure and the initial bottom-hole flowing pressure.

3. The method of claim 1, wherein, The machine learning model is a gradient boosting regression tree model.

4. The method of claim 1, wherein, Setting the minimum deviation of the total gas production from the historical measured gas production as an optimization target and optimizing the production correction coefficient according to the optimization target comprises: cyclically executing the following steps until the minimum deviation of the total gas production from the historical measured gas production is determined: The production capacity index of each layer of gas well is determined according to the initial daily gas production of each layer of gas well and the gas production capacity equation corrected by the production correction coefficient.

5. The method of claim 1, wherein, The gas production capacity equation corrected by the production correction coefficient is as follows: wherein, Pj represents the formation pressure of the jth layer gas reservoir; Pwf represents the bottom hole flowing pressure; m represents the production correction coefficient; n represents the number of layers of the gas production well; J represents the deliverability index of the jth layer gas production well; Qj represents the daily gas production of the jth layer gas production well during the production cycle.

6. The method of claim 1, wherein, The material balance equation is as follows: wherein, Pj represents the formation pressure of the jth layer gas reservoir; P0 represents the initial formation pressure of the gas reservoir; Cj represents the deviation factor of the jth layer gas reservoir; C0 represents the deviation factor of the initial state; Qj represents the dynamic reserves of the jth layer gas reservoir; Qj represents the daily gas production cumulative value of the jth layer gas well; n represents the number of gas wells.

7. A multi-zone commingled gas well production splitting device, comprising: The method comprises the following steps: The static parameters and initial dynamic parameters of each layer of gas reservoir are obtained by the parameter acquisition module. The initial daily gas production of each layer of gas well is determined by inputting the static parameters and initial dynamic parameters of each layer of gas reservoir into the daily gas production prediction model. The production capacity index of each layer of gas well is determined according to the initial daily gas production of each layer of gas well and the gas production capacity equation corrected by the production correction coefficient. The total gas production of all layers of gas well in the production cycle is determined according to the production capacity index of each layer of gas well, the gas production capacity equation corrected by the production correction coefficient, the dynamic reserves of each layer of gas reservoir and the material balance equation. The deviation between the total gas production and the historical measured gas production is set as the optimization target. The daily gas production of each layer of gas well in the production cycle is calculated according to the gas production capacity equation corrected by the optimized production correction coefficient, the dynamic reserves of each layer of gas reservoir and the material balance equation. The optimization correction module is specifically used for: The total gas production of all layers of gas well in the production cycle is determined according to the daily gas production of each layer of gas well in the production cycle. The daily gas production of each layer of gas well is determined according to the production capacity index of each layer of gas well, the gas production capacity equation corrected by the production correction coefficient, the formation pressure of each layer of gas reservoir on the day and the well bottom flowing pressure on the day. The daily gas production accumulation value of each layer of gas well is determined according to the daily gas production of each layer of gas well on the day and the daily gas production of each layer of gas well before the day. The formation pressure of each layer of gas reservoir after gas production is determined according to the daily gas production accumulation value of each layer of gas well, the initial formation pressure, the dynamic reserves of each layer of gas reservoir and the material balance equation. The dynamic reserves of each layer of gas reservoir are adjusted according to the daily gas production accumulation value of each layer of gas well.

8. The apparatus of claim 7, wherein, The well bottom flowing pressure after gas production is obtained and determined as the well bottom flowing pressure of the next day. The static parameters of the gas reservoir include any one or more of the following: reservoir burial depth, reservoir effective thickness, shale content, reservoir porosity, reservoir permeability and gas saturation.

9. The apparatus of claim 7, wherein, The initial dynamic parameters include the initial formation pressure and the initial well bottom flowing pressure.

10. The apparatus of claim 7, wherein, The machine learning model is a gradient boosting regression tree model. The optimization correction module is specifically used for: The following steps are executed in a loop until the deviation of the total gas production and the historical measured gas production is determined to be minimum: The production correction factor is adjusted, and the total gas production of all layers of the gas production well in the production cycle is determined according to the deliverability index of each layer, the gas deliverability equation corrected by the adjusted production correction factor, the dynamic reserves of each layer, and the material balance equation.

11. The apparatus of claim 7, wherein, The gas deliverability equation corrected by the production correction factor is as follows: wherein, represents the number of layers of the gas reservoir; j represents the formation pressure of the gas reservoir; represents the bottom hole flowing pressure; m represents the production correction factor; n represents the number of layers of the gas production well; represents the number of layers of the gas reservoir; j represents the productivity index of the gas production well of the layer; represents the number of layers of the gas reservoir; j represents the daily gas production of the gas production well of the layer during the production cycle.

12. The apparatus of claim 7, wherein, The material balance equation is as follows: in, Indicates the first j Formation pressure in gas reservoirs; This indicates the initial formation pressure of the gas reservoir; Indicates the first j Deviation coefficient of gas reservoir; The deviation coefficient representing the initial state; Indicates the first j Dynamic reserves of gas reservoirs; Indicates the first j Cumulative daily gas production of stratified gas wells; n This indicates the number of layers in the gas production well.

13. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1 to 6 when executing the computer program.

14. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method of any one of claims 1 to 6.

15. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to implement the method of any one of claims 1 to 6.

Images