A coal rock gas new production well final recoverable reserves prediction method and device

Abstract

The application discloses a coal rock gas new production well ultimate recoverable reserves prediction method and device. The method comprises the following steps: obtaining effective production dynamic data of at least one put-into-production well, constructing production dynamic data matrices of each of the put-into-production well according to time series of effective production days; calculating instantaneous dynamic indexes and cumulative dynamic indexes of corresponding put-into-production wells through each of the production dynamic data matrices, and constructing first intelligent analogy matrices of each of the put-into-production wells according to the instantaneous dynamic indexes and the cumulative dynamic indexes; determining a preset number of target put-into-production wells representing similar production characteristics of the new production well according to the first intelligent analogy matrices of each of the put-into-production wells; and determining the ultimate recoverable reserves of the new production well through the yield of the target put-into-production well. The scheme of the application can more accurately predict the ultimate recoverable reserves of a single well of a new production well.

Description

Technical Field

[0001] The present invention relates to the technical field of coal-rock gas exploration and development, and in particular to a method and device for predicting the final recoverable reserves of a newly-commissioned coal-rock gas well. Background Art

[0002] In coal-rock gas exploration and development, predicting the ultimate recoverable reserves (EUR) of newly commissioned wells is a core component of development decision-making. It provides key indicators for development plan formulation and optimization, economic benefit assessment and investment decision-making, resource management and policy formulation, and technological advancement and theoretical development. EUR prediction for coal-rock gas wells is influenced by multiple geological and engineering factors, as well as by operations such as fracturing, drainage, and commissioning of adjacent wells during production. Therefore, rolling predictions and regular reviews are necessary.

[0003] Traditional methods for predicting the ultimate recoverable reserves of a single coal-rock gas well mainly rely on analogy, empirical methods, numerical simulation methods, analytical solution methods, machine learning prediction methods, etc. However, due to the scarcity of initial production data of newly commissioned wells, it is difficult to build a reliable prediction model based on limited data. During the production process, factors such as interference from adjacent wells and adjustments to the drainage and production system lead to large data fluctuations. Traditional methods cannot update the prediction results in real time. Moreover, such methods are highly dependent on expert experience, have low computational efficiency, and cannot adapt to the complex development dynamics of coal-rock gas reservoirs. Summary of the Invention

[0004] The present invention provides a method and device for predicting the ultimate recoverable reserves of a newly-commissioned coal-rock gas well. By dynamically selecting a number of intelligent analog indicators based on the effective production time of the newly-commissioned coal-rock gas well, the ultimate recoverable reserves of a single newly-commissioned coal-rock gas well can be predicted more accurately.

[0005] According to one aspect of the present invention, a method for predicting the ultimate recoverable reserves of a newly-commissioned coal-rock gas well is provided, comprising:

[0006] Obtaining effective production performance data of at least one well that has been put into production, and aligning the time series according to the number of effective production days to construct a production performance data matrix for each of the wells that have been put into production;

[0007] Calculating the instantaneous dynamic index and the cumulative dynamic index of the corresponding wells in production through each of the production dynamic data matrices, and constructing a first intelligent analogy matrix for each of the wells in production based on the instantaneous dynamic index and the cumulative dynamic index;

[0008] Determining a preset number of target already-produced wells whose characteristics are similar to the production characteristics of the newly-produced well based on the first intelligent analogy matrix of each already-produced well;

[0009] The ultimate recoverable reserves of the newly produced well are determined by the production of the target already produced well.

[0010] Optionally, the production dynamic data includes: daily gas production, flowback fluid volume and casing pressure; accordingly, aligning the time series according to the number of effective production days to construct the production dynamic data matrix of each of the put into production wells includes:

[0011] Clearing zero or null values ​​in the daily gas production, flowback liquid volume, and casing pressure;

[0012] The production dynamic data of each of the wells in production are aligned according to the effective production days, and the production dynamic data matrix including the daily gas production, flowback fluid volume and casing pressure corresponding to the effective production days of each well in production is constructed.

[0013] Optionally, the instantaneous dynamic indicators include cumulative gas production and cumulative flowback fluid volume; the cumulative dynamic indicators include cumulative gas production and fracturing fluid flowback rate; accordingly, the instantaneous dynamic indicators and cumulative dynamic indicators corresponding to the production wells are calculated through each of the production dynamic data matrices, and a first intelligent analogy matrix for each of the production wells is constructed based on the instantaneous dynamic indicators and cumulative dynamic indicators, including:

[0014] For each production dynamic data matrix, a target time t is set, and the daily gas production and daily liquid discharge at each preset time before and after the target time t are extracted. The daily gas production and daily liquid discharge are sorted by numerical value, and the N highest values ​​and M lowest values ​​are removed. The arithmetic mean of the remaining production dynamic data is calculated to obtain the cumulative gas production and cumulative return liquid volume at time t;

[0015] The cumulative gas production is obtained by adding up the daily gas production from the start of production to the time t; the fracturing fluid flowback rate is obtained by the ratio of the sum of the cumulative flowback fluid volume before gas production and the cumulative flowback fluid volume at the time t to the total fracturing fluid volume;

[0016] Based on the time series formed when the time t takes different values, a first intelligent analogy matrix including the daily gas production, casing pressure, cumulative gas production and fracturing fluid flowback rate is constructed.

[0017] Optionally, determining a preset number of target already-produced wells having production characteristics similar to those of the newly-produced well based on the first intelligent analogy matrix of each already-produced well includes:

[0018] Acquiring production performance data of the newly commissioned well, and constructing a second intelligent analog matrix including the daily gas production, casing pressure, cumulative gas production, and fracturing fluid flowback rate based on the production performance data;

[0019] determining the Euclidean distance between each first intelligent analog matrix and the second intelligent analog matrix according to the daily gas production and the casing pressure;

[0020] A preset number of producing wells with the smallest Euclidean distances are used as the target producing wells.

[0021] Optionally, determining the ultimate recoverable reserves of the newly produced well based on the production of the target already produced well includes:

[0022] Calculate the final recoverable reserves of the newly put into production well corresponding to each target already-produced well based on the daily gas production, casing pressure, cumulative gas production, and fracturing fluid flowback rate of each target already-produced well in the second intelligent analogy matrix;

[0023] The final recoverable reserves of the newly put into production well are determined based on the average value of the final recoverable reserves of the single wells of the newly put into production wells corresponding to the target wells already put into production.

[0024] Optionally, after determining the ultimate recoverable reserves of the newly produced well based on the production rate of the target already produced well, the method further comprises:

[0025] When the production time of the new well increases by a preset number of days or the accumulated production data volume reaches a preset threshold, the final recoverable reserves of the newly put into production well at the current time are determined again based on the production of the target well that has already been put into production;

[0026] Determine the relative error between the final recoverable reserves at the current time and the historical final recoverable reserves. If the error is not less than a preset value, continue iterative prediction until the error is less than the preset value.

[0027] Optionally, the method further includes:

[0028] If the error is smaller than a preset value, the newly produced well is regarded as a produced well and its production data is regarded as the effective production dynamic data.

[0029] According to another aspect of the present invention, a device for predicting the ultimate recoverable reserves of a newly-commissioned coal-rock gas well is provided, comprising:

[0030] A production dynamic data matrix construction unit is used to obtain effective production dynamic data of at least one well that has been put into production, and to align the time series according to the number of effective production days to construct a production dynamic data matrix for each of the wells that have been put into production;

[0031] an intelligent analog matrix construction unit, configured to calculate the instantaneous dynamic index and the cumulative dynamic index of the corresponding wells in production through each of the production dynamic data matrices, and to construct a first intelligent analog matrix for each of the wells in production according to the instantaneous dynamic index and the cumulative dynamic index;

[0032] a target already-producing well determining unit, configured to determine a preset number of target already-producing wells whose characteristics are similar to the production characteristics of the newly-produced well based on the first intelligent analogy matrix of each already-producing well;

[0033] The production application unit is used to determine the ultimate recoverable reserves of the newly put into production well based on the production of the target well already put into production.

[0034] According to another aspect of the present invention, an electronic device is provided, comprising:

[0035] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the ultimate recoverable reserves of a newly commissioned coal gas well as described in any embodiment of the present invention.

[0036] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the final recoverable reserves of a newly-commissioned coal gas well as described in any embodiment of the present invention when executed.

[0037] According to another aspect of the present invention, a computer program product is provided, which includes a computer program, and when the computer program is executed by a processor, it implements the method for predicting the final recoverable reserves of a newly-commissioned coal-rock gas well according to any embodiment of the present invention.

[0038] The technical solution of the embodiment of the present invention obtains effective production dynamic data of at least one well already in production, and constructs a production dynamic data matrix of each of the wells already in production according to the alignment of time series based on the number of effective production days; calculates the instantaneous dynamic index and cumulative dynamic index of the corresponding well already in production through each of the production dynamic data matrices, and constructs a first intelligent analogy matrix of each of the wells already in production based on the instantaneous dynamic index and cumulative dynamic index; determines a preset number of target wells already in production whose characteristics are similar to the production characteristics of the newly-produced well based on the first intelligent analogy matrix of each of the wells already in production; determines the final recoverable reserves of the newly-produced well based on the production of the target wells already in production, and can more accurately predict the final recoverable reserves of a single well of the newly-produced well.

[0039] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 This is a flow chart of a method for predicting the final recoverable reserves of a newly-commissioned coal-rock gas well provided in Example 1 of the present invention;

[0042] Figure 2 This is a flow chart of a first intelligent analogy matrix construction method provided by the second embodiment of the present invention;

[0043] Figure 3 This is a flow chart of a method for determining final recoverable reserves through an intelligent analogy matrix provided in the third embodiment of the present invention;

[0044] Figure 4 This is a schematic structural diagram of a device for predicting the ultimate recoverable reserves of a newly-commissioned coal-rock gas well provided by a fourth embodiment of the present invention;

[0045] Figure 5 It is a structural schematic diagram of an electronic device for implementing the method for predicting the final recoverable reserves of a newly-commissioned coal-rock gas well according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0047] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0048] Example 1

[0049] Figure 1 This is a flow chart of a method for predicting the final recoverable reserves of a newly-commissioned coal gas well provided in the first embodiment of the present invention. This embodiment is applicable to the case of predicting the final recoverable reserves of a newly-commissioned well. The method can be executed by a device for predicting the final recoverable reserves of a newly-commissioned coal gas well. The device can be implemented in the form of hardware and / or software. The device can be configured in an electronic device. Figure 1 As shown, the method includes:

[0050] S110 , obtaining effective production dynamic data of at least one well that has been put into production, aligning the time series according to the number of effective production days, and constructing a production dynamic data matrix for each well that has been put into production.

[0051] The intelligent analogy-based method for predicting the ultimate recoverable reserves of newly commissioned coal gas wells is based on the core concept of comparing data from existing wells in an intelligent analogy database. First, a basic database must be constructed using data from existing coal gas wells. Production data from existing coal gas wells is collected and organized, and basic labels such as basins, reservoirs, blocks, well fields, and platforms are assigned to these wells to facilitate subsequent intelligent analogy applications based on search logic. Basic coal gas well production data includes daily gas production, flowback fluid volume, casing pressure, and tubing pressure. Data platforms and real-time data collection are typically used to obtain coal gas well production dynamics data to ensure the frequency and quality of production dynamics data updates. Furthermore, data such as fracturing fluid usage and ultimate recoverable reserves assessment results for existing coal gas wells are also required. Ultimate recoverable reserves data for individual existing coal gas wells is typically obtained through conventional analytical methods such as numerical simulation, analytical models, and empirical methods. For existing coal gas wells with a long effective production history, specialized software can often provide more reliable individual well ultimate recoverable reserves assessment results. Building a coal-rock gas data platform can provide a data basis and algorithm operating environment for the prediction of the ultimate recoverable reserves of subsequent newly commissioned wells.

[0052] In the embodiment of the present invention, the production dynamic data includes: daily gas production, flowback fluid volume and casing pressure; accordingly, the production dynamic data matrix of each well in production is constructed by aligning the time series according to the number of effective production days, including:

[0053] Clear zero or null values ​​in daily gas production, flowback liquid volume and casing pressure;

[0054] The production dynamic data of each well in production are aligned according to the effective production days, and a production dynamic data matrix containing the daily gas production, flowback fluid volume and casing pressure corresponding to the effective production days of each well in production is constructed.

[0055] Intelligent analog prediction of the ultimate recoverable reserves of newly commissioned coal gas wells requires preprocessing of the coal gas well production dynamics data. The primary goal is to eliminate zero or null daily gas production data, which is often caused by production system anomalies, workovers, and well shut-ins. The specific processing method for coal gas well production dynamics data is to remove zero or null data to generate dynamic data for continuous production of the single well.

[0056] After preprocessing the single well production dynamic data, all gas well dynamic data are aligned according to the effective production days to construct a production dynamic data matrix for each coal rock gas well that has been put into production, including data such as daily gas production, daily liquid volume, and casing pressure corresponding to the effective production days, as shown in the following formula:

[0057] ;

[0058] In the above formula, is the daily gas production of the mth coal gas well in the database at time t, 10 4 m 3 / d; t is the effective production time, and the values ​​of d, t are 1, 2, 3, 4, 5, 6... (i.e. the number of effective production man-days).

[0059] S120. Calculate the instantaneous dynamic index and cumulative dynamic index of the corresponding wells in production through each production dynamic data matrix, and construct a first intelligent analogy matrix for each well in production based on the instantaneous dynamic index and cumulative dynamic index.

[0060] The determination of the ultimate recoverable reserves of a new well is a dynamic process based on data-driven and intelligent analogy. The core is to convert the production characteristics of similar wells that have been put into production and combine them with a dynamic optimization mechanism.

[0061] Instantaneous dynamic indicators reflect the production status or parameter characteristics of a coal-rock gas well at a specific point in time. They are instantaneous and dynamically variable, focusing on depicting short-term fluctuations and immediate responses during the production process. Cumulative dynamic indicators represent the cumulative effect or ratio relationship of production data from the start of production to a specific point in time. They are holistic and historically cumulative, focusing on reflecting the long-term trends and comprehensive results of the production process.

[0062] The first intelligent analogy matrix converts production data from existing wells into a matrix by integrating instantaneous and cumulative dynamic indicators. The essence of generating the intelligent analogy matrix is ​​to provide a computable mathematical object for intelligent analogy. Specifically, without a matrix that aligns indicators by time point (e.g., each column of the matrix corresponds to a different indicator at the same time point), vector subtraction and square sum operations cannot be performed directly. The matrix's row-column alignment ensures that indicators from new and existing wells are compared on the same time scale, avoiding calculation errors caused by time misalignment.

[0063] S130 , determining a preset number of target already-produced wells whose production characteristics are similar to those of the newly-produced well based on the first intelligent analogy matrix of each already-produced well.

[0064] S140. Determine the ultimate recoverable reserves of the newly produced well based on the production of the target well already in production.

[0065] Newly commissioned wells only have short-term production data (e.g., 1-3 months), making it impossible to directly predict long-term production capacity. By comparing the lifecycle production curves of similar, established wells, the production capacity changes of the old wells can be transferred to the new wells, providing a reference for predicting the new wells' ultimate recoverable reserves.

[0066] Within the same reservoir or adjacent geological units, existing and newly commissioned wells often share similar sedimentary environments, reservoir properties, fluid properties (crude oil viscosity, natural gas composition), and geostress conditions, forming the basis for comparable production characteristics. From a production perspective, existing wells, through long-term development, have accumulated comprehensive production decline curves, pressure change data, and recovery factor characteristics. When a new well is commissioned, multi-dimensional index matching is used to identify existing wells with highly similar production characteristics, essentially providing a reference sample for the new well. The ultimate recoverable reserves of the existing wells can then serve as a benchmark for predicting the reserves of new wells, as the reserve recovery efficiency of reservoirs under similar conditions is reproducible. By leveraging statistical laws and analogical reasoning, even in the absence of long-term production data for new wells, the experience of existing wells can be used to develop production capacity forecasts. This reduces the time cost of new well assessments and improves the reliability of the results. This approach is particularly applicable to the rapid evaluation of highly heterogeneous unconventional reservoirs such as shale gas and tight oil.

[0067] Example 2

[0068] Figure 2 This is a flow chart of a first intelligent analog matrix construction method provided by the second embodiment of the present invention. This embodiment further explains and illustrates the above embodiment. Among them, the instantaneous dynamic indicators include cumulative gas production and cumulative flowback volume; the cumulative dynamic indicators include cumulative gas production and fracturing fluid flowback rate; the instantaneous dynamic indicators and cumulative dynamic indicators of the corresponding wells in production are calculated through each production dynamic data matrix. Figure 2 As shown, the method includes:

[0069] S210. For each production dynamic data matrix, set a target time t, extract the daily gas production and daily liquid discharge at each preset time before and after the target time t, sort the daily gas production and daily liquid discharge by numerical value, remove the N highest values ​​and M lowest values, calculate the arithmetic mean of the remaining production dynamic data, and obtain the cumulative gas production and cumulative return liquid volume at time t.

[0070] Based on the production performance data matrix of a single coal-rock gas well, we propose using a dynamic mean-average algorithm to calculate the instantaneous and cumulative dynamic indicators of the gas well. Instantaneous dynamic indicators include daily gas production and daily fluid flow, while cumulative dynamic indicators include cumulative gas production and fracturing fluid flowback rate. For example, the instantaneous and cumulative dynamic indicators of the gas well are constructed at 30-day intervals, as shown in the following formula:

[0071] ;

[0072] in, is the daily gas production of the mth well in the coal-rock gas production database at time t, 10 4 m 3 / d, where t takes values ​​of 30, 60, 90, 120, 150, 180, 210, 240, 270, 300, 330, 660…; is the casing pressure of the mth well in the coal-rock gas production database at time t, in MPa, where t ranges from 30, 60, 90, 120, 150, 180, 210, 240, 270, 300, 330, 660, and so on. Rank (8-22) extends the dynamic parameter at a given time t by 14 data points forward and backward, sorts all data by value, removes the 7 highest and 7 lowest data points, and calculates the arithmetic mean of the 8th to 22nd ranked data points as the instantaneous dynamic index corresponding to time t. This method of calculating the average value by ranking the instantaneous dynamic parameters maximizes the use of sample data and eliminates the influence of abnormally high and low values ​​on the instantaneous dynamic parameter calculation. This instantaneous dynamic index calculation yields the instantaneous dynamic parameter matrix for each coal-rock gas production well in the database.

[0073] S220. Obtain the cumulative gas production by accumulating the daily gas production from the start of production to time t; and obtain the fracturing fluid flowback rate by calculating the ratio of the sum of the cumulative flowback fluid volume before gas production and the cumulative flowback fluid volume at time t to the total fluid volume used for fracturing.

[0074] ;

[0075] ;

[0076] ;

[0077] In the above formula, is the cumulative gas production of the mth well in the coal-rock gas production database at time t, 10 4 m 3 , where t takes values ​​of 30, 60, 90, 120, 150, 180, 210, 240, 270, 300, 330, 660…; is the cumulative flowback volume of the mth well in the coal-rock gas production well database at time t, 10 4 m 3 , where t takes values ​​of 30, 60, 90, 120, 150, 180, 210, 240, 270, 300, 330, 660…; is the fracturing fluid flowback rate of the mth well in the coal gas production database at time t, dimensionless unit, where t takes values ​​of 30, 60, 90, 120, 150, 180, 210, 240, 270, 300, 330, 660, etc.; is the cumulative flowback volume of the mth well in the coal-rock gas production database before gas production, m 3 ; is the total amount of fluid used for fracturing the mth well in the database of coal-rock gas wells in production, m 3 .

[0078] S230. Based on the time series formed when the time t takes different values, construct a first intelligent analogy matrix including daily gas production, casing pressure, cumulative gas production and fracturing fluid flowback rate.

[0079] The instantaneous and cumulative ecological dynamic index algorithms are used to obtain the instantaneous and cumulative dynamic indexes of each coal-rock gas well in production in the database, and a single-well intelligent analogy index matrix is ​​constructed:

[0080] .

[0081] In an embodiment of the present invention, determining a preset number of target producing wells having production characteristics similar to those of the newly produced well based on the first intelligent analogy matrix of each producing well includes:

[0082] Obtain production performance data of newly commissioned wells and construct a second intelligent analog matrix based on the production performance data, including daily gas production, casing pressure, cumulative gas production, and fracturing fluid return rate;

[0083] Determine the Euclidean distance between each first intelligent analog matrix and the second intelligent analog matrix according to the daily gas production and the casing pressure;

[0084] A preset number of producing wells with the smallest Euclidean distance are taken as target producing wells.

[0085] The construction of the second intelligent analogy matrix is ​​similar to that of the first intelligent analogy matrix. The production dynamic data of newly put into production coal-rock gas wells are dynamically collected, and the intelligent analogy production dynamic indicator matrix of a single newly put into production coal-rock gas well is constructed according to the various formulas in the previous article.

[0086] Select intelligent analogy indicators based on the effective production time of newly commissioned coal-rock gas wells. The number of intelligent analogy indicators is as follows:

[0087] ;

[0088] In the above formula, Select the number of intelligent analogy indicators for the i-th newly put into production coal-rock gas well; d is the effective production time of the i-th newly commissioned coal-rock gas well at the current evaluation time. This step is to select as many intelligent analog indicators as possible. For example, if a newly commissioned well has been producing for more than 90 days, a 90-day intelligent analog indicator should be selected. If it has been producing for more than 120 days, the 90-day intelligent analog indicator has a reduced prediction accuracy, and a 120-day intelligent analog indicator should be selected accordingly.

[0089] The standardized Euclidean distance between the newly commissioned coal-rock gas well and each existing coal-rock gas well in the database is calculated using the intelligent analogy index of daily gas production and casing pressure:

[0090] ;

[0091] In the above formula, It refers to the standardized Euclidean distance between the instantaneous production dynamic indicators of the newly put into production coal-rock gas well i and the put into production coal-rock gas well m in the database, dimensionless; is the standard deviation of daily gas production, 10 4 m 3 / d; is the casing pressure standard deviation, MPa.

[0092] After the instantaneous dynamic index and the cumulative dynamic index standardized Euclidean distance are calculated, the instantaneous dynamic index standardized Euclidean distance is first sorted from small to large according to the value, that is:

[0093] .

[0094] The five existing coal-rock gas wells with the smallest standardized Euclidean distances were selected as the wells with similar production characteristics to the newly commissioned coal-rock gas wells. If the standardized Euclidean distances were equal, the standardized Euclidean distances of the cumulative gas production and flowback rate of the corresponding two wells were additionally calculated as a supplementary ranking basis.

[0095] ;

[0096] In the above formula, It refers to the standardized Euclidean distance between the cumulative production performance indicators of the newly put into production coal-rock gas well i and the put into production coal-rock gas well m in the database, dimensionless; is the standard deviation of cumulative gas production, 10 4 m 3 ; is the standard deviation of flowback rate, MPa.

[0097] The wells were sorted from small to large based on the standardized Euclidean distance between daily gas production and casing pressure, and supplemented by the standardized Euclidean distance between cumulative gas production and flowback rate. The top five coal-rock gas wells in the sorting were selected as wells with similar production characteristics. The production data of the five wells and the predicted ultimate recoverable reserves of each well were extracted to provide a data basis for the prediction of the ultimate recoverable reserves of each newly commissioned coal-rock gas well.

[0098] Example 3

[0099] Figure 3 This is a flowchart of a method for determining the final recoverable reserves through an intelligent analogy matrix provided by the third embodiment of the present invention. This embodiment further explains the above embodiment. Figure 3 As shown, the method includes:

[0100] S310. Calculate the final recoverable reserves of the newly put into production well corresponding to each target already-produced well based on the daily gas production, casing pressure, cumulative gas production, and fracturing fluid flowback rate of each target already-produced well in the second intelligent analogy matrix.

[0101] The final recoverable reserves prediction data matrix of a single well is constructed by selecting wells with similar production characteristics:

[0102] ;

[0103] In the above formula, It refers to the daily gas production of the first day of the production well with the smallest standardized Euclidean distance to the newly-commissioned coal gas well i, 10 4 m 3 / d; It refers to the casing pressure on the first day of production of the well with the smallest standardized Euclidean distance to the newly-commissioned coal gas well i, in MPPa; It refers to the daily gas production of the first day of the i-th newly put into production well, 10 4 m 3 / d; It refers to the casing pressure on the first day of production of the well with the smallest standardized Euclidean distance to the newly-commissioned coal gas well i, in MPa; The effective production time of the i-th newly commissioned well is defined as the production data of all wells with similar production characteristics. The ultimate recoverable reserves of a newly commissioned well are calculated by integrating the final recoverable reserves of an existing coal-rock gas well and the production pressure.

[0104] ;

[0105] ;

[0106] ;

[0107] ;

[0108] ;

[0109] In the above formula, To predict the ultimate recoverable reserves of the i-th newly put into production well by sorting the first well that has been put into production according to the standardized Euclidean distance, 10 4 m 3 ; To predict the ultimate recoverable reserves of the i-th newly put into production well by sorting the second well in production according to the standardized Euclidean distance, 10 4 m 3 ; To predict the ultimate recoverable reserves of the i-th newly put into production well by sorting the third well that has been put into production according to the standardized Euclidean distance, 10 4 m 3 ; To predict the ultimate recoverable reserves of the i-th newly put into production well by sorting the fourth well that has been put into production according to the standardized Euclidean distance, 10 4 m 3 ; To predict the ultimate recoverable reserves of the i-th newly put into production well by sorting the fifth well that has been put into production according to the standardized Euclidean distance, 10 4 m 3 ; Evaluate the final recoverable reserves of a single well for the first well in production ranked by standardized Euclidean distance in the database, 10 4 m 3 ; Evaluate the final recoverable reserves of a single well for the second producing well ranked by standardized Euclidean distance in the database, 10 4 m 3 ; Evaluate the ultimate recoverable reserves of a single well for the third well in production ranked by standardized Euclidean distance in the database, 10 4 m 3 ; Evaluate the final recoverable reserves of the fourth well in production ranked by standardized Euclidean distance in the database, 10 4 m 3 ; Evaluate the ultimate recoverable reserves of the fifth producing well in the database sorted by standardized Euclidean distance, 10 4 m 3 .

[0110] S320: Determine the final recoverable reserves of the newly put into production well based on the average value of the final recoverable reserves of the newly put into production wells corresponding to the target already put into production wells.

[0111] ;

[0112] In the above formula, is the final predicted recoverable reserves of the newly put into production coal gas well i, 10 4 m 3 ,The final prediction result is to sort the predicted EUR of 5 wells with similar production ,characteristics, and take the arithmetic mean of the three data after removing the ,highest and lowest values.

[0113] In an embodiment of the present invention, after determining the ultimate recoverable reserves of the newly produced well based on the production rate of the target already produced well, the method further includes:

[0114] When the production time of the new well increases by a preset number of days or the accumulated production data volume reaches a preset threshold, the final recoverable reserves of the newly put into production well at the current time are determined again based on the production of the target well that has already been put into production;

[0115] Determine the relative error between the current final recoverable reserves and the historical final recoverable reserves. If the error is not less than the preset value, continue iterating the prediction until the error is less than the preset value.

[0116] When a new well's production time reaches a preset number of days (e.g., 30 days) or the cumulative production data reaches a pre-set threshold (e.g., 10 new sets of valid production data), this indicates that the new well has more actual production information. At this point, the final recoverable reserves of the new well at the current point in time are recalculated according to the established algorithm using the production data of the previously selected target producing wells. This process is equivalent to updating the production capacity forecast for the new well incorporating the newly acquired data. After the calculation is complete, the final recoverable reserves determined at the current point in time are compared with the previously predicted historical final recoverable reserves, and the relative error between the two is calculated to measure the magnitude of the change in the forecast result. If this relative error is at least a preset value (e.g., 5%), it indicates that the current forecast deviates significantly from the historical forecast and may not yet be stable and reliable. Therefore, further iterative forecasting is required. This process is repeated, continuously adjusting the forecast model based on the latest production data from the new well until the relative error between the current and historical final recoverable reserves is less than the preset value, resulting in a more accurate and stable final recoverable reserves forecast.

[0117] In an embodiment of the present invention, the method further includes:

[0118] If the error is less than the preset value, the newly produced well is regarded as a produced well and its production data is regarded as effective production dynamic data.

[0119] When the relative error between the current estimated recoverable reserves of a new well and the historical forecast is less than a preset threshold (e.g., 5%), the forecast based on existing production data has stabilized and the new well's production characteristics can reliably reflect the productivity patterns of the reservoir in which it resides. At this point, the newly commissioned well is officially included in the database of existing wells, making it a reference target for subsequent productivity forecasts of new wells. Simultaneously, all production data accumulated since the well's commissioning is marked as valid production performance data and included as part of the historical reference sample, used to optimize similar well screening models and performance prediction algorithms.

[0120] In summary, the present invention proposes a EUR prediction method for newly commissioned coal-rock gas wells based on intelligent analogy, proposes an instantaneous dynamic index calculation method and constructs a single-well production characteristic index system. Based on the instantaneous index and cumulative index in the single-well intelligent analogy index system, the standardized Euclidean distance method is introduced to calculate the similarity of production characteristics between newly commissioned wells and existing coal-rock gas wells, and the existing coal-rock gas wells with the highest similarity are selected based on the results of the standardized Euclidean distance calculation. The final recoverable reserves of the newly commissioned wells are calculated based on the linear conversion of the production pressure integrals of the newly commissioned wells and similar existing coal-rock gas wells. The final recoverable reserves of the newly commissioned wells are calculated for multiple similar existing coal-rock gas wells, and the final recoverable reserves of the newly commissioned coal-rock gas wells are determined using the mean and dynamic mean methods.

[0121] Advantages and advancements of this approach include:

[0122] (1) Using the dynamic mean method to remove the influence of abnormal production data on the instantaneous production dynamic indicators of a single well;

[0123] (2) Based on the instantaneous production dynamic intelligent analogy indicators of daily gas production and casing pressure, the cumulative production dynamic intelligent analogy indicators of cumulative gas production and fracturing fluid flowback rate are selected as auxiliary intelligent analogy evaluation indicators;

[0124] (3) Calculate the ultimate recoverable reserves of a newly produced well by linearly converting the production pressure integral of similar coal-rock gas wells;

[0125] (4) The number of intelligent analogy indicators is dynamically selected according to the effective production time of the newly commissioned coal-rock gas well, which can realize the rolling prediction of the final recoverable reserves of the newly commissioned coal-rock gas well. As the number of intelligent analogy indicators increases, the final recoverable reserves of the newly commissioned coal-rock gas well can be predicted more accurately. The method for predicting the final recoverable reserves of a newly commissioned coal-rock gas well based on intelligent analogy can be effectively applied to coal-rock gas planning schemes, conceptual design, pilot test schemes, trial production schemes, development schemes and coal-rock gas reservoir production dynamic analysis. At the same time, this method can also be used in the construction of coal-rock gas data platforms, providing a basic algorithm for the application scenario of intelligent evaluation of recoverable reserves of coal-rock gas wells, and realizing the rolling iterative prediction of the final recoverable reserves of a newly commissioned coal-rock gas well, which has great application value.

[0126] Example 4

[0127] Figure 4 This is a schematic diagram of the structure of a device for predicting the final recoverable reserves of a newly-commissioned coal gas well provided by the fourth embodiment of the present invention. Figure 4 As shown, the device includes:

[0128] The production dynamic data matrix construction unit 410 is used to obtain effective production dynamic data of at least one well in production, and to align the time series according to the number of effective production days to construct the production dynamic data matrix of each well in production.

[0129] The intelligent analog matrix construction unit 420 is used to calculate the instantaneous dynamic index and cumulative dynamic index of the corresponding wells in production through each production dynamic data matrix, and construct the first intelligent analog matrix of each well in production according to the instantaneous dynamic index and cumulative dynamic index.

[0130] The target producing well determining unit 430 is configured to determine a preset number of target producing wells having production characteristics similar to those of the newly produced wells based on the first intelligent analogy matrix of each producing well.

[0131] The production application unit 440 is used to determine the ultimate recoverable reserves of the newly put into production well based on the production of the target well that has been put into production.

[0132] Optionally, the production dynamics data includes daily gas production, flowback fluid volume, and casing pressure. Accordingly, the production dynamics data matrix construction unit 410 is configured to execute:

[0133] Clear zero or null values ​​in daily gas production, flowback liquid volume and casing pressure;

[0134] The production dynamic data of each well in production are aligned according to the effective production days, and a production dynamic data matrix containing the daily gas production, flowback fluid volume and casing pressure corresponding to the effective production days of each well in production is constructed.

[0135] Optionally, the instantaneous dynamic indicators include cumulative gas production and cumulative flowback fluid volume; the cumulative dynamic indicators include cumulative gas production and fracturing fluid flowback rate; accordingly, the intelligent analog matrix construction unit 420 is used to perform:

[0136] For each production dynamic data matrix, set a target time t, extract the daily gas production and daily liquid discharge at each preset time before and after the target time t, sort the daily gas production and daily liquid discharge by numerical value, remove the N highest values ​​and the M lowest values, and calculate the arithmetic mean of the remaining production dynamic data to obtain the cumulative gas production and cumulative return liquid volume at time t;

[0137] The cumulative gas production is obtained by accumulating the daily gas production from the start of production to time t; the fracturing fluid return rate is obtained by the ratio of the sum of the cumulative return fluid volume before gas production and the cumulative return fluid volume at time t to the total fracturing fluid volume;

[0138] Based on the time series formed when the time t takes different values, the first intelligent analogy matrix including daily gas production, casing pressure, cumulative gas production and fracturing fluid flowback rate is constructed.

[0139] Optionally, the target producing well determination unit 430 is configured to execute:

[0140] Obtain production performance data of newly commissioned wells and construct a second intelligent analog matrix based on the production performance data, including daily gas production, casing pressure, cumulative gas production, and fracturing fluid return rate;

[0141] Determine the Euclidean distance between each first intelligent analog matrix and the second intelligent analog matrix according to the daily gas production and the casing pressure;

[0142] A preset number of producing wells with the smallest Euclidean distance are taken as target producing wells.

[0143] Optionally, the yield application unit 440 is configured to perform:

[0144] Calculate the final recoverable reserves of each newly commissioned well corresponding to each target already-produced well based on the daily gas production, casing pressure, cumulative gas production, and fracturing fluid flowback rate of each target already-produced well in the second intelligent analogy matrix;

[0145] The ultimate recoverable reserves of the newly put into production wells are determined based on the average of the single-well ultimate recoverable reserves of the newly put into production wells corresponding to each target already put into production well.

[0146] Optionally, after determining the final recoverable reserves of the newly produced well based on the production of the target already produced well, the production application unit 440 is further configured to execute:

[0147] When the production time of the new well increases by a preset number of days or the accumulated production data volume reaches a preset threshold, the final recoverable reserves of the newly put into production well at the current time are determined again based on the production of the target well that has already been put into production;

[0148] Determine the relative error between the current final recoverable reserves and the historical final recoverable reserves. If the error is not less than the preset value, continue iterating the prediction until the error is less than the preset value.

[0149] Optionally, the output application unit 440 is further configured to execute:

[0150] If the error is less than the preset value, the newly produced well is regarded as a produced well and its production data is regarded as effective production dynamic data.

[0151] The device for predicting the final recoverable reserves of a newly-commissioned coal-rock gas well provided in an embodiment of the present invention can execute the method for predicting the final recoverable reserves of a newly-commissioned coal-rock gas well provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0152] Example 5

[0153] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0154] like Figure 5 As shown, electronic device 10 includes at least one processor 11 and memory, such as read-only memory (ROM) 12 and random access memory (RAM) 13, communicatively connected to at least one processor 11. The memory stores computer programs executable by the at least one processor. Processor 11 can perform various appropriate actions and processes based on the computer programs stored in ROM 12 or loaded from storage unit 18 into RAM 13. RAM 13 can also store various programs and data required for the operation of electronic device 10. Processor 11, ROM 12, and RAM 13 are interconnected via bus 14. An input / output (I / O) interface 15 is also connected to bus 14.

[0155] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0156] Processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the method for predicting the ultimate recoverable reserves of newly commissioned coal and rock gas wells.

[0157] In some embodiments, the method for predicting the ultimate recoverable reserves of a newly commissioned coal-rock gas well can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for predicting the ultimate recoverable reserves of a newly commissioned coal-rock gas well described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for predicting the ultimate recoverable reserves of a newly commissioned coal-rock gas well by any other appropriate means (e.g., by means of firmware).

[0158] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0159] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0160] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or apparatus. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0162] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0163] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0164] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0165] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for predicting the ultimate recoverable reserves of a newly-commissioned coal-rock gas well, characterized in that: include: Obtaining effective production performance data of at least one well that has been put into production, and aligning the time series according to the number of effective production days to construct a production performance data matrix for each of the wells that have been put into production; The production dynamic data includes: daily gas production, flowback liquid volume and casing pressure; Calculating the instantaneous dynamic index and cumulative dynamic index of the corresponding wells in production through each of the production dynamic data matrices, and constructing a first intelligent analog matrix for each of the wells in production based on the instantaneous dynamic index and the cumulative dynamic index; the instantaneous dynamic index includes the cumulative gas production and the cumulative flowback fluid volume; the cumulative dynamic index includes the cumulative gas production and the fracturing fluid flowback rate; Determining a preset number of target producing wells having production characteristics similar to those of the newly produced well based on the first intelligent analogy matrix of each of the producing wells; wherein the similarity of the production characteristics is determined based on the sedimentary environment, reservoir physical properties, fluid properties, and geostress conditions; Determine the ultimate recoverable reserves of the newly produced well based on the production of the target already produced well; The calculating of the instantaneous dynamic index and the cumulative dynamic index of the corresponding wells in production by using each of the production dynamic data matrices, and constructing a first intelligent analogy matrix for each of the wells in production according to the instantaneous dynamic index and the cumulative dynamic index, includes: For each production dynamic data matrix, a target time t is set, and the daily gas production and daily liquid discharge at each preset time before and after the target time t are extracted. The daily gas production and daily liquid discharge are sorted by numerical value, and the N highest values ​​and M lowest values ​​are removed. The arithmetic mean of the remaining production dynamic data is calculated to obtain the cumulative gas production and cumulative return liquid volume at time t; The cumulative gas production is obtained by adding up the daily gas production from the start of production to the time t; the fracturing fluid flowback rate is obtained by the ratio of the sum of the cumulative flowback fluid volume before gas production and the cumulative flowback fluid volume at the time t to the total fracturing fluid volume; Based on the time series formed when the time t takes different values, a first intelligent analogy matrix including the daily gas production, casing pressure, cumulative gas production and fracturing fluid flowback rate is constructed.

2. The method according to claim 1, characterized in that The step of aligning the time series according to the number of effective production days to construct the production dynamic data matrix of each of the wells in production includes: Clearing zero or null values ​​in the daily gas production, flowback liquid volume, and casing pressure; The production dynamic data of each of the wells in production are aligned according to the effective production days, and the production dynamic data matrix including the daily gas production, flowback fluid volume and casing pressure corresponding to the effective production days of each well in production is constructed.

3. The method according to claim 1, characterized in that The step of determining a preset number of target already-produced wells having production characteristics similar to those of the newly-produced well based on the first intelligent analogy matrix of each already-produced well comprises: Acquiring production performance data of the newly commissioned well, and constructing a second intelligent analog matrix including the daily gas production, casing pressure, cumulative gas production, and fracturing fluid flowback rate based on the production performance data; determining the Euclidean distance between each first intelligent analog matrix and the second intelligent analog matrix according to the daily gas production and the casing pressure; A preset number of producing wells with the smallest Euclidean distances are used as the target producing wells.

4. The method according to claim 1, wherein Determining the ultimate recoverable reserves of the newly produced well based on the production of the target already produced well includes: Calculate the final recoverable reserves of the newly put into production well corresponding to each target already-produced well according to the daily gas production, casing pressure, cumulative gas production, and fracturing fluid flowback rate of each target already-produced well in the first intelligent analogy matrix; The final recoverable reserves of the newly put into production well are determined based on the average value of the final recoverable reserves of the single wells of the newly put into production wells corresponding to the target wells already put into production.

5. The method according to claim 1, wherein After determining the ultimate recoverable reserves of the newly produced well based on the production rate of the target already produced well, the method further includes: When the production time of the new well increases by a preset number of days or the accumulated production data volume reaches a preset threshold, the final recoverable reserves of the newly put into production well at the current time are determined again based on the production of the target well that has already been put into production; Determine the relative error between the final recoverable reserves at the current time and the final recoverable reserves in history. If the error is not less than a preset value, continue iterating the prediction until the error is less than the preset value.

6. The method according to claim 5, characterized in that The method further includes: If the error is smaller than a preset value, the newly produced well is regarded as a produced well and its production data is regarded as the effective production dynamic data.

7. A device for predicting the ultimate recoverable reserves of a newly-commissioned coal-rock gas well, characterized in that: include: A production dynamic data matrix construction unit is used to obtain effective production dynamic data of at least one well that has been put into production, and to align the time series according to the number of effective production days to construct a production dynamic data matrix for each of the wells that have been put into production; The production dynamic data includes: daily gas production, flowback liquid volume and casing pressure; An intelligent analog matrix construction unit is configured to calculate the instantaneous dynamic index and the cumulative dynamic index of the corresponding wells in production through each of the production dynamic data matrices, and to construct a first intelligent analog matrix for each of the wells in production based on the instantaneous dynamic index and the cumulative dynamic index; the instantaneous dynamic index includes the cumulative gas production and the cumulative flowback fluid volume; the cumulative dynamic index includes the cumulative gas production and the fracturing fluid flowback rate; a target producing well determining unit, configured to determine, based on a first intelligent analogy matrix of each of the producing wells, a preset number of target producing wells having production characteristics similar to those of the newly produced well; wherein the similarity of the production characteristics is determined based on sedimentary environment, reservoir physical properties, fluid properties, and geostress conditions; a production application unit, configured to determine the ultimate recoverable reserves of the newly produced well based on the production of the target already produced well; Smart analog matrix building unit for performing: For each production dynamic data matrix, set a target time t, extract the daily gas production and daily liquid discharge at each preset time before and after the target time t, sort the daily gas production and daily liquid discharge by numerical value, remove the N highest values ​​and the M lowest values, and calculate the arithmetic mean of the remaining production dynamic data to obtain the cumulative gas production and cumulative return liquid volume at time t; The cumulative gas production is obtained by accumulating the daily gas production from the start of production to time t; the fracturing fluid return rate is obtained by the ratio of the sum of the cumulative return fluid volume before gas production and the cumulative return fluid volume at time t to the total fracturing fluid volume; Based on the time series formed when the time t takes different values, the first intelligent analogy matrix including daily gas production, casing pressure, cumulative gas production and fracturing fluid flowback rate is constructed.

8. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for predicting the ultimate recoverable reserves of a newly commissioned coal-rock gas well according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for predicting the final recoverable reserves of a newly-commissioned coal-rock gas well according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the method for predicting the ultimate recoverable reserves of a newly-commissioned coal-rock gas well according to any one of claims 1 to 6.

Images