Method, device, medium and equipment for predicting reserve increment of oilfield adjustment well
By combining the net increment method and mathematical models with genetic algorithms and BP neural networks, the error problem of inter-well interference in the prediction of reserves of offshore oilfield adjustment wells has been solved, realizing rapid and accurate reserve increment assessment, which is applicable to various oilfield environments.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA NATIONAL OFFSHORE OIL (CHINA) CO LTD
- Filing Date
- 2022-09-26
- Publication Date
- 2026-06-02
Smart Images
Figure CN115471001B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of dynamic assessment of reserves in oil and gas field development adjustment wells, and particularly to a method, apparatus, medium, and equipment for predicting the increase in reserves of oil field adjustment wells. Background Technology
[0002] Offshore oilfields typically employ a single basic well network for development due to limitations in their engineering facilities. This sparse well network, large well spacing, and high production rates have led to problems during reservoir development, including significant differences in reservoir utilization across the surface and between layers, rapid increases in overall water cut, and excessively high controlled reserves per well, resulting in less than ideal development outcomes. Driven by both strategic security and economic factors, offshore oilfields have begun implementing comprehensive adjustments, essentially initiating a phase of one or more infill intrusion developments. Adjustment wells have become the most important means of increasing production and tapping potential in offshore oilfields. On the one hand, adjustment wells improve water drive control in thin and subsurface reservoirs, enhancing the adaptability of the reservoir to the well network; new wells directly increase recoverable reserves. On the other hand, they improve the injection-production system of the well network, increasing the recoverable reserves of older wells. These advantages make adjustment wells a key component of annual adjustment well reserve assessments in oilfields. The resulting challenge is accurately predicting the recoverable reserves of adjustment wells.
[0003] Currently, methods for predicting recoverable reserves from adjustment wells include numerical simulation and dynamic analysis. Dynamic analysis mainly includes decline analysis and waterdrive characteristic curve methods. Numerical simulation methods have significant errors in predicting reserves for reservoirs with relatively short production histories and insufficient dynamic and static data. The decline curve method is limited by the initial production value and the decline rate, making it difficult to guarantee the accuracy of predictions. The waterdrive curve method can consider more factors affecting development performance when predicting marketable reserves, making the evaluation process more convenient and flexible than the decline method, and the evaluation results are more consistent with the actual situation of long-term oilfield development, but its applicability is limited. In addition, both methods share a common drawback: they ignore the impact of adjustment wells on other wells, assuming that the oil production of the adjustment well is the same as the increased oil production. However, due to inter-well interference, the increased oil production and actual oil production of the adjustment well are not equal. The implementation of adjustment wells changes the seepage field and oil-water distribution patterns of the oilfield; simply assuming that the oil production of the adjustment well is the increased oil production will introduce significant errors in the prediction of recoverable reserves. Therefore, a new method is needed to predict the increase in reserves of oilfield adjustment wells, so as to guide the prediction of the actual increase in reserves of adjustment wells and provide a reference for better carrying out the assessment of the marketable reserves of adjustment wells in China. Summary of the Invention
[0004] To address the aforementioned problems, the purpose of this invention is to provide a method for predicting the increase in reserves of oilfield adjustment wells. This method fully considers the impact of inter-well interference on the recoverable reserves of adjustment wells and cleverly transforms the complex reserve splitting problem caused by inter-well interference into a problem of recoverable reserve difference at the same time point by using the net increment method.
[0005] To achieve the above objectives, the present invention adopts the following technical solution:
[0006] In a first aspect, the present invention provides a method for predicting the increase in reserves of oilfield adjustment wells, comprising the following steps:
[0007] Identify the target oil field and the adjustment wells to be predicted;
[0008] A two-dimensional rectangular coordinate system is established with the oilfield's production years as the horizontal axis and oil production as the vertical axis. Production decline curves excluding production adjustment wells and production decline curves including production adjustment wells are plotted in the two-dimensional rectangular coordinate system.
[0009] Determine the decreasing trend of the production decline curves that do not include the production adjustment wells and the production decline curves that include the production adjustment wells to obtain the decline type of the decline curves;
[0010] Calculate the actual reserve increment of each production adjustment well based on the described decrease type;
[0011] Determine whether there is a correlation between the actual reserve increment and water cut or cumulative oil production of each of the aforementioned production adjustment wells. If there is, then fit the two-dimensional data of the actual reserve increment and water cut or cumulative oil production to establish a first mathematical model; if there is no correlation, then establish a second mathematical model of the three-dimensional data of the actual reserve increment, water cut and cumulative oil production.
[0012] Substitute the cumulative oil production and water cut of the adjustment well to be predicted into the first or second mathematical model to obtain the actual reserve increment of the adjustment well to be predicted.
[0013] Furthermore, the actual reserve increment of each commissioned adjustment well is calculated based on the aforementioned decrease type, including the following steps:
[0014] Assuming the target oilfield commissions its first adjustment well in year n, then with year n+m as the time node, the actual reserve increase of this adjustment well up to year n+m is the difference between the predicted reserve increase considering the first adjustment well and the predicted reserve increase without considering the first adjustment well, specifically calculated according to formula (1):
[0015]
[0016] If a second adjustment well is put into production between year n and year n+m, the actual increase in reserves of the second adjustment well is calculated according to formula (2):
[0017]
[0018] During the m-year period, the actual reserve increase of the i-th adjustment well put into production can be calculated using formula (3):
[0019]
[0020] In formulas (1), (2), and (3), N pi This represents the actual reserve increase of the i-th adjustment well, 10 4 m 3 ;n represents the year in which the first adjustment well began production, in years;m represents the unified time point for calculating the increase in reserves for all adjustment wells, in years;D oi Q represents the initial decline rate of the i-th adjustment well, %; oi This represents the initial declining production of the i-th adjustment well in the offshore oil field, 10 4 m 3 .
[0021] Furthermore, a second mathematical model is established to correlate the actual increase in reserves with water cut and cumulative oil production, including the following steps:
[0022] The actual reserve increment, water cut at the time of production, and cumulative oil production of each well put into production were determined. The data of each group were then trained using a BP neural network with a threshold optimized by a genetic algorithm to obtain a surrogate model.
[0023] By refining the moisture content and cumulative yield, and substituting them into the proxy model, the actual reserve increment is calculated, thereby obtaining comprehensive three-dimensional data.
[0024] By plotting the three-dimensional data in the same coordinate system, a three-dimensional chart is obtained to predict the actual reserve increment of any adjustment well in the oilfield.
[0025] Furthermore, the decreasing types include exponential decreasing, hyperbolic decreasing, and harmonic decreasing.
[0026] Secondly, the present invention provides an apparatus for predicting the increase in reserves of oilfield adjustment wells, comprising:
[0027] The first processing unit identifies the target oilfield and the adjustment wells to be predicted;
[0028] The second processing unit establishes a two-dimensional rectangular coordinate system with the oilfield's production years as the horizontal axis and oil production as the vertical axis. Within the two-dimensional rectangular coordinate system, it plots the production decline curves excluding the production adjustment wells and the production decline curves including the production adjustment wells.
[0029] The third processing unit determines the decreasing trend of the production decline curves that do not include the production adjustment wells and the production decline curves that include the production adjustment wells, and obtains the decreasing type of the decline curves.
[0030] The fourth processing unit calculates the actual reserve increment of each production adjustment well based on the decrease type.
[0031] The fifth processing unit determines whether there is a correlation between the actual reserve increment and water cut or cumulative oil production of each of the commissioned adjustment wells. If there is a correlation, it fits the two-dimensional data of the actual reserve increment and water cut or cumulative oil production to establish a first mathematical model; if there is no correlation, it establishes a second mathematical model of the three-dimensional data of the actual reserve increment, water cut and cumulative oil production.
[0032] The sixth processing unit substitutes the cumulative oil production and water cut of the adjustment well to be predicted into the first mathematical model or the second mathematical model to obtain the actual reserve increment of the adjustment well to be predicted.
[0033] Thirdly, the present invention also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the method for predicting the increase in reserves of oilfield adjustment wells as described above.
[0034] Fourthly, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for predicting the increase in reserves of oilfield adjustment wells.
[0035] The present invention has the following advantages due to the adoption of the above technical solutions:
[0036] 1. The complex problem of splitting reserve increments between wells is transformed into calculating the reserve increment of adjustment wells using the net increment method, thus avoiding the complex simulation and calculation process in the reserve increment splitting process;
[0037] 2. For the first time, a three-dimensional calibration chart was established that takes into account the actual reserve increment of each adjustment well, the water cut of the oilfield at the time of commissioning, and the cumulative oil production, in order to predict the actual reserve increment of any adjustment well in the target oilfield.
[0038] 3. By combining theoretical models with standardized diagrams, this method guides relevant personnel to quickly and accurately calculate the reserve increment of any adjustment well in the target oilfield. The method is simple, minimizes the influence of research skills and experience, and has high applicability and promotion value. Attached Figure Description
[0039] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. In the drawings:
[0040] Figure 1 This is a production decline curve of the target oilfield under different numbers of adjustment wells in an embodiment of the present invention;
[0041] Figure 2 This illustrates the correspondence between the increase in reserves of the adjustment well and the actual water cut of the oilfield when the adjustment well is put into production, as described in this embodiment of the invention.
[0042] Figure 3 This is a three-dimensional calibration chart showing the actual reserve increment, oilfield water cut at the time of commissioning, and cumulative oil production of the first adjustment well in this embodiment of the invention.
[0043] Figure 4 This is a three-dimensional calibration chart showing the actual reserve increment, oilfield water cut at the time of commissioning, and cumulative oil production of the second adjustment well in this embodiment of the invention.
[0044] Figure 5 This is a three-dimensional calibration chart showing the actual reserve increment, oilfield water cut at the time of commissioning, and cumulative oil production of the third adjustment well in this embodiment of the invention.
[0045] Figure 6 This is an error analysis diagram of the mathematical model used to predict the actual reserve increase of the adjustment well in an embodiment of the present invention. Detailed Implementation
[0046] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the invention and to fully convey the scope of the invention to those skilled in the art.
[0047] This invention relates to a method, apparatus, medium, and equipment for predicting the reserve increment of oilfield adjustment wells, comprising the following steps: identifying the target oilfield and the adjustment wells to be studied; plotting a production decline curve with the oilfield's production years as the abscissa and oil production as the ordinate; obtaining the decline type based on the decline curve; calculating the actual reserve increment of each adjustment well based on the decline type; determining whether there is a correlation between the actual reserve increment of the adjustment well and the water cut or cumulative oil production; if so, fitting the two-dimensional data to establish a first mathematical model; if not, establishing a second mathematical model of the actual reserve increment, water cut, and cumulative oil production. Substituting the cumulative oil production and oilfield water cut of the adjustment wells to be predicted into the first or second mathematical model yields the actual reserve increment. The method for predicting the reserve increment of oilfield adjustment wells fully considers the impact of inter-well interference on the recoverable reserves of the adjustment wells, improving the reliability of the prediction.
[0048] Example 1
[0049] Embodiments of the present invention provide a method for predicting the increase in reserves of oilfield adjustment wells, comprising the following steps:
[0050] S1. Determine the target oilfield and the adjustment wells to be studied. Based on the design purpose and well location of the adjustment wells, determine the type of adjustment wells and select the infiltrated adjustment wells as the adjustment wells to be predicted.
[0051] Adjustment wells include infill adjustment wells aimed at improving oil recovery and expansion adjustment wells aimed at expanding the oilfield's perimeter. The locations of infill adjustment wells and expansion adjustment wells differ. Infill adjustment wells refer to scattered wells or wells drilled in batches or rows to supplement the existing well network and improve oilfield development. Expansion adjustment wells, which extend the oilfield beyond the original well spacing, are called expansion wells. Therefore, based on their function, infill adjustment wells are usually located within the existing well network, while expansion adjustment wells are usually located outside the existing well network.
[0052] In this invention, infill wells are selected as the wells to be predicted. Since the reserve increase of wells with expanded perimeters is very clear and minimally affected by older wells, they do not require separate study. However, the reserve increase of infill wells is significantly affected by older wells and requires further study. Therefore, in this invention, the term "well" refers to infill wells.
[0053] S2. Establish a two-dimensional rectangular coordinate system with the oilfield's production years as the x-axis and oil production as the y-axis. Plot production decline curves within this system, excluding production adjustment wells and including production adjustment wells. Figure 1 As shown.
[0054] S3. Determine the decreasing trend of the production decline curve without adjustment wells and the production decline curve with multiple adjustment wells to obtain the decline type of the adjustment wells; the decline type includes exponential decline, hyperbolic decline and harmonic decline, etc.
[0055] S4. Calculate the actual reserve increment of each adjustment well according to the decrease type;
[0056] S5. Determine whether there is a correlation between the actual reserve increment and the water cut or cumulative oil production of the adjustment well. If there is, fit the two-dimensional data of the actual reserve increment and the water cut or cumulative oil production to establish a first mathematical model; if there is no correlation, establish a second mathematical model of the actual reserve increment, the water cut, and the cumulative oil production.
[0057] The method for establishing the first mathematical model is as follows: if a correlation exists, the existing Levenberg-Marquardt algorithm can be used in Matlab software to perform multiple linear / nonlinear regression on the actual reserve increment and water cut or cumulative oil production to obtain the required mathematical model. This is an existing technology and will not be elaborated further.
[0058] The method for establishing the second mathematical model includes the following steps:
[0059] S5-1. The actual reserve increment, oilfield water cut and cumulative oil production at the time of commissioning of each adjustment well are determined. The data of each group are trained by a BP neural network after the threshold is optimized by a genetic algorithm to obtain the surrogate model.
[0060] S5-2. Refine the water cut and cumulative oil production, and substitute them into the proxy model to calculate the actual reserve increment, thereby obtaining comprehensive three-dimensional data.
[0061] Because a 3D map is required in subsequent steps, a large and dense dataset is needed. Currently, the number of adjustment wells and the water cut and cumulative production data they contain clearly do not meet this requirement. Each adjustment well corresponds to a single water cut and cumulative production value, so this goal needs to be indirectly achieved by refining the water cut and cumulative production data. Therefore, refinement refers to subdividing the water cut within the existing range at certain intervals. For example, assuming the original water cut range of the adjustment wells is [50%-80%], it can be subdivided at 5% intervals. The same applies to cumulative production, resulting in multiple combinations of water cut and cumulative production, representing multiple adjustment well scenarios. Substituting these combinations of water cut and cumulative production into the proxy model yields the corresponding actual reserve increments, thus enabling the calibration of the 3D map.
[0062] S5-3. Plot the three-dimensional data in the same coordinate system to obtain a three-dimensional chart for predicting the actual reserve increment of any adjustment well in the oilfield.
[0063] S6. Substitute the cumulative oil production and oilfield water cut of the adjustment well to be predicted into the first mathematical model or the second mathematical model to obtain the actual reserve increment.
[0064] For adjustment wells to be predicted, only their cumulative production and the water cut of the oilfield at the time of production are needed to input them into the chart or model to determine their actual reserve increase. It should be noted that the 3D chart and the first mathematical model are only applicable to the target oilfield under study. If the target oilfield is changed, data must be collected again to build the model.
[0065] The actual reserve increment of each adjustment well is calculated based on the described decreasing type. Specifically, the actual recoverable reserves of the adjustment well are calculated using the theoretically derived net increment method. Taking exponential decreasing as an example, the specific process is as follows:
[0066] Suppose that a certain offshore oil field puts into production a pilot well in year n, and analyze its actual reserve increase.
[0067] As defined, the formula for calculating exponentially decreasing output is:
[0068]
[0069] In the formula, Q represents the production of the offshore oil field, 10 4 m 3 Q o This indicates the initial declining production of the offshore oil field, 10 4 m 3 ;D o t represents the initial decline rate of the offshore oil field, in %; t represents the production decline time of the offshore oil field, in years.
[0070] The cumulative output during the decline phase can be expressed as:
[0071]
[0072] In the formula, N p This represents the cumulative production during the declining phase of an oil field, 10 4 m 3 .
[0073] If there is only one adjustment well P1 in the oilfield production process, then the actual reserve increase in the (n+m)th year (m>1) is:
[0074]
[0075] In the formula, N p1 This indicates the actual increase in reserves of the first adjustment well, 10 4 m 3 ;n represents the year in which the first adjustment well began production, in years;m represents the unified time point for calculating the increase in reserves for all adjustment wells, in years;D o1Q represents the initial decline rate of the first adjustment well, in %; o1 This indicates the initial declining production of the first adjustment well in the offshore oil field, 10 4 m 3 .
[0076] If another adjustment well P2 is put into production in year n+1, then the actual increase in reserves will be:
[0077]
[0078] In the formula, N p2 This indicates the actual increase in reserves from the second adjustment well, 10 4 m 3 ;D o2 Q represents the initial decline rate of the second adjustment well, in %; o2 This indicates the initial declining production of the second adjustment well in the offshore oil field, 10 4 m 3 .
[0079] Similarly, the actual reserve increase of the i-th adjustment well put into production in year n+i-1 is:
[0080]
[0081] In the formula, N pi This represents the actual reserve increase of the i-th adjustment well, 10 4 m 3 ;D oi Q represents the initial decline rate of the i-th adjustment well, %; oi This represents the initial declining production of the i-th adjustment well in the offshore oil field, 10 4 m 3 .
[0082] The reserve increments for the second well and the i-th well are obtained by comparing the predicted reserve increments when adjusting wells with those when not adjusting wells.
[0083] The actual reserve increment of all adjustment wells in the oilfield can be calculated using the above method. The actual reserve increment, oilfield water cut at the time of commissioning, and cumulative oil production of each adjustment well are calibrated. The data from each set are then trained using a BP neural network with a threshold optimized by a genetic algorithm to obtain the surrogate model.
[0084] Taking a domestic continental high-permeability, integrated low-viscosity oilfield as an example, 29 adjustment wells were put into production between 2010 and 2021. The water cut of the oilfield at the time of each adjustment well's commissioning and the actual cumulative production up to 2021 were statistically analyzed. A production decline curve for this oilfield was plotted. Based on experience, it was determined that this oilfield exhibits an exponential decline, such as... Figure 1 As shown.
[0085] The actual reserve increment of each adjustment well is calculated according to formulas (3), (4), and (5). The correspondence between the reserve increment of the adjustment well and the cumulative oil production, as well as the correspondence between the reserve increment of the adjustment well and the actual water cut of the oilfield at the time the adjustment well is put into production, are shown in the attached figure. Figure 2 As shown, observe whether there is a correlation. If a correlation exists, there is no need to build a 3D chart; instead, fit the 2D data to obtain a mathematical model. Otherwise, build the chart and model according to the method in step S5.
[0086] Observation revealed no significant correlation between the aforementioned two-dimensional data for this oilfield, necessitating the creation of a three-dimensional map and model. Data from 22 adjustment wells were selected, and a BP neural network with optimized thresholds was trained using a genetic algorithm to obtain a surrogate model for predicting the actual reserve increment of any adjustment well in the oilfield. Water cut and cumulative production were refined and substituted into the surrogate model to calculate the actual reserve increment.
[0087] The actual reserve increment, the water cut of the oilfield at the time of production, and the cumulative oil production were used to create a three-dimensional calibration chart for predicting the actual reserve increment of any adjustment well in the oilfield, as shown in the attached chart. Figure 3 , 4 As shown in Figure 5, for this oil field, the established neural network and genetic algorithm model parameters are: 2 input nodes, 5 hidden nodes, 1 output node, and a target error of 10. -5 The genetic algorithm has 10 individuals, 30 generations, a crossover probability of 0.2, and a mutation probability of 0.1.
[0088] The model was used to predict data from seven other adjustment wells. Error analysis was then performed between these predicted values and the actual reserve increments obtained through the net increment method. The results showed that the error in over 95% of the predictions was controlled within 10%, as shown in the attached figure. Figure 6 As shown, the established model can quickly and accurately predict the actual increase in reserves of adjustment wells.
[0089] Example 2
[0090] Example 2 also provides an apparatus for predicting the increase in reserves of oilfield adjustment wells, comprising:
[0091] The first processing unit identifies the target oilfield and the adjustment wells to be predicted;
[0092] The second processing unit establishes a two-dimensional rectangular coordinate system with the oilfield's production years as the horizontal axis and oil production as the vertical axis. Within the two-dimensional rectangular coordinate system, it plots the production decline curves excluding the production adjustment wells and the production decline curves including the production adjustment wells.
[0093] The third processing unit determines the decreasing trend of the production decline curves that do not include the production adjustment wells and the production decline curves that include the production adjustment wells, and obtains the decreasing type of the decline curves.
[0094] The fourth processing unit calculates the actual reserve increment of each production adjustment well based on the decrease type.
[0095] The fifth processing unit determines whether there is a correlation between the actual reserve increment and water cut or cumulative oil production of each of the commissioned adjustment wells. If there is a correlation, it fits the two-dimensional data of the actual reserve increment and water cut or cumulative oil production to establish a first mathematical model; if there is no correlation, it establishes a second mathematical model of the three-dimensional data of the actual reserve increment, water cut and cumulative oil production.
[0096] The sixth processing unit is used to substitute the cumulative oil production and water cut of the adjustment well to be predicted into the first mathematical model or the second mathematical model to obtain the actual reserve increment of the adjustment well to be predicted.
[0097] Example 3
[0098] Example 3 also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the method for predicting the increase in reserves of oilfield adjustment wells as described in Example 1.
[0099] Example 4
[0100] Example 4 provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for predicting the increase in reserves of oilfield adjustment wells as described in Example 1.
[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for predicting the increase in reserves of adjustment wells in an oilfield, characterized in that, Including the following steps: S1. Identify the target oil field and the adjustment wells to be predicted; S2. Establish a two-dimensional rectangular coordinate system with the oilfield's production years as the horizontal axis and oil production as the vertical axis. Plot the production decline curves excluding the production adjustment wells and including the production adjustment wells in the two-dimensional rectangular coordinate system. S3. Determine the decreasing trend of the production decline curve that does not include the production adjustment well and the production decline curve that includes the production adjustment well, and obtain the decreasing type of the decline curve. S4. Calculate the actual reserve increment of each production adjustment well based on the decrease type, including the following specific steps: Assuming the target oilfield commissions its first adjustment well in year n, then with year n+m as the time node, the actual reserve increase of this adjustment well up to year n+m is the difference between the predicted reserve increase considering the first adjustment well and the predicted reserve increase without considering the first adjustment well. Specifically, it is calculated according to formula (1): （1） If a second adjustment well is put into production between year n and year n+m, the actual increase in reserves of the second adjustment well is calculated according to formula (2): （2） The actual reserve increase of the i-th adjustment well put into production during the m-year period can be calculated by formula (3): （3） In formulas (1), (2) and (3), This represents the actual increase in reserves of the i-th adjustment well. ; Indicates the year in which the first adjustment well began production; m represents the unified time point for calculating the increase in reserves for all adjustment wells; Represents the initial decline rate of the i-th adjustment well, %; This represents the initial decreasing production of the i-th adjustment well in the oil field. ; S5. Determine whether there is a correlation between the actual reserve increment and water cut or cumulative oil production of each of the put-in-production adjustment wells. If there is, fit the two-dimensional data of the actual reserve increment and water cut or cumulative oil production to establish a first mathematical model; if there is no correlation, establish a second mathematical model of the three-dimensional data of the actual reserve increment, water cut and cumulative oil production. S6. Substitute the cumulative oil production and water cut of the adjustment well to be predicted into the first mathematical model or the second mathematical model to obtain the actual reserve increment of the adjustment well to be predicted.
2. The method for predicting the increase in reserves of oilfield adjustment wells according to claim 1, characterized in that, Establish a second mathematical model for the actual increase in reserves, water cut, and cumulative oil production, including the following steps: The actual reserve increment, water cut at the time of production, and cumulative oil production of each well put into production were determined. The data of each group were then trained using a BP neural network with a threshold optimized by a genetic algorithm to obtain a surrogate model. By refining the moisture content and cumulative yield, and substituting them into the proxy model, the actual reserve increment is calculated, thereby obtaining comprehensive three-dimensional data. By plotting the three-dimensional data in the same coordinate system, a three-dimensional chart is obtained to predict the actual reserve increment of any adjustment well in the oilfield.
3. The method for predicting the increase in reserves of oilfield adjustment wells according to claim 1, characterized in that, The decreasing types include exponential decreasing, hyperbolic decreasing, and harmonic decreasing.
4. A device for predicting the increase in reserves of oilfield adjustment wells, characterized in that, include: The first processing unit identifies the target oilfield and the adjustment wells to be predicted; The second processing unit establishes a two-dimensional rectangular coordinate system with the oilfield's production years as the horizontal axis and oil production as the vertical axis. Within the two-dimensional rectangular coordinate system, it plots the production decline curves excluding the production adjustment wells and the production decline curves including the production adjustment wells. The third processing unit determines the decreasing trend of the production decline curves that do not include the production adjustment wells and the production decline curves that include the production adjustment wells, and obtains the decreasing type of the decline curves. The fourth processing unit calculates the actual reserve increment of each production adjustment well based on the decrease type, including the following specific steps: Assuming the target oilfield commissions its first adjustment well in year n, then with year n+m as the time node, the actual reserve increase of this adjustment well up to year n+m is the difference between the predicted reserve increase considering the first adjustment well and the predicted reserve increase without considering the first adjustment well. Specifically, it is calculated according to formula (1): （1） If a second adjustment well is put into production between year n and year n+m, the actual increase in reserves of the second adjustment well is calculated according to formula (2): （2） The actual reserve increase of the i-th adjustment well put into production during the m-year period can be calculated by formula (3): （3） In formulas (1), (2) and (3), This represents the actual increase in reserves of the i-th adjustment well. ; Indicates the year in which the first adjustment well began production; m represents the unified time point for calculating the increase in reserves for all adjustment wells; Represents the initial decline rate of the i-th adjustment well, %; This represents the initial decreasing production of the i-th adjustment well in the oil field. ; The fifth processing unit determines whether there is a correlation between the actual reserve increment and water cut or cumulative oil production of each of the commissioned adjustment wells. If there is a correlation, it fits the two-dimensional data of the actual reserve increment and water cut or cumulative oil production to establish a first mathematical model; if there is no correlation, it establishes a second mathematical model of the three-dimensional data of the actual reserve increment, water cut and cumulative oil production. The sixth processing unit is used to substitute the cumulative oil production and water cut of the adjustment well to be predicted into the first mathematical model or the second mathematical model to obtain the actual reserve increment of the adjustment well to be predicted.
5. A computer-readable storage medium, characterized in that, The system contains computer instructions that, when executed by a processor, implement the method for predicting the increase in reserves of oilfield adjustment wells as described in any one of claims 1 to 3.
6. A computer device, characterized in that, The invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements a method for predicting the increase in reserves of oilfield adjustment wells as described in any one of claims 1 to 3.