Oil and gas reservoir production decline curve modeling method, device and equipment based on prefabricated search space symbol regression algorithm, medium and product

Abstract

The embodiment of the invention provides an oil and gas reservoir production decline curve modeling method and device based on a prefabricated search space symbol regression algorithm, equipment, a medium and a product, and relates to the technical field of oil and gas field development. The method comprises the steps of obtaining multiple pieces of first oil and gas reservoir production data; performing symbolic regression modeling according to the plurality of first oil and gas reservoir production data and a preset search space to obtain a plurality of expressions; inputting the plurality of expressions into a preset evaluation model to obtain evaluation values corresponding to the expressions; and determining the curve of the expression corresponding to the minimum value in the plurality of evaluation values as the oil and gas reservoir yield decline curve. According to the method, the search space is predefined, so that the algorithm can autonomously explore various possible function combinations, evolve various candidate function forms, comprehensively evaluate the complexity and fitting precision of the candidate function forms, and finally output the optimal oil and gas reservoir yield decline curve. According to the method, tedious geological modeling and numerical solution processes are omitted, and the determination efficiency of the oil and gas reservoir yield decline curve is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil and gas field development, and particularly relates to an oil and gas reservoir production decline curve modeling method and device based on a pre-prepared search space symbolic regression algorithm, equipment, medium and product. BACKGROUND

[0002] Oil and gas reservoir production determination is a core link of oil and gas field development. From early empirical formula to modern numerical simulation technology, its development has always been around how to accurately depict production and its change law. This law is affected by many factors such as heterogeneity, fluid properties and development strategy, and the accuracy of production determination directly affects key indicators such as remaining reserves calculation and economic limit production calculation. Therefore, how to determine the oil and gas reservoir production is crucial.

[0003] In the prior art, the oil and gas reservoir production decline curve is mainly determined by a numerical simulation method. Engineers will first establish a mathematical model to describe the multiphase flow process in the reservoir based on the geological characteristics of the oil and gas reservoir and the fluid percolation mechanism, and solve it by numerical calculation method. By adjusting the model parameters to reflect the actual oil and gas reservoir dynamic characteristics, the oil and gas reservoir production decline curve is determined.

[0004] However, the prior art has the problem of low efficiency in determining the oil and gas reservoir production decline curve. Mainly because complex parameter optimization and repeated verification are needed in the modeling and solving process, there is an inherent contradiction between calculation accuracy and efficiency, and when dealing with large-scale calculation tasks, it faces the dilemma of large consumption of computing resources and long period, which leads to the reduction of the efficiency of determining the oil and gas reservoir production decline curve. SUMMARY

[0005] The embodiments of the present application provide an oil and gas reservoir production decline curve modeling method, device, equipment, medium and product based on a pre-prepared search space symbolic regression algorithm, to solve the problem of low efficiency in determining the oil and gas reservoir production decline curve in the prior art.

[0006] In a first aspect, the embodiments of the present application provide an oil and gas reservoir production decline curve modeling method based on a pre-prepared search space symbolic regression algorithm, comprising:

[0007] Obtain a plurality of first oil and gas reservoir production data; wherein the plurality of first oil and gas reservoir production data is used to represent the oil and gas reservoir production at each time point in a preset first time period, and the end time of the first time period is earlier than the current time;

[0008] According to the plurality of first oil and gas reservoir production data and a preset search space, symbolic regression modeling is performed to obtain a plurality of expressions; wherein, the search space is an expression search space of a preset oil and gas reservoir production decline model, the search space is used to limit the generation range of the plurality of expressions, the plurality of expressions refer to oil and gas reservoir production decline curve expressions, and the plurality of expressions are used to fit the oil and gas reservoir production decline law through different function forms;

[0009] The plurality of expressions are input into a preset evaluation model to obtain evaluation values corresponding to each of the expressions; wherein, the evaluation model refers to an oil and gas reservoir production decline fitting evaluation model, the plurality of evaluation values are used to represent the complexity of the plurality of expressions, and the plurality of evaluation values are used to represent the accuracy of the plurality of expressions in fitting the oil and gas reservoir production decline law;

[0010] The curve of the expression corresponding to the minimum value in the plurality of evaluation values is determined as an oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of the oil and gas reservoir production with time in the first time period.

[0011] In a second aspect, an embodiment of the present application provides an oil and gas reservoir production decline curve modeling device based on a pre-prepared search space symbolic regression algorithm, comprising:

[0012] A first acquisition module is configured to acquire a plurality of first oil and gas reservoir production data; wherein, the plurality of first oil and gas reservoir production data are used to represent the oil and gas reservoir production at each time point in a preset first time period, and the end time of the first time period is earlier than the current time;

[0013] A model construction module is configured to perform symbolic regression modeling according to the plurality of first oil and gas reservoir production data and a preset search space to obtain a plurality of expressions; wherein, the search space is an expression search space of a preset oil and gas reservoir production decline model, the search space is used to limit the generation range of the plurality of expressions, the plurality of expressions refer to oil and gas reservoir production decline curve expressions, and the plurality of expressions are used to fit the oil and gas reservoir production decline law through different function forms;

[0014] A production decline fitting evaluation value calculation module is configured to input the plurality of expressions into a preset evaluation model to obtain evaluation values corresponding to each of the expressions; wherein, the evaluation model refers to an oil and gas reservoir production decline fitting evaluation model, the plurality of evaluation values are used to represent the complexity of the plurality of expressions, and the plurality of evaluation values are used to represent the accuracy of the plurality of expressions in fitting the oil and gas reservoir production decline law;

[0015] A curve determination module is configured to determine the curve of the expression corresponding to the minimum value in the plurality of evaluation values as an oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of the oil and gas reservoir production with time in the first time period.

[0016] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory connected with the processor in communication;

[0017] The memory stores computer-executable instructions.

[0018] The processor, when executing the computer-executable instructions stored in the memory, is configured to implement the method for modeling oil and gas reservoir production decline curve based on pre-defined search space symbol regression algorithm according to any one of the first aspect.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions, when executed by a processor, are configured to implement the method for modeling oil and gas reservoir production decline curve based on pre-defined search space symbol regression algorithm according to any one of the first aspect.

[0020] In a fifth aspect, the present application provides a computer program product, comprising a computer program, wherein the computer program, when executed by a processor, is configured to implement the method for modeling oil and gas reservoir production decline curve based on pre-defined search space symbol regression algorithm according to any one of the first aspect.

[0021] The method for modeling oil and gas reservoir production decline curve based on pre-defined search space symbol regression algorithm provided by the present application, through pre-defined search space, enables the algorithm to autonomously explore various possible function combinations, automatically evolves multiple candidate function forms, and comprehensively evaluates the complexity and fitting accuracy thereof, and finally outputs the optimal oil and gas reservoir production decline curve. This method saves the cumbersome geological modeling and numerical solution process, avoids the repeated labor of manual parameter adjustment, reduces the determination time of the decline curve under the condition of ensuring that the obtained decline curve meets the basic principles of oil and gas reservoir engineering, simultaneously reduces the prediction deviation caused by insufficient geological understanding or parameter error, and improves the determination efficiency of the oil and gas reservoir production decline curve. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0023] Figure 1 An application scenario schematic diagram of the method for modeling oil and gas reservoir production decline curve based on pre-defined search space symbol regression algorithm provided by the embodiments of the present application is shown.

[0024] Figure 2 A flowchart of the method for modeling oil and gas reservoir production decline curve based on pre-defined search space symbol regression algorithm provided by the embodiments of the present application is shown. Figure 1 ;

[0025] Figure 3 A flowchart of the oil and gas reservoir production decline curve modeling method based on the pre-prepared search space symbol regression algorithm provided for the embodiments of the present application Figure 2 ;

[0026] Figure 4 A flowchart of the oil and gas reservoir production decline curve modeling method based on the pre-prepared search space symbol regression algorithm provided for the embodiments of the present application Figure 3 ;

[0027] Figure 4 A flowchart of the oil and gas reservoir production decline curve modeling method based on the pre-prepared search space symbol regression algorithm provided for the embodiments of the present application Figure 6 ;

[0028] Figure 7 A structural diagram of the oil and gas reservoir production decline curve modeling device based on the pre-prepared search space symbol regression algorithm provided for the embodiments of the present application

[0029] Figure 1 A structural diagram of the electronic device provided for the embodiments of the present application.

[0030] The specific embodiments of the present application have been shown through the above-described drawings, and will be described in more detail hereinafter. These drawings and written descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0031] The exemplary embodiments will be described in detail herein with reference to the attached drawings. The same or similar components are denoted by the same or similar reference numerals throughout the drawings and the following description, unless otherwise specified. The embodiments described in the following exemplary embodiments do not represent all the embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application, as detailed in the appended claims.

[0032] In the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using "first", "second", and the like. It can be understood by those skilled in the art that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different. It should be noted that in the embodiments of the present application, "exemplary" or "for example" is used to represent as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific manner. In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more than two.

[0033] It should be noted that "at" in the embodiments of the present application can be at the moment when a certain condition occurs, or in a period of time after a certain condition occurs, which is not limited in the embodiments of the present application. In addition, the method, device, equipment, medium and product based on the pre-prepared search space symbol regression algorithm provided in the embodiments of the present application are only used as an example, and the method, device, equipment, medium and product based on the pre-prepared search space symbol regression algorithm can also include more or less content.

[0034] In order to clearly describe the technical solutions of the embodiments of the present application, the following briefly introduces some terms and technologies involved in the embodiments of the present application:

[0035] Oil and gas reservoir production decline curve: is a mathematical representation curve describing the gradual decline of oil and gas field or single well production with time. It describes the dynamic change characteristics in the development process of oil and gas reservoirs by establishing the function relationship between production and time. This kind of curve usually presents a monotonous decreasing form, and its specific mathematical form can be expressed as exponential type, hyperbolic type or harmonic type, etc. Different decline modes reflect the influence of physical mechanisms such as formation energy attenuation and pressure drop on production capacity, and it is an important analysis tool for predicting future production, evaluating recoverable reserves and optimizing development plan in oil and gas reservoir engineering.

[0036] Symbolic regression is a kind of machine learning method based on evolutionary computation, which automatically discovers the hidden mathematical relationships in data by intelligently searching the mathematical expression space. Unlike traditional regression methods that fix the model form, symbolic regression can autonomously explore various possible function combinations and constantly optimize the expression structure and parameters using evolutionary algorithms such as genetic programming, ultimately outputting an analytical expression that not only fits the data but also meets the complexity requirements. This method is particularly suitable for modeling complex systems where the physical laws are unclear or traditional models are difficult to describe. It achieves data-driven formula discovery while maintaining model interpretability, and has been successfully applied in various fields such as engineering and scientific computing.

[0037] The exemplary embodiments will be described in detail hereinbelow with reference to the drawings. In the following description, the same numbers refer to the same or similar elements throughout the drawings. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present invention. Instead, they are merely examples of apparatuses and methods consistent with some aspects of the present invention, as detailed in the appended claims.

[0038] The technical solutions of the present application will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes may not be described again in some examples. The embodiments of the present application will be described below with reference to the drawings.

[0039] In order to clearly understand the technical solutions of the present application, the prior art solutions will be described in detail first. Oil and gas reservoir production determination is the core link of oil and gas field development. From early empirical formula to modern numerical simulation technology, its development has always been around how to accurately depict the production and its change law. This law is affected by many factors such as heterogeneity, fluid properties and development strategy. The accuracy of production determination directly affects key indicators such as remaining reserves calculation and economic limit production calculation. Therefore, how to determine the oil and gas reservoir production is crucial.

[0040] In the prior art, the oil and gas reservoir production decline curve is mainly determined by numerical simulation method. First, engineers will establish a mathematical model to describe the multiphase flow process in the reservoir based on the geological characteristics of the oil and gas reservoir and the fluid percolation mechanism, and solve it by numerical calculation method. By adjusting the model parameters to reflect the actual oil and gas reservoir dynamic characteristics, the oil and gas reservoir production decline curve is determined. However, in the modeling and solving process of the prior art, complex parameter optimization and repeated verification are required, and there is an inherent contradiction between calculation accuracy and efficiency. When dealing with large-scale computing tasks, it faces the dilemma of large consumption of computing resources and long cycle, which leads to the reduction of the determination efficiency of the oil and gas reservoir production decline curve. Therefore, the prior art has the problem of low determination efficiency of the oil and gas reservoir production decline curve.

[0041] Therefore, in order to solve the problem of low efficiency in determining the oil and gas reservoir production decline curve in the prior art, it is found in the research that a data-driven method based on a pre-defined search space symbolic regression algorithm can be used to automatically generate and optimize the formula through a pre-defined mathematical expression search space, thereby avoiding the complex calculation process of traditional numerical simulation and improving the calculation efficiency: ①The machine learning algorithm can be used to mine the production change rule from the historical production data, and an intelligent prediction model of time-yield can be constructed to avoid the complex process of traditional geological modeling. This method uses neural networks, support vector machines and other algorithms to automatically learn data features and establish an end-to-end prediction model, which shortens the calculation period from weekly to hourly and reduces the dependence on geological parameters. ②The optimal expression can be automatically searched in the pre-defined mathematical element space based on the pre-defined search space symbolic regression algorithm. By setting a search space containing basic operations, elementary functions and other elements, the algorithm can evolve into a mathematical formula that meets the actual engineering requirements, which not only maintains the physical interpretability but also minimizes human intervention and realizes high-efficiency automated modeling. ③The domain knowledge constraints can be embedded in the generation process of the search space, such as setting the monotonicity condition of production decline and the physical rules of material balance equation. This guided search strategy based on prior knowledge can effectively reduce invalid calculation paths, accelerate the convergence speed of the algorithm, and ensure the reasonableness of the results.

[0042] Specifically, a data-driven intelligent modeling method can be used to automatically explore mathematical expressions that meet the production rules by constructing a structured search space containing mathematical operators and engineering constraint conditions. This method uses historical production data as input and performs intelligent search and parameter optimization of function form under pre-set constraints to realize the automatic conversion from raw data to mathematical model, thereby avoiding the complex geological modeling and manual parameter adjustment process in traditional methods and improving the determination efficiency of the oil and gas reservoir production decline curve.

[0043] The oil and gas reservoir production decline curve modeling method, device, equipment, medium and product based on the pre-defined search space symbolic regression algorithm of the embodiments of the present application can make the algorithm autonomously explore various possible function combinations, automatically evolve multiple candidate function forms, comprehensively evaluate their complexity and fitting accuracy, and finally output the optimal oil and gas reservoir production decline curve. This method saves the tedious geological modeling and numerical solution process, avoids the repeated labor of manual parameter adjustment, reduces the determination time of the decline curve under the condition of ensuring that the obtained decline curve meets the basic principles of oil and gas reservoir engineering, reduces the prediction deviation caused by insufficient geological understanding or parameter error, and improves the determination efficiency of the oil and gas reservoir production decline curve.

[0044] Based on the above creative findings, the technical scheme of the present application is proposed.

[0045] The application scenario of the oil and gas reservoir production decline curve modeling method based on the pre-prepared search space symbol regression algorithm provided by the embodiments of the present application is introduced below. Figure 1 The application scenario of the oil and gas reservoir production decline curve modeling method based on the pre-prepared search space symbol regression algorithm provided by the embodiments of the present application is introduced below. Figure 2 As shown in the figure, the application scenario includes a mobile terminal 101 and a server 102. The mobile terminal 101 collects a plurality of first oil and gas reservoir production data and sends the plurality of first oil and gas reservoir production data to the server 102. The server 102 constructs a model according to the plurality of first oil and gas reservoir production data and a preset search space, obtains a plurality of expressions, inputs the plurality of expressions into a preset evaluation model, obtains evaluation values corresponding to each expression, and determines the expression corresponding to the minimum value in the plurality of evaluation values as the oil and gas reservoir production decline curve.

[0046] The embodiments of the present application are introduced below in conjunction with the drawings of the specification.

[0047] Figure 1 The flowchart of the oil and gas reservoir production decline curve modeling method based on the pre-prepared search space symbol regression algorithm provided by the embodiments of the present application is shown in Figure 2 . As shown in the figure, Figure 3 In this embodiment, the execution subject of the embodiments of the present application is a server. The oil and gas reservoir production decline curve modeling method based on the pre-prepared search space symbol regression algorithm provided by the embodiments of the present application includes the following steps:

[0048] S201, obtaining a plurality of first oil and gas reservoir production data; wherein the plurality of first oil and gas reservoir production data is used to represent the oil and gas reservoir production at each time point in a preset first time period, and the end time of the first time period is earlier than the current time.

[0049] Specifically, the plurality of first oil and gas reservoir production data can be obtained by extracting historical production data from an oilfield production database or collecting real-time data from an oil well real-time monitoring system. These data include but are not limited to daily oil production, cumulative oil production, water cut and gas-oil ratio, etc. These data are used to establish the basis of the oil and gas reservoir production decline rule, to ensure that the expressions generated subsequently can accurately reflect the actual production dynamic characteristics.

[0050] S202, symbol regression modeling according to the plurality of first oil and gas reservoir production data and a preset search space, obtaining a plurality of expressions; wherein the search space is the expression search space of the preset oil and gas reservoir production decline model, the search space is used to limit the generation range of the plurality of expressions, the plurality of expressions refer to the oil and gas reservoir production decline curve expressions, and the plurality of expressions are used to fit the oil and gas reservoir production decline rule through different function forms.

[0051] Specifically, a pre-prepared search space symbolic regression algorithm can be used to construct a search space containing various mathematical operators and engineering parameters based on multiple first oil and gas reservoir production data, and multiple candidate expressions can be automatically generated and optimized by evolutionary algorithms such as genetic programming. These expressions can describe the decline characteristics of production over time from different angles, including but not limited to classic patterns such as exponential decline, hyperbolic decline, and harmonic decline, and can also discover complex decline laws that are difficult to capture by traditional methods. This process can control the complexity of the model while ensuring the accuracy of the fitting by setting the fitness function and complexity penalty term, and finally output a set of multiple expressions that are reasonable in mathematical form and physical meaning, providing a variety of candidate solutions for subsequent optimization and selection, and avoiding the subjectivity and limitations of manually selecting decline models in traditional methods.

[0052] For example, a pre-prepared search space symbolic regression algorithm can be used to fit and model multiple first oil and gas reservoir production data. The model generates multiple mathematical expressions through iterative evolution in a defined expression space, which can be defined as:

[0053]

[0054]

[0055] The iterative process can be represented as:

[0056]

[0057] wherein, represents the expression space of the oil and gas reservoir production decline curve, represents the operation operator, X represents the set of oil and gas reservoir decline production, represents the set of real constants of the decline curve, represents a single oil and gas reservoir production decline curve expression, represents the selection of multiple oil and gas reservoir production decline curve expressions, and the relatively optimal expressions with high decline fitting accuracy and low complexity are retained, represents the cross operation of the decline curve formula, represents the mutation operation of the decline curve formula, is the number of iterations.

[0058] During the iteration process, the relevant parameters are dynamically adjusted through continuous optimization. In the initial stage, based on the preset mathematical operators and parameter space, diversified candidate expressions are generated, which seek a balance between fitting accuracy and model complexity. As the iteration progresses, the fitness function and complexity penalty term work together to constantly eliminate inefficient expressions and retain those that can accurately describe the production decline law and have physical rationality. Through crossover and mutation operations, the expression space gradually evolves to form a better combination of mathematical models. The final output expression set not only covers the classic decline pattern, but also captures the complex decline law.

[0059] wherein the expression search space of the oil and gas reservoir production decline model is composed of basic mathematical operators, elementary functions, variables, constants, and initial expression of decline curve consistent with oil and gas reservoir engineering theory. Among them, the initial function expression is the core component of the space, such as exponential decline, hyperbolic decline or harmonic decline function and their combination forms. This space limits the available function types and parameter range to ensure that the candidate expressions generated by the model meet the oil and gas reservoir engineering theory, such as reflecting the nonlinear decay law of production over time. This design can not only constrain the algorithm to explore within the physically interpretable range and exclude complex polynomials without geological significance, but also retain the necessary flexibility to adapt to different decline patterns, such as early rapid decline or late slow decay, thereby balancing computational efficiency and prediction accuracy.

[0060] Common initial function expressions include: exponential decline expression, hyperbolic decline expression, harmonic decline expression, Stretched Exponential Production Decline Model (SEPD) model expression, Duong model expression, and Lithological-Geological Model (LGM) model expression.

[0061] The exponential decline expression is:

[0062]

[0063] wherein, is the oil and gas reservoir production at time t, is the initial production when t = 0, and D is the decline rate, is the time.

[0064] The hyperbolic decline expression is:

[0065]

[0066] wherein b is the production decline index.​​

[0067] The harmonic decreasing expression is:

[0068]

[0069] The SEPD model expression is:

[0070]

[0071] in, The characteristic time constant, For exponential parameters.

[0072] The Duong model expression is:

[0073]

[0074] in, For a decreasing exponent, It is the intercept of the double logarithmic curve.

[0075] The LGM model expression is:

[0076]

[0077] in, These are parameters for controlling the curve shape. It is a hyperbolic decreasing exponent.

[0078] S203. Input multiple expressions into a preset evaluation model to obtain the evaluation value corresponding to each expression; wherein, the evaluation model refers to the oil and gas reservoir production decline fitting evaluation model, and multiple evaluation values ​​are used to represent the complexity of multiple expressions, as well as the accuracy of multiple expressions in fitting the oil and gas reservoir production decline law.

[0079] Specifically, a composite evaluation method combining information criteria and engineering constraints can be adopted. This method generates a comprehensive evaluation value by calculating the fitting error of each expression to historical production data, model complexity, and whether it conforms to the physical laws of oil and gas reservoir engineering. This evaluation value reflects both the goodness of mathematical fit and ensures that the expressions have clear physical meaning. It is used to select an accurate production prediction model that conforms to the dynamic characteristics of oil and gas reservoirs from multiple expressions, avoiding the problem of simply pursuing mathematical fit while neglecting engineering rationality, and ultimately achieving a balance between data-driven approaches and engineering experience.

[0080] For example, the evaluation value corresponding to each expression can be calculated based on expression complexity and fitting accuracy. Expression complexity includes indicators such as the number of symbols, computation depth, formula length, and nesting structure. Fitting accuracy can be measured by the coefficient of determination, mean absolute percentage error, and mean squared error to assess the model's ability to fit historical data. The formula is as follows:

[0081]

[0082]

[0083]

[0084] wherein, is the determination coefficient, is the mean absolute percentage error, is the mean square error, represents the true value, represents the predicted value, represents the average value of the true value, and n represents the sample number.

[0085] The two evaluation methods are weighted to finally obtain the optimal expression process as follows:

[0086]

[0087] wherein, represents the optimal expression, represents the fitting error, which can be represented by the determination coefficient, the mean absolute percentage error or the mean square error, represents the formula complexity, represents the complexity penalty weight.

[0088] S204, the curve of the expression corresponding to the minimum value in the plurality of evaluation values is determined as the oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the case that the oil and gas reservoir production changes with time in the first time period.

[0089] Specifically, by establishing a multi-objective optimization decision mechanism, considering the evaluation dimensions such as fitting degree, model simplicity and engineering applicability, the normalized weighted scoring method is used to standardize and calculate the comprehensive score of each evaluation value of each candidate expression, and finally the expression with the minimum comprehensive score is selected as the oil and gas reservoir production decline curve. The formula not only ensures the coincidence degree with the historical production data, but also has reasonable mathematical form and clear physical meaning, and can be directly used for production prediction, recoverable reserve evaluation and development plan optimization and other engineering decisions. At the same time, the simple function form is also convenient for field engineers to understand and use, realizing the unity of theoretical accuracy and engineering practicability.

[0090] The embodiment provides a kind of oil and gas reservoir production decline curve modeling method based on prefabricated search space symbol regression algorithm, by predefining search space, algorithm can independently explore various possible function combinations, automatically evolve multiple candidate function forms, and comprehensively evaluate its complexity and fitting accuracy, finally output the optimal oil and gas reservoir production decline curve.This method saves the cumbersome geological modeling and numerical solution process, avoids the repeated labor of artificial parameter adjustment, reduces the determination time of decline curve under the condition of ensuring that the obtained decline curve meets the basic principles of oil and gas reservoir engineering, reduces the prediction deviation caused by insufficient geological understanding or parameter error, improves the determination efficiency of oil and gas reservoir production decline curve.

[0091] Figure 2 The flowchart of the oil and gas reservoir production decline curve modeling method based on the prefabricated search space symbol regression algorithm provided by the embodiments of the present application Figure 4 In the embodiment, in Figure 3 Based on the provided embodiments, the oil and gas reservoir production decline curve modeling method based on the prefabricated search space symbol regression algorithm is further explained.The oil and gas reservoir production decline curve modeling method based on the prefabricated search space symbol regression algorithm comprises:

[0092] S301, obtain a plurality of empirical formulas, operator set and a plurality of nonlinear functions;Wherein, a plurality of empirical formulas are a plurality of oil and gas reservoir production decline model empirical formulas preset, a plurality of empirical formulas are used to guide the generation direction of search space, operator set includes a plurality of mathematical operators, operator set is used to build the calculation logic of search space, a plurality of nonlinear functions are a plurality of preset decline law nonlinear functions, and a plurality of nonlinear functions are used to enhance the fitting ability of search space.

[0093] Specifically, typical production decline model can be extracted from classical oil and gas reservoir engineering theory and actual oil field production experience as empirical formula, mathematical operation basis and special nonlinear function are combined to build operator set, which is used to form search space foundation with sufficient expression ability.These initial elements not only retain the engineering reliability of traditional decline analysis method, but also provide the possibility for discovering new composite decline law through extended mathematical operation ability, and lay the search foundation with engineering guidance and mathematical flexibility for subsequent automated modeling process.

[0094] S302, space construction is carried out according to a plurality of empirical formulas, operator set and a plurality of nonlinear functions, and search space is obtained.

[0095] Specifically, empirical formulas can be used as basic templates and combined with mathematical operators and nonlinear functions from the operator set to construct a multidimensional parameterized search space using methods such as Cartesian product or syntax tree generation. This search space includes both the parameterized form of the classic decreasing model and new function structures generated through operator combinations. It provides a rich candidate model space for symbolic regression algorithms based on a pre-defined search space, while ensuring engineering rationality. This enables the algorithm to discover expressions of decreasing output patterns that are difficult to construct using traditional methods but better reflect actual production dynamics.

[0096] For example, a pre-defined search space-based symbolic regression algorithm framework can be used as a modeling tool for declining curves. This framework offers advantages such as simple structure, clear form, and high operational efficiency, accelerating the modeling process with large datasets or complex expression spaces. It also allows for simultaneous optimization of both formula complexity and fitting error, making it well-suited for modeling declining curves in oil and gas reservoirs. Based on the symbolic regression algorithm, an initial symbolic regression expression search space conforming to the declining curve laws of oil and gas reservoirs is constructed and added. This search space contains selected, representative mathematical functions and combinations used in oil and gas reservoir engineering. By restricting the symbolic regression algorithm to search for expressions within this customized function space, the flexibility of model discovery is preserved, the adaptability to declining curves in oil and gas reservoirs is enhanced, and modeling efficiency and interpretability are improved.

[0097] Meanwhile, relevant variables, symbolic operators, and corresponding constraints in the symbolic regression algorithm based on the pre-built search space are defined, and the overall symbolic operator settings are shown in Table 1.

[0098] Table 1. Variable and Operator Parameter Settings

[0099]

[0100] Time is set as the independent variable t, and daily gas production is set as the dependent variable q. Addition, subtraction, multiplication, division, and exponentiation are selected as basic binary symbolic operators, while exponential functions, user-defined inverse proportional functions, and power functions are selected as unary symbolic operators. Nested constraints are defined for exponential functions, inverse proportional functions, and power functions to avoid the accumulation of redundant expressions within them. The nested constraints are achieved by defining the frequency of occurrence of different operators, including exponentiation, addition, and exponential functions, within these functions.

[0101] S303. Obtain production data of multiple first oil and gas reservoirs; wherein, the production data of multiple first oil and gas reservoirs are used to represent the oil and gas reservoir production at each time point within a preset first time period, and the end time of the first time period is earlier than the current time.

[0102] S304. Based on the production data of multiple first oil and gas reservoirs and the preset search space, symbolic regression modeling is performed to obtain multiple expressions; where the search space is the expression search space of the preset oil and gas reservoir production decline model, the search space is used to limit the generation range of multiple expressions, the multiple expressions refer to the oil and gas reservoir production decline curve expressions, and the multiple expressions are used to fit the oil and gas reservoir production decline law through different functional forms.

[0103] S305. Input multiple expressions into a preset evaluation model to obtain the evaluation value corresponding to each expression; wherein, the evaluation model refers to the oil and gas reservoir production decline fitting evaluation model, and the multiple evaluation values ​​are used to represent the complexity of multiple expressions, as well as the accuracy of multiple expressions in fitting the oil and gas reservoir production decline law.

[0104] S306. The curve of the expression corresponding to the minimum value among multiple evaluation values ​​is determined as the oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of oil and gas reservoir production over time in the first time period.

[0105] S303-S307 are similar to S201-S204, and will not be described again in this embodiment.

[0106] The technical effect of this scheme in this embodiment is that by acquiring multiple empirical formulas, operator sets, and nonlinear functions, a guided search space is constructed, thereby enhancing the model's fitting ability and the diversity of generation directions. This method ensures that the computational logic of the search space is richer and more flexible, enabling the generated oil and gas reservoir production decline curve to accurately reflect the oil and gas reservoir production decline law, thus improving the accuracy of the oil and gas reservoir production decline curve.

[0107] In one possible design, S202, based on production data from multiple primary oil and gas reservoirs and a pre-defined search space, performs symbolic regression modeling to obtain multiple expressions, including:

[0108] S2021. Preprocess the production data of multiple first oil and gas reservoirs to obtain the production data of multiple second oil and gas reservoirs.

[0109] Specifically, data smoothing can eliminate random fluctuations and measurement noise in production data, combined with outlier detection and correction to handle abnormal production data points, and then normalization or standardization to eliminate dimensional influences. This preprocessing improves the quality of raw production data, preserves the true characteristics of production change trends, provides a more reliable data foundation for subsequent model building, effectively avoids interference from noisy data on the fitting of the decline pattern, and maintains the dynamic characteristics of the oil and gas reservoir reflected by the data unchanged.

[0110] S2022. Symbolic regression modeling was performed based on production data from multiple secondary oil and gas reservoirs and the search space to obtain multiple expressions.

[0111] Specifically, a symbolic regression algorithm can be used to dynamically combine empirical formulas with mathematical operators and nonlinear functions within a predefined search space through evolutionary operations such as selection, crossover, and mutation, automatically generating multiple candidate expressions. This method can efficiently explore various possible combinations of functions to automatically discover the optimal mathematical model for production decline from preprocessed production data. It retains the physical meaning of traditional decline analysis while adaptively capturing atypical decline characteristics of complex oil and gas reservoirs, thus improving the accuracy and generalization ability of production prediction models.

[0112] The technical effect of this solution in this embodiment is that by preprocessing the production data of the first oil and gas reservoir, refined production data of the second oil and gas reservoir is generated, thereby improving the effectiveness of model construction and the accuracy of expression generation. The preprocessing step helps to remove noise and irrelevant information, enabling the model constructed within the preset search space to accurately fit the oil and gas reservoir production decline pattern, ultimately improving the reliability of the gas reservoir production decline curve.

[0113] Figure 2 A flowchart illustrating the method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm provided in this application embodiment. Figure 5 In this embodiment, in Figure 4 Based on the provided embodiments, the method for modeling oil and gas reservoir production decline curves based on the pre-designed search space symbolic regression algorithm is further explained. The method for modeling oil and gas reservoir production decline curves based on the pre-designed search space symbolic regression algorithm includes:

[0114] S401. Obtain production data of multiple first oil and gas reservoirs; wherein, the production data of multiple first oil and gas reservoirs are used to represent the oil and gas reservoir production at each time point within a preset first time period, and the end time of the first time period is earlier than the current time.

[0115] S402. Based on the production data of multiple first oil and gas reservoirs and the preset search space, symbolic regression modeling is performed to obtain multiple expressions; where the search space is the expression search space of the preset oil and gas reservoir production decline model. The search space is used to limit the generation range of multiple expressions. Multiple expressions refer to the oil and gas reservoir production decline curve expressions. Multiple expressions are used to fit the oil and gas reservoir production decline law through different functional forms.

[0116] S401-S402 are similar to S201-S202, and will not be described again in this embodiment.

[0117] S403. The complexity evaluation model and the accuracy evaluation model are weighted and summed to obtain the evaluation model.

[0118] Specifically, by setting complexity and accuracy weighting coefficients, the complexity score and accuracy score of each expression can be calculated separately, and then linear weighted fusion can be performed. This method is used to balance the simplicity of the model with the prediction accuracy, prevent overfitting or underfitting, and ensure that the final selected oil and gas reservoir production decline curve is both engineering-practical and accurately reflects the actual production dynamics. The weighting coefficients can be dynamically adjusted according to the specific oil and gas reservoir characteristics and engineering requirements.

[0119] S404. Input multiple expressions into a preset evaluation model to obtain the evaluation value corresponding to each expression; wherein, the evaluation model refers to the oil and gas reservoir production decline fitting evaluation model, and the multiple evaluation values ​​are used to represent the complexity of multiple expressions, as well as the accuracy of multiple expressions in fitting the oil and gas reservoir production decline law.

[0120] S405. The curve of the expression corresponding to the minimum value among multiple evaluation values ​​is determined as the oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of oil and gas reservoir production over time in the first time period.

[0121] S404-S405 are similar to S203-S204, and will not be described again in this embodiment.

[0122] The technical advantage of this scheme in this embodiment is that by weighted summation of the complexity evaluation model and the accuracy evaluation model, a comprehensive evaluation model is formed. This method enables the selection of oil and gas reservoir production decline curves to simultaneously consider the complexity of the expression and the fitting accuracy, ensuring that the finally selected oil and gas reservoir production decline curve not only has high accuracy but also maintains appropriate complexity, thereby optimizing computational efficiency.

[0123] Figure 2 A flowchart illustrating the method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm provided in this application embodiment. Figure 6 In this embodiment, in Figure 6 Based on the provided embodiments, the method for modeling oil and gas reservoir production decline curves based on the pre-designed search space symbolic regression algorithm is further explained. The method for modeling oil and gas reservoir production decline curves based on the pre-designed search space symbolic regression algorithm includes:

[0124] S501. Obtain production data of multiple first oil and gas reservoirs; wherein, the production data of multiple first oil and gas reservoirs are used to represent the oil and gas reservoir production at each time point within a preset first time period, and the end time of the first time period is earlier than the current time.

[0125] S502. Based on the production data of multiple first oil and gas reservoirs and the preset search space, symbolic regression modeling is performed to obtain multiple expressions. Among them, the search space is the expression search space of the preset oil and gas reservoir production decline model. The search space is used to limit the generation range of multiple expressions. Multiple expressions refer to the oil and gas reservoir production decline curve expressions. Multiple expressions are used to fit the oil and gas reservoir production decline law through different functional forms.

[0126] S503. Input multiple expressions into a preset evaluation model to obtain the evaluation value corresponding to each expression; wherein, the evaluation model refers to the oil and gas reservoir production decline fitting evaluation model, and the multiple evaluation values ​​are used to represent the complexity of multiple expressions, as well as the accuracy of multiple expressions in fitting the oil and gas reservoir production decline law.

[0127] S504. The curve of the expression corresponding to the minimum value among multiple evaluation values ​​is determined as the oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of oil and gas reservoir production over time in the first time period.

[0128] S501-S504 are similar to S201-S204, and will not be described again in this embodiment.

[0129] S505. Input the oil and gas reservoir production decline curve into each time point in the first time period to obtain the theoretical production value of each time point in the first time period.

[0130] Specifically, by substituting historical production time-series data as independent variables into the functional expression of the oil and gas reservoir production decline curve, and using numerical calculation methods to solve for the theoretical production value at the corresponding time points, the oil and gas reservoir decline curve can be plotted to verify the formula's ability to reproduce historical production dynamics. This process can quantify the goodness of fit of the calculation formula, provide a benchmark reference for subsequent formula parameter optimization, ensure the consistency between the theoretical calculation curve and the actual historical production trend, and identify the applicability limitations of the formula in specific production stages, guiding targeted model correction work.

[0131] S506. Optimize the oil and gas reservoir production decline curve based on the theoretical production values ​​at each time point within the first time period to obtain the optimized oil and gas reservoir production decline curve.

[0132] Specifically, parameter optimization methods based on gradient descent or genetic algorithms can be employed. By minimizing the sum of squared residuals between theoretical and actual production values, the parameters in the oil and gas reservoir production decline curve are automatically adjusted while maintaining the basic mathematical form of the formula. This optimization process improves the accuracy of the calculation formula in matching historical production data, eliminates systematic biases caused by improper initial parameter settings, and ensures that the optimized formula accurately reflects the past dynamic characteristics of the oil and gas reservoir while possessing better extrapolation and prediction capabilities, providing a more reliable mathematical model foundation for subsequent production predictions.

[0133] S507. Input the optimized oil and gas reservoir production decline curve into each time point within the preset second time period to obtain the predicted production value at each time point within the second time period; wherein, the start time of the second time period is later than the current time.

[0134] Specifically, the predicted production value can be used to formulate future development plans for oil fields, including but not limited to the design of production allocation schemes and the determination of equipment maintenance cycles. At the same time, it can be combined with oil and gas reservoir engineering constraints to automatically identify the economic exploitation life of oil fields, providing a quantitative basis for development decisions and realizing intelligentization of the entire process from historical data analysis to future production prediction.

[0135] The technical effect of this solution in this embodiment is that by optimizing the determined oil and gas reservoir production decline curve, it can not only accurately reflect production changes within historical time periods but also effectively predict production in future time periods. This process reduces prediction errors and improves the adaptability and prediction accuracy of the gas reservoir production decline curve by comparing and adjusting the theoretical production values ​​of historical data with actual data, thereby providing a reliable basis for oil and gas reservoir management and decision-making.

[0136] In one possible design, S506, the oil and gas reservoir production decline curve is optimized based on the theoretical production values ​​at each time point within the first time period, resulting in an optimized oil and gas reservoir production decline curve, including:

[0137] S5061. Calculate the deviation between the production data of multiple first oil and gas reservoirs and the theoretical production values ​​at each time point within the first time period.

[0138] Specifically, the deviation between actual and theoretical production values ​​can be quantified by calculating indicators such as absolute error, relative error, or root mean square error. A time-weighted approach is also used to highlight the importance of recent production data. This deviation calculation is used to evaluate the fitting accuracy of the current production calculation formula, identify systematic errors in the formula at specific production stages, provide a clear objective function for subsequent parameter optimization, and ensure that the optimized calculation formula accurately reflects the actual dynamic characteristics of oil and gas reservoir production, thereby improving the reliability of future production predictions.

[0139] S5062. Optimize the oil and gas reservoir production decline curve based on the deviation to obtain the optimized oil and gas reservoir production decline curve.

[0140] Specifically, a constrained least squares optimization algorithm can be used, with the objective function of minimizing the sum of squared deviations. While maintaining the physical meaning of the formula, the algorithm automatically adjusts the undetermined parameters in the formula. This optimization process eliminates systematic errors in the model, ensuring that the calculation formula accurately matches historical production dynamics and conforms to the basic principles of oil and gas reservoir engineering. The resulting optimized formula improves the fitting accuracy to the already developed stage and reliably predicts future production trends, providing accurate quantitative basis for oilfield development adjustment decisions.

[0141] The technical effect of this scheme in this embodiment is as follows: by calculating the deviation between historical oil and gas reservoir production data and theoretical production values, and optimizing the oil and gas reservoir production decline curve based on this deviation, the accuracy and predictive ability of the formula are improved. This optimization process effectively reduces the error between the model and actual production, enabling the optimized gas reservoir production decline curve to more accurately reflect the actual production situation of the oil and gas reservoir, thereby enhancing the reliability and practicality of future production prediction.

[0142] Figures 2 to 5 A schematic diagram of the structure of the oil and gas reservoir production decline curve modeling device based on a prefabricated search space symbolic regression algorithm provided in this application embodiment. Figures 2 to 5 As shown, the oil and gas reservoir production decline curve modeling device based on the prefabricated search space symbolic regression algorithm includes:

[0143] The first acquisition module 601 is used to acquire multiple first oil and gas reservoir production data; wherein, the multiple first oil and gas reservoir production data are used to represent the oil and gas reservoir production at each time point within a preset first time period, and the end time of the first time period is earlier than the current time.

[0144] The model building module 602 is used to perform symbolic regression modeling based on the production data of multiple first oil and gas reservoirs and a preset search space to obtain multiple expressions. The search space is the expression search space of the preset oil and gas reservoir production decline model. The search space is used to limit the generation range of multiple expressions. The multiple expressions refer to the oil and gas reservoir production decline curve expressions. The multiple expressions are used to fit the oil and gas reservoir production decline law through different functional forms.

[0145] The production decline fitting evaluation value calculation module 603 is used to input multiple expressions into a preset evaluation model to obtain the evaluation value corresponding to each expression; wherein, the evaluation model refers to the oil and gas reservoir production decline fitting evaluation model, and the multiple evaluation values ​​are used to represent the complexity of multiple expressions, as well as the accuracy of multiple expressions in fitting the oil and gas reservoir production decline law.

[0146] The curve determination module 604 is used to determine the curve of the expression corresponding to the minimum value among multiple evaluation values ​​as the oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of oil and gas reservoir production over time in the first time period.

[0147] In one possible implementation, the oil and gas reservoir production decline curve modeling device based on a pre-designed search space symbolic regression algorithm further includes:

[0148] The second acquisition module is used to acquire multiple empirical formulas, an operator set, and multiple nonlinear functions. Among them, the multiple empirical formulas are multiple preset empirical formulas for oil and gas reservoir production decline models, which are used to guide the generation direction of the search space. The operator set includes multiple mathematical operators, which are used to construct the computational logic of the search space. The multiple nonlinear functions are multiple preset nonlinear functions with declining patterns, which are used to enhance the fitting ability of the search space.

[0149] The space construction module is used to construct the search space based on multiple empirical formulas, operator sets, and multiple nonlinear functions.

[0150] In one possible implementation, the model building module 602 includes:

[0151] The preprocessing unit is used to preprocess production data from multiple first oil and gas reservoirs to obtain production data from multiple second oil and gas reservoirs.

[0152] The model building unit is used to perform symbolic regression modeling based on production data from multiple secondary oil and gas reservoirs and the search space, resulting in multiple expressions.

[0153] In one possible implementation, the evaluation model includes a complexity evaluation model and an accuracy evaluation model, and the oil and gas reservoir production determination device further includes:

[0154] The weighted summation module is used to perform a weighted summation of the complexity evaluation model and the accuracy evaluation model to obtain the evaluation model.

[0155] In one possible implementation, the oil and gas reservoir production determination device further includes:

[0156] The first calculation unit is used to input the oil and gas reservoir production decline curve into each time point within the first time period to obtain the theoretical production value of each time point within the first time period.

[0157] The optimization unit is used to optimize the oil and gas reservoir production decline curve based on the theoretical production values ​​at each time point within the first time period, and obtain the optimized oil and gas reservoir production decline curve.

[0158] The second calculation unit is used to input the optimized oil and gas reservoir production decline curve into each time point within the preset second time period to obtain the predicted production value at each time point within the second time period; wherein, the start time of the second time period is later than the current time.

[0159] In one possible implementation, the optimization unit includes:

[0160] The deviation calculation component is used to calculate the deviation between the production data of multiple first oil and gas reservoirs and the theoretical production values ​​at each time point within the first time period.

[0161] An optimization component is used to optimize the oil and gas reservoir production decline curve based on the deviation, resulting in an optimized oil and gas reservoir production decline curve.

[0162] The oil and gas reservoir production decline curve modeling device based on a pre-designed search space symbolic regression algorithm provided in this embodiment can perform... Figure 7 The technical solution of the embodiment of the method for modeling the decline curve of oil and gas reservoir production based on the pre-designed search space symbolic regression algorithm is shown. Its implementation principle and technical effect are similar to those of the method described above. Figure 7 The embodiment of the method for modeling the decline curve of oil and gas reservoir production based on the pre-designed search space symbolic regression algorithm is similar and will not be described in detail here.

[0163] ​ This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of this application. ​ As shown, the electronic device includes at least one processor 710 and a memory 720. The electronic device also includes a communication component 730. The processor 710, memory 720, and communication component 730 are connected via a bus 740.

[0164] In the specific implementation process, at least one processor 710 executes computer execution instructions stored in memory 720, so that at least one processor 710 is used to implement a method for modeling the declining oil and gas reservoir production curve based on a pre-made search space symbolic regression algorithm as described in the above embodiment.

[0165] The specific implementation process of processor 710 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0166] In the above embodiments, it should be understood that the processor 710 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0167] The memory 720 may include high-speed RAM memory, and may also include non-volatile memory NVM, such as at least one disk storage.

[0168] Bus 740 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 740 can be divided into address bus, data bus, control bus, etc. For ease of illustration, the bus 740 in the accompanying drawings of this application is not limited to only one bus or one type of bus.

[0169] The above description of the functions implemented by electronic devices and main control devices has introduced the solutions provided by the embodiments of the present invention. It is understood that, in order to implement the above functions, the electronic device or main control device includes hardware structures and / or software modules corresponding to the execution of each function. By combining the units and algorithm steps of the various examples described in the embodiments of the present invention, the embodiments of the present invention can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of the embodiments of the present invention.

[0170] This application also provides a computer-readable storage medium storing computer-executable instructions. When executed by a processor, these instructions are used to implement the oil and gas reservoir production decline curve modeling method based on a pre-designed search space symbolic regression algorithm described in the above embodiments. In the specific implementation of the aforementioned oil and gas reservoir production decline curve modeling method based on a pre-designed search space symbolic regression algorithm, each module can be implemented as a processor.

[0171] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0172] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in application-specific integrated circuits (ASICs). Alternatively, the processor and the readable storage medium can exist as discrete components in an electronic device or a host device.

[0173] This application also provides a computer program product, including a computer program that, when executed by a processor, is used to implement a method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm as described in the above embodiments.

[0174] The computer program is stored in a readable storage medium, and at least one processor can read the computer program from the readable storage medium and execute the computer program to perform the scheme provided in any of the above embodiments.

[0175] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disk, or optical disk.

[0176] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application 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 or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm, characterized in that, include: Acquire production data from multiple first oil and gas reservoirs; wherein, the multiple first oil and gas reservoir production data are used to represent the oil and gas reservoir production at each time point within a preset first time period, and the end time of the first time period is earlier than the current time. Symbolic regression modeling is performed based on the production data of the multiple first oil and gas reservoirs and a preset search space to obtain multiple expressions; wherein, the search space is the expression search space of the preset oil and gas reservoir production decline model, the search space is used to limit the generation range of the multiple expressions, the multiple expressions refer to the oil and gas reservoir production decline curve expressions, and the multiple expressions are used to fit the oil and gas reservoir production decline law through different functional forms. The multiple expressions are input into a preset evaluation model to obtain the evaluation value corresponding to each expression; wherein, the evaluation model refers to the oil and gas reservoir production decline fitting evaluation model, and the multiple evaluation values ​​are used to represent the complexity of the multiple expressions and the accuracy of the multiple expressions in fitting the oil and gas reservoir production decline law. The curve of the expression corresponding to the minimum value among the multiple evaluation values ​​is determined as the oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of oil and gas reservoir production over time in the first time period.

2. The method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm according to claim 1, characterized in that, Before acquiring production data from multiple first oil and gas reservoirs, the process also includes: Multiple empirical formulas, an operator set, and multiple nonlinear functions are obtained. The multiple empirical formulas are preset empirical formulas for multiple oil and gas reservoir production decline models. The multiple empirical formulas are used to guide the generation direction of the search space. The operator set includes multiple mathematical operators. The operator set is used to construct the calculation logic of the search space. The multiple nonlinear functions are preset nonlinear functions with declining patterns. The multiple nonlinear functions are used to enhance the fitting ability of the search space. The search space is obtained by constructing a space based on the multiple empirical formulas, the set of operators, and the multiple nonlinear functions.

3. The method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm according to claim 1, characterized in that, The method involves performing symbolic regression modeling based on the production data of the multiple first oil and gas reservoirs and a preset search space, resulting in multiple expressions, including: The production data of the multiple first oil and gas reservoirs are preprocessed to obtain the production data of multiple second oil and gas reservoirs; Symbolic regression modeling is performed based on the production data of the multiple second oil and gas reservoirs and the search space to obtain the multiple expressions.

4. The method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm according to claim 1, characterized in that, The evaluation model includes a complexity evaluation model and an accuracy evaluation model. Before inputting the multiple expressions into the preset evaluation model to obtain the evaluation value corresponding to each expression, the method further includes: The complexity evaluation model and the accuracy evaluation model are weighted and summed to obtain the evaluation model.

5. The method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm according to claim 1, characterized in that, After determining the curve of the expression corresponding to the minimum value among the plurality of evaluation values ​​as the oil and gas reservoir production decline curve, the method further includes: Input each time point within the first time period into the oil and gas reservoir production decline curve to obtain the theoretical production value for each time point within the first time period. The oil and gas reservoir production decline curve is optimized based on the theoretical production value at each time point in the first time period to obtain the optimized oil and gas reservoir production decline curve. Input each time point within the preset second time period into the optimized oil and gas reservoir production decline curve to obtain the predicted production value for each time point within the second time period; wherein, the start time of the second time period is later than the current time.

6. The method for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm according to claim 5, characterized in that, The optimization of the oil and gas reservoir production decline curve based on the theoretical production values ​​at each time point within the first time period to obtain the optimized oil and gas reservoir production decline curve includes: Calculate the deviation between the production data of the multiple first oil and gas reservoirs and the theoretical production values ​​at each time point within the first time period; The production decline curve of the oil and gas reservoir is optimized based on the deviation to obtain the optimized production decline curve of the oil and gas reservoir.

7. A device for modeling oil and gas reservoir production decline curves based on a pre-designed search space symbolic regression algorithm, characterized in that, include: The first acquisition module is used to acquire multiple first oil and gas reservoir production data; wherein, the multiple first oil and gas reservoir production data are used to represent the oil and gas reservoir production at each time point within a preset first time period, and the end time of the first time period is earlier than the current time. The model building module is used to perform symbolic regression modeling based on the production data of the multiple first oil and gas reservoirs and a preset search space to obtain multiple expressions; wherein, the search space is the expression search space of the preset oil and gas reservoir production decline model, the search space is used to limit the generation range of the multiple expressions, the multiple expressions refer to the oil and gas reservoir production decline curve expressions, and the multiple expressions are used to fit the oil and gas reservoir production decline law through different functional forms. The production decline fitting evaluation value calculation module is used to input the multiple expressions into a preset evaluation model to obtain the evaluation value corresponding to each expression; wherein, the evaluation model refers to the oil and gas reservoir production decline fitting evaluation model, and the multiple evaluation values ​​are used to represent the complexity of the multiple expressions and the accuracy of the multiple expressions in fitting the oil and gas reservoir production decline law. The formula determination module is used to determine the curve of the expression corresponding to the minimum value among the multiple evaluation values ​​as the oil and gas reservoir production decline curve; wherein, the oil and gas reservoir production decline curve is used to represent the change of oil and gas reservoir production over time in the first time period.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; When the processor executes the computer execution instructions stored in the memory, it is used to implement the oil and gas reservoir production decline curve modeling method based on the pre-made search space symbolic regression algorithm as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the oil and gas reservoir production decline curve modeling method based on a pre-designed search space symbolic regression algorithm as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The method includes a computer program, which, when executed by a processor, is used to implement the oil and gas reservoir production decline curve modeling method based on a pre-designed search space symbolic regression algorithm as described in any one of claims 1 to 6.

Images