A method, system and electronic device for quantitatively evaluating the potential of a heterogeneous gas reservoir

Abstract

This invention relates to the field of unconventional oil and gas exploration and development, and discloses a method, system, and electronic equipment for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs. The quantitative evaluation method includes: S1, selecting influencing parameters closely related to the distribution of residual gas; S2, using the Pearson correlation coefficient method to evaluate the correlation between the recoverable reserves of a single well and the correlation coefficient, and after verification, selecting the main controlling factors; S3, using the random forest algorithm and the multiple linear regression method respectively to quantitatively characterize the influence of the main controlling factors on the recoverable reserves of a single well, obtaining the weights of each main controlling factor in the two methods, and then standardizing them to obtain the weights of the main controlling factors; S4, establishing a quantitative evaluation model for the exploitation potential of residual gas based on the weights of the main controlling factors, and calculating the exploitation potential index of residual gas. This invention uses a quantitative evaluation method for the exploitation potential of residual gas, and the established exploitation potential index can better characterize the residual gas characteristics of a single well, providing guidance for the efficient development of tight sandstone gas reservoirs and improving gas field recovery rates.

Description

Technical Field

[0001] This invention relates to the field of unconventional oil and gas exploration and development, and in particular to a method, system and electronic equipment for quantitatively evaluating the potential of heterogeneous gas reservoirs. Background Technology

[0002] my country's tight gas resources account for approximately 10% of the global total, demonstrating abundant reserves and indicating enormous development potential and a profound impact on national energy security. Tight gas resources are mainly distributed in geologically complex but resource-rich areas such as the Sichuan Basin, Ordos Basin, and Tarim Basin. The geological conditions of these basins provide an ideal environment for the formation and storage of tight gas. The Sichuan Basin, as one of the important areas for tight gas development, boasts particularly substantial resources. However, tight sandstone gas reservoirs such as the L gas field in the Sichuan Basin face numerous challenges, with small effective reservoir size, multiple superimposed layers, and strong heterogeneity being particularly prominent. These heterogeneous oil and gas reservoirs exhibit significant differences in physical properties and extremely high permeability between reservoir layers, resulting in low sweep efficiency of traditional water-drive and gas-drive methods, making efficient reservoir development difficult. These characteristics directly lead to limited well drainage ranges, making it difficult to significantly increase single-well production, thus affecting the overall recovery rate and stable production capacity of the gas field.

[0003] Regarding the evaluation of the remaining gas potential in heterogeneous gas reservoirs, some literature reports the establishment of seismic identification models, comprehensive well logging geological indicators, and well logging electrical standards, fully integrating the characteristics of reservoir stimulation technology, thus forming a research approach and methodology for selecting wells and evaluating reservoir layers for potential tapping in old wells. Other literature, specifically concerning the tight sandstone gas reservoirs in the Sulige gas field, first determined the remaining gas distribution pattern based on geological understanding and production characteristics, clarifying the distribution law of remaining gas, and then formulated corresponding potential tapping strategies for different types of remaining reserves.

[0004] Patent CN 114427432 A discloses a method for determining the development potential of residual gas in a gas reservoir, comprising the following steps: establishing a numerical simulation model of the gas reservoir; obtaining the static and dynamic parameter fields of the gas reservoir under its current state based on the numerical simulation model; screening existing infill wells in the gas reservoir and predicting the recoverable reserves of each infill well using the numerical simulation model, and establishing a correlation chart between the recoverable reserves of each well and the static and dynamic parameter fields; determining the main controlling factors for the development of residual gas in the gas reservoir based on the correlation chart between the recoverable reserves of each well and the static and dynamic parameter fields within the control range of each well; establishing a correlation model between the recoverable reserves of each well and the main controlling factors of residual gas using a multiple regression method based on the main controlling factors; establishing a prediction model for the residual gas development potential index of the gas reservoir based on the correlation model between the recoverable reserves of each well and the main controlling factors of residual gas; and obtaining the residual gas development potential index of the gas reservoir based on the prediction model for the residual gas development potential index of the gas reservoir. This method, by increasing well density, can more effectively cover and utilize residual gas resources. However, the current characterization of residual gas distribution in tight sandstone gas reservoirs is not refined enough, and the main controlling factors and distribution patterns are not clearly understood. This limits the effectiveness of well infill drilling technology to some extent. The evaluation of the exploitation potential of this planar layout is mainly qualitative and relatively general. Furthermore, the strict selection of well locations and the complex infill drilling process make it impossible to provide quantitative conclusions. Therefore, it is necessary to develop a quantitative evaluation method suitable for the exploitation potential of residual gas in heterogeneous gas reservoirs. Summary of the Invention

[0005] The purpose of this invention is to address the problem that existing methods for evaluating the potential of gas reservoirs rely heavily on qualitative analysis, which makes it difficult to accurately guide the development of tight gas reservoirs. This invention provides a method, system, and electronic equipment for quantitatively evaluating the potential of heterogeneous gas reservoirs.

[0006] In a first aspect, the present invention provides a method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs, comprising the following steps: S1. Select influencing parameters that are closely related to the distribution of residual gas, with at least 5 influencing parameters; S2. The correlation between the recoverable reserves of a single well and the correlation coefficient is evaluated using the Pearson correlation coefficient method, and the correlation between the influencing parameters is verified using the single-factor regression method to screen out the main controlling factors. S3. The influence of the main control factors on the recoverable reserves of a single well is quantitatively characterized by the random forest algorithm and the multiple linear regression method, respectively. The weights of the main control factors in the two methods are obtained. The weights of the main control factors are standardized to obtain the weights of the main control factors. S4. Establish a quantitative evaluation model for the remaining gas tapping potential based on the weights of the main controlling factors, and calculate the remaining gas tapping potential index to evaluate the gas reservoir tapping potential.

[0007] In the technical solution of this invention, firstly, the influencing parameters closely related to the distribution of residual gas are determined. Then, the Pearson correlation coefficient method is used to evaluate the correlation between the recoverable reserves of a single well and the correlation coefficient, and the correlation between the recoverable reserves of a single well and the correlation coefficient is verified, thus obtaining the main controlling factors affecting the distribution of residual gas. Then, the weights of the main controlling factors are obtained using the random forest algorithm and the multiple linear regression method, respectively. Taking into account the influence weights of the main controlling factors on the recoverable reserves of a single well, a quantitative evaluation model of the residual gas tapping potential in the target area is established using the multi-factor comprehensive weighting method, and the residual gas tapping potential index is calculated for use in evaluating the gas reservoir tapping potential.

[0008] Through the above technical solution, this invention provides a quantitative evaluation method for the potential of residual gas. Instead of using infill wells, it employs the Pearson correlation coefficient method to evaluate and verify the correlation between the recoverable reserves of a single well and the correlation coefficient to obtain the main controlling factors affecting the distribution of residual gas. Weight coefficients are calculated using the random forest algorithm and multiple linear regression, and a quantitative characterization model of the potential for residual gas is constructed using a multi-factor comprehensive weighting method. The residual gas potential index is calculated, upgrading the evaluation of residual gas potential from qualitative description to quantitative analysis. This provides technical support for the efficient development of tight sandstone gas reservoirs and the improvement of reservoir recovery rates. It solves the problem that existing technologies rely heavily on qualitative analysis for potential evaluation, failing to provide quantitative conclusions.

[0009] As a preferred embodiment of the present invention, the number of influencing parameters is 8 to 12.

[0010] As a preferred embodiment of the present invention, the method for selecting the influencing parameters is as follows: based on production practice and gas reservoir numerical simulation results, parameters that affect the distribution of remaining gas are selected as influencing parameters for potential exploration analysis and evaluation.

[0011] As a preferred embodiment of the present invention, the influencing parameters are single-well controlled reserves, pressure, permeability, gas saturation, porosity, gas viscosity, initial production allocation, effective thickness, and average decline rate.

[0012] As a more preferred embodiment of the present invention, the main controlling factors are single-well controlled reserves, pressure, permeability, gas saturation, and porosity.

[0013] As a preferred embodiment of the present invention, the method for evaluating the correlation between the recoverable reserves of a single well and the correlation coefficient using the Pearson correlation coefficient method is as follows: Using the recoverable reserves of a single well as the target variable, the Pearson correlation coefficient method is used to calculate the Pearson correlation coefficient between each of the aforementioned correlation coefficients and the target variable. The formula for calculating the Pearson correlation coefficient is as follows:

[0014] in Let be the Pearson correlation coefficient of the i-th influencing parameter. Let i be the value of the i-th influencing parameter; Let i be the value of the target variable corresponding to the i-th influencing parameter; This is the average value of the correlation coefficients; The average value of the target variable; The correlation coefficients were ranked by their absolute values, and those ranking between 70% and 90% were selected as the main control factors.

[0015] As a preferred embodiment of the present invention, the detailed steps of step S3 are as follows: Based on the analysis results of the main control factors, the random forest algorithm is used to analyze the impact of the main control factors on the recoverable reserves of a single well when the main control factors change within a certain range, and to determine the weight coefficient of each main control factor. Based on the analysis results of the main control factors, the correlation equation between the recoverable reserves of a single well and the main control factors was established by using the multiple linear regression method. The weight coefficient of each main control factor was determined by the influence of each residual gas main control factor on the recoverable reserves of the single well when the factors change within a certain range. The weight coefficients determined by the random forest algorithm and the weight coefficients determined by the multiple linear regression method are standardized to obtain the final weights of the main controlling factors.

[0016] As a preferred embodiment of the present invention, the quantitative evaluation model for the remaining gas tapping potential is as follows:

[0017]

[0018] In the formula: PI a represents the remaining gas exploitation potential index. i Let be the weight of the i-th controlling factor, dimensionless; Let i be the value of the i-th controlling factor. These are the maximum and minimum values ​​of the controlling factors, respectively.

[0019] In a second aspect, the present invention provides a quantitative evaluation system for the exploitation potential of heterogeneous gas reservoirs, the system comprising: The parameter selection module is used to select influencing parameters that are closely related to the distribution of residual gas, and the influencing parameters are at least 5. The module for screening the main controlling factors is used to evaluate the correlation between the recoverable reserves of a single well and the correlation coefficient using the Pearson correlation coefficient method, and to verify the correlation between the influencing parameters using the single-factor regression method, thereby screening out the main controlling factors. The weight calculation module is used to quantitatively characterize the influence of the main control factors on the recoverable reserves of a single well using the random forest algorithm and the multiple linear regression method, respectively, to obtain the weights of the main control factors for each of the two methods, and to standardize the weights of the main control factors to obtain the weights of the main control factors. The potential index calculation module is used to establish a quantitative evaluation model of the remaining gas tapping potential based on the weights of the main control factors, and to calculate the remaining gas tapping potential index.

[0020] The present invention also provides an electronic device, including at least one processor and a memory communicatively connected to the at least one processor; the memory stores instructions that are executed by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the above-described method for quantitatively evaluating the potential of heterogeneous gas reservoirs.

[0021] The present invention also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the above-described method for quantitatively evaluating the potential of heterogeneous gas reservoirs.

[0022] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. This invention provides a quantitative evaluation method for the remaining gas tapping potential of heterogeneous gas reservoirs. Instead of using infill wells, it employs the Pearson correlation coefficient method to evaluate and verify the correlation between the recoverable reserves of a single well and the correlation coefficient using a single-factor regression method to obtain the main controlling factors affecting the distribution of remaining gas. By using the random forest algorithm and multiple linear regression to calculate weight coefficients, and utilizing a multi-factor comprehensive weighting method to construct a quantitative characterization model of the remaining gas tapping potential, it calculates the remaining gas tapping potential index. This solves the problem in existing technologies where tapping potential evaluation relies heavily on qualitative analysis and cannot provide quantitative conclusions.

[0023] 2. This invention employs a quantitative evaluation method for the remaining gas tapping potential, eliminating the subjectivity of subjective qualitative evaluation. It can provide guidance and basis for the selection of tapping wells and potential areas. The established tapping potential index can better characterize the remaining gas characteristics of a single well, and can provide guidance for the efficient development of tight sandstone gas reservoirs and the improvement of gas field recovery rate. Attached Figure Description

[0024] Figure 1 This is a flowchart of the quantitative evaluation method for the tapping potential of heterogeneous gas reservoirs according to the present invention. Figure 2 This is a heat map showing the correlation between recoverable reserves of a single well and influencing parameters in Example 2; Figure 3This is a correlation analysis diagram of the recoverable reserves and controlled reserves of a single well in Example 2; Figure 4 This is a graph showing the correlation between recoverable reserves and pressure in a single well in Example 2; Figure 5 This is a correlation analysis diagram of recoverable reserves and permeability in a single well in Example 2; Figure 6 This is a correlation analysis diagram of single-well recoverable reserves and gas saturation in Example 2; Figure 7 This is a correlation analysis diagram of recoverable reserves and porosity in a single well in Example 2; Figure 8 The histogram of importance analysis used in Example 2 is an example of random forest analysis. Figure 9 The histogram of importance analysis using multiple linear regression in Example 2. Figure 10 This is the weighted mean standardized histogram in Example 2; Figure 11 The production curve of well L8-3 in Example 2 Figure 12 This is the production curve of well L6-1 in Example 2. Detailed Implementation

[0025] The present invention will now be described in further detail with reference to specific embodiments. However, this should not be construed as limiting the scope of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0026] Unless otherwise specified, the use of terms such as "upper," "lower," "left," "right," "center," "inner," and "outer" to indicate orientation or positional relationships in the description of specific embodiments of the present invention is based on the orientation or positional relationships shown in the accompanying drawings, or the orientation or positional relationship in which the product / equipment / device is typically placed during use. These terms are merely for the purpose of facilitating the description of the present invention or simplifying the description in specific embodiments, enabling those skilled in the art to quickly understand the solution, and do not indicate or imply that a particular device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship. Therefore, they should not be construed as limitations on the present invention.

[0027] Furthermore, the use of terms such as "horizontal," "vertical," "suspended," and "parallel" does not imply that the corresponding device / component / element must be absolutely horizontal, vertical, suspended, or parallel, but rather that it can be slightly tilted or have a deviation. For example, "horizontal" merely means that its direction is more horizontal relative to "vertical," not that the structure must be completely horizontal, but that it can be slightly tilted. Alternatively, it can be simplified to mean that the corresponding device / component / element, when set in a "horizontal," "vertical," "suspended," or "parallel" direction, can have an error / deviation of ±10% relative to the corresponding direction, more preferably within ±8%, more preferably within ±6%, more preferably within ±5%, and more preferably within ±4%. As long as the corresponding device / component / element is within the error / deviation range, it can still achieve its function in the present invention.

[0028] Furthermore, the use of terms such as "first," "second," and "third" in terminology is merely for distinguishing descriptions of identical or similar components and should not be interpreted as emphasizing or implying the relative importance of a particular component.

[0029] Furthermore, in the description of the embodiments of the present invention, "several", "more than", and "a number of" represent at least two. The number can be any number, such as 2, 3, 4, 5, 6, 7, 8, or 9, and can even exceed nine.

[0030] Furthermore, in the description of the technical solution of this invention, unless otherwise explicitly specified / limited / restricted, the terms "set up," "install," "connect," "link," "provided with," "laid out," and "arranged" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to common connection methods in the art, such as welding, riveting, bolting, and threaded connections. Such connections can be mechanical, electrical, or communication connections; they can be direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components.

[0031] Example 1 like Figure 1 As shown in the figure, this embodiment provides a method for quantitatively evaluating the tapping potential of heterogeneous gas reservoirs, including the following steps: S1. Select influencing parameters that are closely related to the distribution of residual gas, with at least 5 influencing parameters.

[0032] The method for selecting influencing parameters is as follows: Based on production practice and gas reservoir numerical simulation results, parameters that affect the distribution of remaining gas are selected as influencing parameters for potential development analysis and evaluation. Specifically, gas reservoir numerical simulation involves using software to establish a geological model of heterogeneous gas reservoirs, obtaining reservoir formation parameters, well parameters, production data, and reservoir physical property parameters. Numerical simulation is then performed to determine the multiple parameters with the greatest impact on the distribution of remaining gas. Simultaneously, multiple parameters with the greatest impact on the distribution of remaining gas are determined from production practice. Integrating the results of production practice and gas reservoir numerical simulation yields the influencing parameters for potential development analysis and evaluation.

[0033] S2. The correlation between recoverable reserves of a single well and the correlation coefficient was evaluated using the Pearson correlation coefficient method, and the correlation between influencing parameters was verified using the single-factor regression method to screen out the main controlling factors.

[0034] The method for evaluating the correlation between recoverable reserves of a single well and the correlation coefficient using the Pearson correlation coefficient method is as follows: Using the recoverable reserves of a single well as the target variable, the Pearson correlation coefficient method is used to calculate the Pearson correlation coefficient between each correlation coefficient and the target variable. The formula for calculating the Pearson correlation coefficient is as follows:

[0035] in Let be the Pearson correlation coefficient of the i-th influencing parameter. Let i be the value of the i-th influencing parameter; Let i be the value of the target variable corresponding to the i-th influencing parameter; This is the average value of the correlation coefficients; The average value of the target variable; The correlation coefficients were ranked by their absolute values, and those ranking between 70% and 90% were selected as the main control factors.

[0036] Single-factor regression analysis, by establishing a regression model, can verify the correlation between influencing parameters and screen out the main controlling factors that significantly affect the recoverable reserves of a single well. The general method is as follows: collect historical data of influencing parameters, clean the data, handle missing and outlier values, determine the dependent variable (the variable that needs to be predicted or explained) and independent variables (variables that may affect the dependent variable), use the least squares method or other appropriate regression methods to establish a regression model between the dependent and independent variables, estimate the parameters of the regression model, such as regression coefficients and intercept terms, verify the significance of the model through significance tests (such as t-tests and F-tests), determine whether the influence of independent variables on the dependent variable is significant, calculate indicators such as the coefficient of determination (R²), evaluate the goodness of fit of the model, and select independent variables with a significance level less than a set threshold (such as 0.05) as the main controlling factors based on the results of the significance test.

[0037] S3. The influence of the main controlling factors on the recoverable reserves of a single well is quantitatively characterized using both the random forest algorithm and the multiple linear regression method. The weights of each main controlling factor are obtained for both methods. These weights are then standardized to obtain the final weights of the main controlling factors. Detailed steps are as follows: Based on the analysis results of the controlling factors, the random forest algorithm is used to analyze the impact of changes in the controlling factors within a certain range on the recoverable reserves of a single well, and to determine the weight coefficients of each controlling factor. Specifically: Control factor data is collected, preprocessed, and converted to a format suitable for the random forest algorithm (typically requiring data standardization or normalization). The dataset is then divided into training and testing sets, typically using 70% for training and 30% for testing. A model is built using the random forest algorithm, setting appropriate parameters such as the number of trees and maximum depth. The feature importance of each controlling factor, i.e., the weight coefficient, is calculated using the random forest model. The controlling factors are ranked according to their feature importance, and the degree of influence of each factor on the recoverable reserves of a single well is analyzed. Based on the determined weight coefficients, weights are allocated to each controlling factor, and the model is validated using the test set. The model performance is evaluated by calculating the mean squared error or coefficient of determination.

[0038] Based on the analysis results of the main controlling factors, a correlation equation between the recoverable reserves of a single well and the main controlling factors was established using the multiple linear regression method. The weight coefficients of each main controlling factor were determined by the magnitude of its influence on the recoverable reserves of a single well when the main controlling factors of the residual gas changed within a certain range. Specifically, the correlation equation between the recoverable reserves of a single well and the main controlling factors of the residual gas was established using the multiple linear regression method. Using the average value of the main controlling factors of each residual gas zone as a benchmark, and selecting -20% to 20% as a preset range of change, the magnitude of change in the recoverable reserves of a single well when the main controlling factor of the residual gas changed within the range of -20% to 20% was calculated. The contribution weight of the main controlling factors to the recoverable reserves of a single well was determined based on the maximum influence of each factor on the recoverable reserves of the single well.

[0039] The weight coefficients determined by the random forest algorithm and the weight coefficients determined by the multiple linear regression method are standardized, and the mean of the weights of the random forest and the multiple linear regression is calculated as the weight of the final controlling factor.

[0040] Random forest algorithms excel at capturing complex nonlinear relationships, but their parameters fluctuate significantly. Multiple linear regression is stable, but it cannot characterize the nonlinear effects of multiple factors. Standardizing the weights obtained from random forests and multiple linear regressions allows for a comprehensive consideration of both nonlinear and linear effects, ensuring that weight values ​​are on the same order of magnitude. This ultimately determines the weights of each factor, improving the reliability and stability of the weight coefficients and providing a more accurate basis for oil and gas reserve prediction and development decisions. S4. Establish a quantitative evaluation model for the remaining gas exploitation potential based on the weights of the main controlling factors, and calculate the remaining gas exploitation potential index to evaluate the gas reservoir exploitation potential. The quantitative evaluation model for the remaining gas exploitation potential is as follows:

[0041]

[0042] In the formula: PI a represents the remaining gas exploitation potential index. i Let be the weight of the i-th controlling factor, dimensionless; Let i be the value of the i-th controlling factor. These are the maximum and minimum values ​​of the controlling factors, respectively.

[0043] Example 2 This embodiment provides a quantitative evaluation method for the exploitation potential of heterogeneous gas reservoirs. The method of Embodiment 1 is adopted, taking the L gas field reservoir in the Sichuan Basin as an example. The reservoir is tight sandstone, and the recoverable reserves and residual gas distribution of a single well are controlled by a variety of dynamic and static parameters.

[0044] S1. Based on production practice and gas reservoir numerical simulation results, nine parameters closely related to recoverable reserves are selected for single-well controlled reserves, pressure, permeability, porosity, gas saturation, gas viscosity, initial production, effective thickness, and average decline rate to analyze and evaluate the potential for exploitation.

[0045] S2. The correlation between recoverable reserves of a single well and the correlation coefficient was evaluated using the Pearson correlation coefficient method. The evaluation results are as follows: Figure 2 The parameters with the highest to lowest correlation to recoverable reserves per well are: controlled reserves, pressure, permeability, gas saturation, porosity, gas viscosity, initial production, effective thickness, and average decline rate. A single-factor regression analysis was used to verify the correlation between recoverable reserves per well and the five parameters with the highest correlation (i.e., controlled reserves, pressure, permeability, gas saturation, and porosity). All five parameters showed a positive correlation, with R² values ​​above 0.3. Figure 3-7 .

[0046] S3. Using the random forest algorithm, the weights of the five parameters most correlated with the recoverable reserves of a single well (i.e., controlled reserves, pressure, permeability, gas saturation, and porosity) are scored. Controlled reserves and pressure have the highest weight coefficients, while the weight coefficients of the other parameters are relatively low. Figure 8 .

[0047] Multiple linear regression was used to score the weights of the five parameters most correlated with recoverable reserves in a single well (i.e., controlled reserves, pressure, permeability, gas saturation, and porosity). Controlled reserves and pressure had the highest weight coefficients, while the weight coefficients of the other parameters were relatively low. Figure 9 .

[0048] The scoring results using multiple linear regression and the random forest algorithm show consistent trends, but the weight coefficients differ somewhat. By standardizing the mean of the weights from both methods, the final weights of each factor are determined. Figure 10 .

[0049] S4. Taking into account the influence weights of five main controlling factors (i.e., single-well controlled reserves, pressure, permeability, gas saturation, and porosity) on the recoverable reserves of a single well, a quantitative evaluation model for the remaining gas tapping potential of the target area is established using the multi-factor comprehensive weighting method.

[0050] The quantitative evaluation model for the remaining gas tapping potential is as follows:

[0051]

[0052]

[0053]

[0054]

[0055]

[0056] In the formula This indicates the remaining recoverable gas reserves. This represents the maximum / minimum recoverable gas reserves, expressed in ×10⁻¹⁰. 8 m 3 ; Indicates pressure, This indicates the maximum / minimum pressure, in MPa. Indicates gas saturation. This represents the maximum / minimum gas saturation, expressed in % (%). Indicates penetration rate. This represents the maximum / minimum permeability, expressed in mD. Indicates porosity. This represents the maximum / minimum porosity, expressed as a percentage.

[0057] The residual gas tapping potential index of well L8-3, calculated using the above formula, is 0.85, indicating excellent tapping potential. The production curve shows that the well's daily gas production has stabilized at around 30,000 cubic meters for one and a half years since its commissioning, demonstrating strong production capacity. Figure 11 The calculated residual gas tapping potential index for well L6-1 using the above formula is 0.62, indicating good tapping potential. The production curve shows a step-like decline in daily gas production after 300 days of operation, currently around 10,000 cubic meters per day, indicating average production capacity. Figure 12 This indicates that the exploitation potential index established in this invention can effectively characterize the residual gas characteristics of a single well and can provide guidance for improving gas field recovery rates.

[0058] Example 3 This embodiment provides a quantitative evaluation system for the tapping potential of heterogeneous gas reservoirs. The system includes: The parameter selection module is used to select influencing parameters that are closely related to the distribution of residual gas; there must be at least 5 influencing parameters. The module for screening the main controlling factors is used to evaluate the correlation between the recoverable reserves of a single well and the correlation coefficient using the Pearson correlation coefficient method, and to verify the correlation between the influencing parameters using the single-factor regression method, thereby screening out the main controlling factors. The weight calculation module is used to quantitatively characterize the influence of the main control factors on the recoverable reserves of a single well using the random forest algorithm and the multiple linear regression method, respectively. It obtains the weights of each main control factor in the two methods, and standardizes the weights of each main control factor to obtain the weights of the main control factors. The potential index calculation module is used to establish a quantitative evaluation model of the remaining gas tapping potential based on the weights of the main control factors, and to calculate the remaining gas tapping potential index.

[0059] The systems or modules described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing this application, the functions of each module can be implemented in one or more software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules, etc.

[0060] This embodiment also provides an electronic device, including at least one processor, a memory communicatively connected to the at least one processor, and at least one input / output interface communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a quantitative evaluation of the exploitation potential of a heterogeneous gas reservoir as described in Embodiment 1 above. The input / output interface may include a display, keyboard, mouse, and USB interface for inputting and outputting data.

[0061] The electronic device can be an electronic device for the client, such as a mobile phone, laptop, tablet, desktop computer, etc., to execute the quantitative evaluation method for the tapping potential of heterogeneous gas reservoirs in Example 1.

[0062] 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. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0063] When the integrated units of this invention are implemented as software functional units and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0064] This embodiment also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set. The at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the above-described method for quantitatively evaluating the potential of heterogeneous gas reservoirs.

[0065] A computer-readable storage medium can be a tangible device that holds and stores instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof.

[0066] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for quantitatively evaluating the development potential of heterogeneous gas reservoirs, characterized in that, Includes the following steps: S1. Select influencing parameters that are closely related to the distribution of residual gas, with at least 5 influencing parameters; S2. The correlation between the recoverable reserves of a single well and the correlation coefficient is evaluated using the Pearson correlation coefficient method, and the correlation between the influencing parameters is verified using the single-factor regression method to screen out the main controlling factors. S3. The influence of the main control factors on the recoverable reserves of a single well is quantitatively characterized by the random forest algorithm and the multiple linear regression method, respectively. The weights of the main control factors in the two methods are obtained. The weights of the main control factors are standardized to obtain the weights of the main control factors. S4. Establish a quantitative evaluation model for the remaining gas tapping potential based on the weights of the main controlling factors, and calculate the remaining gas tapping potential index.

2. The method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs according to claim 1, characterized in that, The method for selecting the influencing parameters is as follows: based on production practice and gas reservoir numerical simulation results, parameters that affect the distribution of remaining gas are selected as influencing parameters for potential exploration analysis and evaluation.

3. The method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs according to claim 1, characterized in that, The influencing parameters are single-well controlled reserves, pressure, permeability, gas saturation, porosity, gas viscosity, initial production allocation, effective thickness, and average decline rate.

4. The method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs according to claim 3, characterized in that, The main controlling factors are single-well controlled reserves, pressure, permeability, gas saturation, and porosity.

5. The method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs according to claim 1, characterized in that, The method for evaluating the correlation between the recoverable reserves of a single well and the correlation coefficient using the Pearson correlation coefficient method is as follows: Using the recoverable reserves of a single well as the target variable, the Pearson correlation coefficient method is used to calculate the Pearson correlation coefficient between each of the aforementioned correlation coefficients and the target variable. The formula for calculating the Pearson correlation coefficient is as follows: in Let be the Pearson correlation coefficient of the i-th influencing parameter. Let i be the value of the i-th influencing parameter; Let i be the value of the target variable corresponding to the i-th influencing parameter; This represents the average value of the parameter. The average value of the target variable; The influencing parameters were ranked by the absolute value of the Pearson correlation coefficient, and the parameters ranked in the 70-90% range were selected as the main control factors.

6. The method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs according to claim 1, characterized in that, The detailed steps of step S3 are as follows: Based on the analysis results of the main control factors, the random forest algorithm is used to analyze the impact of the main control factors on the recoverable reserves of a single well when the main control factors change within a certain range, and to determine the weight coefficient of each main control factor. Based on the analysis results of the main control factors, the correlation equation between the recoverable reserves of a single well and the main control factors was established by using the multiple linear regression method. The weight coefficient of each main control factor was determined by the influence of each residual gas main control factor on the recoverable reserves of the single well when the factors change within a certain range. The weight coefficients determined by the random forest algorithm and the weight coefficients determined by the multiple linear regression method are standardized to obtain the final weights of the main controlling factors.

7. A method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs according to any one of claims 1-6, characterized in that, The quantitative evaluation model for the remaining gas tapping potential is as follows: In the formula: PI a represents the remaining gas exploitation potential index. i Let be the weight of the i-th controlling factor, dimensionless; Let i be the value of the i-th controlling factor. These are the maximum and minimum values ​​of the controlling factors, respectively.

8. A quantitative evaluation system for the tapping potential of heterogeneous gas reservoirs, characterized in that, The system includes: The parameter selection module is used to select influencing parameters that are closely related to the distribution of residual gas, and the influencing parameters are at least 5. The module for screening the main controlling factors is used to evaluate the correlation between the recoverable reserves of a single well and the influencing parameters using the Pearson correlation coefficient method, and to verify the correlation between the influencing parameters using the univariate regression method, thereby screening out the main controlling factors. The weight calculation module is used to quantitatively characterize the influence of the main control factors on the recoverable reserves of a single well using the random forest algorithm and the multiple linear regression method, respectively, to obtain the weights of the main control factors for each of the two methods, and to standardize the weights of the main control factors to obtain the weights of the main control factors. The potential index calculation module is used to establish a quantitative evaluation model of the remaining gas tapping potential based on the weights of the main control factors, and to calculate the remaining gas tapping potential index.

9. An electronic device comprising at least one processor and a memory communicatively connected to said at least one processor; said memory storing instructions executable by said at least one processor, characterized in that, The instructions are executed by the at least one processor to enable the at least one processor to perform a quantitative evaluation method for the exploitation potential of heterogeneous gas reservoirs as described in any one of claims 1-7.

10. A computer-readable storage medium storing at least one instruction, at least one program, a code set, or an instruction set, characterized in that, The at least one instruction, the at least one program segment, the code set, or the instruction set are loaded and executed by the processor to implement the method for quantitatively evaluating the exploitation potential of heterogeneous gas reservoirs as described in any one of claims 1-7.

Images