Gas reservoir productivity prediction method and system based on logging grading parameters and electronic equipment
By using a method based on well logging classification parameters, and comprehensively considering formation pressure, permeability, gas saturation, and gas layer thickness, a production capacity prediction model is established by dividing the region into classification zones. This solves the problem of low accuracy in predicting production capacity of low-permeability gas reservoirs at sea and achieves higher accuracy in gas reservoir production capacity prediction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-24
- Publication Date
- 2026-04-03
AI Technical Summary
Existing technologies have low accuracy in predicting gas production capacity in low-permeability offshore gas reservoirs, especially when the reservoir is highly heterogeneous, has poor physical properties, and is affected by many factors. Existing methods have limitations and large errors.
A method based on well logging classification parameters is adopted. By obtaining formation pressure, permeability, gas saturation and gas layer thickness, the formation is divided into multiple classification zones. A production capacity prediction model is established using the mean permeability, mean gas saturation and gas layer thickness ratio, and the prediction is made by comprehensively considering multiple parameters.
It improves the accuracy of production capacity prediction for low-permeability gas reservoirs at sea, reduces errors, and enhances the prediction effect for gas reservoirs with strong heterogeneity and poor physical properties.
Smart Images
Figure CN121787253A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the technical field of oil and gas field exploration and development, and more specifically, to a gas reservoir productivity prediction method, system, and electronic equipment based on well logging classification parameters. Background Technology
[0002] Gas reservoir productivity is a core indicator for evaluating the exploitation value of a gas reservoir and guiding the formulation of development plans. It directly determines the economic benefits and development strategies of a gas field. The level of gas reservoir productivity essentially depends on the productivity contribution of each reservoir unit within it. Therefore, accurate assessment of reservoir productivity is the foundation for scientifically predicting gas reservoir productivity and achieving efficient development. In gas field exploration and development practice, establishing accurate and reliable productivity prediction methods is of paramount importance for optimizing well location deployment, designing production systems, and improving overall recovery rates.
[0003] In existing technologies, the industry mainly uses analogy methods, theoretical formula methods, well logging model methods, numerical simulation methods, and machine learning methods for production capacity prediction. However, while these prediction methods are well-suited for conventional reservoirs, they have certain limitations in offshore low-permeability gas reservoirs with strong heterogeneity, poor physical properties, and numerous factors affecting production capacity. Specifically: analogy methods have significant uncertainties and can only provide an estimated production capacity range; theoretical formula methods vary greatly across different regions and formations and are difficult to accurately determine, making production capacity prediction using this method quite complex; well logging model methods typically use well logging physical property results to predict production capacity, but production capacity is influenced by multiple factors and there is no single linear relationship between them, resulting in larger errors in low-porosity and low-permeability reservoirs; numerical simulation methods lack actual production data constraints, are highly susceptible to human intervention, and have a narrow scope of application; machine learning methods mainly utilize data-driven production capacity prediction, but the models have poor interpretability and do not consider geological concepts. Summary of the Invention
[0004] The purpose of this invention is to overcome the shortcomings of existing technologies in predicting the low production capacity of offshore low-permeability gas reservoirs with strong reservoir heterogeneity, poor physical properties, and many factors affecting production capacity. This invention provides a gas reservoir production capacity prediction method, system, and electronic equipment based on well logging classification parameters, thereby improving the production capacity prediction accuracy of offshore low-permeability gas reservoirs with strong reservoir heterogeneity, poor physical properties, and many factors affecting production capacity.
[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a method for predicting gas reservoir productivity based on well logging classification parameters is provided, comprising the following steps: Obtain data on the area to be predicted, including formation pressure, permeability, gas saturation, and gas layer thickness; At least three permeability characteristic values are selected as classification boundaries to divide the area to be predicted into at least four classification zones; The average permeability of the graded zones is obtained based on the permeability, the average gas saturation of the graded zones is obtained based on the gas saturation, and the gas layer thickness percentage of the graded zones is obtained based on the gas layer thickness. A production capacity prediction model is established based on the formation pressure, the average permeability, the average gas saturation, and the proportion of gas layer thickness. The gas reservoir production capacity is predicted based on the aforementioned production capacity prediction model.
[0006] In one alternative approach, the capacity forecasting model specifically uses the following formula:
[0007] in, This indicates the predicted flow rate within meters. Indicates formation pressure; Indicates the number of hierarchical zones; Indicates the first The parameter weight values for each hierarchical zone; Indicates the first Average penetration rate of each graded zone; Indicates the first Average gas saturation of each graded zone; Indicates the first The percentage of air layer thickness in each graded zone.
[0008] In one alternative approach, the classification boundaries include permeability characteristic values for low-permeability gas reservoirs, permeability characteristic values for developing reservoirs with good production capacity, permeability characteristic values for ultra-low-permeability gas reservoirs, permeability characteristic values for reservoirs meeting reserve and production capacity requirements, and lower limit permeability characteristic values for gas reservoirs. The area to be predicted includes five classification zones: the permeability of the first classification zone is greater than the permeability characteristic value of the low-permeability gas reservoir; the permeability of the second classification zone is between the permeability characteristic value of the low-permeability gas reservoir and the permeability characteristic value for developing reservoirs with good production capacity; the permeability of the third classification zone is between the permeability characteristic value for developing reservoirs with good production capacity and the permeability characteristic value of the ultra-low-permeability gas reservoir; the permeability of the fourth classification zone is between the permeability characteristic value of the ultra-low-permeability gas reservoir and the permeability characteristic value for reservoirs meeting reserve and production capacity requirements; and the permeability of the fifth classification zone is between the permeability characteristic value for reservoirs meeting reserve and production capacity requirements and the lower limit permeability characteristic value for gas reservoirs.
[0009] In one alternative approach, the parameter weight values of the first, second, third, fourth, and fifth graded regions decrease sequentially.
[0010] In an alternative approach, the method further includes a training process for determining the parameter weight values, wherein the constraints of the training process specifically utilize the following formula:
[0011] in, Indicated The minimum absolute value; This indicates the actual unobstructed flow rate per meter; This represents the parameter weight value of the first of the hierarchical regions; This represents the parameter weight value of the second hierarchical region; This represents the parameter weight value of the third hierarchical region; This represents the parameter weight value of the fourth hierarchical region; This represents the parameter weight value of the fifth graded region.
[0012] In one alternative approach, the gas layer thickness percentage is specifically calculated using the following formula:
[0013] in, Indicates the first The percentage of gas layer thickness in each graded zone; Indicates the first The thickness of the gas layer in each graded zone; This indicates the total thickness of the gas layer.
[0014] In one alternative approach, the area to be predicted is divided into normal pressure strata and high pressure strata based on the formation pressure coefficient, and a production capacity prediction model is established for the normal pressure strata and the high pressure strata respectively.
[0015] According to a second aspect of the present invention, a gas reservoir productivity prediction system based on well logging classification parameters is provided, comprising: Data acquisition module: used to acquire formation pressure, permeability, gas saturation, and gas layer thickness; The prediction classification module is used to divide the prediction area into at least four classification zones. Data processing module: used to obtain the average permeability of the graded zones based on the permeability, used to obtain the average gas saturation of the graded zones based on the gas saturation, and used to obtain the gas layer thickness percentage of the graded zones based on the gas layer thickness. Production capacity prediction model establishment module: used to establish a production capacity prediction model based on the formation pressure, the average permeability, the average gas saturation, and the gas layer thickness ratio; Production capacity prediction module: used to predict gas reservoir production capacity based on the production capacity prediction model.
[0016] According to a third aspect of the present invention, an electronic device is provided, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which enables the processor to implement the gas reservoir production capacity prediction method based on well logging classification parameters as described above.
[0017] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the gas reservoir production capacity prediction method based on well logging classification parameters as described above.
[0018] Compared with the prior art, the beneficial effects of the present invention are: This invention discloses a gas reservoir productivity prediction method, system, and electronic equipment based on well logging classification parameters. This method performs multi-parameter prediction of gas reservoir productivity by comprehensively considering formation pressure, mean permeability, mean gas saturation, and gas layer thickness ratio, making the parameter consideration more comprehensive. Simultaneously, the area to be predicted is first divided into at least four classification zones using permeability characteristic values. Then, the overall permeability, gas saturation, and gas layer thickness are replaced by the mean permeability, mean gas saturation, and gas layer thickness, respectively. Using relative quantities instead of absolute quantities for analysis is more conducive to improving the gas reservoir productivity prediction effect for offshore low-permeability gas reservoirs with strong reservoir heterogeneity. Through the above methods, this invention comprehensively improves the productivity prediction accuracy for offshore low-permeability gas reservoirs with strong reservoir heterogeneity, poor physical properties, and many factors affecting productivity. Attached Figure Description
[0019] Figure 1 This is a flowchart illustrating the gas reservoir productivity prediction method based on well logging classification parameters of the present invention. Figure 2 This is a cross-plot of unobstructed flow rate and permeability. Figure 3 This is a cross-plot of unobstructed flow rate and gas saturation. Figure 4 This is a cross-plot of unobstructed flow rate and gas layer thickness with permeability greater than 3 mD; Figure 5 This is a cross-plot of unobstructed flow rate and formation pressure. Figure 6 It is a cross-plot of the unrestricted flow rate per meter predicted based on well logging classification parameters, the unrestricted flow rate per meter predicted based on single permeability regression, and the actual unrestricted flow rate per meter. Figure 7 This is an absolute error analysis chart of the unrestricted flow rate per meter predicted based on single permeability regression and the actual unrestricted flow rate per meter; Figure 8 Absolute error analysis diagram of the predicted and actual unobstructed flow rates per meter based on well logging classification parameters. Detailed Implementation
[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The present invention will be further described below with reference to specific embodiments.
[0021] Furthermore, if the embodiments of the present invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the meaning of "and / or" throughout the text is to include three parallel solutions; for example, "A and / or B" includes solution A, solution B, or a solution that simultaneously satisfies A and B.
[0022] Example 1 Figure 1 A flowchart of a first embodiment of the gas reservoir productivity prediction method based on well logging classification parameters of the present invention is shown, which is executed by a rear-wheel trajectory prediction system. Figure 1 As shown, the method includes the following steps: Step S1: Obtain data for the area to be predicted, including formation pressure, permeability, gas saturation, and gas layer thickness.
[0023] Specifically, the data for the area to be predicted includes static well logging data, dynamic production data, and formation data, mainly including formation pressure coefficient, permeability, water saturation, and gas layer thickness.
[0024] The formation pressure is obtained based on the formation pressure coefficient, using the following formula:
[0025] In the formula, Indicates formation pressure; Indicates the formation pressure coefficient; Indicates vertical depth.
[0026] The gas saturation is obtained based on the water saturation using the following formula:
[0027] In the formula, Indicates gas saturation; Indicates water saturation.
[0028] Specifically, the cross-plots of permeability, gas saturation, sweet spot thickness, and formation pressure versus millimeter free flow are shown below. Figure 2 , Figure 3 , Figure 4 and Figure 5 As shown in the figure, the unobstructed flow rate is positively correlated with permeability, gas saturation, sweet spot thickness, and formation pressure. Each parameter has a different degree of influence on production capacity. Therefore, it is necessary to consider multiple influencing factors and comprehensively predict production capacity based on the previous analysis of single factors (physical properties, thickness, etc.).
[0029] Step S2: Select at least three permeability characteristic values as grading boundaries to divide the area to be predicted into at least four grading zones.
[0030] Step S3: Obtain the average permeability of the graded zones based on the permeability, obtain the average gas saturation of the graded zones based on the gas saturation, and obtain the gas layer thickness percentage of the graded zones based on the gas layer thickness.
[0031] Specifically, the percentage of gas layer thickness is calculated using the following formula:
[0032] in, Indicates the first The percentage of gas layer thickness in each graded zone; Indicates the first The thickness of the gas layer in each graded zone; This indicates the total thickness of the gas layer.
[0033] Specifically, production capacity is not simply positively correlated with the length of well drilling; simply increasing the drilling length has a limited contribution to production capacity. What truly affects production capacity is the thickness of the gas reservoir sweet spot, and the percentage of gas reservoir thickness under different physical properties is an important reference indicator for evaluating the sweet spot. Considering this issue, this invention does not simply use the absolute value of the gas reservoir thickness, but rather extracts the percentage of gas reservoir thickness under different physical property levels.
[0034] Step S4: Based on the formation pressure, the average permeability, the average gas saturation, and the proportion of gas layer thickness, establish a production capacity prediction model.
[0035] Step S5: Predict the gas reservoir production capacity based on the production capacity prediction model.
[0036] The above method uses a multi-parameter approach to predict gas reservoir productivity by comprehensively considering formation pressure, mean permeability, mean gas saturation, and the proportion of gas layer thickness, making the parameter considerations more comprehensive. Furthermore, the area to be predicted is first divided into at least four graded zones using permeability characteristic values. Then, the overall permeability, gas saturation, and gas layer thickness are replaced by the mean permeability, mean gas saturation, and proportion of gas layer thickness, respectively. Using relative quantities instead of absolute quantities for analysis is more conducive to improving the gas reservoir productivity prediction effect for offshore low-permeability gas reservoirs with strong reservoir heterogeneity. Through the above methods, this invention comprehensively improves the productivity prediction accuracy for offshore low-permeability gas reservoirs with strong reservoir heterogeneity, poor physical properties, and numerous factors affecting productivity.
[0037] In some embodiments, the capacity forecasting model specifically uses the following formula:
[0038] in, This indicates the predicted flow rate within meters. Indicates formation pressure; Indicates the number of hierarchical zones; Indicates the first The parameter weight values for each hierarchical zone; Indicates the first Average penetration rate of each graded zone; Indicates the first Average gas saturation of each graded zone; Indicates the first The percentage of air layer thickness in each graded zone.
[0039] Specifically, the production capacity prediction model of this invention is used to calculate the unobstructed flow rate per meter. The unobstructed flow rate per meter is an index obtained by converting the unobstructed flow rate of a gas well to a unit thickness. The unobstructed flow rate per meter reflects the gas production capacity per unit thickness of the gas reservoir; therefore, it can be used as a key parameter for evaluating gas reservoir production capacity. Simultaneously, the unobstructed flow rate per meter directly determines the maximum stable production capacity that a gas well can achieve under cleaning and blowout conditions; therefore, this invention can accurately reflect the stable production capacity under cleaning and blowout conditions.
[0040] In some embodiments, the classification boundaries include permeability characteristic values for low-permeability gas reservoirs, permeability characteristic values for developing reservoirs with good production capacity, permeability characteristic values for ultra-low permeability gas reservoirs, permeability characteristic values for reservoirs meeting reserve and production capacity requirements, and lower limit permeability characteristic values for gas reservoirs. The area to be predicted includes five classification zones. The permeability of the first classification zone is greater than the permeability characteristic value of the low-permeability gas reservoir. The permeability of the second classification zone is between the permeability characteristic value of the low-permeability gas reservoir and the permeability characteristic value for developing reservoirs with good production capacity. The permeability of the third classification zone is between the permeability characteristic value for developing reservoirs with good production capacity and the permeability characteristic value of the ultra-low permeability gas reservoir. The permeability of the fourth classification zone is between the permeability characteristic value of the ultra-low permeability gas reservoir and the permeability characteristic value for reservoirs meeting reserve and production capacity requirements. The permeability of the fifth classification zone is between the permeability characteristic value for reservoirs meeting reserve and production capacity requirements and the lower limit permeability characteristic value for gas reservoirs.
[0041] Specifically, the permeability characteristic value for low-permeability gas reservoirs is 10 mD, the permeability characteristic value for reservoirs with good production capacity is 3 mD, the permeability characteristic value for ultra-low permeability gas reservoirs is 1 mD, the permeability characteristic value for reservoirs meeting reserve and production capacity requirements is 0.5 mD, and the lower limit permeability characteristic value for gas reservoirs is 0.1 mD. The permeability of the first classification zone is greater than 10 mD. The permeability of the second classification zone is 3 mD-10 mD. The permeability of the third classification zone is 1 mD-3 mD. The permeability of the fourth classification zone is 0.5 mD-1 mD. The permeability of the fifth classification zone is 0.1 mD-0.5 mD.
[0042] In some embodiments, the parameter weight values of the first, second, third, fourth, and fifth graded zones decrease sequentially. The parameter weight values of the graded zones are determined based on the contribution of different physical properties to production capacity.
[0043] In some embodiments, a training process for determining the parameter weight values is further included, wherein the constraints of the training process specifically utilize the following formula:
[0044] in, Indicated The minimum absolute value; This indicates the actual unobstructed flow rate per meter; This represents the parameter weight value of the first of the hierarchical regions; This represents the parameter weight value of the second hierarchical region; This represents the parameter weight value of the third hierarchical region; This represents the parameter weight value of the fourth hierarchical region; This represents the parameter weight value of the fifth graded region.
[0045] Specifically, during this training process, the parameter weights are optimized using the known actual unobstructed flow rate and the predicted unobstructed flow rate to minimize the difference between the two. The optimized capacity prediction model is then used to predict capacity.
[0046] In some embodiments, the area to be predicted is divided into normal pressure strata and high pressure strata based on the formation pressure coefficient, and a production capacity prediction model is established for the normal pressure strata and the high pressure strata respectively.
[0047] Specifically, the formation pressure coefficient for distinguishing between normal-pressure and high-pressure strata is set to 1.2. After the distinction is made, the formation pressure of the normal-pressure strata is obtained based on the formation pressure coefficient, and this pressure is then incorporated into the aforementioned productivity prediction model to establish a productivity prediction model for the normal-pressure strata. Similarly, the formation pressure of the high-pressure strata is obtained based on the formation pressure coefficient, and this pressure is then incorporated into the aforementioned productivity prediction model to establish a productivity prediction model for the high-pressure strata. By establishing separate productivity prediction models for normal-pressure and high-pressure strata, the accuracy of productivity prediction is further improved.
[0048] Example 2 This embodiment compares two experiments. Specifically, it compares the predictions made using a gas reservoir productivity prediction method based on well logging classification parameters and a prediction based on a single permeability regression model, and then compares the actual results.
[0049] Experiment 1: Correlation.
[0050] like Figure 6 As shown in the figure, it can be seen that the prediction results based on the gas reservoir productivity prediction method based on well logging classification parameters are more consistent with the actual results. The figure is titled "Prediction Results Based on Well Logging Classification Parameters". The correlation between the two reached 0.94, which is higher than the 0.85 of the single permeability regression prediction results.
[0051] Experiment 2: Error.
[0052] The absolute error analysis charts for the flow rate per meter of unobstructed flow based on single permeability regression prediction, the flow rate per meter of unobstructed flow based on well logging classification parameters, and the actual flow rate per meter of unobstructed flow are shown below. Figure 7 and Figure 8 As shown in the figure. The comparison results show that the error between the meter-wide flow rate predicted based on well logging classification parameters and the actual result is smaller, averaging only 0.89 million cubic meters / day / meter, while the absolute error of the evaluation based on single permeability regression prediction reaches an average of 1.81 million cubic meters / day / meter. This indicates that the proposed method has higher prediction accuracy and smaller error.
[0053] Example 3 This embodiment, based on Embodiment 1, provides a gas reservoir production capacity prediction system based on well logging classification parameters, which can execute the gas reservoir production capacity prediction method based on well logging classification parameters as described in Embodiment 1. Specifically, it includes: a data acquisition module, a target classification module, a data processing module, a production capacity prediction model establishment module, and a production capacity prediction module.
[0054] The data acquisition module is used to obtain formation pressure, permeability, gas saturation, and gas layer thickness.
[0055] The prediction classification module is used to divide the prediction area into at least four classification zones.
[0056] The data processing module is used to obtain the average permeability of the graded zones based on the permeability, to obtain the average gas saturation of the graded zones based on the gas saturation, and to obtain the gas layer thickness percentage of the graded zones based on the gas layer thickness.
[0057] The production capacity prediction model building module is used to build a production capacity prediction model based on the formation pressure, the average permeability, the average gas saturation, and the proportion of gas layer thickness.
[0058] The production capacity prediction module is used to predict the gas reservoir production capacity based on the production capacity prediction model.
[0059] The above system performs multi-parameter prediction of gas reservoir productivity by comprehensively considering formation pressure, mean permeability, mean gas saturation, and the proportion of gas layer thickness, making the parameters more comprehensive. Simultaneously, the area to be predicted is first divided into at least four graded zones using permeability characteristic values. Then, the overall permeability, gas saturation, and gas layer thickness are replaced by the mean permeability, mean gas saturation, and proportion of gas layer thickness, respectively. Using relative quantities instead of absolute quantities for analysis is more conducive to improving the gas reservoir productivity prediction effect for offshore low-permeability gas reservoirs with strong reservoir heterogeneity. Through the above methods, this invention comprehensively improves the productivity prediction accuracy for offshore low-permeability gas reservoirs with strong reservoir heterogeneity, poor physical properties, and many factors affecting productivity.
[0060] Example 4 The specific embodiments of the present invention do not limit the specific implementation of the electronic device.
[0061] An electronic device may include: a processor, a communications interface, memory, and a communications bus.
[0062] The processor, communication interface, and memory communicate with each other via a communication bus. The communication interface is used to communicate with other devices, such as electronic equipment or other server network elements. The processor executes the program, implementing the steps described above in the gas reservoir production capacity prediction method based on well logging classification parameters to predict gas reservoir production capacity.
[0063] Specifically, a program may include program code, which includes computer-executable instructions.
[0064] Specifically, the processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The electronic device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.
[0065] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.
[0066] The program can be called by the processor to cause the electronic device to perform the following operations: Obtain data on the area to be predicted, including formation pressure, permeability, gas saturation, and gas layer thickness; At least three permeability characteristic values are selected as classification boundaries to divide the area to be predicted into at least four classification zones; The average permeability of the graded zones is obtained based on the permeability, the average gas saturation of the graded zones is obtained based on the gas saturation, and the gas layer thickness percentage of the graded zones is obtained based on the gas layer thickness. A production capacity prediction model is established based on the formation pressure, the average permeability, the average gas saturation, and the proportion of gas layer thickness. The gas reservoir production capacity is predicted based on the aforementioned production capacity prediction model.
[0067] The data stream described above is consistent with the data stream in Embodiment 1. For details, please refer to the description in Embodiment 1. This embodiment will not repeat the description.
[0068] The aforementioned electronic equipment performs multi-parameter prediction of gas reservoir productivity by comprehensively considering formation pressure, average permeability, average gas saturation, and the proportion of gas layer thickness, making the parameter considerations more comprehensive. Simultaneously, the area to be predicted is first divided into at least four graded zones using permeability characteristic values. Then, the overall permeability, gas saturation, and gas layer thickness are replaced by the average permeability, average gas saturation, and proportion of gas layer thickness, respectively. Using relative quantities instead of absolute quantities for analysis is more conducive to improving the gas reservoir productivity prediction effect for offshore low-permeability gas reservoirs with strong reservoir heterogeneity. Through the above methods, this invention comprehensively improves the productivity prediction accuracy for offshore low-permeability gas reservoirs with strong reservoir heterogeneity, poor physical properties, and many factors affecting productivity.
[0069] Example 5 This invention provides a computer-readable storage medium storing at least one executable instruction that, when executed on an electronic device, causes the electronic device to perform the gas reservoir productivity prediction method based on well logging classification parameters described in Embodiment 1 above.
[0070] Executable instructions can be used to cause an electronic device to perform the following operations: Obtain data on the area to be predicted, including formation pressure, permeability, gas saturation, and gas layer thickness; At least three permeability characteristic values are selected as classification boundaries to divide the area to be predicted into at least four classification zones; The average permeability of the graded zones is obtained based on the permeability, the average gas saturation of the graded zones is obtained based on the gas saturation, and the gas layer thickness percentage of the graded zones is obtained based on the gas layer thickness. A production capacity prediction model is established based on the formation pressure, the average permeability, the average gas saturation, and the proportion of gas layer thickness. The gas reservoir production capacity is predicted based on the aforementioned production capacity prediction model.
[0071] By comprehensively considering formation pressure, mean permeability, mean gas saturation, and the proportion of gas layer thickness, multi-parameter prediction of gas reservoir productivity is performed, making the parameters more comprehensive. Simultaneously, the area to be predicted is first divided into at least four graded zones using characteristic permeability values. Then, the overall permeability, gas saturation, and gas layer thickness are replaced by the mean permeability, mean gas saturation, and proportion of gas layer thickness, respectively. Using relative quantities instead of absolute quantities for analysis is more conducive to improving the prediction effect of gas reservoir productivity for offshore low-permeability gas reservoirs with strong reservoir heterogeneity. Through the above methods, this invention comprehensively improves the accuracy of productivity prediction for offshore low-permeability gas reservoirs with strong reservoir heterogeneity, poor physical properties, and many factors affecting productivity.
[0072] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Furthermore, the embodiments of this invention are not directed to any particular programming language.
[0073] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. Similarly, for the sake of brevity and to aid in understanding one or more aspects of the invention, in the description of exemplary embodiments of the invention above, various features of the embodiments are sometimes grouped together in a single embodiment, figure, or description thereof. The claims, which follow the detailed description, are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.
[0074] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components, except that at least some of such features and / or processes or units are mutually exclusive.
[0075] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.
Claims
1. A gas reservoir productivity prediction method based on well logging classification parameters, characterized in that, Includes the following steps: Obtain data on the area to be predicted, including formation pressure, permeability, gas saturation, and gas layer thickness; At least three permeability characteristic values are selected as classification boundaries to divide the area to be predicted into at least four classification zones; The average permeability of the graded zones is obtained based on the permeability, the average gas saturation of the graded zones is obtained based on the gas saturation, and the gas layer thickness percentage of the graded zones is obtained based on the gas layer thickness. A production capacity prediction model is established based on the formation pressure, the average permeability, the average gas saturation, and the proportion of gas layer thickness. The gas reservoir production capacity is predicted based on the aforementioned production capacity prediction model.
2. The gas reservoir productivity prediction method based on well logging classification parameters according to claim 1, characterized in that, The capacity forecasting model specifically uses the following formula: in, This indicates the predicted flow rate within meters. Indicates formation pressure; Indicates the number of hierarchical zones; Indicates the first The parameter weight values for each hierarchical zone; Indicates the first Average penetration rate of each graded zone; Indicates the first Average gas saturation of each graded zone; Indicates the first The percentage of gas layer thickness in each graded zone.
3. The gas reservoir productivity prediction method based on well logging classification parameters according to claim 2, characterized in that, The classification boundaries include the permeability characteristic value of low-permeability gas reservoirs, the permeability characteristic value of gas reservoirs with good development potential, the permeability characteristic value of ultra-low permeability gas reservoirs, the permeability characteristic value that meets the reserve and production capacity requirements, and the lower limit permeability characteristic value of gas reservoirs. The area to be predicted includes five classification zones. The permeability of the first classification zone is greater than the permeability characteristic value of the low-permeability gas reservoir. The permeability of the second classification zone is between the permeability characteristic value of the low-permeability gas reservoir and the permeability characteristic value of gas reservoirs with good development potential. The permeability of the third classification zone is between the permeability characteristic value of gas reservoirs with good development potential and the permeability characteristic value of ultra-low permeability gas reservoirs. The permeability of the fourth classification zone is between the permeability characteristic value of ultra-low permeability gas reservoirs and the permeability characteristic value that meets the reserve and production capacity requirements. The permeability of the fifth classification zone is between the permeability characteristic value that meets the reserve and production capacity requirements and the lower limit permeability characteristic value of gas reservoirs.
4. The gas reservoir productivity prediction method based on well logging classification parameters according to claim 3, characterized in that, The parameter weight values of the first, second, third, fourth, and fifth graded regions decrease sequentially.
5. The gas reservoir productivity prediction method based on well logging classification parameters according to claim 4, characterized in that, It also includes a training process for determining the weight values of the parameters, wherein the constraints of the training process specifically use the following formula: in, Indicated The minimum absolute value; This indicates the actual unobstructed flow rate per meter; This represents the parameter weight value of the first of the hierarchical regions; This represents the parameter weight value of the second hierarchical region; This represents the parameter weight value of the third hierarchical region; This represents the parameter weight value of the fourth hierarchical region; This represents the parameter weight value of the fifth graded region.
6. The gas reservoir productivity prediction method based on well logging classification parameters according to any one of claims 1 to 5, characterized in that, The specific formula for the gas layer thickness percentage is as follows: in, Indicates the first The percentage of gas layer thickness in each graded zone; Indicates the first The thickness of the gas layer in each graded zone; This indicates the total thickness of the gas layer.
7. The gas reservoir productivity prediction method based on well logging classification parameters according to any one of claims 1 to 5, characterized in that, The area to be predicted is divided into normal pressure strata and high pressure strata based on the formation pressure coefficient, and a production capacity prediction model is established for the normal pressure strata and the high pressure strata respectively.
8. A gas reservoir productivity prediction system based on well logging classification parameters, characterized in that, include: Data acquisition module: used to acquire formation pressure, permeability, gas saturation, and gas layer thickness; The prediction classification module is used to divide the prediction area into at least four classification zones. Data processing module: used to obtain the average permeability of the graded zones based on the permeability, used to obtain the average gas saturation of the graded zones based on the gas saturation, and used to obtain the gas layer thickness percentage of the graded zones based on the gas layer thickness. Production capacity prediction model establishment module: used to establish a production capacity prediction model based on the formation pressure, the average permeability, the average gas saturation, and the gas layer thickness ratio; Production capacity prediction module: used to predict gas reservoir production capacity based on the production capacity prediction model.
9. An electronic device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to implement the gas reservoir production capacity prediction method based on well logging classification parameters as described in any one of claims 1 to 7 when executed.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the gas reservoir production capacity prediction method based on well logging classification parameters as described in any one of claims 1 to 7.