Synergistic yield increasing method based on tight oil reservoir energy storage fracturing technology
By establishing an oil production prediction model and using intelligent optimization algorithms to optimize gas injection parameters, the problem of unreasonable gas injection parameter design in tight oil reservoirs has been solved, achieving efficient production and extraction throughout the entire life cycle.
Patent Information
- Application Number
- CN202511969471.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-24
- Publication Date
- 2026-02-24
- Estimated Expiration
- 2045-12-24
AI Technical Summary
In the development of existing tight oil reservoirs, the design of gas injection parameters for energy storage fracturing technology has not fully considered the complex coupling relationship between gas injection parameters, resulting in mismatch between the gas injection scheme and the target reservoir properties and energy requirements, making it impossible to achieve efficient production and extraction throughout the entire life cycle.
By establishing an oil production prediction model, screening and combining neighbor sets, calculating coupling promotion degree and fitness, and using intelligent optimization algorithms to optimize the combination of gas injection parameters, the optimal parameter scheme is obtained and energy storage fracturing operations are implemented.
This achieved a reasonable match between gas injection parameters and reservoir properties and well network conditions, thereby increasing the oil production of tight oil reservoirs throughout their entire life cycle and improving production and extraction efficiency.
Smart Images
Figure CN121556832A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of oil and gas development technology, specifically to a synergistic production enhancement method based on tight reservoir energy storage fracturing technology. Background Technology
[0002] Tight oil reservoirs are characterized by low porosity, low permeability, and strong heterogeneity, resulting in low recovery rates. Production enhancement in tight oil reservoirs primarily relies on volumetric fracturing and huff-and-puff energy replenishment technologies. Both technologies have limitations. For example, volumetric fracturing has a limited injection volume, making it difficult to provide large-scale energy replenishment to the reservoir, leading to rapid production decline after fracturing. While huff-and-puff energy replenishment can replenish energy and improve crude oil properties, its effect is limited to a very small area near the wellbore, resulting in limited production enhancement and a short cycle. Against this backdrop, combining the advantages of both technologies to form energy storage fracturing technology can effectively overcome the shortcomings of either technology alone.
[0003] However, the actual effect of energy storage fracturing technology depends on the rationality of the design of carbon dioxide injection parameters. The design of these injection parameters generally relies on existing technologies and does not fully consider the complex coupling relationship between injection parameters and their synergistic impact on production enhancement. It cannot take maximizing the cumulative oil production of tight oil reservoirs throughout their entire life cycle as the global goal and dynamically and synergistically optimize the injection parameters. This leads to a mismatch between the final injection scheme and the actual physical properties and energy requirements of the target reservoir, making it impossible to achieve efficient production enhancement and recovery of tight oil reservoirs throughout their entire life cycle. Summary of the Invention
[0004] To address the aforementioned technical problems, a synergistic production enhancement method based on tight reservoir energy storage fracturing technology is proposed to solve existing issues.
[0005] The solution to the technical problem presented in this application is to provide a synergistic production enhancement method based on tight reservoir energy storage fracturing technology, comprising the following steps: Historical data of well groups in the same reservoir as the target well during gas injection development were selected. The historical data included multiple gas injection parameters and cumulative oil production. An oil production prediction model of cumulative oil production with respect to gas injection parameters was established. Define constraint ranges for all gas injection parameters of the target well, and randomly generate multiple parameter combination schemes within the constraint range to form an initial population; For each seed in the population, perform the following procedure: Based on the parameter combination scheme, the oil production prediction model is used to predict the oil production value. The distribution differences of gas injection parameters in different seed parameter combination schemes are evaluated, and the combination neighbor set of each seed is selected. Based on the synergy of the changes of different gas injection parameters in the parameter combination schemes of all seeds in the combination neighbor set and the trend of the changes of oil production prediction value, the coupling promotion degree of each seed is calculated. By analyzing the distribution characteristics of coupling promotion degree and oil production prediction values of different seeds, the neighborhood feature set of each seed is determined. Based on the coupling promotion degree and oil production prediction value of each seed, and combined with the differences between each seed and the seeds in the neighborhood feature set in terms of coupling promotion degree and prediction value, the fitness of each seed is calculated. The intelligent optimization algorithm is then used to iteratively optimize the solution and obtain the optimal parameter combination scheme for energy storage fracturing operation on the target well.
[0006] Preferably, the gas injection parameters include gas injection volume, gas injection rate, and well shut-in time.
[0007] Preferably, the oil production prediction model is constructed as follows: using the gas injection parameters of the well group as the independent variable and the cumulative oil production of the well group as the dependent variable, a regression model is used for fitting to obtain the oil production prediction model.
[0008] Preferably, the step of selecting the combined neighbor set for each seed includes: forming a parameter vector from all gas injection parameters within the parameter combination scheme of each seed; calculating the metric distance between each seed and the parameter vectors of the other seeds; sorting the metric distances between each seed and all other seeds in ascending order; and selecting the top-ranked seeds to form the combined neighbor set for each seed.
[0009] Preferably, the calculation of the coupling facilitation degree for each seed includes: The parameter correlation degree of each seed is calculated by comparing the correlation of different gas injection parameters within the parameter vectors of all seeds in the neighborhood set. The oil production prediction values of all seeds in the combined neighbor set are sorted in ascending order to form an oil production prediction sequence. The differences of all adjacent elements in the oil production prediction sequence are positively fused to serve as the oil production change of each seed. The degree of coupling promotion is positively correlated with the change in oil production and the degree of parameter correlation.
[0010] Preferably, the calculation process of the parameter correlation degree is as follows: for each seed, all seeds in its combined neighbor set are arranged in ascending order according to the oil production prediction value, and the parameter vectors of all the arranged seeds are extracted by dimension to form each gas injection parameter sequence. The correlation degree of any two gas injection parameter sequences is positively fused and used as the parameter correlation degree of each seed.
[0011] Preferably, the calculation process for the change in oil production is as follows: the average of the relative change rates of all adjacent elements in the oil production prediction sequence is used as the change in oil production for each seed.
[0012] Preferably, determining the neighborhood feature set of each seed includes: forming a two-dimensional array by combining the oil production prediction value and coupling promotion degree of each seed, defining it as a feature point, and forming the neighborhood feature set of the seed represented by the other feature points distributed within the neighborhood range of any feature point.
[0013] Preferably, the neighborhood range is a circular region centered on the feature point corresponding to each seed and with a preset cutoff distance as the radius.
[0014] Preferably, the calculation of the fitness of each seed includes: positively fusing the difference in coupling facilitation between each seed and all seeds in its neighborhood feature set as the first difference of each seed; positively fusing the difference in oil production prediction between each seed and all seeds in its neighborhood feature set as the second difference of each seed; and using the result of positive mapping of the first difference and the result of positive mapping of the second difference as weights, weighting and summing the coupling facilitation of each seed and the normalized oil production prediction as the fitness of each seed.
[0015] This application has at least the following beneficial effects: This application establishes an oil production prediction model using historical data from similar well groups under the same geological background. Its advantages include quantitatively revealing the complex nonlinear relationship between gas injection parameters and cumulative oil production. By setting reasonable constraints on the gas injection parameters and randomly generating parameter combinations to form an initial population, it avoids ineffective searches by intelligent optimization algorithms in areas where engineering is infeasible, while ensuring a broad exploration of various possible parameter combinations, providing a high-quality starting point for optimization. Screening the neighborhood set of each seed's combination is beneficial because it focuses on locally comparable schemes based on parameter space similarity. Calculating the coupling promotion degree of each seed is beneficial because it reflects the significant promoting effect of strong coupling between gas injection parameters in parameter combination schemes on oil production improvement in tight oil Class I wells, considering the synergistic changes between different gas injection parameters and the growth trend of oil production prediction values. Determining the neighborhood feature set of each seed is beneficial because it combines the coupling promotion degree with... In the comprehensive performance space composed of oil production prediction values, a neighborhood feature set consisting of other seeds with similar performance levels is defined for each seed. This allows for the evaluation of the relative advantage of each seed with other seeds in a local range, providing a more robust guide for the optimization search. The fitness of each seed is calculated, which is beneficial because it assesses the significant advantage of parameter combinations for that seed at the same level by considering the coupling promotion degree between each seed and other seeds in its neighborhood feature set, as well as the differences in oil production prediction values. This reflects the effect of gas injection parameters within the corresponding parameter combination on the cumulative oil production in the target well containing tight oil. Furthermore, an intelligent optimization algorithm is used for iterative optimization to obtain the optimal parameter combination. Energy storage fracturing operations are then implemented on the target well. This is beneficial because by finding the optimal parameter combination within the constraints of gas injection parameters that maximizes cumulative oil production, the amount of carbon dioxide injected is reasonably matched with reservoir properties and well network conditions, enabling efficient production and recovery throughout the entire lifecycle of the tight oil reservoir. Attached Figure Description
[0016] The following section provides a more detailed description of a synergistic production enhancement method based on tight reservoir energy storage fracturing technology, in conjunction with the accompanying drawings.
[0017] Figure 1 A flowchart illustrating the steps of a synergistic production enhancement method based on tight reservoir energy storage fracturing technology, provided in this application embodiment; Figure 2 A flowchart illustrating the steps of a method for obtaining the coupling facilitation degree of each seed provided in an embodiment of this application. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description, in conjunction with the accompanying drawings and implementation examples, provides a method for synergistic production enhancement based on tight oil reservoir energy storage fracturing technology. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0020] Please see Figure 1 The diagram illustrates a flowchart of a synergistic production enhancement method based on tight reservoir energy storage fracturing technology according to an embodiment of this application. The method includes the following steps: Step 1: Select historical data of well groups of the same type as the target well during gas injection development. The historical data includes multiple gas injection parameters and cumulative oil production. Establish an oil production prediction model for the cumulative oil production with respect to the gas injection parameters. Define constraint ranges for all gas injection parameters of the target well and randomly generate multiple parameter combination schemes within the constraint range to form an initial population. Based on the parameter combination schemes, use the oil production prediction model to make predictions to obtain the predicted oil production value.
[0021] In tight oil reservoir development, both CO2 pre-fracturing and CO2 huff and puff have certain limitations. CO2 pre-fracturing lacks external energy replenishment during the production stage, making it unable to provide sufficient elastic energy for the entire large reservoir volume. CO2 huff and puff mainly increases production by reducing crude oil viscosity and replenishing formation energy, but this increase relies primarily on the contact and diffusion of CO2 with crude oil. In extremely tight rocks, reservoir permeability is low, and gas molecules diffuse very slowly. Most of the injected CO2 accumulates in a very limited area around the wellbore, resulting in some crude oil not being effectively displaced.
[0022] To overcome the above limitations, a new type of carbon dioxide energy storage fracturing technology has been formed by deeply integrating carbon dioxide pre-fracturing and huff-and-puff technology. First, fracturing is used to build an efficient seepage channel, and then repeated energy replenishment and crude oil modification are carried out through periodic huff-and-puff operations to achieve more effective development of tight oil reservoirs.
[0023] This embodiment uses Well A in the Yushulin tight reservoir as the target well. The target well is a Class I tight oil well with a sandstone thickness of 12.0m, an effective thickness of 10.8m, a reservoir temperature of 100.2℃, a pressure coefficient of 1.0, and an original formation pressure of 20.2MPa.
[0024] To achieve a reasonable match between CO2 injection volume and reservoir properties and well network conditions, it is necessary to fully consider the promoting effect of gas injection on oil production and optimize the CO2 injection parameters to improve the displacement effect and the affected range of well penetration, thereby achieving efficient production and recovery of tight oil reservoirs throughout their entire life cycle.
[0025] By using a database of oilfield gas injection development in historical periods, wells with the same geological reservoir type as the target well are selected as well groups of the same type, namely well groups belonging to the tight oil type I. Historical data of the same well groups are obtained, including different gas injection parameters and corresponding cumulative oil production. Among them, the gas injection parameters include the amount of carbon dioxide injected, the gas injection rate, and the well shut-in time. Establish a mapping relationship between cumulative oil production and all gas injection parameters, and construct an oil production prediction model; In this embodiment, the gas injection volume, gas injection rate, and well shut-in time of similar well groups are used as independent variables, and the cumulative oil production of similar well groups is used as the dependent variable. The model is fitted using a multivariate polynomial regression algorithm, and the fitted function is used as the oil production prediction model. The multivariate polynomial regression algorithm is a well-known technology and will not be described in detail here.
[0026] Secondly, define constraint ranges for all gas injection parameters of the target well; In this embodiment, engineering experts reasonably set the constraint range of all gas injection parameters of the target well. Among them, the constraint range of carbon dioxide injection volume is 4500t~6000t, the constraint range of gas injection rate is 550t / day-650t / day, and the constraint range of well shut-in time is 10 days~15 days. As other implementation methods, implementers can set them according to the actual situation.
[0027] Based on the constraints of different gas injection parameters, multiple parameter combination schemes are randomly generated as the initial population of the intelligent optimization algorithm. In this embodiment, a value is randomly selected from the constraints of each gas injection parameter, and all the selected values corresponding to the gas injection parameters are combined into a parameter combination scheme. This operation is repeated to generate multiple parameter combination schemes. The number of parameter combination schemes is 1000. As another implementation method, the implementer can set it according to the actual situation. Secondly, the intelligent optimization algorithm is a genetic algorithm. The genetic algorithm is a well-known technology and will not be described in detail here.
[0028] The parameter combination scheme for each seed is input into the oil production prediction model to predict the cumulative oil production and obtain the oil production prediction value corresponding to the parameter combination scheme for each seed. Thus, multiple parameter combination schemes for the target well and corresponding oil production prediction values were obtained.
[0029] Step 2: Evaluate the distribution differences of gas injection parameters in different seed parameter combination schemes, screen out the combination neighbor set of each seed, and calculate the coupling promotion degree of each seed based on the synergy of the changes in different gas injection parameters in all seed parameter combination schemes within the combination neighbor set and the trend of changes in oil production prediction values.
[0030] Different parameter combinations will have different effects on cumulative oil production. For example, increasing the injection volume and injection rate within a certain range can ensure the diffusion rate of injected carbon dioxide, improve the fluidity of crude oil in the well, and further promote oil production. Increasing the well shut-in time can allow the injected carbon dioxide to diffuse fully, increasing the production of tight oil wells. There is generally a coupling relationship between the injection volume, injection rate, and well shut-in time. To more accurately optimize the carbon dioxide injection parameters in a coordinated manner, the optimal parameter combination scheme can be obtained.
[0031] Furthermore, the flowchart of the method for obtaining the coupling facilitation degree of each seed provided in this embodiment is as follows: Figure 2 As shown.
[0032] For each seed, normalize all gas injection parameters within the parameter combination scheme; then, combine the normalized gas injection parameters within each seed's parameter combination scheme into a parameter vector. In this embodiment, the maximum value normalization method is used for normalization. For example, the maximum value of the constraint range corresponding to each gas injection parameter is obtained, and the ratio of each gas injection parameter to the corresponding maximum value in the parameter combination scheme is calculated as the normalized gas injection parameter.
[0033] Based on the above analysis, the combined nearest neighbor set is obtained by analyzing the differences in parameter vectors among different seeds within the population, specifically: Calculate the metric distance between any seed and all other seeds in the parameter vector; In this embodiment, the distance is measured by calculating the Euclidean distance between any seed and the parameter vectors of all other seeds. The Euclidean distance is a well-known technique and will not be described in detail here.
[0034] Sort the metric distances between any seed and all other seeds in ascending order, and select the top-ranked seeds to form a combined neighbor set for any seed. In this embodiment, the top 30 seeds are selected to form a combined neighbor set for any seed. As for other implementation methods, the implementer can set them according to the actual situation.
[0035] Secondly, based on the correlation of the same gas injection parameter within the parameter vector corresponding to the seed in the combined neighbor set, and the growth of the corresponding oil production forecast, the coupling promotion degree is calculated, specifically as follows: For any given seed, all seeds in its neighborhood set are sorted in ascending order of oil production prediction value, and the parameter vectors of all sorted seeds are extracted by dimension to form each gas injection parameter sequence. In this embodiment, since each dimension in the parameter vector represents a gas injection parameter, all values in the same dimension are combined to form a sequence of gas injection parameters.
[0036] It should be noted that if there are cases where the oil production forecasts are equal, the seeds of the equal oil production forecasts will be randomly arranged.
[0037] The oil production prediction values are normalized, and the normalized oil production prediction values of all seeds in the combined neighbor set are arranged in ascending order to form an oil production prediction sequence. In this embodiment, the maximum value normalization method is used to normalize the oil production forecast. The maximum value normalization method is a well-known technique and will not be described in detail here.
[0038] The mean of the relative change rates of all adjacent elements within the oil production prediction sequence is taken as the oil production change of any seed. It should be noted that the larger the change in oil production, the more significant the upward trend in cumulative oil production.
[0039] The correlation between any two gas injection parameter sequences is positively fused and used as the parameter correlation degree of any seed. In this embodiment, the correlation is measured by calculating the Pearson correlation coefficient of the two gas injection parameter sequences. The calculation of the Pearson correlation coefficient is a well-known technique and will not be described in detail here. As other implementations, implementers can use other methods of the prior art, such as the Spearman correlation coefficient, etc. This embodiment does not impose any special restrictions on this. Secondly, the specific process of forward fusion is as follows: the mean of the correlation between any two gas injection parameter sequences is taken as the parameter correlation degree. As another implementation, implementers can calculate the sum of the correlation between any two gas injection parameter sequences as the parameter correlation degree.
[0040] It should be noted that the greater the correlation between the parameters, the stronger the positive correlation between different gas injection parameter sequences, reflecting a strong coupling relationship between the gas injection parameters and a synergistic effect among them.
[0041] The coupling promotion degree of any seed is positively correlated with both the change in oil production and the correlation degree of the parameters. It should be noted that a positive correlation means that the dependent variable increases as the independent variable increases and decreases as the independent variable decreases.
[0042] In this embodiment, the specific calculation process of the coupling promotion degree is as follows: The parameter correlation degree is positively mapped, and the normalized result of the product of the positive mapping result and the oil production change is taken as the coupling promotion degree. The normalization process uses the maximum-minimum value normalization method, which is a well-known technique and will not be elaborated upon here. Secondly, the specific process of the positive mapping is as follows: The reciprocal of the difference between the value 1 and the parameter correlation degree is taken as the result of the positive mapping. When calculating the reciprocal, to avoid the denominator being 0, a parameter tuning factor is added to the denominator. The value range of the parameter tuning factor is... In this embodiment, the parameter tuning factor is set to 1. In other implementations, the implementer can set it according to the actual situation. In other implementations, the implementer can also perform positive mapping through an exponential function, and take the result of the exponential function with the natural constant as the base and the parameter correlation degree as the exponent as the result of the positive mapping.
[0043] It should be noted that the greater the degree of coupling promotion, the stronger the coupling relationship between the gas injection parameters in the adjacent clusters. At the same time, the more significant the upward trend of the oil production prediction value, the more it reflects that the strong coupling between the gas injection parameters has a significant promoting effect on the oil production in tight oil Class I wells. Moreover, the gas injection parameters have a strong synergistic effect, which helps to achieve a more reasonable match between the injection volume and reservoir properties and well network conditions in the future.
[0044] Thus, the coupling promotion degree of various sub-subs is obtained.
[0045] Step 3: By analyzing the distribution characteristics of the coupling promotion degree and oil production prediction values of different seeds, determine the neighborhood feature set of each seed. Based on the coupling promotion degree and oil production prediction value of each seed, and considering the differences between each seed and the seeds in the neighborhood feature set in terms of coupling promotion degree and prediction value, calculate the fitness of each seed. Then, use an intelligent optimization algorithm to iteratively optimize and obtain the optimal parameter combination scheme to carry out energy storage fracturing operations on the target well.
[0046] Furthermore, based on the coupling promotion degree of different seeds and the distribution characteristics of oil production prediction values, a neighborhood feature set is obtained, specifically: The normalized oil production prediction value and the coupling promotion degree are combined into a two-dimensional array, and this array is defined as a feature point. The distance between any two feature points represented by the seeds is calculated and denoted as the relative distance. In this embodiment, the relative distance is measured by calculating the Euclidean distance.
[0047] For any given seed, all other seeds whose relative distance to it is less than or equal to a preset cutoff distance are combined to form the neighborhood feature set of that seed. In this embodiment, a neighborhood definition method based on a preset cutoff distance is adopted. All other seeds whose relative distance to each seed is less than or equal to the cutoff distance are grouped into a neighborhood feature set. Specifically, based on the Density Peak Clustering (DPC) clustering algorithm, a cutoff distance is set for the two-dimensional array of all seeds. The value of the cutoff distance is determined according to a density criterion: that is, the cutoff distance ensures that the neighborhood of each seed contains, on average, 1% to 2% of the other seeds in the total number of seeds. The neighborhood refers to a circular neighborhood centered on each seed with a radius equal to the cutoff distance. The DPC clustering algorithm is a well-known technique and will not be described in detail here.
[0048] Secondly, if the predicted oil production value or coupling promotion degree within the two-dimensional array of a certain seed is greater than that within the two-dimensional array of seeds in the neighboring feature point set, it indicates that the parameter combination scheme of that seed is more conducive to promoting the increase of cumulative oil production in tight oil Class I wells. Therefore, the differences in predicted oil production value and coupling promotion degree between various seeds and seeds in their neighboring feature sets are analyzed, and the fitness is calculated, specifically as follows: The differences in coupling facilitation between each sub and all seeds in its neighborhood feature set are positively fused and used as the first difference of each sub. In this embodiment, the differences in coupling facilitation between each sub and all seeds in its neighborhood feature set are positively fused to form the first difference of each sub. The specific process of positive fusion is as follows: the sum of the differences in coupling facilitation between each sub and all seeds in its neighborhood feature set is taken as the first difference of each sub. In other implementations, the implementer may take the mean of the differences in coupling facilitation between each sub and all seeds in its neighborhood feature set as the first difference of each sub.
[0049] The difference in normalized oil production prediction values between each seed and all seeds in its neighborhood feature set is positively fused and used as the second difference of each seed. In this embodiment, the differences in normalized oil production prediction values between each sub and all seeds in its neighborhood feature set are positively fused to serve as the second difference of each sub. The specific process of positive fusion is as follows: the sum of the differences in normalized oil production prediction values between each sub and all seeds in its neighborhood feature set is used as the second difference of each sub. In other implementations, the implementer may use the mean of the differences in normalized oil production prediction values between each sub and all seeds in its neighborhood feature set as the second difference of each sub.
[0050] It should be noted that, if the first difference is positive and the larger the value, the greater the coupling promotion degree corresponding to the seed is compared with the coupling promotion degree of other seeds in the neighborhood feature set, reflecting that the gas injection parameters in the parameter combination scheme corresponding to the seed have a stronger promoting effect on the cumulative oil production of Class I tight oil wells; if the first difference is negative and the smaller the value, the weaker the promoting effect of the gas injection parameters in the parameter combination scheme corresponding to the seed on the cumulative oil production of Class I tight oil wells; secondly, if the second difference is positive and the larger the value, the higher the predicted oil production value corresponding to the seed is compared with other seeds, reflecting that the gas injection parameters in the parameter combination scheme corresponding to the seed have a better effect on the cumulative oil production of Class I tight oil wells.
[0051] Apply positive mappings to the first and second differences respectively; In this embodiment, the specific process of positive mapping is as follows: the first difference and the second difference are normalized by the maximum-minimum normalization method, and the sum of the value 1 and the normalization result is taken as the result of positive mapping. Through the normalization process, the first difference and the second difference are avoided to be negative. Through the positive mapping process, the normalization result is avoided to be 0. As another implementation method, the implementer can use an exponential function to perform positive mapping.
[0052] The results of positive mapping of the first difference and the second difference are used as weights to sum the coupling promotion degree of each component and the normalized oil production prediction value, which is then used as the fitness of each component. In this embodiment, the fitness calculation process is as follows:
[0053] in, Let j be the fitness of the j-th seed. The result of orthographic mapping for the first difference of the j-th seed. The result of orthographic mapping for the second difference of the j-th seed. Let the coupling facilitation degree be the j-th seed. This represents the normalized oil production prediction value corresponding to the j-th seed.
[0054] It should be noted that the greater the coupling promotion degree, the stronger the synergistic effect between the gas injection parameters in the parameter combination scheme corresponding to the seed. The greater the result of the first difference mapping, the greater the coupling promotion degree of the seed is compared with the other seeds in its neighborhood. The greater the result of the second difference mapping, the greater the oil production of the seed is compared with the other seeds in its neighborhood. The greater the predicted oil production value, the higher the predicted oil production under the gas injection parameters in the parameter combination scheme corresponding to the seed. The greater the obtained fitness, the better the parameter combination scheme corresponding to the seed is in improving the oil production in Class I tight oil wells. It is more conducive to improving the sufficiency of carbon dioxide energy storage in the development of tight oil reservoirs, thereby ensuring efficient production and recovery of tight oil reservoirs throughout their entire life cycle.
[0055] Furthermore, based on fitness, an intelligent optimization algorithm is used for optimization, specifically: Based on the initial population and fitness, an intelligent optimization algorithm is used to iteratively find the optimal parameter combination scheme. In this embodiment, the intelligent optimization algorithm adopts a genetic algorithm, wherein the maximum number of iterations of the genetic algorithm is set to 100, and the genetic algorithm uses a tournament method for crossover and mutation, with a crossover probability of 0.8 and a mutation probability of 0.07. As other implementation methods, implementers can set them according to the actual situation. The genetic algorithm is a well-known technology and will not be described in detail here.
[0056] Furthermore, mining is carried out based on the optimal parameter combination scheme. In this embodiment, the optimal parameter combination scheme for Well A in the Yushulin tight reservoir is a carbon dioxide injection volume of 5600t, an injection rate of 600t / day, and a well shut-in period of 15 days, specifically: Process design: After perforation of the new well, carbon dioxide is injected at super-fracture pressure, followed by water-based fracturing and stimulation after well shut-in. The gas injection process uses casing injection, with a P110 casing short-connector installed in the new well and a 70MPa fracturing wellhead. Fracturing parameter design: Casing fracturing 8-12m 3 / min, liquid addition intensity 425.4m 3 / m, sand strength 20.2m 3 / m, temporarily plug the seam 5 times; Implementation status: Based on 4m 3 With a flow rate of / min, a daily gas injection volume of 600t, an operating pressure of approximately 31MPa, a shutdown pressure of approximately 23MPa, and a cumulative gas injection of 5600t, the planned injection volume was executed at 100% completion, and the final injection pressure reached twice the original formation pressure. The well was shut in for 15 days, and fracturing was completed according to the plan. The shutdown pressure was 32.3MPa, approximately 6MPa higher than that of adjacent wells. Table 1 shows a comparison of the formation pressure increase factors in tight oil CO2 energy storage fracturing wells.
[0057] Table 1 Comparison of Formation Pressure Increase Factors in Tight Oil Carbon Dioxide Storage Fracturing Wells
[0058] Application results: Well A produced 16.8 tons of oil per day in the initial stage of production. After 128 days of production, it has produced 10.3 tons of oil per day, with a cumulative production of 1571 tons. Compared with neighboring platform wells, Well A's initial production increased by 1.9 times. The comparison table of the initial production increase of tight oil carbon dioxide storage fracturing wells is shown in Table 2.
[0059] Table 2 Comparison of Initial Production Increase in Tight Oil Carbon Dioxide Storage Fracturing Wells
[0060] It should be understood that, although Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order in which these steps are executed, and they can be performed in other orders. Furthermore, Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
[0061] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0062] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application. Therefore, any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application, without departing from the content of the technical solution of this application, shall fall within the protection scope of the technical solution of this application.
Claims
1. A synergistic production enhancement method based on tight oil reservoir energy storage fracturing technology, characterized in that, The method includes the following steps: Historical data of well groups in the same reservoir as the target well during gas injection development were selected. The historical data included multiple gas injection parameters and cumulative oil production. An oil production prediction model of cumulative oil production with respect to gas injection parameters was established. Define constraint ranges for all gas injection parameters of the target well, and randomly generate multiple parameter combination schemes within the constraint range to form an initial population; For each seed in the population, perform the following procedure: Based on the parameter combination scheme, the oil production prediction model is used to predict the oil production value. The distribution differences of gas injection parameters in different seed parameter combination schemes are evaluated, and the combination neighbor set of each seed is selected. Based on the synergy of the changes of different gas injection parameters in the parameter combination schemes of all seeds in the combination neighbor set and the trend of the changes of oil production prediction value, the coupling promotion degree of each seed is calculated. By analyzing the distribution characteristics of coupling promotion degree and oil production prediction values of different seeds, the neighborhood feature set of each seed is determined. Based on the coupling promotion degree and oil production prediction value of each seed, and combined with the differences between each seed and the seeds in the neighborhood feature set in terms of coupling promotion degree and prediction value, the fitness of each seed is calculated. The intelligent optimization algorithm is then used to iteratively optimize the solution and obtain the optimal parameter combination scheme for energy storage fracturing operation on the target well.
2. The synergistic production enhancement method based on tight reservoir energy storage fracturing technology as described in claim 1, characterized in that, The gas injection parameters include gas injection volume, gas injection rate, and well shut-in time.
3. The synergistic production enhancement method based on tight reservoir energy storage fracturing technology as described in claim 1, characterized in that, The process of constructing the oil production prediction model is as follows: using the gas injection parameters of the well group as the independent variable and the cumulative oil production of the well group as the dependent variable, a regression model is used for fitting to obtain the oil production prediction model.
4. The method for synergistic production enhancement based on tight reservoir energy storage fracturing technology as described in claim 1, characterized in that, The step of selecting the combined neighbor set for each seed includes: forming a parameter vector from all the gas injection parameters in the parameter combination scheme of each seed; calculating the metric distance between the parameter vectors of each seed and the other seeds; sorting the metric distances between each seed and all the other seeds in ascending order; and selecting the top-ranked seeds to form the combined neighbor set for each seed.
5. The synergistic production enhancement method based on tight reservoir energy storage fracturing technology as described in claim 4, characterized in that, The calculation of the coupling facilitation degree for each seed includes: The parameter correlation degree of each seed is calculated by comparing the correlation of different gas injection parameters within the parameter vectors of all seeds in the neighborhood set. The oil production prediction values of all seeds in the combined neighbor set are sorted in ascending order to form an oil production prediction sequence. The differences of all adjacent elements in the oil production prediction sequence are positively fused to serve as the oil production change of each seed. The degree of coupling promotion is positively correlated with the change in oil production and the degree of parameter correlation.
6. The method for synergistic production enhancement based on tight reservoir energy storage fracturing technology as described in claim 5, characterized in that, The calculation process of the parameter correlation degree is as follows: For each seed, all seeds in its combined neighbor set are arranged in ascending order according to the oil production prediction value, and the parameter vectors of all the arranged seeds are extracted by dimension to form each gas injection parameter sequence. The correlation degree of any two gas injection parameter sequences is positively fused and used as the parameter correlation degree of each seed.
7. The method for synergistic production enhancement based on tight reservoir energy storage fracturing technology as described in claim 5, characterized in that, The calculation process for the change in oil production is as follows: the average of the relative change rates of all adjacent elements in the oil production prediction sequence is used as the change in oil production for each seed.
8. The method for synergistic production enhancement based on tight reservoir energy storage fracturing technology as described in claim 1, characterized in that, The determination of the neighborhood feature set of each seed includes: forming a two-dimensional array of the oil production prediction value and coupling promotion degree of each seed, defining it as a feature point, and forming the neighborhood feature set of the seed represented by the other feature points distributed in the neighborhood range of any feature point.
9. A synergistic production enhancement method based on tight reservoir energy storage fracturing technology as described in claim 8, characterized in that, The neighborhood range is a circular area centered on the feature point corresponding to each seed and with a preset cutoff distance as the radius.
10. The method for synergistic production enhancement based on tight reservoir energy storage fracturing technology as described in claim 1, characterized in that, The calculation of the fitness of each seed includes: positively fusing the difference in coupling facilitation between each seed and all seeds in its neighborhood feature set as the first difference of each seed; positively fusing the difference in oil production prediction between each seed and all seeds in its neighborhood feature set as the second difference of each seed; and using the result of positive mapping of the first difference and the result of positive mapping of the second difference as weights, weighting and summing the coupling facilitation of each seed and the normalized oil production prediction as the fitness of each seed.