Intelligent regulation and control method and equipment for gas reservoir water invasion and storage medium

Abstract

A gas reservoir water invasion intelligent regulation and control method, equipment and a storage medium relate to the technical field of oil and gas development, and mainly comprise the steps of randomly generating a production simulation model to construct a multi-target water invasion dynamic data set, training a machine learning model by using a normalized data set, and establishing a multi-target water invasion dynamic data set; calculating a main control factor influencing the dynamic state of water invasion and a weight corresponding to the main control factor by utilizing the trained machine learning model, establishing a comprehensive evaluation model of the drainage well, inputting corresponding parameters of a production well with water output in a well pattern of a production area into the comprehensive evaluation model of the drainage well, determining a drainage well pattern consisting of the production well and the drainage well, and evaluating the drainage well. Establishing a drainage and mining system multi-objective optimization mathematical model, and solving to obtain Pareto solution sets and well control parameters corresponding to different drainage and mining system schemes by using a multi-objective optimization algorithm; according to the method, the Pareto solution sets of different schemes and the corresponding well control parameters are accurately obtained through the multi-objective optimization algorithm, the water invasion damage of the gas reservoir is intelligently regulated and controlled, and a support effect is provided for stable production of the gas reservoir.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas development, and in particular to a method, equipment and storage medium for intelligently controlling water intrusion in a gas reservoir. Background Art

[0002] Natural gas is an important component of fossil energy and is usually developed through exhaustion. However, natural gas reservoirs are usually connected to groundwater bodies. As the formation pressure gradually decreases during the exploitation process, formation water will invade the gas reservoir, resulting in a decrease in gas phase permeability and an increase in the abandoned gas reservoir pressure, which will have a serious impact on the stable production capacity and recovery rate of gas wells. Therefore, water control in gas reservoirs is of great significance to maintaining the efficient development of natural gas.

[0003] Drainage and gas production is one of the effective methods for water control in gas reservoirs. The key to improving the drainage and gas production effect of gas reservoirs lies in the design of drainage well networks and the optimization of drainage well control parameters for existing production wells. Well network design is mainly to determine drainage wells, but the existing design basis only includes one of structural characteristics, water invasion conditions, and economic benefits. If only a single factor is considered, it will cause the confirmation of important factors, making the well network design effect lower than expected. The determination of well control parameters of the drainage system can be regarded as a nonlinear optimization problem with constraints. The existing artificial pursuit of a single goal through the development status matching process parameters is difficult to obtain the optimal solution, making it difficult to effectively alleviate the water invasion damage suffered by gas reservoirs in field applications. Summary of the invention

[0004] In view of this, the present invention proposes a method for intelligent control of water invasion in gas reservoirs, which can achieve efficient optimization and construction of drainage and production well networks and obtain accurate parameters related to well control.

[0005] In order to solve at least one of the above technical problems, the technical solution provided by the present invention is a method for intelligently controlling water invasion in gas reservoirs, comprising the following steps:

[0006] Step S1: randomly generate multiple groups of well group production simulation models including different geological parameters, engineering parameters, development parameters and target parameters to construct a multi-target water invasion dynamic data set, and normalize the data set;

[0007] Step S2: using the normalized data set to train a machine learning model, using the trained machine learning model to calculate the factors affecting water intrusion dynamics and rank their importance, and obtain the main controlling factors affecting water intrusion dynamics and the weights corresponding to the main controlling factors;

[0008] Step S3: Establish a comprehensive evaluation model for drainage wells, input corresponding parameters of production wells with water production in the production area well network into the comprehensive evaluation model for drainage wells, determine production wells with evaluation values ​​greater than 0.5 calculated in the comprehensive evaluation model for drainage wells as drainage wells, and then determine a drainage well network consisting of production wells and drainage wells;

[0009] Among them, the comprehensive evaluation model of drainage wells is specifically shown in formula (1):

[0010]

[0011] In formula (1), V is the comprehensive evaluation value of the drainage well, t is the number of main control factors, t = 1, 2, ..., n, α t Represents the weight value of each main control factor, C t is the specific value of each main control factor, C tmin is the minimum value of each main controlling factor in the gas reservoir, C tmax is the minimum value of each main controlling factor in the gas reservoir;

[0012] Step S4: Based on the drainage and production well network, a multi-objective optimization mathematical model of the drainage and production system is established, wherein the objective function of the mathematical model is shown in equations (2) to (2.2):

[0013] minf(x)=[f EW , -f EG ] (2)

[0014]

[0015] In formula (2), f EW is the cumulative water production of all gas wells, f EG is the cumulative gas production of all gas wells, G i represents the daily gas production of the i-th gas producing well, W j represents the daily water production of the jth drainage well;

[0016] The constraints are the upper and lower limits of the daily gas production of the gas production well and the upper and lower limits of the daily water production of the drainage well, as shown in formula (3):

[0017]

[0018] In formula (3), i represents the i-th gas producing well, i = 1, 2, ..., n, G i represents the daily gas production of the i-th gas producing well, G imin represents the minimum daily gas production of the i-th gas producing well, G imax W represents the maximum daily gas production of the i-th gas production well, j represents the j-th drainage well, j = 1, 2, ..., n, W j represents the daily water production of the jth drainage well, W jmin represents the minimum daily water production of the jth drainage well, W jmax represents the maximum daily water production of the jth drainage well;

[0019] Step S5: Use a multi-objective optimization algorithm to solve the multi-objective optimization mathematical model of the drainage system, and obtain the Pareto solution set and well control parameters corresponding to different drainage system schemes.

[0020] Another object of the present invention is to provide a device for intelligently controlling water invasion in gas reservoirs, comprising:

[0021] processor;

[0022] A storage module storing a program for intelligent control of water invasion in gas reservoirs that can be run on the processor, wherein the program for intelligent control of water invasion in gas reservoirs implements the steps described in any one of claims 1 to 6 when executed by the processor;

[0023] Output module, used to output calculation results.

[0024] In addition, the present invention also provides a computer-readable storage medium, which stores a code program executable by a processor, characterized in that the computer-readable storage medium includes multiple instructions, and the multiple instructions are configured to enable the processor to execute the intelligent control method of gas reservoir water invasion.

[0025] The technical effects of the present invention are:

[0026] The present invention discloses a method, device and storage medium for intelligent control of water invasion in gas reservoirs, which can be solved by a multi-objective optimization algorithm to accurately obtain Pareto solution sets of different schemes and corresponding well control parameters, effectively realize intelligent control of water invasion damage in gas reservoirs, and provide support for stable production of gas reservoirs. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a flow chart of the intelligent control method of gas reservoir in the present invention;

[0029] Figure 2 It is a schematic diagram of a conceptual numerical simulation model of the gas reservoir intelligent control method of the present invention;

[0030] Figure 3 A result diagram of ranking the importance of factors affecting the intelligent gas reservoir control method of the present invention;

[0031] Figure 4 Schematic diagram of the optimal well pattern in the target area of ​​the gas reservoir intelligent control method of the present invention;

[0032] Figure 5 A schematic diagram of the Pareto front obtained by solving the gas reservoir intelligent control method of the present invention;

[0033] Figure 6 It is the well control parameter of each single well under the optimal drainage and production system of the gas reservoir intelligent control method in the present invention. DETAILED DESCRIPTION

[0034] The present invention will be further described in detail below in conjunction with the embodiments and drawings.

[0035] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention.

[0036] A method for intelligently controlling water invasion in a gas reservoir comprises the following steps:

[0037] Step S1: randomly generate multiple groups of well group production simulation models including different geological parameters, engineering parameters, development parameters and target parameters to construct a multi-target water invasion dynamic data set, and normalize the data set;

[0038] The geological parameters include porosity, permeability, and water saturation; the engineering parameters include the number of gas producing wells and the well spacing; the development parameters include formation pressure and water-gas ratio; and the target parameters include cumulative gas production and cumulative water production;

[0039] A large number of different geological factors, engineering factors, and corresponding development status parameter combinations and corresponding multiple target values ​​are normalized to construct a water intrusion dynamic data set containing multiple targets. The normalization processing formula is specifically shown in formula (5):

[0040]

[0041] In formula (5), S z is the normalized value, S is the initial value, S max is the maximum value in the data set, S min is the minimum value in the data set.

[0042] Step S2: using the normalized data set to train a machine learning model, using the trained machine learning model to calculate the factors affecting water intrusion dynamics and rank their importance, and obtain the main controlling factors affecting water intrusion dynamics and the weights corresponding to the main controlling factors;

[0043] The machine learning model is one of random forest, GBDT, XGBoost, and LightGBM. Its training set, validation set, and test set are divided by the above-mentioned water intrusion dynamic dataset in a ratio of 8:1:1. The training set is used to train the basic machine learning model, the validation set is used to adjust the hyperparameters of the machine learning model, and the test set is used to test the performance of the machine learning model.

[0044] The method for ranking importance is the Pearson correlation coefficient method. The main controlling factors are the influencing factors with a correlation coefficient greater than 0.1. The method for calculating the weight of the main controlling factors is: summing the correlation coefficients corresponding to each main controlling factor, and then dividing the correlation coefficient of each main controlling factor by the sum of the correlation coefficients of each main controlling factor to obtain the weight corresponding to each main controlling factor.

[0045] Step S3: Establish a comprehensive evaluation model for drainage wells, input corresponding parameters of production wells with water production in the production area well network into the comprehensive evaluation model for drainage wells, determine production wells with evaluation values ​​greater than 0.5 calculated in the comprehensive evaluation model for drainage wells as drainage wells, and then determine a drainage well network consisting of production wells and drainage wells;

[0046] Among them, the comprehensive evaluation model of drainage wells is specifically shown in formula (1):

[0047]

[0048] In formula (1), V is the comprehensive evaluation value of the drainage well, t is the number of main control factors, t = 1, 2, ..., n, α t Represents the weight value of each main control factor, C t is the specific value of each main control factor, C tmin is the minimum value of each main controlling factor in the gas reservoir, C tmax is the minimum value of each main controlling factor in the gas reservoir;

[0049] Step S4: Based on the drainage and production well network, a multi-objective optimization mathematical model of the drainage and production system is established, which mainly includes setting optimization variables, constraints, and optimization objectives; the optimization variables are the daily gas production of the gas production wells and the daily drainage of the drainage wells; the constraints are the upper and lower limits of the daily gas production of the gas production wells and the upper and lower limits of the daily water production of the drainage wells; the optimization objectives are to minimize the cumulative water production of all gas production wells and maximize the cumulative gas production of all gas production wells, wherein the objective function of the mathematical model is shown in formulas (2)-(2.2):

[0050] minf(x)=[fEW , -f EG ] (2)

[0051]

[0052] In formula (2), f EW is the cumulative water production of all gas wells, f EG is the cumulative gas production of all gas wells, G i represents the daily gas production of the i-th gas producing well, W j represents the daily water production of the jth drainage well;

[0053] The constraints are the upper and lower limits of the daily gas production of the gas production well and the upper and lower limits of the daily water production of the drainage well, as shown in formula (3):

[0054]

[0055] In formula (3), i represents the i-th gas producing well, i = 1, 2, ..., n, G i represents the daily gas production of the i-th gas producing well, G imin represents the minimum daily gas production of the i-th gas producing well, G imax W represents the maximum daily gas production of the i-th gas production well, j represents the j-th drainage well, j = 1, 2, ..., n, W j represents the daily water production of the jth drainage well, W jmin represents the minimum daily water production of the jth drainage well, W jmax represents the maximum daily water production of the jth drainage well;

[0056] Step S5: Use a multi-objective optimization algorithm to solve the multi-objective optimization mathematical model of the drainage system, and obtain the Pareto solution set and well control parameters corresponding to different drainage system schemes, wherein the multi-objective optimization algorithm is one of NSGA-Ⅱ, MOPSO, and MOEA / D.

[0057] The performance of the multi-objective optimization algorithm and its solution set in multiple objectives are evaluated using the HV index. The specific index is shown in formula (4):

[0058]

[0059] In formula (4), PS is the Pareto solution set, M is the reference point, and v is the hypercube.

[0060] The present invention provides a gas reservoir water invasion intelligent control device, comprising:

[0061] processor;

[0062] A storage module storing a program for intelligent control of water invasion in gas reservoirs that can be run on the processor, wherein the program for intelligent control of water invasion in gas reservoirs implements the steps described in any one of claims 1 to 6 when executed by the processor;

[0063] Output module, used to output calculation results.

[0064] The processor includes:

[0065] The data set construction module is used to construct a large amount of water intrusion dynamic data including different geological factors, engineering factors, corresponding development status parameter combinations and corresponding multiple target values;

[0066] Machine learning model training module, used to screen the main controlling factors affecting water intrusion dynamics and obtain the corresponding weights;

[0067] The drainage well network determination module is used to construct a comprehensive evaluation model for drainage wells to determine the drainage well network;

[0068] The module for constructing a multi-objective optimization mathematical model of the drainage system is used to construct a multi-objective optimization mathematical model of the drainage system including optimization variables, constraints, and optimization objectives;

[0069] The well control parameter optimization module is used to solve the Pareto solution set of different schemes and the corresponding well control parameters through a multi-objective optimization algorithm.

[0070] The present invention also provides a computer-readable storage medium storing a code program executable by a processor, wherein the computer-readable storage medium includes a plurality of instructions, and the plurality of instructions are configured to enable the processor to execute the above-mentioned intelligent control method for water invasion in gas reservoirs.

[0071] Example:

[0072] Taking a production block in a gas field that is damaged by water intrusion as an example, 500 sets of production simulation models with different porosity, permeability, water saturation, number of gas producing wells, well spacing, formation pressure at the beginning of drainage and gas production, and water-gas ratio are randomly generated. The schematic diagram of the production simulation model is shown in the figure. Figure 2 As shown in the figure, the relationship between the formation depth and the model is mainly shown. The cumulative gas production and cumulative water production under the corresponding parameter combination are obtained by running numerical simulation. After normalization, a data set containing 500 groups of different parameter combinations is constructed.

[0073] A training set consisting of 400 groups of data was used to train the XGBoost model, and a validation set consisting of 50 groups of data was used to adjust the hyperparameters of the XGBoost model. The hyperparameter adjustment results are shown in Table 1. A test set consisting of 50 groups of data was used to test the performance of the XGBoost model.

[0074] Table 1 Hyperparameters of XGBoost model

[0075] Parameter name Value Parameter name Value Maximum tree depth 9 The number of independent trees that make up the set 2000 Learning Rate 0.10 The minimum sample weight and 5

[0076] The ranking results of the importance of influencing factors are as follows Figure 3 As shown in the figure, water-gas ratio, permeability, well spacing, number of gas producing wells, and porosity are the main controlling factors affecting gas and water production after water invasion. The weight corresponding to the water-gas ratio is 0.20, the weight corresponding to the permeability is 0.10, the weight corresponding to the well spacing is 0.20, the weight corresponding to the number of gas producing wells is 0.10, and the weight corresponding to the porosity is 0.40.

[0077] The main control factor parameters of each water-seeping well are input into the comprehensive evaluation model of drainage wells. The drainage wells deployed in the target area are TZ4, TZ5, TZ15 and the original drainage well TZ18. The schematic diagram of the optimal well network in the target area is shown in Figure 4 shown.

[0078] The mathematical model for optimizing the drainage system is solved using NSGA-Ⅱ, MOPSO, and MOEA / D. The Pareto frontier diagram obtained is shown in the figure below. Figure 5 The HV index of different multi-objective optimization algorithms was calculated, and the calculation results are shown in Table 2.

[0079] Table 2 HV index values ​​of different algorithms

[0080] Optimization Algorithm NSGA-II MOEA / D MOPSO HV index value 0.273 0.142 0.202

[0081] NSGA-II has the highest HV index value, and the cumulative gas production of the optimal solution in the whole area in 10 years is 700.93×10 8 m 3 The total water production in the area is 11.61×10 8 m 3 The corresponding gas reservoir overall optimization daily production is 1094×10 4 m 3 / d, the daily drainage volume of the gas reservoir is 1298m 3 / d, the well control parameters of each single well under the optimal drainage system are as follows Figure 6 shown.

[0082] It can be seen that the present invention determines the drainage wells by comprehensively considering various factors, increases the credibility of the drainage and production well network design, and reduces the computational cost of directly optimizing the well locations; multi-objective intelligent optimization of well control parameters effectively avoids falling into local optimality, ensures the operability of the optimization results, and realizes intelligent regulation of water invasion damage to gas reservoirs, providing strong support for stable natural gas production.

[0083] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the embodiments of the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for intelligently controlling water intrusion in gas reservoirs, characterized in that: The following steps are involved: Step S1: randomly generate multiple groups of well group production simulation models including different geological parameters, engineering parameters, development parameters and target parameters to construct a multi-target water invasion dynamic data set, and normalize the data set; Step S2: using the normalized data set to train a machine learning model, using the trained machine learning model to calculate the factors affecting water intrusion dynamics and rank their importance, and obtain the main controlling factors affecting water intrusion dynamics and the weights corresponding to the main controlling factors; Step S3: Establish a comprehensive evaluation model for drainage wells, input corresponding parameters of production wells with water production in the production area well network into the comprehensive evaluation model for drainage wells, determine production wells with evaluation values ​​greater than 0.5 calculated in the comprehensive evaluation model for drainage wells as drainage wells, and then determine a drainage well network consisting of production wells and drainage wells; Among them, the comprehensive evaluation model of drainage wells is specifically shown in formula (1): In formula (1), V is the comprehensive evaluation value of the drainage well, t is the number of main control factors, t = 1, 2, ..., n, α t Represents the weight value of each main control factor, C t is the specific value of each main control factor, C tmin is the minimum value of each main controlling factor in the gas reservoir, C tmax is the minimum value of each main controlling factor in the gas reservoir; Step S4: Based on the drainage and production well network, a multi-objective optimization mathematical model of the drainage and production system is established, wherein the objective function of the mathematical model is shown in equations (2) to (2.2): minf(x)=[f EW ,-f EG ](2) In formula (2), f EW is the cumulative water production of all gas wells, f EG is the cumulative gas production of all gas wells, G i represents the daily gas production of the i-th gas producing well, W j represents the daily water production of the jth drainage well; The constraints are the upper and lower limits of the daily gas production of the gas production well and the upper and lower limits of the daily water production of the drainage well, as shown in formula (3): In formula (3), i represents the i-th gas producing well, i = 1, 2, ..., n, G i represents the daily gas production of the i-th gas producing well, G imin represents the minimum daily gas production of the i-th gas producing well, G imax W represents the maximum daily gas production of the i-th gas production well, j represents the j-th drainage well, j = 1, 2, ..., n, W j represents the daily water production of the jth drainage well, W jmin represents the minimum daily water production of the jth drainage well, W jmax represents the maximum daily water production of the jth drainage well; Step S5: Use a multi-objective optimization algorithm to solve the multi-objective optimization mathematical model of the drainage system, and obtain the Pareto solution set and well control parameters corresponding to different drainage system schemes.

2. The method for intelligently controlling water intrusion in gas reservoirs according to claim 1, characterized in that: The geological parameters include porosity, permeability, and water saturation; the engineering parameters include the number of gas producing wells and the well spacing; the development parameters include formation pressure and water-gas ratio; and the target parameters include cumulative gas production and cumulative water production.

3. The method for intelligently controlling water intrusion in gas reservoirs according to claim 1, characterized in that: The machine learning model in step S2 is one of random forest, GBDT, XGBoost, and LightGBM.

4. The method for intelligently controlling water intrusion in gas reservoirs according to claim 1, characterized in that: The method for ranking the importance in step S2 is the Pearson correlation coefficient method. The main control factor is an influencing factor with a correlation coefficient greater than 0.

1. The method for calculating the weight of the main control factor is: summing the correlation coefficients corresponding to each main control factor, and then dividing the correlation coefficient of each main control factor by the sum of the correlation coefficients of each main control factor, so as to obtain the weight corresponding to each main control factor.

5. The method for intelligently controlling water intrusion in gas reservoirs according to claim 1, characterized in that: The multi-objective optimization algorithm described in step S5 is one of NSGA-Ⅱ, MOPSO, and MOEA / D.

6. The method for intelligently controlling water intrusion in gas reservoirs according to claim 5, characterized in that: The performance of the multi-objective optimization algorithm and its solution set in multiple objectives are evaluated using the HV index, and the specific index is shown in formula (4): In formula (4), PS is the Pareto solution set, M is the reference point, and v is the hypercube.

7. An intelligent control device for water intrusion in gas reservoirs, characterized in that: include, processor; A storage module storing a program for intelligent control of water invasion in gas reservoirs that can be run on the processor, wherein the program for intelligent control of water invasion in gas reservoirs implements the steps described in any one of claims 1 to 6 when executed by the processor; Output module, used to output calculation results.

8. The intelligent control device for water intrusion in gas reservoirs according to claim 7 is characterized by: The processor comprises: The data set construction module is used to construct a large amount of water intrusion dynamic data including different geological factors, engineering factors, corresponding development status parameter combinations and corresponding multiple target values; Machine learning model training module, used to screen the main controlling factors affecting water intrusion dynamics and obtain the corresponding weights; The drainage well network determination module is used to construct a comprehensive evaluation model for drainage wells to determine the drainage well network; The module for constructing a multi-objective optimization mathematical model of the drainage system is used to construct a multi-objective optimization mathematical model of the drainage system including optimization variables, constraints, and optimization objectives; The well control parameter optimization module is used to solve the Pareto solution set of different schemes and the corresponding well control parameters through a multi-objective optimization algorithm.

9. A computer-readable storage medium storing a code program executable by a processor, characterized in that: The computer-readable storage medium includes a plurality of instructions, and the plurality of instructions are configured to enable a processor to execute the intelligent control method for water invasion in gas reservoirs according to any one of claims 1 to 6.

Images