Oil reservoir production optimization method and system based on structure cross grey predictive evolution

Abstract

The invention discloses an oil reservoir production optimization method and system based on structure cross grey predictive evolution. The method comprises the following steps: iteratively generating a filial generation population of an oil reservoir land in a research area based on a grey predictive evolution algorithm; calculating the predicted fitness of each filial generation in the filial generation population based on a radial basis algorithm; in each iteration, selecting a target filial generation corresponding to the optimal prediction fitness based on a greedy selection algorithm to carry out next iteration; comparing economic benefits between the water injection scheme of the target filial generation and the water injection scheme of the global optimal filial generation in each iteration, and obtaining an optimal water injection scheme of the oil reservoir of the research area by using a structure crossover algorithm according to a comparison result and the number of iterations of a grey prediction evolution algorithm; therefore, the balance between the convergence speed and the optimization effect of the proxy-assisted evolutionary algorithm can be enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of oil reservoir production optimization, and in particular to an oil reservoir production optimization method and system based on structural cross grey prediction evolution. Background Art

[0002] Water injection reservoir production is an important technical means to improve oil field recovery and extend the production life of oil fields, and has been widely used around the world. By injecting water into the reservoir, the formation pressure is maintained and the crude oil is pushed to the production well, thereby increasing the recovery rate of crude oil. Especially in the late stage of development of old oil fields, water injection technology has become an important measure to maintain production and stabilize production. In recent years, with the advancement of science and technology, water injection technology has been continuously developed and optimized, and has far surpassed the traditional single water drive technology. A combination of multiple methods has been developed to adapt to the characteristics and needs of different oil reservoirs. In terms of water quality control, modern technology ensures the quality of injected water by filtering out suspended particles and harmful substances, thereby avoiding damage to the reservoir. Reasonable water injection well layout is also key. Through precise geological exploration and reservoir simulation, the optimal location and number of water injection wells are determined to achieve the best oil recovery effect.

[0003] The application of dynamic water injection speed regulation technology makes the water injection process more flexible and efficient. By real-time monitoring of reservoir pressure and production data, the water injection speed and injection volume are adjusted to ensure the balance and stability of formation pressure and avoid water channeling. However, since the water injection efficiency is affected by many factors, including the layout of water injection wells, water injection speed and formation pressure, it becomes very difficult to dynamically achieve the optimal water injection effect under some complex geological conditions.

[0004] In addition, the application of advanced technologies such as chemical flooding and microbial flooding has further improved the water injection effect. Chemical flooding technologies include polymer flooding and surfactant flooding, which enhance oil recovery capacity by changing the oil-water interfacial tension and fluid viscosity. Microbial flooding technology uses the metabolites of specific microorganisms to change the physical and chemical properties of the reservoir and promote crude oil flow and recovery. However, although advanced technologies such as chemical flooding and microbial flooding can improve the recovery rate, their high cost also limits their widespread application.

[0005] In the context of the above-mentioned reservoir production technology, digital and intelligent technologies have been introduced to enable real-time monitoring and data analysis of oil fields, thereby optimizing water injection parameters and improving production results. Some optimization algorithms used, such as genetic algorithms, have relatively slow convergence speeds due to their random search characteristics. This may result in the algorithm taking a long time to find a better solution in the optimization problem of complex reservoirs. At the same time, in the process of reservoir production optimization, it is often necessary to perform numerical simulations on multiple schemes to evaluate their effects. However, the computational complexity of numerical simulations is usually large, especially for large and complex reservoirs, which may result in high computational costs and affect optimization efficiency.

[0006] Although various existing algorithms have shown superior performance in solving reservoir production optimization problems, for complex reservoir production optimization problems, the balance between the convergence speed and optimization effect of the agent-assisted evolutionary algorithm needs to be further strengthened. Summary of the invention

[0007] The present invention provides a reservoir production optimization method and system based on structural cross grey prediction evolution, which can strengthen the balance between the convergence speed and optimization effect of the agent-assisted evolutionary algorithm.

[0008] In a first aspect, a method for optimizing reservoir production based on structural cross grey prediction evolution is provided, comprising the following steps:

[0009] The offspring population of the oil reservoir in the study area is iteratively generated based on the grey prediction evolutionary algorithm;

[0010] Calculating the predicted fitness of each offspring in the offspring population based on a radial basis algorithm;

[0011] In each iteration, the target offspring corresponding to the best predicted fitness is selected based on the greedy selection algorithm for the next iteration;

[0012] The economic benefits of the water injection scheme of the target child generation in each iteration are compared with the water injection scheme of the global optimal child generation, and the optimal water injection scheme of the oil reservoir in the study area is obtained according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm using a structural crossover algorithm.

[0013] According to the first aspect, in a first possible implementation of the first aspect, the step of “iteratively generating a progeny population of an oil reservoir in a study area based on a grey prediction evolutionary algorithm” specifically includes the following steps:

[0014] The first three generations of offspring population The generation formula is as follows:

[0015]

[0016] The offspring population after the third generation The generation formula is as follows:

[0017] Suppose that from the three consecutive generations of offspring population X g-2 ,X g-1 ,X g Randomly select one offspring x from each r1 ,x r2 ,x r3 ;

[0018] Let d 12 =|x r1,j -xr2,j |,d 13 =|x r1,j -x r3,j |,d 23 =|x r2,j -x r3,j |;

[0019] Maxd r =max{d 12 ,d 23 ,d 13},Mind r =min{d 12 ,d 23 ,d 13};

[0020] but

[0021]

[0022] In the formula, is the jth dimension of the i-th offspring of the t-th generation population in the first three generations; is the jth dimension of the i-th offspring of the g-th generation population after the third generation; D is the dimension; up j and low j are the upper and lower bounds of the injection volume of the jth dimension respectively; rand(0,1) is a random number generated by a uniform distribution in the range [0,1]; γ is the threshold of control prediction; w, a, and b are the interference coefficient, gray development coefficient, and gray control parameter respectively.

[0023] According to the first aspect, in a second possible implementation manner of the first aspect, a calculation formula of the radial basis algorithm is as follows:

[0024]

[0025] In the formula, The predicted fitness calculated by the radial basis algorithm; ||x x -x i || and are the Euclidean norm and basis function respectively; p(x) is the linear polynomial in the dimensional variable of the feature space.

[0026] According to the first aspect, in a third possible implementation manner of the first aspect, the step of “in each iteration, selecting the target offspring corresponding to the optimal predicted fitness for the next iteration based on a greedy selection algorithm” specifically includes the following steps:

[0027] Compare the predicted fitness of each offspring between the first three generations of offspring populations and the offspring population of the current iteration after the third generation, and calculate the target offspring corresponding to the best predicted fitness for the next iteration as follows:

[0028]

[0029] In the formula, The first three generations of progeny populations; It is the offspring population after the third generation.

[0030] According to the first aspect, in a fourth possible implementation of the first aspect, the step of "comparing the economic benefits between the water injection scheme of the target child generation of each iteration and the water injection scheme of the global optimal child generation, and using the structural crossover algorithm to obtain the optimal water injection scheme for the oil reservoir in the study area according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm" specifically includes the following steps:

[0031] If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is not optimal, the structural crossover algorithm is used to generate the target water injection scheme of the current iteration, and it is judged whether the current iteration has reached the maximum number of iterations; if it has reached it, the target water injection scheme of the current iteration is used as the optimal water injection scheme; if it has not reached it, the next iteration is carried out, and the structural crossover algorithm is used to generate the target water injection scheme of the current iteration as the water injection scheme of the global optimal child generation for economic benefit comparison in the next iteration, until the optimal water injection scheme is obtained when the maximum number of iterations is reached;

[0032] If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is optimal, then determine whether the current iteration has reached the maximum number of iterations; if reached, the water injection scheme of the target child generation corresponding to the current iteration is used as the optimal water injection scheme; if not reached, proceed to the next iteration, and the water injection scheme of the target child generation corresponding to the current iteration is used as the water injection scheme of the global optimal child generation for economic benefit comparison in the next iteration, until the optimal water injection scheme is obtained when the maximum number of iterations is reached.

[0033] According to the fourth possible implementation manner of the first aspect, in the fifth possible implementation manner of the first aspect, the step of “generating a target water injection scheme for the current iteration by using a structural crossover algorithm” specifically includes the following steps:

[0034] When it is detected that the water content of one of the stages of water injection schemes of the target child generation corresponding to the current iteration is the same as that of one of the stages of water injection schemes of the global optimal child generation, and the economic benefit of one of the stages of water injection schemes corresponding to the current iteration is better, then one of the stages of water injection schemes corresponding to the current iteration is defined as the target stage water injection scheme, and one of the stages of water injection schemes of the global optimal child generation is replaced by the target stage water injection scheme, and the water injection scheme of the replaced global optimal child generation is regarded as the target water injection scheme of the current iteration.

[0035] According to the first aspect, in a sixth possible implementation manner of the first aspect, the calculation formula of the economic benefit J(x, s) is as follows:

[0036]

[0037] Where t is the time step; r0, r w and r i are oil price, water removal cost and water injection cost respectively; Q 0,t , Q w,t and Q i，t are the oil production rate of all production wells at time step t, the water production rate of all production wells at time step t, and the injection flow rate of all injection wells at time step t; b is the annual discount rate; pt is the elapsed time of the tth time step.

[0038] In the second aspect, a reservoir production optimization system based on structural cross grey prediction evolution is provided, comprising:

[0039] The offspring population generation module is used to iteratively generate offspring populations of the oil reservoirs in the study area based on the grey prediction evolutionary algorithm;

[0040] A fitness prediction module, which is in communication with the offspring population generation module and is used to calculate the predicted fitness of each offspring in the offspring population based on a radial basis function algorithm;

[0041] A greedy selection algorithm module, which is in communication connection with the fitness prediction module, and is used to select the target offspring corresponding to the best predicted fitness for the next iteration based on the greedy selection algorithm in each iteration; and

[0042] The structural crossover algorithm module is communicated with the greedy selection algorithm module, and is used to compare the economic benefits between the water injection scheme of the target child generation in each iteration and the water injection scheme of the global optimal child generation, and use the structural crossover algorithm to obtain the optimal water injection scheme for the oil reservoir in the study area according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm.

[0043] In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method for optimizing oil reservoir production based on structural cross grey prediction evolution as described above is implemented.

[0044] In a fourth aspect, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein the processor implements the reservoir production optimization method based on structural cross-grey prediction evolution as described above when running the computer program.

[0045] Compared with the prior art, the advantages of the present invention are as follows: the grey prediction evolutionary algorithm is used to perform a global search to find the optimal value with the assistance of the radial basis model algorithm, which inherits the advantages of the grey prediction evolutionary algorithm in terms of fast convergence speed and fewer parameters required, and improves its technical complexity more efficiently. At the same time, the structural crossover algorithm is combined for local adjustment, and the method of finding the optimal value is optimized, so that the economic benefits generated by the final water injection scheme are higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic flow chart of an embodiment of a method for optimizing oil reservoir production based on structural cross grey prediction evolution according to the present invention;

[0047] Figure 2 It is a schematic flow chart of another embodiment of a method for optimizing oil reservoir production based on structural cross grey prediction evolution according to the present invention;

[0048] Figure 3 It is a schematic flow chart of another embodiment of a method for optimizing oil reservoir production based on structural cross grey prediction evolution according to the present invention;

[0049] Figure 4 It is a structural schematic diagram of an oil reservoir production optimization system based on structural cross grey prediction evolution according to the present invention. DETAILED DESCRIPTION

[0050] Reference will now be made in detail to specific embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Although the present invention will be described in conjunction with specific embodiments, it will be understood that it is not intended to limit the present invention to the embodiments described. On the contrary, it is intended to cover changes, modifications and equivalents included in the spirit and scope of the present invention as defined by the appended claims. It should be noted that the method steps described herein can all be implemented by any functional block or functional arrangement, and any functional block or functional arrangement can be implemented as a physical entity or a logical entity, or a combination of the two.

[0051] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0052] Note: The example to be introduced below is only a specific example, and is not intended to limit the embodiments of the present invention to the following specific steps, values, conditions, data, sequences, etc. Those skilled in the art can apply the concept of the present invention to construct more embodiments not mentioned in this specification by reading this specification.

[0053] See also Figure 1 As shown, an embodiment of the present invention provides a reservoir production optimization method based on structural cross grey prediction evolution, comprising the following steps:

[0054] S100, iteratively generates the progeny population of the oil reservoir in the study area based on the grey prediction evolutionary algorithm;

[0055] S200, calculating the predicted fitness of each offspring in the offspring population based on a radial basis algorithm;

[0056] S300, in each iteration, selecting the target offspring corresponding to the optimal predicted fitness based on the greedy selection algorithm for the next iteration;

[0057] S400, comparing the economic benefits of the water injection scheme of the target child generation in each iteration with the water injection scheme of the global optimal child generation, and using a structural crossover algorithm to obtain the optimal water injection scheme for the oil reservoir in the study area according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm.

[0058] Specifically, in this embodiment, the present invention uses the grey prediction evolutionary algorithm to perform a global search to find the optimal value with the assistance of the radial basis model algorithm, which inherits the advantages of the grey prediction evolutionary algorithm, which has a fast convergence speed and requires fewer parameters, and improves its technical complexity more efficiently. At the same time, the structural crossover algorithm is combined for local adjustment, and the method of finding the optimal value is optimized, so that the economic benefits generated by the final water injection scheme are higher.

[0059] Preferably, in other embodiments of the present application, see also Figure 2 As shown, the step of "S100, iteratively generating a progeny population of the oil reservoir in the study area based on the grey prediction evolutionary algorithm" specifically includes the following steps:

[0060] The first three generations of offspring population The generation formula is as follows:

[0061]

[0062] The offspring population after the third generation The generation formula is as follows:

[0063] Suppose that from the three consecutive generations of offspring population X g-2 ,Xg-1 ,X g Randomly select one offspring x from each r1 ,x r2 ,x r3 ;

[0064] Let d 12 =|x r1,j -x r2,j |,d 13 =|x r1,j -x r3,j |,d 23 =|x r2,j -x r3,j |;

[0065] Maxd r =max{d 12 ,d 23 ,d 13},Mind r =min{d 12 ,d 23 ,d 13};

[0066] but

[0067]

[0068] In the formula, is the jth dimension of the i-th offspring of the t-th generation population in the first three generations; is the jth dimension of the i-th offspring of the g-th generation population after the third generation; D is the dimension; up j and low j are the upper and lower bounds of the injection volume of the jth dimension respectively; rand(0,1) is a random number generated by a uniform distribution in the range [0,1]; γ is the threshold of control prediction; w, a, and b are the interference coefficient, gray development coefficient, and gray control parameter respectively.

[0069] Specifically, in this embodiment, the generation process of the first three generations of offspring populations in the oil reservoir in the study area can be regarded as the initialization process of the grey prediction evolution algorithm GPE. Population initialization refers to randomly generating the first three generations of populations (target populations) in the feasible domain.

[0070] The generation process of the offspring population after the third generation is the experimental population, and the population sequence of three consecutive generations is regarded as a time series. Based on these three population sequences, an exponential function is constructed To predict the next generation of population.

[0071] Preferably, in another embodiment of the present application, the calculation formula of the radial basis algorithm is as follows:

[0072]

[0073] In the formula, is the predicted fitness calculated by the radial basis algorithm; ||X x -X i || and are the Euclidean norm and basis function respectively; p(x) is the linear polynomial in the dimensional variable of the feature space.

[0074] Specifically, in this embodiment, the radial basis function algorithm performs best for problems with varying degrees of nonlinearity on small-sized training data, and scales relatively well as the search dimension increases. The radial basis function model used in the present invention is in interpolation form.

[0075] Mathematically, given n input-output data pairs as follows:

[0076] (x1,f(x1)),(x2,f(x2))...,(x N ,f(x N )),x i ∈R n ,f(x i )∈R,i=1,2,,...,N,

[0077] The radial basis function interpolates this set of points using the following formula.

[0078]

[0079] ||X x -X i || and are Euclidean norm and basis function respectively; representative basis functions include cubic spline, thin plate spline, Gaussian function, linear spline and multi-quadratic spline. The present invention can be defined as The cubic spline basis function of α is used to construct the RBF model. i ∈R means to point x i The i-th weight coefficient of the cubic spline interpolation. p(x) is a linear polynomial in the dimensional variables of the feature space, satisfying Then the unknown parameters in the above equation are obtained by solving the following system.

[0080]

[0081] where the matrix Φ∈R N×N With elements ;i,j=1,2,...,N,α=(α1,α2,...,α N ) T ∈R N Represents the vector of weight coefficients. P∈RN×(d+1) is the basis function matrix of the linear polynomial p(x) at the interpolation point, c = (c1, c2, ..., c d+1 ) T ∈R d+1 is the coefficient vector of the linear polynomial p(x), F = (f(x1), f(x2), ..., f(x N )) T ∈R N Note that as long as the interpolation points are affine independent, the coefficient matrix in the above formula is non-singular.

[0082] Preferably, in another embodiment of the present application, the step of "S300, in each iteration, selecting the target offspring corresponding to the optimal predicted fitness for the next iteration based on the greedy selection algorithm" specifically includes the following steps:

[0083] Compare the predicted fitness of each offspring between the first three generations of offspring populations and the offspring population of the current iteration after the third generation, and calculate the target offspring corresponding to the best predicted fitness for the next iteration as follows:

[0084]

[0085] In the formula, The first three generations of progeny populations; It is the offspring population after the third generation.

[0086] Specifically, in this embodiment, a greedy selection mechanism / true function is used as the selection operator of GPE. and test offspring The objective function value is calculated and the better individual is selected to enter the next iterative calculation.

[0087] Preferably, in another embodiment of the present application, the step of "S400, comparing the economic benefits between the water injection scheme of the target child generation of each iteration and the water injection scheme of the global optimal child generation, and using the structural crossover algorithm to obtain the optimal water injection scheme for the oil reservoir in the study area according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm" specifically includes the following steps:

[0088] If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is not optimal, the structural crossover algorithm is used to generate the target water injection scheme of the current iteration, and it is judged whether the current iteration has reached the maximum number of iterations; if it has reached it, the target water injection scheme of the current iteration is used as the optimal water injection scheme; if it has not reached it, the next iteration is carried out, and the structural crossover algorithm is used to generate the target water injection scheme of the current iteration as the water injection scheme of the global optimal child generation for economic benefit comparison in the next iteration, until the optimal water injection scheme is obtained when the maximum number of iterations is reached;

[0089] If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is optimal, then determine whether the current iteration has reached the maximum number of iterations; if reached, the water injection scheme of the target child generation corresponding to the current iteration is used as the optimal water injection scheme; if not reached, proceed to the next iteration, and the water injection scheme of the target child generation corresponding to the current iteration is used as the water injection scheme of the global optimal child generation for economic benefit comparison in the next iteration, until the optimal water injection scheme is obtained when the maximum number of iterations is reached.

[0090] Specifically, in this embodiment, the economic benefits of the water injection scheme of the target child generation in each iteration are compared with the water injection scheme of the global optimal child generation. If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is optimal, the termination condition judgment operation is entered. If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is not optimal, the structural crossover operation is entered.

[0091] The termination condition judgment operation is specifically as follows: when the number of iterations reaches the set maximum number of iterations, the algorithm output is terminated; if the maximum number of iterations is not reached, the previous operation is continued for the next iteration.

[0092] Preferably, in other embodiments of the present application, see also Figure 3 As shown, the step of "generating the target water injection scheme of the current iteration by using the structural crossover algorithm" specifically includes the following steps:

[0093] When it is detected that the water content of one of the stages of water injection schemes of the target child generation corresponding to the current iteration is the same as that of one of the stages of water injection schemes of the global optimal child generation, and the economic benefit of one of the stages of water injection schemes corresponding to the current iteration is better, then one of the stages of water injection schemes corresponding to the current iteration is defined as the target stage water injection scheme, and one of the stages of water injection schemes of the global optimal child generation is replaced by the target stage water injection scheme, and the water injection scheme of the replaced global optimal child generation is regarded as the target water injection scheme of the current iteration.

[0094] Specifically, in this embodiment, if the economic benefit of the water injection scheme of the target child corresponding to the current iteration is optimal, it is determined whether the maximum number of iterations has been reached. If not, the next global proxy model / radial basis function construction is entered and the previous process is repeated, and the number of iterations is increased by 1. If the maximum number of iterations has been reached, the search is terminated and the optimal water injection scheme is output.

[0095] If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is not optimal, then the water injection schemes of each stage of the target child generation are compared with the water injection schemes of each stage of the global optimal child generation to check whether there is a water injection scheme for a certain stage with the same water content and the water injection scheme for this stage has better economic benefits. If so, the water injection scheme for this stage of the global optimal child generation is replaced with the target stage water injection scheme of the target child generation to generate a new water injection scheme; then determine whether the maximum number of iterations has been reached. If not, enter the next global proxy model construction and then repeat the previous process, the number of iterations is increased by 1, if the maximum number is reached, the search is terminated and the optimal water injection scheme is output. If there is no same water content, directly determine whether the maximum number of iterations has been reached. If not, enter the next global proxy model construction and then repeat the previous process, the number of iterations is increased by 1, if the maximum number is reached, the search is terminated and the optimal water injection scheme is output. The optimal water injection scheme at this time is between the water injection schemes of the global optimal child generation.

[0096] Preferably, in another embodiment of the present application, the calculation formula of the economic benefit J(x, s) is as follows:

[0097]

[0098] Where t is the time step; r0, r w and r i are oil price, water removal cost and water injection cost respectively; Q 0，t , Q w，t and Q i，t are the oil production rate of all production wells at time step t, the water production rate of all production wells at time step t, and the injection flow rate of all injection wells at time step t; b is the annual discount rate; pt is the elapsed time of the tth time step.

[0099] Finally, a synthetic reservoir model, EggModel, can be used to conduct simulation experiments, that is, to test the performance of this method in the reservoir production process. To reduce the error caused by randomness, each set of experiments was run 30 times independently. The simulation experiment set the water injection cost to $5 / barrel, the oil price to $80 / barrel, and the water removal cost to $19 / barrel.

[0100] The embodiment of the present invention also provides a reservoir production optimization system based on structural cross grey prediction evolution, comprising:

[0101] The offspring population generation module is used to iteratively generate offspring populations of the oil reservoirs in the study area based on the grey prediction evolutionary algorithm;

[0102] A fitness prediction module, which is in communication with the offspring population generation module and is used to calculate the predicted fitness of each offspring in the offspring population based on a radial basis function algorithm;

[0103] A greedy selection algorithm module, which is in communication connection with the fitness prediction module, and is used to select the target offspring corresponding to the best predicted fitness for the next iteration based on the greedy selection algorithm in each iteration; and

[0104] The structural crossover algorithm module is communicated with the greedy selection algorithm module, and is used to compare the economic benefits between the water injection scheme of the target child generation in each iteration and the water injection scheme of the global optimal child generation, and use the structural crossover algorithm to obtain the optimal water injection scheme for the oil reservoir in the study area according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm.

[0105] Therefore, the present invention uses the grey prediction evolutionary algorithm to perform a global search to find the optimal value with the assistance of the radial basis model algorithm, which inherits the advantages of the grey prediction evolutionary algorithm in that it converges quickly and requires fewer parameters, and improves its technical complexity more efficiently. At the same time, the structural crossover algorithm is combined for local adjustment, and the method of finding the optimal value is optimized, so that the economic benefits generated by the final water injection scheme are higher.

[0106] Specifically, this embodiment corresponds one-to-one to the above method embodiment, and the functions of each module have been described in detail in the corresponding method embodiment, so they will not be repeated here.

[0107] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the method steps of the above method are implemented.

[0108] The present invention implements all or part of the process in the above method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0109] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program running on the processor, and when the processor executes the computer program, all or part of the method steps in the above method are implemented.

[0110] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of a computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0111] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0112] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, servers or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0113] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), servers, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0114] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0116] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A reservoir production optimization method based on structural cross grey prediction evolution, characterized in that: The following steps are involved: The offspring population of the oil reservoir in the study area is iteratively generated based on the grey prediction evolutionary algorithm; Calculating the predicted fitness of each offspring in the offspring population based on a radial basis algorithm; In each iteration, the target offspring corresponding to the best predicted fitness is selected based on the greedy selection algorithm for the next iteration; The economic benefits of the water injection scheme of the target child generation in each iteration are compared with the water injection scheme of the global optimal child generation, and the optimal water injection scheme of the oil reservoir in the study area is obtained according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm using a structural crossover algorithm.

2. The method for optimizing oil reservoir production based on structural cross grey prediction evolution according to claim 1, characterized in that: The step of "iteratively generating a progeny population of the oil reservoir in the study area based on the grey prediction evolutionary algorithm" specifically includes the following steps: The first three generations of offspring population The generation formula is as follows: The offspring population after the third generation The generation formula is as follows: Suppose that from the three consecutive generations of offspring population X g-2 ,X g-1 ,X g Randomly select one offspring x from each r1 ,x r2 ,x r3 ; Let d 12 = |x r1,j - x r2,j |, d 13 = |x r1,j - x r3,j |, d 23 = |x r2,j - x r3,j |; Maxd r =max{d 12 ,d 23 ,d 13 },Mind r =min{d 12 ,d 23 ,d 13 }; but In the formula, is the jth dimension of the i-th offspring of the t-th generation population in the first three generations; is the jth dimension of the i-th offspring of the g-th generation population after the third generation; D is the dimension; up j and low j are the upper and lower bounds of the injection volume of the jth dimension respectively; rand(0,1) is a random number generated by a uniform distribution in the range [0,1]; γ is the threshold of control prediction; w, a, and b are the interference coefficient, gray development coefficient, and gray control parameter respectively.

3. The method for optimizing oil reservoir production based on structural cross grey prediction evolution according to claim 1, characterized in that: The calculation formula of the radial basis algorithm is as follows: In the formula, The predicted fitness calculated by the radial basis algorithm; ||x x -x i || and are the Euclidean norm and basis function respectively; p(x) is the linear polynomial in the dimensional variable of the feature space.

4. The method for optimizing oil reservoir production based on structural cross grey prediction evolution according to claim 1, characterized in that: The step of "selecting the target offspring corresponding to the optimal predicted fitness for the next iteration based on the greedy selection algorithm in each iteration" specifically includes the following steps: Compare the predicted fitness of each offspring between the first three generations of offspring populations and the offspring population of the current iteration after the third generation, and calculate the target offspring corresponding to the best predicted fitness for the next iteration as follows: In the formula, The first three generations of progeny populations; It is the offspring population after the third generation.

5. The method for optimizing oil reservoir production based on structural cross grey prediction evolution according to claim 1, characterized in that: The step of "comparing the economic benefits of the water injection scheme of the target child generation in each iteration with the water injection scheme of the global optimal child generation, and using the structural crossover algorithm to obtain the optimal water injection scheme for the oil reservoir in the study area according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm" specifically includes the following steps: If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is not optimal, the structural crossover algorithm is used to generate the target water injection scheme of the current iteration, and it is judged whether the current iteration has reached the maximum number of iterations; if it has reached it, the target water injection scheme of the current iteration is used as the optimal water injection scheme; if it has not reached it, the next iteration is carried out, and the structural crossover algorithm is used to generate the target water injection scheme of the current iteration as the water injection scheme of the global optimal child generation for economic benefit comparison in the next iteration, until the optimal water injection scheme is obtained when the maximum number of iterations is reached; If the economic benefit of the water injection scheme of the target child generation corresponding to the current iteration is optimal, then determine whether the current iteration has reached the maximum number of iterations; if reached, the water injection scheme of the target child generation corresponding to the current iteration is used as the optimal water injection scheme; if not reached, proceed to the next iteration, and the water injection scheme of the target child generation corresponding to the current iteration is used as the water injection scheme of the global optimal child generation for economic benefit comparison in the next iteration, until the optimal water injection scheme is obtained when the maximum number of iterations is reached.

6. The method for optimizing oil reservoir production based on structural cross grey prediction evolution according to claim 5, characterized in that: The step of "generating the target water injection scheme of the current iteration by using the structural crossover algorithm" specifically includes the following steps: When it is detected that the water content of one of the stages of water injection schemes of the target child generation corresponding to the current iteration is the same as that of one of the stages of water injection schemes of the global optimal child generation, and the economic benefit of one of the stages of water injection schemes corresponding to the current iteration is better, then one of the stages of water injection schemes corresponding to the current iteration is defined as the target stage water injection scheme, and one of the stages of water injection schemes of the global optimal child generation is replaced by the target stage water injection scheme, and the water injection scheme of the replaced global optimal child generation is regarded as the target water injection scheme of the current iteration.

7. The method for optimizing oil reservoir production based on structural cross grey prediction evolution according to any one of claims 1, 5 and 6, characterized in that: The calculation formula of the economic benefit J(x, s) is as follows: Where t is the time step; r0, r w and r i are oil price, water removal cost and water injection cost respectively; Q 0，t , Q w，t and Q i，t are the oil production rate of all production wells at time step t, the water production rate of all production wells at time step t, and the injection flow rate of all injection wells at time step t; b is the annual discount rate; pt is the elapsed time of the tth time step.

8. A reservoir production optimization system based on structural cross grey prediction evolution, characterized in that: include: The offspring population generation module is used to iteratively generate offspring populations of the oil reservoirs in the study area based on the grey prediction evolutionary algorithm; A fitness prediction module, which is in communication with the offspring population generation module and is used to calculate the predicted fitness of each offspring in the offspring population based on a radial basis function algorithm; A greedy selection algorithm module, which is in communication connection with the fitness prediction module, and is used to select the target offspring corresponding to the best predicted fitness for the next iteration based on the greedy selection algorithm in each iteration; and The structural crossover algorithm module is communicated with the greedy selection algorithm module, and is used to compare the economic benefits between the water injection scheme of the target child generation in each iteration and the water injection scheme of the global optimal child generation, and use the structural crossover algorithm to obtain the optimal water injection scheme for the oil reservoir in the study area according to the comparison results and the number of iterations of the grey prediction evolutionary algorithm.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for optimizing oil reservoir production based on structural cross grey prediction evolution as claimed in any one of claims 1 to 7 is implemented.

10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor runs the computer program, the method for optimizing oil reservoir production based on structural cross grey prediction evolution as described in any one of claims 1 to 7 is implemented.

Images