Method for determining optimal layer series combination and related device

Abstract

The invention discloses a method for determining an optimal layer series combination and a related device. The method comprises the steps that a plurality of layer series combinations are obtained according to the layer number of each oil layer and serve as an initial population, and the fitness value of each layer series combination in the initial population is calculated; calculating the selection probability of each layer series combination according to the fitness value of each layer series combination, screening and reserving a preset number of layer series combinations from the initial population according to the selection probability, performing cross processing and variation processing on the screened layer series combinations to generate a next-generation population, calculating the fitness value of each layer series combination in the next-generation population, repeatedly executing the step of generating a next-generation population according to the fitness value of each layer series combination until an iteration termination condition is met, and terminating iteration; and after the iteration is terminated, determining an optimal layer series combination from the initial population and the layer series combination of the next generation population generated in the iteration process. And layer series division can be efficiently and accurately carried out on an oil layer.

Description

Technical Field

[0001] The invention relates to the technical field of oil production technology, and in particular to a method for determining an optimal layer combination and a related device. Background Art

[0002] Layered sandstone reservoirs are often subdivided into many small layers vertically, and the heterogeneity between layers is strong. After years of water injection development and entering the high water cut period, the single-layer breakthrough and interlayer interference of layered sandstone reservoirs are very serious, the oil recovery efficiency and recovery degree of each layer vary greatly, and the interlayer and plane residual oil are unevenly distributed, resulting in the development effect getting worse year by year. Strata reorganization and optimization plays an important role in reducing the interlayer differences of such reservoirs, improving the degree of water injection control and the degree of oil layer utilization. It is one of the important measures to solve the interlayer contradictions of water-driven sandstone reservoirs in the high water cut period, improve the effect of water injection development and increase the recovery rate.

[0003] At present, the methods for formulating stratum reorganization plans include conventional reservoir engineering methods, reservoir numerical simulation methods and other mathematical methods. At this stage, each method has certain limitations. For example, conventional reservoir engineering methods mainly analyze the feasibility of stratum combination from aspects such as production degree, interlayer, fluid properties and remaining reserves. The method is relatively fast, but the determined stratum combination plan is single, and it is difficult to distinguish and compare the effects of various combinations, and the decision makers are more influenced by subjective factors. Although the reservoir numerical simulation method can comprehensively consider many factors that affect the development effect after stratum combination, and can compare a variety of stratum combination methods, it is time-consuming and greatly affects work efficiency. Most other mathematical methods can only analyze some parameters, with relatively low accuracy, and are not suitable for widespread trial. Therefore, there is an urgent need for a method with high accuracy, high efficiency and the ability to select the best from a variety of stratum combination methods. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a method for determining an optimal layer combination and a related device that overcomes the above problems or at least partially solves the above problems.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining an optimal layer combination, comprising:

[0006] According to the layer numbers of each oil layer, a plurality of layer combinations are obtained as the initial population, and the fitness value of each layer combination in the initial population is calculated; the layer combination includes a plurality of layers, and the layer includes a plurality of layer numbers;

[0007] According to the fitness value of each layer combination, the selection probability of each layer combination is calculated; according to the selection probability, a preset number of layer combinations are screened and retained from the initial population; crossover processing and mutation processing are performed on each screened layer combination to generate a next generation population; the fitness value of each layer combination in the next generation population is calculated; the step of generating the next generation population according to the fitness value of each layer combination is repeatedly performed until an iteration termination condition is met, and then the iteration is terminated;

[0008] After the iteration is terminated, the optimal layer combination is determined from the layer combinations of the initial population and the next generation population generated by the iteration process.

[0009] In one embodiment, the main controlling factor of the oil layer is at least one physical property characteristic of the oil layer;

[0010] The fitness value of the layer combination is determined by the following method:

[0011] According to the data of each main controlling factor of each oil layer, the first variance of each main controlling factor corresponding to each layer in the layer combination is calculated respectively, and the first variance represents the difference between the oil layers corresponding to each layer number in the same layer in the layer combination;

[0012] According to the data of each main controlling factor of each oil layer, the number of layers in the layer combination, and the number of horizons of each layer in the layer combination, the second variance of each main controlling factor corresponding to the layer combination is calculated respectively, and the second variance represents the difference in the oil layers corresponding to the horizon numbers between different layers in the layer combination;

[0013] According to the first variance of each main controlling factor corresponding to each layer system and the second variance of each main controlling factor corresponding to the layer system combination, the fitness value of the layer system combination is calculated, and the fitness value represents the excellence of the layer system combination.

[0014] In one embodiment, the first variance of the main controlling factor corresponding to the layer system is determined by:

[0015] According to the data of the main controlling factors of the oil layers corresponding to the layer numbers in the layer system and the number of layers in the layer system, the standard deviation of the main controlling factors in the layer system is calculated as the first variance of the main controlling factors corresponding to the layer system.

[0016] In one embodiment, the second variance of the main controlling factor corresponding to the layer combination is determined by:

[0017] According to the data of the main controlling factors of each oil layer, taking each layer in the layer combination as a unit, respectively calculating the average value of the main controlling factors of the oil layer corresponding to each layer number in the unit as the data of the main controlling factors corresponding to each layer;

[0018] According to the data of the main controlling factors corresponding to each layer system and the number of layers in the layer system combination, the standard variance of the main controlling factors in the layer system combination is calculated as the second variance of the main controlling factors corresponding to the layer system combination.

[0019] In one embodiment, the calculating the fitness value of the layer combination includes:

[0020] According to the first variance of each main controlling factor corresponding to each layer in the layer combination and the number of layers in the layer combination, the average value of the first variance of each main controlling factor corresponding to each layer is calculated;

[0021] According to the second variance of each main control factor corresponding to the layer combination and the average value of the first variance of each main control factor corresponding to each layer in the layer combination, the fitness value of the layer combination is calculated using the following formula:

[0022]

[0023] In the above formula, σ represents the fitness value of the layer combination, q represents the qth main control factor, λ1 represents the weight coefficient of the average value of the first variance of the layer in the layer combination corresponding to the qth main control factor, and λ2 represents the weight coefficient of the second variance of the qth main control factor corresponding to the layer combination. represents the average value of the first variance of the qth main controlling factor in the layer combination, σ qg It represents the second variance of the qth main controlling factor corresponding to the layer combination.

[0024] In one embodiment, the step of calculating the selection probability of each layer combination according to the fitness value of each layer combination includes:

[0025] Calculating the selection probability of each layer combination according to the fitness value of each layer combination in the initial population and the number of layer combinations in the initial population;

[0026] The selected layer combinations are cross-processed, including:

[0027] Using a single-point crossover operator, each layer in the screened layer combination is cross-processed according to the pre-set crossover probability;

[0028] Accordingly, the selected layer combinations are subjected to mutation processing, including:

[0029] The single-point mutation algorithm is used to mutate the layer combination after crossover processing to generate the next generation population.

[0030] In one embodiment, the main controlling factor is determined by:

[0031] Obtain data on the stratigraphic division factors of each oil layer;

[0032] According to the number of layers of the oil layer and the data of the layer division factors of each oil layer, a first matrix is ​​constructed, and the first matrix is ​​standardized; a covariance matrix of the first matrix after the standardization is calculated, and the eigenvalues ​​of the covariance matrix are calculated, and the contribution rate of each layer division factor is calculated according to the eigenvalues;

[0033] According to the order of contribution rate, a preset number of layer division factors starting from the maximum contribution rate are selected as the determined main controlling factors.

[0034] In one embodiment, the iteration termination condition is that the number of iterations is greater than or equal to a preset iteration number threshold;

[0035] After the iteration is terminated, the optimal layer combination is determined from the layer combinations of the initial population and all next generation populations generated by the iteration process, including:

[0036] In order of fitness values, a preset number of layer combinations starting from the highest fitness value are selected from the layer combinations of the initial population and the next generation population generated by the iterative process as the determined optimal layer combination.

[0037] In a second aspect, an embodiment of the present invention provides a device for determining an optimal layer combination, comprising:

[0038] The fitness value calculation module is used to obtain a plurality of stratum combinations according to the stratum numbers of each oil layer as the initial population, and calculate the fitness value of each stratum combination in the initial population; the stratum combination includes a plurality of stratums, and the stratums include a plurality of stratum numbers;

[0039] A generation module is used to calculate the selection probability of each layer combination according to the fitness value of each layer combination, screen and retain a preset number of layer combinations from the initial population according to the selection probability, perform crossover processing and mutation processing on each screened layer combination, generate a next generation population, calculate the fitness value of each layer combination in the next generation population, and repeatedly perform the step of generating the next generation population according to the fitness value of each layer combination until the iteration termination condition is met, then the iteration is terminated;

[0040] The determination module is used to determine the optimal layer combination from the layer combination of the initial population and the next generation population generated by the iteration process after the iteration is terminated.

[0041] In a third aspect, an embodiment of the present invention provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and when the computer executable instructions are executed by a processor, the above-mentioned method for determining the optimal layer system combination is implemented;

[0042] In a fourth aspect, an embodiment of the present invention provides a terminal device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for determining the optimal layer combination when executing the program.

[0043] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0044] The method for determining the optimal stratum combination provided in the embodiment of the present invention obtains several stratum combinations according to the stratum number of each oil layer to form an initial population, calculates the fitness value of each stratum combination in the initial population, calculates the selection probability of each stratum combination according to the fitness value, screens out a preset number of stratum combinations from the initial population and retains them according to the selection probability, performs crossover processing and mutation processing on each screened stratum combination to generate a next generation population, repeats the step of generating the next generation population until the iteration termination condition is met, then the iteration terminates, and determines the optimal stratum combination from the stratum combinations of the initial population and the next generation population generated by the iteration process. In the embodiment of the present invention, a genetic algorithm is used to reorganize and optimize several stratum combinations in each population, thereby expanding the possibility of more stratum combinations, avoiding the problem of relying on the experience of professionals in the prior art, improving the accuracy of the obtained optimal stratum combination of high water-cut oilfields, greatly shortening the cycle of studying the optimal stratum combination of oilfields, overcoming the problem of long time consumption in the prior art, improving the efficiency of calculating the optimal stratum combination, and providing a basis for guiding the fine development of oilfield water injection in the later stage.

[0045] In addition, according to the geological and fluid characteristics of each layer of the oil field and parameters such as development indicators, the principal component analysis method is used to select the main controlling factors from several layer division factors that affect the layer combination results. According to the data of the main controlling factors, the fitness value of the layer combination is calculated, which reduces noise data, improves the accuracy of the fitness value of the layer combination, and further improves the accuracy of the determined optimal layer combination.

[0046] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0047] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0049] Figure 1a One of the flow charts of the method for determining the optimal layer combination in an embodiment of the present invention;

[0050] Figure 1b This is the second flow chart of the method for determining the optimal layer combination in an embodiment of the present invention;

[0051] Figure 2 is a flow chart of a method for determining a main control factor in an embodiment of the present invention;

[0052] Figure 3 One of the flow charts for calculating the fitness value of a layer combination in an embodiment of the present invention;

[0053] Figure 4 This is the second flow chart of calculating the fitness value of a layer combination in an embodiment of the present invention;

[0054] Figure 5 A flowchart of generating the next generation population in an embodiment of the present invention;

[0055] Figure 6 Schematic diagram of the structure of the device for determining the optimal layer combination in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0057] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a method for determining an optimal layer combination and a related device.

[0058] Example

[0059] The embodiment of the present invention provides a method for determining an optimal layer combination, the process of which is as follows: Figure 1a and 1b As shown, the following steps are included:

[0060] Step S101: according to the layer numbers of each oil layer, a plurality of layer combinations are obtained as the initial population, and the fitness value of each layer combination in the initial population is calculated; the layer combination includes a plurality of layer systems, and the layer system includes a plurality of layer numbers;

[0061] Step S102: Calculate the selection probability of each layer combination according to the fitness value of each layer combination, select and retain a preset number of layer combinations from the initial population according to the selection probability, perform crossover processing and mutation processing on each selected layer combination, generate the next generation population, calculate the fitness value of each layer combination in the next generation population, and repeat the step of generating the next generation population according to the fitness value of each layer combination until the iteration termination condition is met, then terminate the iteration;

[0062] Step S103: After the iteration is terminated, the optimal layer combination is determined from the layer combinations of the initial population and the next generation population generated by the iteration process.

[0063] In order to facilitate the understanding of this solution, the oil layer corresponding to the layer number in the stratum system is called a small layer in the embodiment of the present invention. For example, an oil field has 10 layers, that is, 10 small layers, and the layer numbers of the oil layers are L1, L2, L3...L10, then the oil layer corresponding to L1 is the first small layer, and the oil layer corresponding to L2 is the second small layer. A specific example is used to illustrate: taking the total number of small layers as 10 and the division layer coefficient as 3 as an example, a randomly generated stratum system combination is shown in the following Table 1:

[0064] Table 1:

[0065] L1 L2 L3 L4 L5 L6 L7 L8 L9 L10 Layer 1 1 1 1 0 0 0 0 0 0 0 Layer 2 0 0 0 1 1 1 1 0 0 0 Layer 3 0 0 0 0 0 0 0 1 1 1

[0066] “1” indicates that the layer is included in the layer system, and “0” indicates that the layer is not included in the layer system, which is the encoding method of the genetic algorithm in step S102.

[0067] In some optional embodiments, the oil field has multiple physical properties such as permeability and porosity, each oil layer has these physical properties, and the data of the same physical property of different oil layers may be different, such as Figure 2 As shown, the main controlling factors are determined in the following way:

[0068] Step S201: obtaining data of stratum division factors of each oil layer;

[0069] The stratum division factors are the physical properties of the oil field that affect the stratum combination results. Optionally, the stratum division factors include permeability, porosity, effective thickness, geological reserves, oil-bearing area, recovery degree, water content, remaining oil saturation, remaining reserves, the proportion of remaining reserves to total reserves, well section length, etc. The embodiments of the present invention will not enumerate them one by one.

[0070] Step S202: constructing a first matrix according to the number of layers of the oil layer and the data of the layer division factors of each oil layer, and performing standardization on the first matrix; calculating the covariance matrix of the first matrix after standardization, and calculating the eigenvalue of the covariance matrix, and calculating the contribution rate of each layer division factor according to the eigenvalue;

[0071] Step S203: selecting a preset number of layer division factors starting from the maximum contribution rate in the order of contribution rate as the determined main control factors.

[0072] Multiple stratum division factors, that is, multiple indicators that affect stratum division, are screened out from the multiple stratum division factors through principal component analysis, as the main controlling factors, namely, principal components.

[0073] In the above step S202, the first matrix is ​​an n*m matrix, where n is the number of oil layers in the oil field, and m is the number of layer division factors. The constructed first matrix is ​​as follows:

[0074]

[0075] Where A is the first matrix, and a is an element in matrix A, for example, a 11 is the data of the first layer of the first stratum division factor, a n1 The first stratification factor is the data in the nth sub-layer.

[0076] Then, the first matrix A is normalized to obtain the processed matrix B, as shown below:

[0077]

[0078] Where b is an element in the matrix B. For example, the matrix A is normalized by the following formula:

[0079]

[0080] In formula (1), b ij represents the element in the i-th row and j-th column of the B matrix, represents the column mean of the jth column in matrix A, V j represents the sample difference of matrix A;

[0081] Specifically, the column mean of the j-th column in matrix A is calculated using the following formula:

[0082]

[0083] In formula (2), n represents the number of oil layers, a ij Represents the element in the i-th row and j-th column of matrix A.

[0084] The sample difference of matrix A is calculated using the following formula:

[0085]

[0086] The parameters in formula (3) have been explained above and will not be described in detail in the embodiment of the present invention.

[0087] Then, using the following formula, we get the covariance matrix of matrix B, as shown below:

[0088]

[0089] Among them, the element c in the matrix C ij is the element in the i-th row and j-th column of matrix C,

[0090]

[0091] In formula (5), k represents a positive integer from 1 to n;

[0092] In the above step S202, the eigenvalue β of the matrix C is calculated. It should be noted that each layer division factor corresponds to an eigenvalue β. The eigenvalue β corresponding to each layer division factor is arranged in order from large to small. The sorting result is as follows:

[0093] β1≥β2≥…≥β M ;

[0094] Among them, β M is the eigenvalue ranked Mth in value, and the values ​​of M and m are the same;

[0095] Then, according to the corresponding characteristic values ​​of each stratum division factor, the contribution rate of each stratum division factor is calculated by the following formula:

[0096]

[0097] In formula (6), u i Represents β i The contribution rate of the corresponding layer division factor and other parameters in formula (6) have been explained in the foregoing, and will not be repeated here in the embodiment of the present invention.

[0098] The contribution rate of each stratum division factor is added up to obtain the cumulative contribution rate through the following formula:

[0099]

[0100] The parameters in formula (7) have been described above and will not be described in detail in the embodiment of the present invention.

[0101] Then, based on the M eigenvalues ​​calculated above, the eigenvector corresponding to each eigenvalue of the matrix C is calculated as follows:

[0102]

[0103] Among them, the eigenvector d1 corresponds to the eigenvalue β1, the eigenvector d2 corresponds to the eigenvalue β2, and so on, which will not be described in detail in the embodiment of the present invention.

[0104] Based on the cumulative contribution rate calculated above, the first, second, ..., and rth (r≤M) stratum partitioning factors corresponding to the eigenvalues ​​with cumulative contribution rates exceeding 80% are selected to obtain r principal components (principal components are main controlling factors), as shown below:

[0105]

[0106] Among them, the i-th principal component: H i＝ d 1i b1+d 2i b2+…+d mi b m (i=1, 2, ..., r);

[0107] In some optional embodiments, the main controlling factor of the oil layer is at least one physical property of the oil layer; in the above step S101, the fitness value of the layer combination, such as Figure 3 As shown, it can be determined by the following method:

[0108] Step S301: According to the data of each main controlling factor of each oil layer, the first variance of each main controlling factor corresponding to each layer in the layer combination is calculated respectively, and the first variance represents the difference between the oil layers corresponding to each layer number in the same layer in the layer combination.

[0109] The first variance of the main controlling factor can also be called the intra-stratum variance of the main controlling factor.

[0110] Step S302: According to the data of each main controlling factor of each oil layer, the number of layers in the layer combination, and the number of layers of each layer in the layer combination, the second variance of each main controlling factor corresponding to the layer combination is calculated respectively, and the second variance represents the difference in the oil layers corresponding to the layer numbers between different layers in the layer combination.

[0111] The second variance of the main controlling factor can also be called the inter-stratum variance of the main controlling factor.

[0112] Step S303: Calculate the fitness value of the layer combination according to the first variance of each main controlling factor corresponding to each layer and the second variance of each main controlling factor corresponding to the layer combination, where the fitness value represents the excellence of the layer combination.

[0113] In some optional embodiments, in the above step S301, the first variance of the main controlling factor corresponding to the layer system is determined by:

[0114] According to the data of the main controlling factors of the oil layers corresponding to the layer numbers in the layer system and the number of layers in the layer system, the standard deviation of the main controlling factors in the layer system is calculated as the first variance of the main controlling factors corresponding to the layer system.

[0115] Specifically, the first variance of the main controlling factor corresponding to the stratum is calculated by the following formula, that is, the intra-stratum variance of the main controlling factor corresponding to each stratum:

[0116]

[0117] In the above formula, σ qli represents the first variance of the main controlling factor corresponding to the stratum, i represents the i-th stratum in the stratum combination, n represents the number of layers in the stratum, q represents the q-th main controlling factor, j represents the j-th layer of the i-th stratum, q ij represents the data of the jth layer of the qth main controlling factor in the i-th layer system, q ia It represents the average value of the qth main controlling factor in the i-th layer.

[0118] Among them, the average value of the qth main control factor in the i-th layer is calculated by the following formula:

[0119]

[0120] The parameters in formula (9) have been described above and will not be described in detail in the embodiment of the present invention.

[0121] In some optional embodiments, in the above step S302, the second variance of the main controlling factor corresponding to the layer combination is determined by:

[0122] (1) Based on the data of the main controlling factors of each oil layer, taking each layer in the layer combination as a unit, the average value of the main controlling factors of the oil layer corresponding to each layer number in the unit is calculated respectively as the data of the main controlling factors corresponding to each layer;

[0123] Specifically, the data of the main controlling factors corresponding to each layer system are calculated according to the following formula:

[0124]

[0125] In formula (10), S represents the number of layers in the layer combination, q a represents the qth main controlling factor in the S layers ia The average value of .

[0126] (2) Based on the data of the main controlling factors corresponding to each layer system and the number of layers in the layer system combination, the standard deviation of the main controlling factors in the layer system combination is calculated as the second variance of the main controlling factors corresponding to the layer system combination.

[0127] Specifically, according to the following formula, the second variance of the main controlling factor corresponding to the layer combination is:

[0128]

[0129] In formula (11), σ qg It represents the second variance of the main controlling factor corresponding to the layer combination.

[0130] In some optional embodiments, the above step S303, calculating the fitness value of the layer combination, as shown in 4, can be implemented in the following way:

[0131] Step S401: Calculate the average value of the first variance of each main controlling factor corresponding to each layer in the layer combination according to the first variance of each main controlling factor corresponding to each layer in the layer combination and the number of layers in the layer combination;

[0132] Specifically, the following formula is used to calculate the average value of the first variance of each main controlling factor in each layer system;

[0133]

[0134] In formula (12), It represents the average value of the first variance of each main control factor. Other parameters have been described in the foregoing, and will not be repeated here in the embodiment of the present invention.

[0135] Based on the principle of layer reorganization, it is hoped that the intra-layer variance of each main control factor is as small as possible, and the inter-layer variance is as large as possible, that is, The smaller the better, σ qg The bigger the better, in other words, It represents the average value of the variance of the qth main controlling factor in the same stratum, and represents the difference between the oil layers corresponding to the layer numbers in the same stratum. The smaller the value of , the smaller the difference between the oil layers in the same formation. qg It represents the variance of the qth main controlling factor between different strata in a stratum combination, which characterizes the difference of oil layers corresponding to each layer number between different strata, so σ qg The larger the value is, the greater the difference between the oil layers in different strata.

[0136] Specifically, the following formula is used to Perform normalization:

[0137]

[0138] Step S402: According to the second variance of each main controlling factor corresponding to the layer combination and the average value of the first variance of each main controlling factor corresponding to each layer in the layer combination, the fitness value of the layer combination is calculated using the following formula:

[0139]

[0140] In formula (12), σ represents the fitness value of the layer combination, q represents the qth main control factor, λ1 represents the weight coefficient of the average value of the first variance of the layer in the layer combination corresponding to the qth main control factor, λ2 represents the weight coefficient of the second variance of the qth main control factor corresponding to the layer combination, and α q represents the weight coefficient of the qth main control factor. Other parameters have been described in the foregoing and will not be repeated here in the embodiment of the present invention.

[0141] Among them, the sum of λ1 and λ2 is 1,

[0142] In some optional embodiments, the following parameters are pre-set: 1) population size G, i.e., the number of layer combinations in the population; 2) the total number of divided layers S; 3) the number of chromosomes N, i.e., the total number of small layers; 4) the termination evolution generation T, i.e., the maximum number of iterations; 5) the crossover probability P c ; 6) Mutation probability P m In the above step S102, according to the fitness value of each layer combination, the selection probability of each layer combination is calculated. According to the selection probability, a preset number of layer combinations are screened and retained from the initial population, and the screened layer combinations are crossover processed and mutated respectively to generate the next generation population. Figure 5 As shown, this can be achieved by:

[0143] Step S501: Calculate the selection probability of each layer combination according to the fitness value of each layer combination in the initial population and the number of layer combinations in the initial population, and select and retain a preset number of layer combinations from the initial population according to the selection probability;

[0144] Specifically, the selection probability of the layer combination is calculated according to the following formula:

[0145]

[0146] In formula (14), G represents the number of layer combinations in the population.

[0147] There are many ways to screen out a preset number of layer combinations based on the selection probability. For example, a random number between [0,1] is randomly generated as a selection operator. From each layer combination of the initial population, the layer combination with a selection probability greater than the selection operator is screened out. It is determined whether the number of the screened layer combinations is consistent with the number of layer combinations in the initial population. If so, the screened layer combination is used as the parent of the next crossover process. If not, a selection operator is generated again. From each layer combination of the initial population, the layer combination with a selection probability greater than the second selection operator is screened out. The layer combination screened twice is determined. Is the number of layer combinations consistent with the number of layer combinations in the initial population? If so, the layer combinations screened out twice are used as the parents of the next crossover process. If not, continue to generate selection operators and screen layer combinations according to the selection operator until the number of all layer combinations screened out is consistent with the number of layer combinations in the initial population. Then, no more selection operators are randomly generated and all the screened layer combinations are used as the parents of the next crossover process. Let's use a specific example to illustrate: for example, there are 5 layer combinations in the initial population: ABCDE. After calculation, the selection probability of these 5 layers is shown in Table 2 below:

[0148] Table 2:

[0149] Layer combination A B C D E Selection probability 0.73 0.85 0.58 0.32 0.21

[0150] The first time a selection operator is randomly generated, for example, if it is 0.8, then B is selected and 1 layer combination is screened out, which is less than 5; the second time a selection operator is randomly generated, for example, if it is 0.7, then B and A are selected, and the layer combination screened out twice is BBA, which is 3, which is less than 5, then the third time a selection operator is randomly generated, for example, if it is 0.71, then B and A are selected, and the layer combination screened out three times is BBABA, which is 5, which is the same as the number of layer combinations in the initial population, then no more selection operators are generated and the selection ends.

[0151] The embodiment of the present invention does not limit the method of screening and retaining a preset number of layer combinations from the initial population according to the selection probability.

[0152] Step S502: using a single-point crossover operator to perform crossover processing on each layer in the screened layer combination according to a preset crossover probability;

[0153] The selected G layer combinations are paired randomly between each other, a crossover position is randomly selected, and then the crossover probability P is set. c Mutual pairing is performed at this crossover position.

[0154] Step S503: using a single-point mutation algorithm to perform mutation processing on each layer combination after the crossover processing to generate the next generation population.

[0155] Randomly select the mutation position; randomly generate the comparison probability, if the comparison probability is less than the mutation probability P m , then 1 changes to 0 or 0 changes to 1 at the mutation position. It should be noted that if a small layer changes from 1 to 0, then the layer changes from 0 to 1 in some other layer system. Similarly, if a layer changes from 0 to 1, then the layer must change from 1 to 0 in some other layer system.

[0156] In some optional embodiments, the iteration termination condition is that the number of iterations is greater than or equal to a preset iteration number threshold. After the iteration is terminated, the optimal layer combination can be determined in the following manner:

[0157] In order of fitness values, from the layer combinations of the initial population and the next generation population generated by the iterative process (including the layer combinations of the next generation population generated in each iteration during the iterative process, that is, the layer combinations of all next generation populations generated in the iterative process), select a preset number of layer combinations starting from the highest fitness value as the determined optimal layer combination; for example, the layer combination with the highest fitness value can be selected as the determined optimal layer combination, optionally, 10 layer combinations starting from the highest fitness value are selected as the determined optimal layer combination, and this embodiment of the present invention is not limited to this.

[0158] Based on the same inventive concept, the embodiment of the present invention also provides a device for determining an optimal layer combination, the structure of which is as follows: Figure 6 As shown, including:

[0159] The fitness value calculation module 601 is used to obtain a plurality of stratum combinations according to the stratum numbers of each oil layer as the initial population, and calculate the fitness value of each stratum combination in the initial population; the stratum combination includes a plurality of stratum systems, and the stratum system includes a plurality of stratum number;

[0160] The generation module 602 is used to calculate the selection probability of each layer combination according to the fitness value of each layer combination, screen and retain a preset number of layer combinations from the initial population according to the selection probability, perform crossover processing and mutation processing on each screened layer combination, generate the next generation population, calculate the fitness value of each layer combination in the next generation population, and repeatedly perform the step of generating the next generation population according to the fitness value of each layer combination until the iteration termination condition is met, then the iteration is terminated;

[0161] The determination module 603 is used to determine the optimal layer combination from the layer combination of the initial population and the next generation population generated by the iteration process after the iteration is terminated.

[0162] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0163] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are executed by a processor, the above-mentioned method for determining the optimal layer combination is implemented.

[0164] Based on the same inventive concept, an embodiment of the present invention also provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for determining the optimal layer combination when executing the program.

[0165] Unless otherwise specifically stated, terms such as processing, computing, calculating, determining, displaying, etc. may refer to the actions and / or processes of one or more processing or computing systems, or similar devices, which operate and convert data represented as physical (e.g., electronic) quantities within registers or memories of a processing system into other data similarly represented as physical quantities within memories, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0166] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0167] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0168] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0169] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0170] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0171] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A method for determining an optimal layer combination, characterized in that: include: According to the layer numbers of each oil layer, a plurality of layer combinations are obtained as the initial population, and the fitness value of each layer combination in the initial population is calculated; the layer combination includes a plurality of layers, and the layer includes a plurality of layer numbers; According to the fitness value of each layer combination, the selection probability of each layer combination is calculated; according to the selection probability, a preset number of layer combinations are screened and retained from the initial population; crossover processing and mutation processing are performed on each screened layer combination to generate a next generation population; the fitness value of each layer combination in the next generation population is calculated; the step of generating the next generation population according to the fitness value of each layer combination is repeatedly performed until an iteration termination condition is met, and then the iteration is terminated; After the iteration is terminated, the optimal layer combination is determined from the layer combinations of the initial population and the next generation population generated by the iteration process.

2. The method according to claim 1, characterized in that The main controlling factor of the oil layer is at least one physical property characteristic of the oil layer; The fitness value of the layer combination is determined by the following method: According to the data of each main controlling factor of each oil layer, the first variance of each main controlling factor corresponding to each layer in the layer combination is calculated respectively, and the first variance represents the difference between the oil layers corresponding to each layer number in the same layer in the layer combination; According to the data of each main controlling factor of each oil layer, the number of layers in the layer combination, and the number of horizons of each layer in the layer combination, the second variance of each main controlling factor corresponding to the layer combination is calculated respectively, and the second variance represents the difference in the oil layers corresponding to the horizon numbers between different layers in the layer combination; According to the first variance of each main controlling factor corresponding to each layer system and the second variance of each main controlling factor corresponding to the layer system combination, the fitness value of the layer system combination is calculated, and the fitness value represents the excellence of the layer system combination.

3. The method according to claim 2, characterized in that The first variance of the main controlling factor corresponding to the stratum is determined in the following way: According to the data of the main controlling factors of the oil layers corresponding to the layer numbers in the layer system and the number of layers in the layer system, the standard deviation of the main controlling factors in the layer system is calculated as the first variance of the main controlling factors corresponding to the layer system.

4. The method according to claim 2, characterized in that The second variance of the main controlling factor corresponding to the layer combination is determined in the following way: According to the data of the main controlling factors of each oil layer, taking each layer in the layer combination as a unit, respectively calculating the average value of the main controlling factors of the oil layer corresponding to each layer number in the unit as the data of the main controlling factors corresponding to each layer; According to the data of the main controlling factors corresponding to each layer system and the number of layers in the layer system combination, the standard variance of the main controlling factors in the layer system combination is calculated as the second variance of the main controlling factors corresponding to the layer system combination.

5. The method according to claim 2, characterized in that The step of calculating the fitness value of the layer combination comprises: According to the first variance of each main controlling factor corresponding to each layer in the layer combination and the number of layers in the layer combination, the average value of the first variance of each main controlling factor corresponding to each layer is calculated; According to the second variance of each main control factor corresponding to the layer combination and the average value of the first variance of each main control factor corresponding to each layer in the layer combination, the fitness value of the layer combination is calculated using the following formula: In the above formula, σ represents the fitness value of the layer combination, q represents the qth main control factor, λ1 represents the weight coefficient of the average value of the first variance of the layer in the layer combination corresponding to the qth main control factor, and λ2 represents the weight coefficient of the second variance of the qth main control factor corresponding to the layer combination. represents the average value of the first variance of the qth main controlling factor in the layer combination, σ qg It represents the second variance of the qth main controlling factor corresponding to the layer combination.

6. The method according to claim 1, characterized in that The step of calculating the selection probability of each layer combination according to the fitness value of each layer combination includes: Calculating the selection probability of each layer combination according to the fitness value of each layer combination in the initial population and the number of layer combinations in the initial population; The selected layer combinations are cross-processed, including: Using a single-point crossover operator, each layer in the screened layer combination is cross-processed according to the pre-set crossover probability; Accordingly, the selected layer combinations are subjected to mutation processing, including: The single-point mutation algorithm is used to mutate the layer combination after crossover processing to generate the next generation population.

7. The method according to any one of claims 2 to 5, characterized in that: The main controlling factors are determined in the following way: Obtain data on the stratigraphic division factors of each oil layer; According to the number of layers of the oil layer and the data of the layer division factors of each oil layer, a first matrix is ​​constructed, and the first matrix is ​​standardized; Calculating the covariance matrix of the first matrix after standardization, and calculating the eigenvalues ​​of the covariance matrix, and calculating the contribution rate of each layer division factor according to the eigenvalues; According to the order of contribution rate, a preset number of layer division factors starting from the maximum contribution rate are selected as the determined main controlling factors.

8. The method according to claim 1, characterized in that The iteration termination condition is that the number of iterations is greater than or equal to a preset iteration number threshold; After the iteration is terminated, the optimal layer combination is determined from the layer combination of the initial population and the next generation population generated by the iteration process, including: In order of fitness values, a preset number of layer combinations starting from the highest fitness value are selected from the layer combinations of the initial population and the next generation population generated by the iterative process as the determined optimal layer combination.

9. A device for determining an optimal layer combination, characterized in that: include: The fitness value calculation module is used to obtain a plurality of stratum combinations according to the stratum numbers of each oil layer as the initial population, and calculate the fitness value of each stratum combination in the initial population; the stratum combination includes a plurality of stratums, and the stratums include a plurality of stratum numbers; A generation module is used to calculate the selection probability of each layer combination according to the fitness value of each layer combination, screen and retain a preset number of layer combinations from the initial population according to the selection probability, perform crossover processing and mutation processing on each screened layer combination, generate a next generation population, calculate the fitness value of each layer combination in the next generation population, and repeatedly perform the step of generating the next generation population according to the fitness value of each layer combination until the iteration termination condition is met, then the iteration is terminated; The determination module is used to determine the optimal layer combination from the layer combination of the initial population and the next generation population generated by the iteration process after the iteration is terminated.

10. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, which, when executed by a processor, implement the method for determining the optimal layer combination described in any one of claims 1-8.

11. A terminal device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for determining the optimal layer combination according to any one of claims 1 to 8 is implemented.

Images