A method, system and readable medium for predicting reserves increment of oilfield measure wells

Abstract

The present invention belongs to the technical field of reserve assessment of measure wells in oil and gas field development, and relates to a method, device and readable medium for predicting reserve increment of measure wells in oil fields, comprising: determining a target oil field and collecting measure well data; calculating the reserve increment of the measure well according to the measure well data; determining the main controlling factors of the reserve increment of the measure well according to the measure well data and the reserve increment of the measure well and the degree of correlation between the reserve increment of the measure well and the influencing factors; establishing a data set according to the reserve increment of the measure well and the main controlling factors, and training a prediction model established based on an artificial intelligence algorithm through the data set; determining the main controlling factor value of the measure well to be tested, inputting the main controlling factor value into the prediction model, and calculating the reserve increment of the measure well to be tested.

Description

Technical Field

[0001] The invention relates to a method, system and readable medium for predicting reserve increment of oilfield measure wells based on main control factor analysis and artificial intelligence algorithm, belonging to the technical field of reserve assessment of oil and gas field development measure wells. Background Art

[0002] Measure wells are an important means to stabilize oil well production and improve economic benefits after offshore oil fields enter the adjustment and potential tapping stage. After the implementation of measure wells, the seepage field and oil-water distribution law around the single well are changed, which will affect the production and cause changes in the decline law, causing changes in the recoverable reserves of the single well. The reserve increment of measure wells is an important factor affecting the company's key indicators such as reserve-production ratio and barrel oil DD&A. Therefore, it is of great significance to accurately predict the reserve increment of measure wells.

[0003] According to the industry standard SY / T 5367-2010 "Methods for Calculating Recoverable Reserves of Petroleum", the commonly used calculation methods for recoverable reserves of measure wells include numerical simulation method, decline curve method and water drive characteristic curve method. In principle, the numerical simulation method is applicable to the calculation of recoverable reserves of oil reservoirs of any type, any development method and any development stage, but its certainty and reliability depend on the accuracy of geological models and historical fitting; the decline curve method is limited by the initial value of production and the value of decline rate, and it is difficult to guarantee the accuracy of its prediction results; the water drive curve method can consider the impact of more factors on the development effect in the process of predicting the marketable reserves of oil fields, so the evaluation process is more convenient and flexible than the decline method, and the evaluation results are more in line with the actual situation of long-term development of oil fields, but the scope of application is limited. More importantly, the decline curve method and the water drive characteristic curve method require a stable decline or water drive law for more than 3 years or 12 months, which requires a large amount of production dynamic data of measure wells, resulting in a lag in the prediction results and cannot quickly and accurately predict the reserve increment of measure wells. Therefore, it is urgent to establish a new method for predicting the incremental reserves of oilfield measure wells to guide the efficient development of oilfields and provide support for the evaluation of market reserves of measure wells. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide a method, system and readable medium for predicting the reserve increment of oil field measure wells based on main controlling factor analysis and artificial intelligence algorithm, which fully considers the main controlling factors of the reserve increment of the measure wells, introduces artificial intelligence algorithm to construct a prediction model, and realizes the rapid and accurate prediction of the reserve increment of the measure wells.

[0005] To achieve the above-mentioned purpose, the present invention proposes the following technical scheme: a method for predicting the incremental reserves of oilfield measure wells, comprising the following steps: determining a target oilfield and collecting measure well data; calculating the incremental reserves of the measure wells based on the measure well data; determining the main controlling factors of the incremental reserves of the measure wells based on the measure well data and the incremental reserves of the measure wells and the degree of correlation between the incremental reserves of the measure wells and the influencing factors; establishing a data set based on the incremental reserves of the measure wells and the main controlling factors, and training a prediction model established based on an artificial intelligence algorithm through the data set; determining the main controlling factor values ​​of the measure wells to be tested, inputting the main controlling factor values ​​into the prediction model, and calculating the incremental reserves of the measure wells to be tested.

[0006] Furthermore, the measure well data include: production dynamic data of the target measure well, daily oil production changes before and after the measure, initial water content and recoverable reserves before the measure, reservoir property data of the target measure well and fluid property data of the target measure well; the reservoir property data of the target measure well include oil layer thickness, formation porosity and formation permeability; the fluid property data of the target measure well include formation crude oil volume coefficient and crude oil viscosity.

[0007] Furthermore, the method for calculating the reserve increment of the measure well is: calculating the recoverable reserves before the measure and the recoverable reserves after the measure; and subtracting the recoverable reserves before the measure from the recoverable reserves after the measure to obtain the reserve increment of the measure well.

[0008] Furthermore, the calculation formula for recoverable reserves before the measures is: Exponentially decreasing formula:

[0009] Hyperbolic decreasing formula:

[0010] Harmonic decreasing formula:

[0011] in, It indicates the recoverable reserves before measures; It represents the cumulative oil production before the decline stage before the measure; represents the initial output of the fitting of the decreasing phase before the measure; represents the initial decline rate of the decline phase fitted before the measure; n represents the decreasing index of the decreasing phase fit; represents the abandoned production of the oil well; T max Indicates the maximum production time corresponding to the waste output.

[0012] The calculation formula for recoverable reserves after the above measures is: Exponential Decrease Formula:

[0013] Hyperbolic decreasing formula:

[0014] Harmonic decreasing formula:

[0015] in, It indicates the recoverable reserves after the measures; It represents the cumulative oil production before the decline phase after the measure; represents the initial output of the post-measure decline phase fit; They represent the initial decline rates of the post-measure decline phase fits respectively; n represents the decreasing index of the decreasing phase fit; represents the abandoned production of the oil well; T max Indicates the maximum production time corresponding to the waste output.

[0016] Furthermore, the method for determining the main controlling factors of the measure well reserve increment is: taking the measure well data as the influencing factors of the measure well reserve increment, plotting each influencing factor against the measure well reserve increment, and generating a relationship diagram between each influencing factor and the measure well reserve increment; determining the relationship between each influencing factor and the measure well reserve increment through qualitative analysis of the relationship diagram; taking the measure well reserve increment as a reference sequence and the influencing factors as a comparison sequence, performing grey correlation analysis, calculating the degree of correlation between each influencing factor and the measure well reserve increment, eliminating the influencing factors with weak correlation, and determining the main controlling factors of the measure well reserve increment through quantitative analysis.

[0017] Furthermore, the grey correlation analysis includes: taking the reserve increment of the measure well as a reference sequence, taking the influencing factors as a comparison sequence, and using the averaging method to perform dimensionless processing on the original parameter sequence; based on the reference sequence and the comparison sequence, calculating the correlation coefficient between the two, and calculating the correlation degree according to the correlation coefficient. The greater the correlation degree, the stronger the correlation between the reference sequence and the comparison sequence.

[0018] Further, the calculation formula of the correlation coefficient is:

[0019]

[0020]

[0021]

[0022] in, ρis the resolution coefficient; ε ( i ) is the correlation coefficient; S Δ ( i ) is the absolute difference between the comparison sequence and the reference sequence value; S min ( i ) is the minimum absolute difference; S max ( i ) is the maximum absolute difference; The calculation formula of the correlation degree is:

[0023] in, r is the correlation, N is the total number of influencing factors.

[0024] Furthermore, the artificial intelligence algorithm is a BP neural network, and the method for establishing the prediction model is: normalizing the data in the data set, and dividing the data in the data set into training samples and verification samples; inputting the training samples into the BP neural network to generate output parameters; calculating the loss function through the output parameters; adjusting the weights and bias of the BP neural network through the back propagation algorithm to minimize the loss function. When the weights and bias of the network reach a certain value, the error between the parameter data generated by the input training data and the target parameter data is within a preset range, thereby establishing a prediction model between the reserve increment of the measure well and the main controlling factors.

[0025] The present invention also discloses a reserve increment prediction system for oilfield measure wells, comprising: a measure well data collection module, used to determine the target oilfield and collect measure well data; a reserve increment calculation module, used to calculate the reserve increment of the measure well according to the measure well data; a main control factor determination module, used to determine the main control factor of the reserve increment of the measure well according to the measure well data and the reserve increment of the measure well, according to the degree of correlation between the reserve increment of the measure well and the influencing factors; a prediction model training module, used to establish a data set according to the reserve increment of the measure well and the main control factor, and train a prediction model established based on an artificial intelligence algorithm through the data set; a model output module, used to determine the main control factor value of the measure well to be tested, input the main control factor value into the prediction model, and calculate the reserve increment of the measure well to be tested.

[0026] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement any of the above-mentioned methods for predicting reserves increments in oilfield measure wells.

[0027] The technical solution of the present invention has at least the following technical effects or advantages: 1. The present invention can quickly and accurately predict the reserve increment of the measure well based on the production data of the initial application of the measure well, as well as the reservoir property data and fluid property data, thus avoiding the lag of the traditional dynamic analysis method, timely and effectively guiding the efficient development of the oil field, and providing support for the evaluation of the listed reserves of the measure well; 2. With the extensive application of measure wells, the data set is continuously updated, and the prediction model between the reserve increment of measure wells and the main controlling factors is constantly revised, thereby continuously improving the prediction accuracy of the model; 3. The oilfield measure well reserve increment prediction method based on main control factor analysis and artificial intelligence algorithm provided by the present invention frees the measure well reserve increment prediction work from complex reservoir engineering analysis, lowers the operation threshold, and has high applicability and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flow chart of a method for predicting the incremental reserves of oilfield wells based on main control factor analysis and artificial intelligence algorithm in one embodiment of the present invention; Figure 2 It is a relationship diagram between the reserve increment of a certain type of measure well and the daily oil production change before and after the measure in one embodiment of the present invention; Figure 3 is a relationship diagram between the reserve increment and the initial water content of a certain type of measure well in one embodiment of the present invention; Figure 4 It is a relationship diagram between the reserve increment of a certain type of measure well and the recoverable reserves before the measure in one embodiment of the present invention; Figure 5 is a diagram showing the relationship between the reserve increment and the oil layer thickness of a certain type of measure well in one embodiment of the present invention; Figure 6 is a diagram showing the relationship between the reserve increment and formation porosity of a certain type of measure well in one embodiment of the present invention; Figure 7 is a relationship diagram between the reserve increment and formation permeability of a certain type of measure well in one embodiment of the present invention; Figure 8 It is a relationship diagram between the reserve increment of a certain type of measure well and the volume coefficient of formation crude oil in one embodiment of the present invention; Fig. 9 is a relationship diagram between the reserve increment and crude oil viscosity of a certain type of measure well in one embodiment of the present invention; Fig.10 It is a calculation result diagram of the correlation between the reserve increment and the influencing factors of a certain type of measure well in one embodiment of the present invention; Fig.11 is a schematic diagram of a BP neural network in one embodiment of the present invention; Fig.12is an intersection diagram of the predicted reserve increment and the actual reserve increment of the training set in one embodiment of the present invention; Fig.13 It is an intersection diagram of the predicted reserve increment and the actual reserve increment of the verification set in one embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is described in detail through specific embodiments. However, it should be understood that the provision of specific embodiments is only for a better understanding of the present invention, and they should not be understood as limitations of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be understood as indicating or implying relative importance.

[0030] In order to solve the problem that a large amount of production dynamic data of the measure well is required in the prior art, which leads to the lag of the prediction result, the present invention proposes a method, system and readable medium for predicting the reserve increment of the oilfield measure well based on the main control factor analysis and artificial intelligence algorithm, comprising the steps of: determining the target oilfield and collecting the measure well data; combining the collected target measure well data, and calculating the reserve increment of the measure well according to the "Method for Calculating Recoverable Petroleum Reserves"; determining the correlation degree between the reserve increment of the measure well and the influencing factors through qualitative analysis and quantitative analysis according to the collected target measure well data and the calculation result of the reserve increment of the measure well, eliminating the influencing factors with weak correlation, and clarifying the main control factor of the reserve increment of the measure well; establishing a data set according to the calculation result of the reserve increment of the measure well and the main control factor, introducing the artificial intelligence algorithm BP neural network, and establishing a prediction model between the reserve increment of the measure well and the main control factor; determining the value of the main control factor of the target measure well, substituting the value of the main control factor of the target measure well into the prediction model between the reserve increment of the measure well and the main control factor, and calculating the reserve increment of the target measure well. The present invention provides a method for predicting the incremental reserves of oilfield measure wells based on the analysis of main control factors and artificial intelligence algorithms, which can quickly and accurately predict the incremental reserves of measure wells based on the production data of the initial application of the measure wells, as well as the reservoir property data and fluid property data, thereby avoiding the lag of the traditional dynamic analysis method, timely and effectively guiding the efficient development of oilfields, and providing support for the evaluation of the listed reserves of measure wells. The scheme of the present invention is described in detail below through embodiments.

[0031] Embodiment 1 This embodiment discloses a method for predicting the incremental reserves of oilfield wells. Figure 1 As shown, the following steps are included: S1 determines the target oil field and collects the data of the measure wells.

[0032] Among them, the measure well data include: production dynamic data of the target measure well, daily oil production changes before and after the measure, initial water content and recoverable reserves before the measure, reservoir property data of the target measure well and fluid property data of the target measure well; the reservoir property data of the target measure well include oil layer thickness, formation porosity and formation permeability; the fluid property data of the target measure well include formation crude oil volume coefficient and crude oil viscosity, as shown in Table 1-4.

[0033] Table 1 Production dynamic data table of a certain well

[0034] Table 2 Initial production data of a certain measure well

[0035] Table 3 Reservoir property data of a certain well

[0036] Table 4 Fluid property data of a certain well

[0037] S2 calculates the reserve increment of the measure well based on the measure well data.

[0038] In this embodiment, the reserve increment of the measure well is calculated according to the industry standard SY / T 5367-2010 "Method for calculating recoverable reserves of petroleum", based on the data of the measure well, wherein the method for calculating recoverable reserves of petroleum discloses a variety of methods for calculating recoverable reserves, any of which can be used to calculate the reserve increment of the measure well. In this embodiment, the reserve increment of the measure well is preferably calculated by the following method: calculating the recoverable reserves before the measure and the recoverable reserves after the measure; subtracting the recoverable reserves before the measure from the recoverable reserves after the measure to obtain the reserve increment of the measure well.

[0039] The calculation formula for recoverable reserves before measures is: Exponential Decrease Formula:

[0040] Hyperbolic decreasing formula:

[0041] Harmonic decreasing formula:

[0042] in, It indicates the recoverable reserves before measures; It represents the cumulative oil production before the decline stage before the measure; represents the initial output of the fitting of the decreasing phase before the measure; represents the initial decline rate of the decline phase fitted before the measure; n represents the decreasing index of the decreasing phase fit; represents the abandoned production of the oil well; T max Indicates the maximum production time corresponding to the abandoned output. In this embodiment, an exponential decrease formula is used, and the recoverable reserves before the measures are obtained by substituting the formula into: N R1 =8.57×10 4 m 3 .

[0043] The calculation formula of recoverable reserves after measures is: Exponential Decrease Formula:

[0044] Hyperbolic decreasing formula:

[0045] Harmonic decreasing formula:

[0046] in, It indicates the recoverable reserves after the measures; It represents the cumulative oil production before the decline phase after the measure; represents the initial output of the post-measure decline phase fit; They represent the initial decline rates of the post-measure decline phase fits respectively; n represents the decreasing index of the decreasing phase fit; represents the abandoned production of the oil well; T max Indicates the maximum production time corresponding to the abandoned output. In this embodiment, an exponential decrease formula is used, and the recoverable reserves after the measures are obtained by substituting the formula into: N R2 = 11.38 × 10 4 m 3 .

[0047] The calculation formula for the reserve increment of the measure well is:

[0048] Among them, Δ N R Indicates the reserve increment of the measure, m 3 ; N R2 Represents recoverable reserves before measures, m 3 ; N R1 Represents recoverable reserves before measures, m 3 According to the above formula, we can obtain the reserve increment of measures ∆N R = N R2 - N R1 = 2.81 × 10 4 m 3 .

[0049] S3 determines the main controlling factors of the measure well reserve increment based on the measure well data and the measure well reserve increment, and based on the degree of correlation between the measure well reserve increment and the influencing factors.

[0050] The method to determine the main controlling factors of reserve increment of measure wells is: The data of the treatment wells, i.e. the daily oil production change before and after the treatment, the initial water content, the recoverable reserves before the treatment, the oil layer thickness, the formation porosity, the formation permeability, the formation crude oil volume coefficient and the crude oil viscosity, etc., are used as the influencing factors of the reserve increment of the treatment wells; Plot each influencing factor against the reserve increment of the measure well, and draw the relationship diagram between each influencing factor and the reserve increment of the measure well, such as Figure 2-Figure 9 As shown in the figure, through the qualitative analysis of the relationship diagram, the relationship between each influencing factor and the reserve increment of the measured well is determined. Among them, the recoverable reserve increment shows an upward trend with the change of daily oil production before and after the measure, the increase of recoverable reserves and oil layer thickness before the measure, and there is a certain positive correlation; it shows a downward trend with the increase of initial water content, and there is a certain negative correlation; while the correlation with formation porosity, formation permeability, formation crude oil volume coefficient and crude oil viscosity is not obvious.

[0051] The reserve increment of the measure wells was taken as the reference sequence, and the influencing factors, namely the change in daily oil production before and after the measures, initial water content, recoverable reserves before the measures, oil layer thickness, formation porosity, formation permeability, formation crude oil volume coefficient and crude oil viscosity, were taken as the comparison sequence. Grey correlation analysis was performed to calculate the relationship between each influencing factor and the reserve increment of the measure wells, and the influencing factors with weak correlation were eliminated. The main controlling factors of the reserve increment of the measure wells were determined through quantitative analysis.

[0052] Grey correlation analysis includes: taking the reserve increment of the measure well as the reference sequence X The initial oil production, initial water content, reservoir property parameters and fluid property parameters after the measures are taken as comparison sequences X j In order to avoid unreasonable results due to different orders of magnitude of different parameters, the original parameter sequence is dimensionless processed by the averaging method; based on the reference sequence and the comparison sequence, the correlation coefficient between the two is calculated. The calculation formula of the correlation coefficient is:

[0053]

[0054]

[0055]

[0056] in, ρ is the resolution coefficient, which is generally taken as 0.5; ε ( i ) is the correlation coefficient; S Δ ( i ) is the absolute difference between the comparison sequence and the reference sequence value; S min ( i ) is the minimum absolute difference; S max ( i ) is the maximum absolute difference. In this embodiment, the minimum absolute difference S min ( i )=0; Maximum absolute difference S max ( i )=2.86, resolution coefficient ρ = 0.5.

[0057] The degree of association is calculated based on the correlation coefficient. The greater the degree of association, the stronger the correlation between the reference sequence and the comparison sequence. The calculation formula for the degree of association is:

[0058] in, r is the degree of association, a decimal; N is the total number of influencing factors. The correlation results are as follows Fig.10 As shown in the figure, the correlations between the four influencing factors, namely the change in daily oil production before and after the measures, the initial water content after the measures, the recoverable reserves before the measures and the oil layer thickness, and the recoverable reserves increment are 0.82, 0.76, 0.77 and 0.73, respectively, which are significantly higher than the correlations of formation porosity, formation permeability, formation crude oil volume coefficient and crude oil viscosity, etc., which are consistent with the results of qualitative analysis, and these four items are regarded as the main controlling factors of the reserves increment of the measured wells.

[0059] S4 establishes a data set based on the reserve increment of the measure wells and the main controlling factors, and uses the data set to train the prediction model based on the artificial intelligence algorithm.

[0060] The artificial intelligence algorithm is BP neural network, and the method of establishing the prediction model is: The data in the data set are normalized and divided into training samples and validation samples, where 80% of the data set is used as training samples and 20% as validation samples; The training samples are input into the BP neural network, such as Fig.11 As shown, the output parameters are generated; the specific formula is: Hidden node output:

[0061] Output node output:

[0062] Activation function ReLU:

[0063] In the formula, f is the activation function; is the weight; b For bias.

[0064] The loss function is calculated by the output parameters. The loss function is the error between the actual output value and the expected output value. The formula of the loss function is:

[0065] in, E is the loss function, is the true value, is the predicted value.

[0066] Through the back propagation algorithm, the weights and biases of the BP neural network are adjusted to minimize the loss function. When the weights and biases of the network reach a certain value, the error between the parameter data generated by the input training data and the target parameter data is within the preset range, thereby establishing a prediction model between the reserve increment of the measure well and the main controlling factors. The specific formula is:

[0067]

[0068] In the formula, is the learning rate. Fig.12 and Fig.13 As shown, the determination coefficient R between the predicted value and the actual value of the training set 2 The coefficient of determination R between the predicted value and the actual value of the validation set reached 0.7830. 2 It reached 0.7968, indicating that the prediction model between the reserve increment of the measured wells and the main controlling factors is reliable.

[0069] S5 determines the main controlling factor value of the well to be tested, inputs the main controlling factor value into the prediction model, and calculates the reserve increment of the well to be tested.

[0070] Calculating the reserve increment of the target measure well includes: collecting the data of the main controlling factors of the target measure well and determining the values ​​of the main controlling factors. Table 5 shows the main controlling factors of two measure wells; substituting the values ​​of the main controlling factors of the target measure well into the prediction model between the reserve increment of the measure well and the main controlling factors to predict the reserve increment of the target measure well. The actual calculated values ​​of the reserve increment of the measure well are 0.95×10 4 m 3 and 4.50×10 4 m 3 The model predicts that the reserve increment is 0.99×10 4 m 3 and 4.07×10 4 m 3 , the prediction errors were 4.21% and 9.56% respectively, both less than 10%. It can be seen that the oilfield measure well reserve increment prediction method based on main controlling factor analysis and artificial intelligence algorithm has a small error and high accuracy.

[0071] Table 5 Table of main control factors of two wells

[0072] This embodiment can quickly and accurately predict the reserve increment of the measure well based on the production data of the initial application of the measure well, as well as the reservoir property data and fluid property data, avoiding the lag of traditional dynamic analysis methods, timely and effectively guiding the efficient development of oil fields, and providing support for the implementation of the market reserve assessment of the measure well.

[0073] Embodiment 2 Based on the same inventive concept, this embodiment discloses an oilfield measure well reserve increment prediction system, comprising: The measure well data collection module is used to determine the target oil field and collect the measure well data; the reserve increment calculation module is used to calculate the reserve increment of the measure well based on the measure well data; A main controlling factor determination module is used to determine the main controlling factors of the reserve increment of the measure well according to the measure well data and the reserve increment of the measure well, and according to the degree of correlation between the reserve increment of the measure well and the influencing factors; The prediction model training module is used to establish a data set based on the reserve increment of the measure well and the main controlling factors, and to train the prediction model established based on the artificial intelligence algorithm through the data set; The model output module is used to determine the main control factor value of the well to be tested, input the main control factor value into the prediction model, and calculate the reserve increment of the well to be tested.

[0074] Embodiment 3 Based on the same inventive concept, this embodiment discloses a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to implement any of the above-mentioned oilfield measure well reserve increment prediction methods.

[0075] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, 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. Furthermore, 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, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), 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 the 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.

[0077] 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.

[0078] 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 The steps for the functions specified in one or more boxes.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not deviate from the spirit and scope of the present invention should be included in the protection scope of the claims of the present invention. The above content is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for predicting the incremental reserves of oilfield wells, characterized in that: The following steps are involved: Determine the target oil field and collect the data of the measure wells; Calculate the reserve increment of the measure well according to the measure well data; According to the measure well data and the measure well reserve increment, and according to the correlation between the measure well reserve increment and the influencing factors, the main controlling factors of the measure well reserve increment are determined; A data set is established according to the reserve increment and main controlling factors of the measure wells, and a prediction model established based on an artificial intelligence algorithm is trained by using the data set; The main controlling factor value of the well to be tested is determined, the main controlling factor value is input into the prediction model, and the reserve increment of the well to be tested is calculated.

2. The method for predicting the incremental reserves of oilfield wells according to claim 1, characterized in that: The measure well data include: production dynamic data of the target measure well, daily oil production changes before and after the measure, initial water content and recoverable reserves before the measure, reservoir property data of the target measure well and fluid property data of the target measure well; the reservoir property data of the target measure well include oil layer thickness, formation porosity and formation permeability; the fluid property data of the target measure well include formation crude oil volume coefficient and crude oil viscosity.

3. The method for predicting the incremental reserves of oilfield wells according to claim 1, characterized in that: The method for calculating the reserve increment of the measure well is: Calculate the recoverable reserves before and after the measures; The reserve increment of the measured well is obtained by subtracting the recoverable reserves before the measure from the recoverable reserves after the measure.

4. The method for predicting the incremental reserves of oilfield wells according to claim 3, characterized in that: The calculation formula for recoverable reserves before the above measures is: Exponentially decreasing formula: Hyperbolic decreasing formula: Harmonic decreasing formula: in, It indicates the recoverable reserves before measures; It represents the cumulative oil production before the decline stage before the measure; represents the initial output of the fitting of the decreasing phase before the measure; represents the initial decline rate of the decline phase fitted before the measure; n represents the decreasing index of the decreasing phase fit; represents the abandoned production of the oil well; T max Indicates the maximum production time corresponding to the waste output; The calculation formula for recoverable reserves after the above measures is: Exponentially decreasing formula: Hyperbolic decreasing formula: Harmonic decreasing formula: in, It indicates the recoverable reserves after the measures; It represents the cumulative oil production before the decline phase after the measure; represents the initial yield of the post-measure decline phase fit; They represent the initial decline rates of the post-measure decline phase fits respectively; n represents the decreasing index of the decreasing phase fit; represents the abandoned production of the oil well; T max Indicates the maximum production time corresponding to the waste output.

5. The method for predicting the incremental reserves of oilfield wells according to claim 1, characterized in that: The method for determining the main controlling factors of the reserve increment of the measure well is: Taking the measure well data as the influencing factors of the measure well reserve increment, plotting each influencing factor against the measure well reserve increment, and generating a relationship diagram between each influencing factor and the measure well reserve increment; By qualitatively analyzing the relationship diagram, the relationship between each influencing factor and the reserve increment of the measure well is determined; Taking the reserve increment of the measure well as a reference sequence and the influencing factors as a comparison sequence, a grey correlation analysis is performed to calculate the correlation between each influencing factor and the reserve increment of the measure well, eliminate the influencing factors with weak correlation, and determine the main controlling factors of the reserve increment of the measure well through quantitative analysis.

6. The method for predicting the incremental reserves of oilfield wells according to claim 5, characterized in that: The grey relational analysis includes: The reserve increment of the measure well is taken as a reference sequence, and the influencing factors are taken as a comparison sequence. The original parameter sequence is dimensionlessly processed by using a averaging method. Based on the reference sequence and the comparison sequence, the correlation coefficient between the two is calculated. The correlation degree is calculated according to the correlation coefficient. The greater the correlation degree, the stronger the correlation between the reference sequence and the comparison sequence.

7. The method for predicting the incremental reserves of oilfield wells according to claim 6, characterized in that: The calculation formula of the correlation coefficient is: in, ρ is the resolution coefficient; ε ( i ) is the correlation coefficient; S Δ ( i ) is the absolute difference between the comparison sequence and the reference sequence value; S min ( i ) is the minimum absolute difference; S max ( i ) is the maximum absolute difference; The calculation formula of the correlation degree is: in, r is the correlation, N is the total number of influencing factors.

8. The method for predicting the incremental reserves of oilfield wells according to claim 1, characterized in that: The artificial intelligence algorithm is a BP neural network, and the method for establishing the prediction model is: Normalizing the data in the data set and dividing the data in the data set into training samples and verification samples; Inputting the training samples into the BP neural network to generate output parameters; Calculate the loss function using the output parameters; Through the back propagation algorithm, the weights and biases of the BP neural network are adjusted to minimize the loss function. When the weights and biases of the network reach a certain value, the error between the parameter data generated by the input training data and the target parameter data is within a preset range, thereby establishing a prediction model between the reserve increment of the measure well and the main controlling factors.

9. An oilfield measure well reserve increment prediction system, characterized in that: include: The measure well data collection module is used to determine the target oil field and collect the measure well data; A reserve increment calculation module, used to calculate the reserve increment of the measure well according to the measure well data; A main controlling factor determination module is used to determine the main controlling factor of the reserve increment of the measure well according to the measure well data and the reserve increment of the measure well, and according to the degree of correlation between the reserve increment of the measure well and the influencing factors; A prediction model training module is used to establish a data set according to the reserve increment of the measure well and the main controlling factors, and to train the prediction model established based on the artificial intelligence algorithm through the data set; The model output module is used to determine the main control factor value of the well to be tested, input the main control factor value into the prediction model, and calculate the reserve increment of the well to be tested.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the oilfield measure well reserve increment prediction method according to any one of claims 1 to 8.

Images