Three-dimensional modeling simulation method and system for oil and gas production early warning

Abstract

The invention relates to the technical field of oil field production real-time monitoring and pre-warning, and particularly discloses a three-dimensional modeling simulation method and system for oil and gas production early warning, and the method comprises the steps: constructing an oil and gas well productivity prediction model according to an IPR curve between the oil well yield and the flowing pressure; using a Begs-Brill method to construct a multiphase pipe flow model of the oil field shaft; constructing an oil nozzle flow model according to the relationship between the mass flow and the pressure difference of the oil-gas mixture passing through the oil nozzle equipment of the oil well; and according to the oil and gas well productivity prediction model, the oil field shaft multiphase pipe flow model and the oil nozzle flow model, an oil well production early warning model based on a support vector machine is constructed, so that the production state of an oil well is monitored in real time, and possible problems are predicted and early warned by learning historical data.

Description

Technical Field

[0001] The invention relates to the technical field of oilfield equipment and facility management, and in particular to a three-dimensional modeling simulation method and system for oil and gas production early warning. Background Art

[0002] In the field of real-time monitoring and early warning simulation of oilfield production, most of them currently install sensors at key locations such as oil and gas wellheads, stations, and official websites to collect key parameters such as pressure, temperature, and flow in real time, and then send the data to the central processing system through the data transmission system.

[0003] Although existing technologies have achieved certain success in oilfield equipment and facility management simulation, they have significant deficiencies in the following aspects: Although sensor technology is relatively mature, stability and accuracy in extreme environments (such as high temperature, high pressure, and corrosive environments) remain a challenge. In addition, the maintenance and replacement costs of sensors are relatively high.

[0004] Therefore, how to solve the defects in the prior art is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] To achieve the purpose of the present invention, the present application provides a three-dimensional modeling simulation method for oil and gas production early warning, comprising: Step S1: constructing an oil and gas well productivity prediction model based on an IPR curve between oil well production and flowing pressure; Step S2: constructing a multiphase pipe flow model of an oilfield wellbore using the Beggs-Brill method; Step S3: constructing a nozzle flow model based on the relationship between the mass flow rate and the pressure difference of the oil-gas mixture passing through the nozzle equipment of the oil well; Step S4: construct an oil well production warning model based on a support vector machine according to the oil and gas well productivity prediction model, the oil field wellbore multiphase pipe flow model and the nozzle flow model to monitor the production status of the oil well in real time and predict and warn possible problems by learning historical data.

[0006] In some specific embodiments, step S1 includes: Step S11: determining the oil, gas and water three-phase seepage formula of the oil well according to the oil production index and flow pressure of the oil well; Step S12: using the Cheng-Prusof equation and the Bendakhlia equation to determine the IPR curve between the oil well production and the flowing pressure at different well inclination angles.

[0007] In some specific embodiments, step S2 includes: Step S21: simulating the physical and chemical processes inside the wellbore through the multiphase pipe flow model of the oil field wellbore, including: fluid flow, pressure distribution and temperature change, so as to provide data support for the oil and gas production process; Step S22: integrating the multi-scale digital core and porosity distribution data of the wellbore through the multiphase pipe flow model of the oil field wellbore to generate an apparent porosity spectrum around the wellbore to enable real-time monitoring of the oil and gas production process.

[0008] In some specific embodiments, step S3 includes: analyzing the relationship between the pressure and production of the oil-gas mixture according to the following formula: ; In the formula, p t Indicates oil pressure, q Indicates oil production, d Indicates the nozzle diameter, R represents the gas-oil ratio, and n, m, and c represent constants.

[0009] In some specific embodiments, step S4 includes: Step S41: establishing a sample set based on the data of the oil wells, wherein the data of the oil wells include: the total number of wells, the number of open wells, the oil production rate, the oil production time rate, the comprehensive decline rate, the water injection volume and the oil production volume; Step S42: pre-processing the oil well data using Z-score normalization or minimum-maximum normalization method; Step S43: using a classification support vector machine as a classifier and using a cross-validation method to optimize and select the parameters of the oil well production early warning model; Step S44: Use the optimized model parameters to train the model, and after the training is completed, generate a model file containing information on the number of support vectors.

[0010] In some specific embodiments, step S43 includes: creating multiple SVM sub-classifiers using a one-to-one strategy, each sub-classifier corresponding to a pair of comparisons of different categories to determine the binary classification problem of the oil well production early warning model, and determining the support vector by introducing Lagrange multipliers, and determining the decision function based on the support vector, seeking a balance between minimizing empirical risk and controlling model complexity to avoid overfitting.

[0011] To achieve the same invention purpose, the present application also provides a three-dimensional modeling simulation system for oil and gas production early warning, including: Oil and gas well productivity prediction model building module: used to build an oil and gas well productivity prediction model based on the IPR curve between oil well production and flowing pressure; Multiphase pipe flow model building module: used to build a multiphase pipe flow model for oil field wellbore using the Beggs-Brill method; Nozzle flow model building module: used to build a nozzle flow model based on the relationship between the mass flow rate and pressure difference of the oil and gas mixture passing through the nozzle equipment of the oil well; Oil well production early warning model construction module: used to construct an oil well production early warning model based on support vector machine according to the oil and gas well capacity prediction model, oil field wellbore multiphase pipe flow model and nozzle flow model, so as to monitor the production status of the oil well in real time and predict and warn possible problems by learning historical data.

[0012] In some specific embodiments, the oil and gas well productivity prediction model building module is used to perform the following steps: Step S11: determining the oil, gas and water three-phase seepage formula of the oil well according to the oil production index and flow pressure of the oil well; Step S12: using the Cheng-Prusof equation and the Bendakhlia equation to determine the IPR curve between the oil well production and the flowing pressure at different well inclination angles.

[0013] In some specific embodiments, the multiphase pipe flow model building module is used to perform the following steps: Step S21: simulating the physical and chemical processes inside the wellbore through the multiphase pipe flow model of the oil field wellbore, including: fluid flow, pressure distribution and temperature change, so as to provide data support for the oil and gas production process; Step S22: integrating the multi-scale digital core and porosity distribution data of the wellbore through the multiphase pipe flow model of the oil field wellbore to generate an apparent porosity spectrum around the wellbore to enable real-time monitoring of the oil and gas production process.

[0014] In some specific embodiments, the oil well production early warning model building module is used to perform the following steps: Step S41: establishing a sample set based on the data of the oil wells, wherein the data of the oil wells include: the total number of wells, the number of open wells, the oil production rate, the oil production time rate, the comprehensive decline rate, the water injection volume and the oil production volume; Step S42: pre-processing the oil well data using Z-score normalization or minimum-maximum normalization method; Step S43: using a classification support vector machine as a classifier and using a cross-validation method to optimize and select the parameters of the oil well production early warning model; Step S44: Use the optimized model parameters to train the model, and after the training is completed, generate a model file containing information on the number of support vectors.

[0015] Beneficial effects of the above technical solution: This application provides detailed data support for oil and gas production by constructing a digital model of the wellbore lifting system to accurately simulate the physical and chemical processes inside the wellbore, such as fluid flow, pressure distribution, and temperature changes. This model optimizes the wellbore design, improves the efficiency of oil and gas production, reduces resource waste, and can predict possible problems in the wellbore. In addition, by integrating multi-scale digital core and porosity distribution data, the model constructed using advanced algorithms can generate a wellbore-wide porosity spectrum, providing a new technical means for real-time monitoring of oil and gas production. An oil well production early warning model is also constructed to monitor the production status of the oil well in real time, and to predict and warn of possible problems by learning historical data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A schematic flow chart of a three-dimensional modeling simulation method for oil and gas production early warning provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a three-dimensional modeling simulation system for oil and gas production early warning provided by an embodiment of the present invention; Figure 3 A flow pattern distribution diagram using the Beggs-Brill method for a three-dimensional modeling simulation method for oil and gas production early warning provided by an embodiment of the present invention; Figure 4 A curve diagram showing the relationship between the mass flow rate and the pressure difference of a fluid in a three-dimensional modeling simulation method for oil and gas production early warning provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar symbols throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0020] Embodiment 1 An embodiment of the present invention provides a three-dimensional modeling simulation method for oil and gas production early warning, referring to Figure 1 As shown, including: Step S1: construct an oil and gas well productivity prediction model based on the IPR curve between oil well production and flowing pressure.

[0021] In a specific embodiment of the present invention, step S1 includes: Step S11: Determine the oil, gas and water three-phase seepage formula of the oil well according to the oil production index and flow pressure of the oil well.

[0022] Specifically, according to the average reservoir pressure , saturation pressure , bottom hole flowing pressure , oil well liquid production , determine the oil well's liquid production index : when hour: ; when hour: ; when hour: ; ; Weighted average by production , and then by , , we can deduce: ; The moisture content is expressed as The maximum oil production of the pure oil IPR curve is expressed as .

[0023] According to the average reservoir pressure , liquid production , saturation pressure , calculate the oil well liquid production as Bottom hole pressure The size of , thus determining the flowing pressure of the oil well: when hour, ; when When the flow pressure By taking a weighted average and calculating using the combined IPR curve, we can get: ; in, is the flowing pressure of oil in the oil well, is the flow pressure of water in the oil well, It is the maximum oil production of pure oil IPR curve.

[0024] ; in, Indicates the moisture content, Indicates the maximum oil production of pure oil IPR curve.

[0025] Step S12: using the Cheng-Prusof equation and the Bendakhlia equation to determine the IPR curve between the oil well production and the flowing pressure at different well inclination angles.

[0026] Specifically, the Cheng-Prusof equation numerically studies the inflow performance (IPR) curves of deviated and horizontal wells, and is applicable to oil wells with different well inclination angles. Bendakhlia simulated the inflow performance (IPR) curve of horizontal wells and derived a dimensionless IPR curve equation applicable to horizontal wells: ; Among them, v and n are functions of the recovery degree, which are obtained by regression fitting based on the actual production data of the oil well.

[0027] Step S2: Use the Beggs-Brill method to construct a multiphase pipe flow model of the oil field wellbore.

[0028] In a specific embodiment of the present invention, step S2 includes: Step S21: simulating the physical and chemical processes inside the wellbore through the multiphase pipe flow model of the oil field wellbore, including: fluid flow, pressure distribution and temperature change, so as to provide data support for the oil and gas production process; Step S22: integrating the multi-scale digital core and porosity distribution data of the wellbore through the multiphase pipe flow model of the oil field wellbore to generate an apparent porosity spectrum around the wellbore to enable real-time monitoring of the oil and gas production process.

[0029] Specifically, in the study of multiphase fluid flow in a wellbore, if the flow is a one-dimensional steady-state process, the physical properties of the fluid in any vertical section are constant; the fluid flow follows the basic principles of conservation of mass, energy, and momentum. During the flow process, mass exchange is not considered, and the deformation of the wellbore structure caused by pressure fluctuations is ignored.

[0030] During the fluid rising process, a submersible electric pump is required to provide the necessary pressure to push the mixture up along the wellbore. To grasp the production dynamics of offshore oil wells, the Beggs-Brill method or the Orkiszewski method is commonly used.

[0031] The present invention applies the Beggs-Brill method, which is a commonly used technology currently used to calculate multiphase flow in different types of wellbores such as inclined and vertical wells, directional wells and horizontal wells.

[0032] The basic equation for pressure gradient is shown below: ; In the formula, dp represents the change in pressure, dZ represents the change in height, p represents pressure, g represents the acceleration due to gravity, v represents the velocity of the mixture, and v sg represents the gas phase apparent (converted) velocity, h represents the vertical coordinate, z represents the flow direction of the fluid, θ represents the angle between the pipeline and the horizontal, ρ g represents gas density, ρ1 represents liquid density, H1 represents liquid holdup, and DA represents the cross-sectional area of ​​the pipeline.

[0033] The Beggs-Brill method divides the gas-liquid two-phase flow state in the horizontal direction into three types: separated flow, intermittent flow and dispersed flow. This classification is based on the Froude number of the flow (as the vertical axis) and the initial volume liquid content (i.e., the liquid holdup without considering sliding, as the horizontal axis). The relevant flow pattern distribution diagram can be used as a reference, such as Figure 3 shown.

[0034] The equation of the partition line is given by: ; ; Among them, N Fr represents the ratio of the inertial force of the flow to the gravity, E1 represents the initial volume liquid content, D represents the pipe diameter, Q l Indicates the liquid flow rate, Q g represents the gas flow rate, L1, L2, L3, and L4 represent the boundaries of different flow types. First, calculate N Fr and E1, then calculate the values ​​of L1, L2, L3, and L4, and then determine the flow type according to the judgment conditions in the table below.

[0035]

[0036] Liquid hold-up Determined according to the following formula: ; In the formula, a means constant; E L Energy forms that represent the internal energy and elastic energy of liquids; b means Index, indicating E L right HL (0) The degree of impact; c means Index, indicating N Fr right H L (0) The degree of impact; is the liquid holdup during horizontal flow; is the liquid holdup of gas-liquid two-phase flow with an inclination angle of θ; is the tilt correction factor.

[0037] Tilt angle correction factor The value of is determined according to the following formula: ; The vertical pipe flow is determined according to the following formula: ; In the formula, represents the liquid density, is the liquid superficial velocity, is the surface tension of the liquid, Indicates no slip holdup rate, Represents the liquid phase velocity number.

[0038] After calculating the liquid holdup, the actual density of the mixture can be calculated by the formula: ; In the formula, ρ represents the density of the gas-liquid mixture, ρ1 represents the density of the liquid phase, and ρ g represents the gas phase density, H 1 represents the volume fraction of liquid in the mixture.

[0039] Step S3: constructing a nozzle flow model based on the relationship between the mass flow rate and the pressure difference of the oil-gas mixture passing through the nozzle device of the oil well.

[0040] In a specific embodiment of the present invention, step S3 includes: analyzing the relationship between the pressure and production of the oil-gas mixture according to the following formula: ; In the formula, p t Indicates oil pressure, q Indicates oil production, d Indicates the nozzle diameter, R represents the gas-oil ratio, and n, m, and c represent constants.

[0041] Specifically, the nozzle equipment located at the wellhead can effectively control the flow rate of the oil-gas mixture by adjusting its size specifications. Its main functions include: limiting the output of sand and gravel in the oil well; preventing gas or water from suddenly rushing into the well; maintaining the safety of ground facilities; and ensuring the high efficiency of oil well operations.

[0042] When the oil-gas mixture is lifted to the wellhead by the power of the submersible pump and flows through the nozzle, it will be affected by the high pressure in front of the nozzle and the low pressure behind the nozzle. In this critical state when the fluid passes through the nozzle, the relationship between the mass flow rate of the fluid and the pressure difference can be described by a specific curve, which can be referred to below. Figure 4 shown.

[0043] In order to maintain stability during the production process, the nozzle design should achieve critical flow. Even if there are fluctuations, it can remain stable and will not be affected.

[0044] When the oil-gas mixture flows through the nozzle, its critical pressure ratio is: .

[0045] Under standard operating conditions, when the oil-gas mixture passes through the nozzle, the interaction between the key flow parameters is clear. Due to the different properties of the gas-liquid two-phase fluid and the diversity of the mixing methods of the oil-gas mixture, the flow characteristics at the nozzle are usually more complicated. Based on the actual operating experience of oil wells at home and abroad, a specific formula is usually used to predict the flow conditions at the nozzle: ; In the formula, p t Indicates oil pressure, q Indicates oil production, d Indicates the nozzle diameter, R Indicates the gas-oil ratio.

[0046] Step S4: construct an oil well production warning model based on a support vector machine according to the oil and gas well productivity prediction model, the oil field wellbore multiphase pipe flow model and the nozzle flow model to monitor the production status of the oil well in real time and predict and warn possible problems by learning historical data.

[0047] In a specific embodiment of the present invention, step S4 includes: Step S41: establishing a sample set based on the data of the oil wells, wherein the data of the oil wells include: the total number of wells, the number of open wells, the oil production rate, the oil production time rate, the comprehensive decline rate, the water injection volume and the oil production volume; Step S42: pre-processing the oil well data using Z-score normalization or minimum-maximum normalization method; Step S43: using a classification support vector machine as a classifier and using a cross-validation method to optimize and select the parameters of the oil well production early warning model; Step S44: Use the optimized model parameters to train the model, and after the training is completed, generate a model file containing information on the number of support vectors.

[0048] In a specific embodiment of the present invention, step S43 includes: creating multiple SVM sub-classifiers using a one-to-one strategy, each sub-classifier corresponds to a pair of comparisons of different categories to determine the binary classification problem of the oil well production early warning model, and determining the support vector by introducing Lagrange multipliers, and determining the decision function based on the support vector, seeking a balance between minimizing empirical risk and controlling model complexity to avoid overfitting.

[0049] Specifically, early warning is essentially a classification prediction activity. Its core task and goal is to accurately classify specific objects so that similar objects can be treated in a unified manner. The essence of classification methods is to identify the belonging of objects. The early warning process is a multi-classification problem. SVM is proposed for classification problems. It is extended to multi-class classification problems and described as follows: ; in, ; X and Y represent two sets; The decision function is determined according to the following formula: ; Dealing with multi-class classification tasks essentially involves developing a mechanism that can divide the data points into M different groups.

[0050] Since the solution of multi-class classifier involves complex quadratic programming and has high computational cost, it is rarely used in practical applications. At present, the processing of multi-class classification problems mostly adopts the paired comparison method, or is improved based on the pair of residual method. Among them, the paired comparison method has been proved to be generally superior to the pair of residual method in performance. Therefore, the present invention selects to adopt the paired comparison method as the classification algorithm.

[0051] The multi-class classification problem is relatively cumbersome and costly, so it is rarely used. At present, multi-class classifiers are classified by a one-to-one strategy, or improved on a one-to-many strategy. It has been proven that the one-to-one strategy is more practical, so the present invention chooses to adopt the one-to-one strategy.

[0052] By creating multiple SVM sub-classifiers, each sub-classifier corresponds to a pair of comparisons of different categories, the corresponding binary classification problem is determined: ; The constraints are: ; ; Among them, C represents the penalty coefficient, represents the feature mapping function, w represents the weight vector, b represents the threshold, represents the slack variable, i, jrepresents the sum index, t represents the variable, and x and y represent the latitude and longitude of the coordinates. In order to maximize the distance from the sample point to the decision hyperplane, the generalization performance of the model is improved; the second term aims to minimize the prediction error of the model.

[0053] By introducing the Lagrange multiplier α , we can get the following convex quadratic programming problem to solve w and b: ; Constraints: ; Among them, there are non-zero Lagrange multipliers α The sample points are called support vectors.

[0054] If the current training result determines that the test sample x belongs to the i-th category, the score of the i-th category is increased by one; if not, the score of the j-th category is increased by one. Finally, the sample x is classified into the category with the highest score. Nonlinear classification is achieved through functions, while seeking a balance between minimizing empirical risk and controlling model complexity to avoid overfitting.

[0055] The core goal of oil well production early warning is to use key production indicators, which are directly related to the possible alarm levels in oil well production, combined with existing alarm level assessments to form a set of known sample data. Using these data, a model is constructed to predict future alarms that have not yet occurred.

[0056] (1) Establishing a sample set There are many factors that affect the change in production, such as the total number of wells, the number of wells opened, oil production speed, oil production time rate, comprehensive decline rate, water injection volume and oil production, etc. The warning level can be represented by the numbers 1, 2, 3, 4, 5. A sample set is established based on the data from the mobile phone.

[0057] (2) Data preprocessing The accuracy of early warning depends on the accuracy of data, so it is necessary to standardize the data. In order to prevent the impact of data errors on early warning results, there are several methods for standardizing data processing: Assume u is the original value of attribute A, and is the normalized value of attribute A.

[0058] 1) Minimum-maximum standardization: Assume that the minimum and maximum values ​​of attribute A are and The minimum and maximum values ​​after standardization are and The standardized formula is: ; The value of attribute A can be normalized to .

[0059] 2) Z-score standardization: The standard deviation, mean, and , , then the formula is: ; All variable data were transformed into numerical values ​​with a mean of 0 and a standard deviation of 1.

[0060] (3) Parameter selection When constructing the model, the function category and parameters are first determined, and the parameter C is selected. The present invention optimizes these parameters using K-kold cross validation. K-fold cross validation is a widely used model validation technique that evaluates the generalization ability of the model by calculating the average value of k training errors. Due to its simple operation, it is currently the most widely used validation method.

[0061] (4) Early warning model Select several groups of data as test samples and the others as training samples, and preprocess the data to normalize them to [0, 1]. The establishment of the oil well production early warning model is to find x i and i The relationship between them is as follows.

[0062] ; When faced with multi-class classification tasks, the present invention uses C-SVC (classification support vector machine) as a classifier and uses the cross-validation method to optimize the model parameters. The optimized parameters are used to train the model, and after the training is completed, a model file containing information such as the number of support vectors is generated. The model file can be used to predict and analyze new data.

[0063] Embodiment 2 An embodiment of the present invention provides a three-dimensional modeling simulation system for oil and gas production early warning, referring to Figure 2 As shown, including: Oil and gas well productivity prediction model building module 10: used to build an oil and gas well productivity prediction model according to an IPR curve between oil well production and flow pressure; Multiphase pipe flow model building module 20: used to build a multiphase pipe flow model of an oil field wellbore using the Beggs-Brill method; The nozzle flow model building module 30 is used to build the nozzle flow model according to the relationship between the mass flow rate and the pressure difference of the nozzle device of the oil well through which the oil and gas mixture passes; Oil well production early warning model construction module 40: used to construct an oil well production early warning model based on a support vector machine according to the oil and gas well capacity prediction model, the oil field wellbore multiphase pipe flow model and the nozzle flow model, so as to monitor the production status of the oil well in real time and predict and warn possible problems by learning historical data.

[0064] In some specific embodiments, the oil and gas well productivity prediction model building module is used to perform the following steps: Step S11: determining the oil, gas and water three-phase seepage formula of the oil well according to the oil production index and flow pressure of the oil well; Step S12: using the Cheng-Prusof equation and the Bendakhlia equation to determine the IPR curve between the oil well production and the flowing pressure at different well inclination angles.

[0065] In some specific embodiments, the multiphase pipe flow model building module is used to perform the following steps: Step S21: simulating the physical and chemical processes inside the wellbore through the multiphase pipe flow model of the oil field wellbore, including: fluid flow, pressure distribution and temperature change, so as to provide data support for the oil and gas production process; Step S22: integrating the multi-scale digital core and porosity distribution data of the wellbore through the multiphase pipe flow model of the oil field wellbore to generate an apparent porosity spectrum around the wellbore to enable real-time monitoring of the oil and gas production process.

[0066] In some specific embodiments, the oil well production early warning model building module is used to perform the following steps: Step S41: establishing a sample set based on the data of the oil wells, wherein the data of the oil wells include: the total number of wells, the number of open wells, the oil production rate, the oil production time rate, the comprehensive decline rate, the water injection volume and the oil production volume; Step S42: pre-processing the oil well data using Z-score normalization or minimum-maximum normalization method; Step S43: using a classification support vector machine as a classifier and using a cross-validation method to optimize and select the parameters of the oil well production early warning model; Step S44: Use the optimized model parameters to train the model, and after the training is completed, generate a model file containing information on the number of support vectors.

[0067] This application provides detailed data support for oil and gas production by constructing a digital model of the wellbore lifting system to accurately simulate the physical and chemical processes inside the wellbore, such as fluid flow, pressure distribution, and temperature changes. This model optimizes the wellbore design, improves the efficiency of oil and gas production, reduces resource waste, and can predict possible problems in the wellbore. In addition, by integrating multi-scale digital core and porosity distribution data, the model constructed using advanced algorithms can generate a wellbore-wide porosity spectrum, providing a new technical means for real-time monitoring of oil and gas production. An oil well production early warning model is also constructed to monitor the production status of the oil well in real time, and to predict and warn of possible problems by learning historical data.

[0068] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions 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 should be based on the protection scope of the claims.

[0069] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referenced to each other. The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the functions in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing terminal device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention. Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0070] The method and device provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

[0071] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", "one specific embodiment" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A three-dimensional modeling simulation method for oil and gas production early warning, characterized in that: include: Step S1: constructing an oil and gas well productivity prediction model based on an IPR curve between oil well production and flowing pressure; Step S2: constructing a multiphase pipe flow model of an oilfield wellbore using the Beggs-Brill method; Step S3: constructing a nozzle flow model based on the relationship between the mass flow rate and the pressure difference of the oil-gas mixture passing through the nozzle equipment of the oil well; Step S4: construct an oil well production warning model based on a support vector machine according to the oil and gas well productivity prediction model, the multiphase pipe flow model of the oil field wellbore and the nozzle flow model to monitor the production status of the oil well in real time and predict and warn possible problems by learning historical data.

2. The three-dimensional modeling simulation method for oil and gas production early warning according to claim 1 is characterized in that: Step S1 includes: Step S11: determining the oil, gas and water three-phase seepage formula of the oil well according to the oil production index and flow pressure of the oil well; Step S12: using the Cheng-Prusof equation and the Bendakhlia equation to determine the IPR curve between the oil well production and the flowing pressure at different well inclination angles.

3. The three-dimensional modeling simulation method for oil and gas production early warning according to claim 1 is characterized in that: Step S2 includes: Step S21: simulating the physical and chemical processes inside the wellbore, including fluid flow, pressure distribution and temperature change, through the multiphase pipe flow model of the oil field wellbore, so as to provide data support for the oil and gas production process; Step S22: integrating the multi-scale digital core and porosity distribution data of the wellbore through the multiphase pipe flow model of the oil field wellbore to generate an apparent porosity spectrum around the wellbore to monitor the oil and gas production process in real time.

4. The three-dimensional modeling simulation method for oil and gas production early warning according to claim 1 is characterized in that: Step S3 includes: analyzing the relationship between the pressure and production of the oil-gas mixture according to the following formula: ； In the formula, p t Indicates oil pressure, q Indicates oil production, d Indicates the nozzle diameter, R represents the gas-oil ratio, and n, m, and c represent constants.

5. The three-dimensional modeling simulation method for oil and gas production early warning according to claim 1 is characterized in that: Step S4 includes: Step S41: establishing a sample set based on the data of the oil wells, wherein the data of the oil wells include: the total number of wells, the number of open wells, the oil production rate, the oil production time rate, the comprehensive decline rate, the water injection volume and the oil production volume; Step S42: pre-processing the oil well data using Z-score normalization or minimum-maximum normalization method; Step S43: using a classification support vector machine as a classifier and using a cross-validation method to optimize and select the parameters of the oil well production early warning model; Step S44: Use the optimized model parameters to train the model, and after the training is completed, generate a model file containing information on the number of support vectors.

6. The three-dimensional modeling simulation method for oil and gas production early warning according to claim 5 is characterized in that: The step S43 includes: using a one-to-one strategy to create multiple SVM sub-classifiers, each sub-classifier corresponds to a pair of comparisons of different categories to determine the binary classification problem of the oil well production early warning model, and determining the support vector by introducing Lagrange multipliers, and determining the decision function based on the support vector, seeking a balance between minimizing empirical risk and controlling model complexity to avoid overfitting.

7. A three-dimensional modeling simulation system for oil and gas production early warning, characterized in that: include: Oil and gas well productivity prediction model building module: used to build an oil and gas well productivity prediction model based on the IPR curve between oil well production and flowing pressure; Multiphase pipe flow model building module: used to build a multiphase pipe flow model for oil field wellbore using the Beggs-Brill method; Nozzle flow model building module: used to build a nozzle flow model based on the relationship between the mass flow rate and pressure difference of the oil and gas mixture passing through the nozzle equipment of the oil well; Oil well production early warning model construction module: used to construct an oil well production early warning model based on support vector machine according to the oil and gas well capacity prediction model, oil field wellbore multiphase pipe flow model and nozzle flow model, so as to monitor the production status of the oil well in real time and predict and warn possible problems by learning historical data.

8. The three-dimensional modeling simulation system for oil and gas production early warning according to claim 7 is characterized in that: The oil and gas well productivity prediction model building module is used to perform the following steps: Step S11: determining the oil, gas and water three-phase seepage formula of the oil well according to the oil production index and flow pressure of the oil well; Step S12: using the Cheng-Prusof equation and the Bendakhlia equation to determine the IPR curve between the oil well production and the flowing pressure at different well inclination angles.

9. The three-dimensional modeling simulation system for oil and gas production early warning according to claim 7, characterized in that: The multiphase pipe flow model building module is used to perform the following steps: Step S21: simulating the physical and chemical processes inside the wellbore through the multiphase pipe flow model of the oil field wellbore, including: fluid flow, pressure distribution and temperature change, so as to provide data support for the oil and gas production process; Step S22: integrating the multi-scale digital core and porosity distribution data of the wellbore through the multiphase pipe flow model of the oil field wellbore to generate an apparent porosity spectrum around the wellbore to enable real-time monitoring of the oil and gas production process.

10. The three-dimensional modeling simulation system for oil and gas production early warning according to claim 7, characterized in that: The oil well production early warning model building module is used to perform the following steps: step S41: establishing a sample set based on the data of the oil wells, wherein the data of the oil wells include: the total number of wells, the number of open wells, the oil production rate, the oil production time rate, the comprehensive decline rate, the water injection volume and the oil production volume; Step S42: pre-processing the oil well data using Z-score normalization or minimum-maximum normalization method; Step S43: using a classification support vector machine as a classifier and using a cross-validation method to optimize and select the parameters of the oil well production early warning model; Step S44: Use the optimized model parameters to train the model, and after the training is completed, generate a model file containing information on the number of support vectors.

Images