Method, system and device for calculating final recoverable reserves of staged fracturing horizontal well

Abstract

The invention relates to the technical field of natural gas development, in particular to a method, system and device for calculating the final recoverable reserves of a staged fracturing horizontal well, and the method comprises the steps: determining the historical production data and production influence factors of a target well; constructing a prediction model based on the yield influence factors and historical yield data; and predicting the final recoverable reserves of the target well according to the prediction model. According to the method, the mapping relation between the engineering parameters and the first-year daily production of the single well is established in the same new block to be developed, and the data statistical analysis result of the production well in the block which is put into production under similar geological conditions is combined, so that effective prediction of the single-well EUR is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of natural gas development, in particular to a method, system and device for calculating ultimate recoverable reserves of a staged fracturing horizontal well. BACKGROUND

[0002] Single well ultimate recoverable reserves (abbreviated as EUR) refers to cumulative gas production within a specific production time, and is one of the core technical indexes of gas reservoir development. The analogy method is simple, but a large number of wells are needed as analogy basis, and the integrity of the geological engineering parameters is required to be higher; the model fitting prediction method mainly based on the production decline model and the numerical simulation model needs long-term actual dynamic data as basis, and the model parameters are determined by fitting the dynamic data to predict the single well EUR.

[0003] The staged fracturing horizontal well is widely used in unconventional fields such as shale oil and gas, tight oil and gas, and the production decline law is complex, which needs full life cycle dynamic data as basis to obtain relatively reliable model parameters. Since the natural production cycle of unconventional oil and gas reservoirs is very long, the relative production cycle of the recorded dynamic data is short, and it is difficult to determine the model parameters. The shorter the dynamic data recording time and the longer the prediction period, the less reliable the EUR calculation result. At the same time, in the development plan of unconventional oil and gas reservoirs, thousands of gas wells are often deployed, and the analysis of each well is time-consuming and laborious. Moreover, dynamic data is constantly accumulated as the production time increases, and updating the model brings higher cost.

[0004] In the conceptual design stage of unconventional oil and gas reservoir development plan, the number of test wells in the block is small, and the production time of each test well is short, and the dynamic data is insufficient. The number of wells in the similar geological conditions of the put into production block is large, and the amount of production data is large. How to make full use of the mass production data in the similar block and combine with the limited dynamic data to predict the change rule of the staged fracturing horizontal well production with time is a difficult problem in the dynamic evaluation of unconventional oil and gas reservoir development.

[0005] Therefore, the single well EUR can be accurately predicted at the beginning of development, which has an important supporting role for the preparation of unconventional oil and gas reservoir development plan and the planning of production capacity scale. SUMMARY

[0006] The present application aims to at least one of the above technical problems to some extent, and proposes a method for calculating ultimate recoverable reserves of a staged fracturing horizontal well, comprising:

[0007] determining the historical production data of the target well and the production influencing factors;

[0008] building a prediction model based on the production influencing factors and the historical production data;

[0009] predicting the ultimate recoverable reserves of the target well according to the prediction model.

[0010] Further, the yield influencing factors include engineering parameters and production parameters; the engineering parameters include the number of fractures, fracture length, fracture height penetration, fracture opening and fracture permeability; and the production parameters include bottom hole pressure.

[0011] Further, the method for constructing the prediction model includes:

[0012] sampling the data corresponding to the yield influencing factors for several times;

[0013] constructing several virtual wells according to the sampled data of the yield influencing factors;

[0014] statistically analyzing the probability distribution of the cumulative gas production of each virtual well at different production times;

[0015] reducing the dimension of the influencing factors based on the principal component analysis method and the cumulative gas production data of the virtual wells to obtain several principal component factors;

[0016] constructing the prediction model with the principal component factors as the input layer.

[0017] Further, when the dimension of the influencing factors is reduced based on the principal component analysis method and the cumulative gas production data of the virtual wells, the mean square prediction error of the cumulative gas production of the virtual wells under different numbers of principal component factors is calculated to determine the number of the selected principal component factors.

[0018] Further, before the prediction model with the principal component factors as the input layer is constructed, the principal component factors are further used as independent variables to calculate the historical cumulative gas production of the virtual wells by the multiple linear regression, and the reliability of the principal component factors is confirmed according to the calculation results.

[0019] Further, after the prediction model is constructed, the fitting relationship of the real production data of the wells with the same geological conditions as the target well is obtained, and the reliability of the prediction model is determined according to the fitting effect of the fitting relationship and the prediction data.

[0020] The present disclosure further provides a system for calculating the ultimate recoverable reserves of a staged fracturing horizontal well, which includes:

[0021] a factor determination module configured to determine the historical production data of the target well and the yield influencing factors;

[0022] a model construction module configured to construct a prediction model based on the yield influencing factors and the historical production data;

[0023] a reserve prediction module configured to predict the ultimate recoverable reserves of the target well according to the prediction model.

[0024] Further, the model construction module executes a method comprising:

[0025] Sampling the data corresponding to the yield influencing factors several times;

[0026] Constructing several virtual wells according to the sampled data of the yield influencing factors;

[0027] Statistically analyzing the probability distribution of the cumulative gas production of each virtual well at different production times;

[0028] Based on the principal component analysis method and the virtual well cumulative gas production data, reducing the dimensions of the influencing factors to obtain several principal component factors;

[0029] Constructing a prediction model taking the principal component factors as the input layer.

[0030] The present disclosure also proposes an electronic device comprising a memory and a processor, wherein the memory stores a computer program or instructions, and the computer program or instructions are executed by the processor to at least implement the segmented fracturing horizontal well ultimate recoverable reserve calculation method.

[0031] The present disclosure also proposes a computer readable storage medium, wherein the computer readable storage medium stores a computer program or instructions, and the computer program or instructions are executed by a processor to at least implement the segmented fracturing horizontal well ultimate recoverable reserve calculation method.

[0032] The beneficial effects of the above technical solutions are that the present disclosure establishes a mapping relationship between engineering parameters and single-well first-year daily production in the same new block to be developed, and combines the statistical analysis results of the production well data in the blocks that have been put into production under similar geological conditions, thereby achieving effective prediction of single-well EUR.

[0033] Other features and advantages of the present application will be set forth in the specification, and in part will become apparent to those skilled in the art upon reference to the specification, or can be learned by practice of the present application. The objectives and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0035] Figure 1The schematic diagram of the method for calculating the ultimate recoverable reserves of the segmented fractured horizontal well given by the embodiment;

[0036] Figure 2 The schematic diagram of the numerical simulation model of the segmented fractured horizontal well given by the embodiment;

[0037] Figure 3 The curve diagram of the cumulative gas production of the virtual well over time given by the embodiment;

[0038] Figure 4 The probability distribution diagram of the cumulative gas production of the virtual well at different times given by the embodiment;

[0039] Figure 5 The schematic diagram of the MAPE calculation values under different numbers of principal components given by the embodiment;

[0040] Figure 6 The multiple linear regression effect diagram under different numbers of principal components given by the embodiment;

[0041] Figure 7 The structure diagram of the prediction model based on principal component analysis and neural network given by the embodiment;

[0042] Figure 8 The comparison diagram of the real value and the predicted value of the cumulative gas production of the virtual well given by the embodiment;

[0043] Figure 9 The corresponding relationship diagram of the cumulative gas production of all wells in the block similar to the target well in the previous 6 months and the cumulative gas production at different times given by the embodiment;

[0044] Figure 10 The corresponding relationship diagram of the fitting curve slope and time given by the embodiment;

[0045] Figure 11 The flowchart of the method for calculating the ultimate recoverable reserves of the segmented fractured horizontal well given by the embodiment;

[0046] Figure 12 The schematic diagram of the system for calculating the ultimate recoverable reserves of the segmented fractured horizontal well given by the embodiment;

[0047] Figure 13 The schematic diagram of the electronic device given by the embodiment;

[0048] Figure 14 The schematic diagram of the computer readable storage medium given by the embodiment. DETAILED DESCRIPTION

[0049] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0050] Figure 1 The proposed segmented fracturing horizontal well ultimate recoverable reserves calculation method of the present application comprises:

[0051] determining the historical production data of the target well and the production influencing factors;

[0052] constructing a prediction model based on the production influencing factors and the historical production data;

[0053] predicting the ultimate recoverable reserves of the target well according to the prediction model.

[0054] According to some embodiments of the present disclosure, the production influencing factors include engineering parameters and production parameters; the engineering parameters include the number of fractures, the fracture length, the fracture height penetration rate, the fracture opening and the fracture permeability; and the production parameters include the bottom hole pressure.

[0055] According to some embodiments of the present disclosure, the construction method of the prediction model comprises:

[0056] sampling the data corresponding to the production influencing factors for several times;

[0057] constructing several virtual wells according to the sampling data of the production influencing factors;

[0058] statistically analyzing the probability distribution of the cumulative gas production of each virtual well at different production times;

[0059] performing dimensionality reduction on the influencing factors based on the principal component analysis method and the cumulative gas production data of the virtual wells, to obtain several principal component factors;

[0060] constructing the prediction model with the principal component factors as the input layer.

[0061] According to some embodiments of the present disclosure, when the dimensionality reduction is performed on the influencing factors based on the principal component analysis method and the cumulative gas production data of the virtual wells, the mean square prediction error of the cumulative gas production of the virtual well under different numbers of principal component factors is calculated, to determine the number of the selected principal component factors.

[0062] According to some embodiments of the present disclosure, before the prediction model taking the principal component factors as the input layer is constructed, the method further comprises: taking the principal component factors as independent variables, calculating the virtual well cumulative gas production by multiple linear regression, and confirming the reliability of the principal component factors according to the calculation result.

[0063] According to some embodiments of the present disclosure, after the prediction model is constructed, the method further comprises: obtaining a fitting relationship of real production data of a put-into-production well with the same geological conditions as the target well, and determining the reliability of the prediction model according to the fitting effect of the fitting relationship and the prediction data.

[0064] The technical solution of the present disclosure is further explained below in combination with a cumulative gas production prediction process of a production well in a new area:

[0065] Step A: Through production history fitting, six parameters such as the number of fractures (nf=45), fracture length (xf=195m), fracture height penetration rate (hf=15m), fracture opening (wf=0.0012m), fracture permeability (Kf=12000mD) and bottom hole pressure (Pwf=6.5MPa) are interpreted, and a basic numerical simulation model is established according to the above parameters as shown in Figure 2 The above six parameters are uniformly sampled for 1000 times to form 1000 simulation schemes, i.e. 1000 production wells, and the cumulative gas production data of the 1000 production wells is shown in Figure 3 The probability distribution of the cumulative gas production of the 1000 wells in different production times is counted, and the result is shown in Figure 4

[0066] Step B: The six parameters are first processed by dimension reduction through principal component analysis, and then the principal component variables are taken as the input layer of the neural network.

[0067] Step B1: Principal component analysis. The mean absolute percentage error (MAPE) is calculated by 10-fold cross-validation, and the calculation formula of the MAPE is:

[0068]

[0069] Wherein, Actual i represents the true value of the cumulative gas production of the first six months of the i th scheme, and Forecast i is the principal component regression value of the cumulative gas production of the first six months of the i th scheme. Figure 5 The MAPE calculation values under different principal component numbers are shown in the table, in this embodiment, three principal components are selected, and the relationship between each principal component and the engineering parameter is as follows:

[0070]

[0071] ​Take 3 principal components as independent variables, use the multiple linear regression formula to calculate the cumulative gas production in the first 6 months, check the reliability of principal component analysis, and the correlation formula is:

[0072] G p0 = 19.34 x z1 + 5.01 x z2 + 16.62 x z3

[0073] Wherein, G p0 represents the cumulative gas production in the first 6 months, x1 represents the number of fractures n f ; x2 represents the fracture length x f ; x3 represents the fracture height penetration rate h f ; x4 represents the fracture opening w f ; x5 represents the fracture permeability K f ; x6 represents the bottom hole pressure P wf .

[0074] Figure 6 Compare the multiple linear regression results of 2 principal components and 3 principal components, the calculated value of 3 principal component regression formula has good correlation with the actual value, which shows that 3 principal components can represent the influence of all 6 parameters.

[0075] Step B2: Take the three principal components z1, z2 and z3 in step B1 as the input layer of neural network, and the cumulative gas production in the first 6 months as the output layer, to form a data set, which is divided into training set, validation set and test set according to the ratio of 8:1:1. A multi-layer artificial neural network is established, the structure is as shown in Figure 7 , and the optimal artificial neural network model is determined by optimization algorithm.

[0076] Figure 8 The comparison effect of the predicted cumulative gas production in the first 6 months by the artificial neural network model under the training set, validation set and test set is shown. At this point, the principal component analysis in this step combined with the artificial neural network model realizes the function of substituting the engineering parameters and production system parameters of the staged fracturing horizontal well into the direct prediction of the cumulative gas production in the first 6 months.

[0077] Step C: Statistically analyze the real production well data in the similar geological conditions. Take the cumulative gas production in the first 6 months as x coordinate, and the cumulative gas production from the 6th month to the 36th month as y coordinate respectively, and establish multiple linear regression charts, as shown in Figure 9 .

[0078] Step D: Obtain the corresponding relationship between the "straight line slope" and the corresponding "time" of each chart (red scatter points in Figure 10 ), as the data basis for curve fitting. Through curve fitting (black solid line in Figure 10 ), the empirical relationship is obtained:

[0079] k(t) = 1.834exp(0.0009134t) - 1.41exp(-0.8707t)

[0080] Step D1: verifying the fitting effect of the relationship. Establish the "straight line slope" corresponding to the "time" of the 37th month to the 60th month (the middle blue scatter points) as the prediction data. The prediction data and the fitting effect of the relationship are good, which shows that the fitting relationship is reliable; Figure 10

[0081] Step D2: according to the fitting relationship of the straight line slope and the time, predict the change rule of the straight line slope k(t) with the time, and calculate the cumulative gas production at the corresponding time:

[0082] G p (t) = k(t) x G p0

[0083] wherein, G p (t) is the cumulative gas production at any time, and the expression of the ultimate recoverable reserves (EUR) is:

[0084] EUR = k(t a ) x G p0

[0085] wherein, t a represents the calculation period of the ultimate recoverable reserves of the gas well, and in the embodiment, 20 years are taken.

[0086] The overall flow of the above embodiment is shown in Figure 11 .

[0087] Based on the same technical concept, as shown in Figure 12 , the disclosure also proposes a segmented fracturing horizontal well ultimate recoverable reserves calculation system, comprising: a factor determination module for determining the influencing factors of the target segmented fracturing horizontal well production; a model construction module for constructing a prediction model based on the influencing factors and historical production data; a reserves prediction module for predicting the ultimate recoverable reserves of the target segmented fracturing horizontal well according to the prediction model.

[0088] As shown in Figure 13 , the present application provides an electronic device 1000, which comprises a memory 1002 and a processor 1001, the memory 1002 stores computer programs or instructions, and the computer programs or instructions are executed by the processor 1001 to at least implement the above method.

[0089] As shown in Figure 14 ​As shown, the present application provides a computer readable storage medium 1100, the computer readable storage medium 1100 stores computer programs or instructions, the computer programs or instructions are executed by a processor, and are used to implement at least the above method.

[0090] For example, the above computer program can be divided into one or more modules / units, one or more modules / units are stored in the memory and executed by the processor to complete the present application. One or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the read-write system. The read-write system can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The read-write system can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that more or less components can be included, or some components can be combined, or different components can be included, for example, the read-write system can also include input and output devices, network access devices, buses and the like.

[0091] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the read-write system, and connects all parts of the read-write system through various interfaces and lines.

[0092] The memory can be used to store computer programs and / or modules, and the processor can realize various functions of the read-write system by running or executing the computer programs and / or modules stored in the memory, and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0093] If the modules / units integrated in the read-write system are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be implemented by a computer program to instruct related hardware to complete, and the computer program can be stored in a computer-readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various method embodiments can be realized. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable storage medium can include any entity or device capable of carrying computer program code, recording media, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0094] Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for calculating the ultimate recoverable reserves of a sectionally fractured horizontal well, characterized in that, include: Determine the historical production data and production influencing factors of the target well; Constructing a prediction model based on the production influencing factors and historical production data; The ultimate recoverable reserves of the target well are predicted based on the prediction model.

2. The method of calculating the recoverable reserves of a fractured horizontal well according to claim 1, wherein, The factors affecting production include: engineering parameters and production parameters; the engineering parameters include: number of fractures, fracture length, fracture height penetration rate, fracture aperture and fracture permeability; the production parameters include: bottom hole pressure.

3. The method for calculating the recoverable reserves of a fractured horizontal well according to claim 1, characterized in that, The method for constructing the prediction model comprises: Sampling the data corresponding to the factors affecting the yield several times; constructing a plurality of virtual wells based on the sampling data of the production influencing factors; Calculate the probability distribution of the cumulative gas production of each virtual well at different production times; Based on the principal component analysis method and the cumulative gas production data of the virtual well, the influencing factors are reduced in dimension to obtain several principal component factors; A prediction model is constructed using the principal component factors as an input layer.

4. The method of calculating the recoverable reserves of a fractured horizontal well according to claim 3, wherein, When the influencing factors are reduced in dimension based on the principal component analysis method and the virtual well cumulative gas production data, the mean square prediction error of the virtual well cumulative gas production under different numbers of principal component factors is calculated to determine the number of principal component factors to be selected.

5. The method for calculating the recoverable reserves of a fractured horizontal well according to claim 3, characterized in that, Before constructing a prediction model with the principal component factors as the input layer, the method further includes: using the principal component factors as independent variables, calculating the historical cumulative gas production of the virtual wells through multivariate linear regression, and confirming the reliability of the principal component factors based on the calculation results.

6. The method for calculating the recoverable reserves of a fractured horizontal well according to claim 1, wherein, After constructing the prediction model, the method further includes: obtaining a fitting relationship formula of actual production data of a well that has been put into production under the same geological conditions as the target well, and determining the reliability of the prediction model based on the fitting effect of the fitting relationship formula and the prediction data.

7. A system for calculating a final recoverable reserves of a sectionally fractured horizontal well, the system comprising: include: Factor determination module, used to determine the historical production data and production influencing factors of the target well; A model building module, configured to build a prediction model based on the production influencing factors and historical production data; The reserve prediction module is used to predict the final recoverable reserves of the target well according to the prediction model.

8. The segmented-fractured horizontal-well ultimate recoverable reserve calculation system of claim 7, wherein, The method performed by the model building module includes: Sampling the data corresponding to the factors affecting the yield several times; constructing a plurality of virtual wells based on the sampling data of the production influencing factors; Calculate the probability distribution of the cumulative gas production of each virtual well at different production times; Based on the principal component analysis method and the cumulative gas production data of the virtual well, the influencing factors are reduced in dimension to obtain several principal component factors; A prediction model is constructed using the principal component factors as an input layer.

9. An electronic device comprising a memory and a processor, characterized in that The memory stores a computer program or instruction, which, when executed by the processor, is used to at least implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions, which, when executed by a processor, are used to at least implement the method according to any one of claims 1 to 7.

Images