Method for predicting productivity of argillaceous shale oil

Abstract

The invention relates to the technical field of shale oil and gas exploitation, in particular to an argillaceous shale oil productivity prediction method which comprises the steps that geological engineering parameters and corresponding productivity of a constructed well and all geological engineering parameters of a to-be-predicted single well are obtained; establishing a productivity influence factor database, and carrying out normalization processing on each geological engineering parameter of the constructed well; determining main control factors of the constructed well, and constructing a main control factor and capacity correlation coefficient database; determining a weight coefficient of each main control factor, and constructing a geological engineering comprehensive index formula; constructing an index-productivity regression curve; determining a design range of each engineering parameter of the to-be-predicted single well according to the geological engineering parameters and the corresponding productivity of each constructed well; calculating a geological engineering comprehensive index range of the to-be-predicted single well, and predicting a productivity interval of the to-be-predicted single well; and determining engineering parameters of the to-be-predicted single well. According to the method, the influence of each geological engineering parameter on the productivity can be accurately evaluated, and the accuracy of yield prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shale oil and gas exploitation, and in particular to a method for predicting the production capacity of muddy shale oil. Background Art

[0002] At present, the main methods for predicting shale oil production capacity include reservoir engineering method, analytical solution and numerical simulation method. The principle of these three methods for predicting production capacity is mainly based on reservoir and seepage simulation technology. On the one hand, it requires rich reservoir, transformation and fluid data, takes a lot of time, and the accuracy of the prediction results cannot be guaranteed. On the other hand, it requires a high theoretical foundation for application personnel, and it is difficult to achieve large-scale batch, simple and convenient application.

[0003] Chinese patent publication number CN114519260A discloses a shale oil production capacity prediction method, system, medium, equipment and terminal. It includes the following steps: determine the evaluation index system according to the evaluation purpose to establish a production influencing factor database; divide the factors affecting production into four levels according to the existing development plan database; construct an average effect database of production influencing factors according to the production influencing factor database; construct a production influencing factor range database according to the average effect database of production influencing factors; construct a comparison matrix between different factors according to the production influencing factor range database; calculate the weight of the influencing factors and perform consistency test; construct a multivariate regression fitting production formula. This method only reflects the geological conditions that affect production capacity through the sweet spot drilling rate, and does not screen specific geological factors. It is impossible to accurately evaluate the contribution of various geological parameters to production capacity, resulting in low accuracy in production prediction.

[0004] China Patent Authorization Announcement No. CN113988475A discloses a shale oil production capacity prediction method based on the equivalent area value method of nuclear magnetic logging T2 spectrum. It includes the following steps: in the same block, according to the geological conditions and research objectives, select the continuous and complete nuclear magnetic logging data of nine layers of nine wells in the study area, extract the nuclear magnetic logging T2 spectrum corresponding to the oil test and production section; quantify the nuclear magnetic logging T2 spectrum value; obtain multiple groups of quantified transverse nuclear magnetic logging T2 spectrum areas corresponding to the oil test and production section, and perform equivalent on multiple groups of quantified transverse nuclear magnetic logging T2 spectrum areas to form an equivalent area value; establish a shale oil production capacity prediction model based on the equivalent area value of nuclear magnetic logging T2 spectrum: intersect the equivalent area value of nuclear magnetic logging T2 spectrum with the daily oil production of the oil test and production section and carry out correlation analysis, so as to obtain a correlation formula that can express the relationship between the nuclear magnetic equivalent area value and the daily oil production as a prediction model; finally, use the established shale oil production capacity prediction model to carry out prediction. This method effectively improves the success rate of shale oil layer identification, but it only predicts production capacity based on geological conditions and does not consider engineering factors such as the amount of liquid and sand added. The final output of shale oil development is affected by both geological and engineering factors.

[0005] Chinese patent authorization announcement number CN113971498A, a shale oil production capacity prediction method and device considering bedding development. It includes the following steps: obtaining prediction parameters for predicting the production capacity of shale oil horizontal wells; determining the lateral fracture density of the shale reservoir, the permeability and porosity of the fracture network, and the vertical bedding crossflow coefficient to construct a corresponding reservoir fracturing horizontal well seepage model; obtaining the seepage model by solving the seepage equation corresponding to each area of ​​shale to obtain the production capacity curve of the shale oil fracturing horizontal well that characterizes the vertical flow of bedding, wherein the area includes the external reservoir, the internal reservoir matrix, the internal reservoir fractures, and the hydraulic fractures; determining the production capacity of shale oil according to the prediction parameters and the production capacity curve. This method constructs a new semi-analytical model to describe the vertical and horizontal heterogeneity of the reservoir transformation volume after volume fracturing of shale oil horizontal wells. The reservoir transformation volume is divided into several small layers to characterize the vertical bedding heterogeneity of the shale formation; the permeability, porosity and density fractals of induced fractures are introduced to describe the lateral heterogeneity of each layer, and the vertical crossflow of the fractal is considered to describe the flow changes caused by the vertical bedding heterogeneity. However, for muddy shale reservoirs, the matrix permeability is extremely low, and it is difficult to obtain the reservoir permeability through conventional indoor experimental methods. At the same time, the permeability after field transformation cannot be accurately obtained. Therefore, this method is not suitable and it is difficult to predict the production capacity of muddy shale oil.

[0006] Chinese patent authorization announcement number CN115146849A, a method for predicting shale oil production capacity by particle swarm optimization CNN. The method includes the following steps: constructing a mathematical model of shale oil production capacity to characterize the relationship between characteristic parameters and target parameters; wherein the characteristic parameters include oil layer thickness, fracture half-length, matrix permeability, production pressure difference, oil saturation, horizontal well length, fracture conductivity, crude oil viscosity, ground liquid volume and cluster number, and the target parameters include production; based on the mathematical model of shale oil production capacity, obtaining multiple groups of corresponding characteristic parameters and target parameters as model training data; establishing a convolutional neural network model for predicting shale oil production capacity, and using a particle swarm algorithm to obtain the optimal weight and optimal deviation value of the convolutional neural network model; training the convolutional neural network model based on the model training data to obtain a shale oil production capacity prediction model. This method requires factors such as fracture half-length and matrix permeability. However, the microseismic, wide-area electromagnetic, and high-frequency pressure methods commonly used in the industry to monitor fracture half-length give different interpretations and large differences. Therefore, it is difficult to accurately obtain the fracture half-length in actual mines. In addition, the matrix permeability of muddy shale reservoirs is extremely low, and it is difficult to obtain the reservoir permeability through conventional indoor experimental methods. Therefore, this method is not suitable and it is difficult to predict the production capacity of muddy shale oil. Summary of the invention

[0007] To this end, the present invention provides a method for predicting the production capacity of mud shale oil, so as to overcome the problem in the prior art that the influence and contribution of various geological parameters on the production capacity cannot be accurately evaluated, resulting in low prediction accuracy of mud shale oil production.

[0008] To achieve the above object, the present invention provides a method for predicting the production capacity of muddy shale oil, comprising:

[0009] Step S1, obtaining several geological engineering parameters and corresponding production capacities of several constructed wells of shale oil, and various geological engineering parameters of a single well to be predicted for shale oil; the geological engineering parameters include geological parameters and engineering parameters;

[0010] Step S2, establishing a production capacity influencing factor database according to the target evaluation system, and normalizing the geological engineering parameters of the constructed wells of muddy shale oil;

[0011] Step S3, determining the main controlling factors of the constructed wells of muddy shale oil based on the normalized results, and calculating the correlation between each main controlling factor and the production capacity, so as to construct a database of correlation coefficients between the main controlling factors and the production capacity; the main controlling factors include at least one geological parameter and at least one engineering parameter;

[0012] Step S4, determining the weight coefficient of each main control factor according to the main control factor and production capacity correlation coefficient database, constructing a geological engineering comprehensive index formula, and obtaining the geological engineering comprehensive index of each of the constructed muddy shale oil wells;

[0013] Step S5, constructing an index-capacity regression curve according to the comprehensive geological engineering index of each constructed shale oil well and the corresponding capacity;

[0014] Step S6, determining a design reference database of engineering parameters based on the geological parameters of the single well to be predicted for the shale oil, and determining the design range of each engineering parameter of the single well to be predicted according to the geological engineering parameters and corresponding production capacities of each constructed well for the shale oil;

[0015] Step S7, calculating the geological engineering comprehensive index range of the single well to be predicted according to the geological engineering comprehensive index formula, and regressing the geological engineering comprehensive index range of the single well to be predicted in the index-capacity regression curve to predict the capacity range of the single well to be predicted for muddy shale oil;

[0016] Step S8, determining the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity based on the predicted production capacity interval, and determining the engineering parameters of the single well to be predicted based on the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity and the design range of the engineering parameters;

[0017] Among them, the geological parameters include nuclear magnetic total porosity, total organic carbon content, free hydrocarbon content, sound wave, and density; the engineering parameters include liquid addition intensity, sand addition intensity, fracture pressure, and slick water ratio.

[0018] Furthermore, in step S2, each geotechnical engineering parameter is normalized by the following formula:

[0019] X z =(X * -X min ) / (X max -X min ),

[0020] Among them, X z is the normalized result of each geological engineering parameter, and its value range is between 0 and 1; X * is the actual value of the normalized parameter; X max is the actual maximum value of the normalized parameter; X min is the actual minimum value of the normalized parameter.

[0021] Furthermore, the step S3 comprises:

[0022] Step S31, calculating the correlation coefficient and positive and negative correlation of each geo-engineering parameter by a preset correlation coefficient calculation method based on the normalization result;

[0023] Step S32, determining the main controlling factors of the constructed wells of muddy shale oil and the correlation between each main controlling factor and the production capacity according to the correlation calculation result;

[0024] Step S33, constructing a database of correlation coefficients between main control factors and production capacity according to the correlation coefficients and positive and negative correlations between each main control factor and production capacity.

[0025] Furthermore, the step S4 comprises:

[0026] Step S41, determining the weight coefficient of each main control factor to the capacity based on the main control factor and capacity correlation coefficient database;

[0027] Step S42, constructing a geological engineering comprehensive index formula according to each main controlling factor and its weight coefficient to the production capacity;

[0028] Step S43, based on the geological engineering comprehensive index formula, obtain the geological engineering comprehensive index of each of the constructed muddy shale oil wells.

[0029] Furthermore, in step S42, the geological engineering comprehensive index formula is:

[0030]

[0031] Among them, M 1 , M 2 , …, M i , …, M n is the weight coefficient of the main control factor that has a positive correlation with the production capacity among the main control factors, i = 1, 2, ..., n; n is the number of main control factors that have a positive correlation with the production capacity among the main control factors; X 1 , X 2 , …, X i , …, X n M is the main control factor that has a positive correlation with production capacity among all the main control factors; n+1 , M n+2 , …, M n+j , …, M n+m is the weight coefficient of the main control factor that has a negative correlation with the production capacity among the main control factors, j = 1, 2, ..., m; m is the number of main control factors that have a negative correlation with the production capacity among the main control factors; X n+1 , X n+2 , …, X n+j , …, X n+m is the main controlling factor that has a negative correlation with production capacity among all the main controlling factors; n+m is the number of main controlling factors.

[0032] Furthermore, the step S41 includes:

[0033] Step S411, based on the database of correlation coefficients between main control factors and production capacity, the correlation coefficients between each main control factor and production capacity are processed in a preset manner to determine the weight coefficient of each main control factor to production capacity, wherein the weight coefficient is calculated based on the correlation coefficients of each main control factor.

[0034] Furthermore, in the step S411, the preset method is implemented by the following formula:

[0035]

[0036] Among them, M Z is the calculation result of the weight coefficient of each main control factor on the capacity, and the value range is between 0 and 1; Y is the sum of the absolute values ​​of the correlation coefficients of each main control factor and the capacity; Y * is the actual value of the correlation coefficient between each main control factor and production capacity.

[0037] Furthermore, the step S31 includes:

[0038] Step S311, determining a preset standard based on the capacity influencing factor database;

[0039] Step S312, based on the preset standard, the geotechnical engineering parameters that do not meet the preset standard in the normalized results of each geotechnical engineering parameter are filtered out to calculate the correlation coefficient of each geotechnical engineering parameter.

[0040] Further, the step S6 comprises:

[0041] Step S61, based on the geological parameters of the single well to be predicted for the muddy shale oil and a design reference database for determining engineering parameters;

[0042] Step S62, calculating the matching degree between the geological parameters of the single well to be predicted for the shale oil and the geological parameters of each of the constructed shale oil wells;

[0043] The matching degree MP is determined by the following formula:

[0044] MP=sqrt(∑ q p＝1 (YB p -EB p ) 2 ); p = 1, 2, ..., q; sqrt() is a preset square root determination function; YB p is the pth geological parameter of each constructed well of shale oil, EB p is the pth geological parameter of the single well to be predicted for muddy shale oil; q is the number of geological parameters;

[0045] Step S63, based on the constructed mud shale oil wells whose matching degrees are greater than the preset matching degree threshold and whose production capacity is greater than the preset production capacity threshold, determine the candidate wells, and based on the engineering parameters of the candidate wells, determine the design range of the engineering parameters of the single well to be predicted; wherein the minimum value of the engineering parameters of the candidate wells is determined as the minimum value of the design range of the engineering parameters corresponding to the single well to be predicted, and the maximum value of the engineering parameters of the candidate wells is determined as the maximum value of the design range of the engineering parameters corresponding to the single well to be predicted.

[0046] Furthermore, the step S8 comprises:

[0047] Step S81, determining the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity based on the predicted production capacity interval; wherein the maximum production capacity in the production capacity interval is determined as the optimal production capacity;

[0048] Step S82, determining the engineering parameters of the single well to be predicted based on the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity and the design range of the engineering parameters.

[0049] Compared with the prior art, the beneficial effect of the present invention is that, by establishing a production capacity influencing factor database and normalizing various geological engineering parameters, the present invention can accurately analyze the contribution of various geological engineering parameters to production, and thereby determine the main controlling factors, and filter out factors that have a small impact on production, thereby reducing the amount of data processing. By calculating the correlation between each main controlling factor and production capacity, a database of main controlling factors and production capacity correlation coefficients is constructed, and the weight coefficients of each main controlling factor are determined, and a geological engineering comprehensive index formula is constructed, the influence of each main controlling factor on production can be further determined, and the geological engineering comprehensive index formula is established to achieve quantitative characterization of each main controlling factor, and the integrated combination of geological parameters and engineering parameters is achieved. By constructing an index-production capacity regression curve, the relationship between the geological engineering comprehensive index and production can be accurately reflected. By determining the design range of each engineering parameter of the single well to be predicted, and calculating the geological engineering comprehensive index range of the single well to be predicted, the production capacity interval of the single well to be predicted can be predicted, thereby determining the engineering parameters corresponding to the optimal production capacity, not only can the production capacity of the single well to be predicted be accurately predicted, but also the optimization of engineering parameters can be guided, and the production capacity optimization of the single well to be predicted of muddy shale oil can be achieved.

[0050] Furthermore, the present invention can reduce the influence of dimension units on data calculation results by normalizing various geo-engineering parameters, so as to accurately evaluate the influence of various geo-engineering parameters on production capacity.

[0051] Furthermore, the present invention calculates the correlation between each main control factor and the production capacity through a preset correlation coefficient calculation method, which can accurately reflect the correlation degree between each main control factor and the output.

[0052] Furthermore, the present invention determines the weight coefficient of each main controlling factor on production capacity and constructs a geological engineering comprehensive index formula, which can fully reflect the differences in the contribution of each main controlling factor to the production results and integrate the positive and negative correlation relationships of the contribution to production capacity, thereby improving the accuracy of production prediction.

[0053] Furthermore, the present invention processes the correlation coefficient between each main control factor and the production capacity in a preset manner, determines the weight coefficient of each main control factor on the production capacity, and can clarify the comprehensive impact of each main control factor on the production capacity.

[0054] Furthermore, the present invention can avoid the situation that the design range of each engineering parameter cannot be determined according to the matching degree of geological parameters in subsequent processing by determining the design reference database of engineering parameters, and realize accurate prediction of production. The constructed wells that are close to the geological parameters of the single well to be predicted can be determined by the matching degree of the geological parameters of the single well to be predicted and the geological parameters of each of the constructed wells of muddy shale oil. When the constructed wells with higher production are taken as candidate wells, the engineering parameters of the candidate wells can be used as reference to determine the design range of each engineering parameter of the single well to be predicted, so as to realize process optimization of construction parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a flow chart of the method for predicting the productivity of muddy shale oil of the present invention;

[0056] Figure 2 It is a step-by-step schematic diagram of step S3 of the present invention;

[0057] Figure 3 It is a step-by-step schematic diagram of step S4 of the present invention;

[0058] Figure 4 Schematic diagram of step S6 of the present invention;

[0059] Figure 5 It is a step-by-step schematic diagram of step S8 of the present invention;

[0060] Figure 6 An index-capacity regression curve diagram of an embodiment of the present invention;

[0061] Figure 7 This is a comparison chart between the actual production capacity and the predicted production capacity of three new wells to be predicted in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0063] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0064] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0065] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0066] See also Figure 1 As shown, it is a flow chart of the mud shale oil production capacity prediction method of the present invention.

[0067] The embodiment of the present invention provides a method for predicting the production capacity of muddy shale oil, comprising:

[0068] Step S1, obtaining several geological engineering parameters and corresponding production capacities of several constructed wells of shale oil, and various geological engineering parameters of a single well to be predicted for shale oil; the geological engineering parameters include geological parameters and engineering parameters;

[0069] Among them, the geological parameters include nuclear magnetic total porosity, total organic carbon content, free hydrocarbon content, sound wave, and density; the engineering parameters include liquid addition intensity, sand addition intensity, fracture pressure, and slick water ratio.

[0070] In implementation, the geological parameters also include transverse fracture density, matrix permeability, vertical bedding crossflow coefficient, fracture conductivity, crude oil viscosity, etc., and the engineering parameters also include liquid addition amount, sand addition amount, etc.

[0071] Step S2, establishing a production capacity influencing factor database according to the target evaluation system, and normalizing the geological engineering parameters of the constructed wells of muddy shale oil;

[0072] In actual application scenarios, actual implementers can design a target evaluation system based on the actual situation, production forecast accuracy requirements, and various geological engineering parameters in historical data.

[0073] Specifically, in step S2, each geotechnical engineering parameter is normalized by the following formula:

[0074] X z =(X * -X min ) / (X max -X min ),

[0075] Among them, X z is the normalized result of each geological engineering parameter, and its value range is between 0 and 1; X* is the actual value of the normalized parameter; X max is the actual maximum value of the normalized parameter; X min is the actual minimum value of the normalized parameter.

[0076] In practice, the present invention can reduce the influence of dimension units on data calculation results by normalizing various geo-engineering parameters, so as to accurately evaluate the influence of various geo-engineering parameters on production capacity.

[0077] Step S3, determining the main controlling factors of the constructed wells of muddy shale oil based on the normalized results, and calculating the correlation between each main controlling factor and the production capacity, so as to construct a database of correlation coefficients between the main controlling factors and the production capacity; the main controlling factors include at least one geological parameter and at least one engineering parameter;

[0078] See also Figure 2 As shown, it is a step-by-step schematic diagram of step S3 of the present invention.

[0079] Specifically, step S3 includes:

[0080] Step S31, calculating the correlation coefficient and positive and negative correlation of each geo-engineering parameter by a preset correlation coefficient calculation method based on the normalization result;

[0081] Specifically, the step S31 includes:

[0082] Step S311, determining a preset standard based on the capacity influencing factor database;

[0083] In implementation, the preset standard includes the standard corresponding to each geo-engineering parameter after normalization.

[0084] It is understandable that the preset standard can be determined based on the geological engineering parameters of several constructed wells with higher historical production capacities in the production capacity influencing factor database. For example, each geological engineering parameter of several constructed wells with higher production capacities is normalized, and the average value corresponding to each normalized geological engineering parameter is calculated and used as the preset standard.

[0085] Step S312, based on the preset standard, the geotechnical engineering parameters that do not meet the preset standard in the normalized results of each geotechnical engineering parameter are filtered out to calculate the correlation coefficient of each geotechnical engineering parameter.

[0086] Step S32, determining the main controlling factors of the constructed wells of muddy shale oil and the correlation between each main controlling factor and the production capacity according to the correlation calculation result;

[0087] In implementation, the preset correlation coefficient calculation method is to calculate the correlation between each main control factor and production capacity by combining three correlation coefficient analysis methods: spearman correlation coefficient, pearson correlation coefficient, and kendall correlation coefficient. In a specific embodiment, firstly, the geological engineering parameters corresponding to the correlation coefficients with the top 6 to 9 correlations in the results calculated by a single correlation coefficient calculation method are taken, and then the union of the geological engineering parameters corresponding to various correlation coefficients is taken, and each parameter in the union is recorded as the main control factor.

[0088] It should be noted that those skilled in the art are aware that any method capable of performing correlation analysis in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0089] Step S33, constructing a database of correlation coefficients between main control factors and production capacity according to the correlation coefficients and positive and negative correlations between each main control factor and production capacity.

[0090] In implementation, the present invention calculates the correlation between each main control factor and the production capacity through a preset correlation coefficient calculation method, which can accurately reflect the correlation degree between each main control factor and the output.

[0091] Step S4, determining the weight coefficient of each main control factor according to the main control factor and production capacity correlation coefficient database, constructing a geological engineering comprehensive index formula, and obtaining the geological engineering comprehensive index of each of the constructed muddy shale oil wells;

[0092] See also Figure 3 As shown, it is a step-by-step schematic diagram of step S4 of the present invention.

[0093] Specifically, step S4 includes:

[0094] Step S41, determining the weight coefficient of each main control factor to the capacity based on the main control factor and capacity correlation coefficient database;

[0095] Specifically, the step S41 includes:

[0096] Step S411, based on the database of correlation coefficients between main control factors and production capacity, the correlation coefficients between each main control factor and production capacity are processed in a preset manner to determine the weight coefficient of each main control factor to production capacity, wherein the weight coefficient is calculated based on the correlation coefficients of each main control factor.

[0097] Specifically, in step S411, the preset method is implemented by the following formula:

[0098]

[0099] Among them, M Zis the calculation result of the weight coefficient of each main control factor on the capacity, and the value range is between 0 and 1; Y is the sum of the absolute values ​​of the correlation coefficients of each main control factor and the capacity; Y * is the actual value of the correlation coefficient between each main control factor and production capacity.

[0100] In implementation, the present invention processes the correlation coefficient between each main control factor and the production capacity in a preset manner, determines the weight coefficient of each main control factor on the production capacity, and can clarify the comprehensive impact of each main control factor on the production capacity.

[0101] Step S42, constructing a geological engineering comprehensive index formula according to each main controlling factor and its weight coefficient to the production capacity;

[0102] Specifically, in step S42, the geological engineering comprehensive index formula is:

[0103]

[0104] Among them, M 1 , M 2 , …, M i , …, M n is the weight coefficient of the main control factor that has a positive correlation with the production capacity among the main control factors, i = 1, 2, ..., n; n is the number of main control factors that have a positive correlation with the production capacity among the main control factors; X 1 , X 2 , …, X i , …, X n M is the main control factor that has a positive correlation with production capacity among all the main control factors; n+1 , M n+2 , …, M n+j , …, M n+m is the weight coefficient of the main control factor that has a negative correlation with the production capacity among the main control factors, j = 1, 2, ..., m; m is the number of main control factors that have a negative correlation with the production capacity among the main control factors; X n+1 , X n+2 , …, X n+j , …, X n+m is the main controlling factor that has a negative correlation with production capacity among all the main controlling factors; n+m is the number of main controlling factors.

[0105] Step S43, based on the geological engineering comprehensive index formula, obtain the geological engineering comprehensive index of each of the constructed muddy shale oil wells.

[0106] In implementation, the present invention determines the weight coefficient of each main controlling factor on production capacity and constructs a comprehensive geological engineering index formula, which can fully reflect the differences in the contribution of each main controlling factor to the production results and integrate the positive and negative correlation relationships of the contribution to production capacity, thereby improving the accuracy of production prediction.

[0107] Step S5, constructing an index-capacity regression curve according to the comprehensive geological engineering index of each constructed shale oil well and the corresponding capacity;

[0108] Step S6, determining a design reference database of engineering parameters based on the geological parameters of the single well to be predicted for the shale oil, and determining the design range of each engineering parameter of the single well to be predicted according to the geological engineering parameters and corresponding production capacities of each constructed well for the shale oil;

[0109] See also Figure 4 As shown, it is a step-by-step schematic diagram of step S6 of the present invention.

[0110] Specifically, the step S6 includes:

[0111] Step S61, based on the geological parameters of the single well to be predicted for the muddy shale oil and a design reference database for determining engineering parameters;

[0112] Step S62, calculating the matching degree between the geological parameters of the single well to be predicted for the shale oil and the geological parameters of each of the constructed shale oil wells;

[0113] The matching degree MP is determined by the following formula:

[0114] MP=sqrt(∑ q p＝1 (YB p -EB p ) 2 ); p = 1, 2, ..., q; sqrt() is a preset square root determination function; YB p is the pth geological parameter of each constructed well of shale oil, EB p is the pth geological parameter of the single well to be predicted for muddy shale oil; q is the number of geological parameters;

[0115] Step S63, based on the constructed mud shale oil wells whose matching degrees are greater than the preset matching degree threshold and whose production capacity is greater than the preset production capacity threshold, determine the candidate wells, and based on the engineering parameters of the candidate wells, determine the design range of the engineering parameters of the single well to be predicted; wherein the minimum value of the engineering parameters of the candidate wells is determined as the minimum value of the design range of the engineering parameters corresponding to the single well to be predicted, and the maximum value of the engineering parameters of the candidate wells is determined as the maximum value of the design range of the engineering parameters corresponding to the single well to be predicted.

[0116] In actual application scenarios, actual implementation personnel can set the preset matching degree threshold according to actual conditions. The larger the preset matching degree threshold, the higher the matching degree requirement for the geological parameters of the single well to be predicted for muddy shale oil and the geological parameters of each of the constructed wells for muddy shale oil. Preferably, the value range of the preset matching degree threshold can be set to 0.8-0.95. Actual implementation personnel can set the preset capacity threshold according to actual conditions. The larger the preset capacity threshold, the higher the capacity requirement. Preferably, the value range of the preset capacity threshold can be set to 16t / day-20t / day.

[0117] In practice, the present invention can avoid the situation that the design range of each engineering parameter cannot be determined according to the matching degree of geological parameters in subsequent processing by determining the design reference database of engineering parameters, and realize accurate prediction of production. The matching degree of the geological parameters of the single well to be predicted and the geological parameters of each of the constructed wells of muddy shale oil can determine the constructed wells that are relatively close to the geological parameters of the single well to be predicted. When the constructed wells with higher production are taken as candidate wells, the engineering parameters of the candidate wells can be used as references to determine the design range of each engineering parameter of the single well to be predicted, and the process optimization of the construction parameters can be realized.

[0118] Step S7, calculating the geological engineering comprehensive index range of the single well to be predicted according to the geological engineering comprehensive index formula, and regressing the geological engineering comprehensive index range of the single well to be predicted in the index-capacity regression curve to predict the capacity range of the single well to be predicted for muddy shale oil;

[0119] Step S8, determining the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity based on the predicted production capacity interval, and determining the engineering parameters of the single well to be predicted based on the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity and the design range of the engineering parameters;

[0120] See also Figure 5 As shown, it is a step-by-step schematic diagram of step S8 of the present invention.

[0121] Specifically, the step S8 includes:

[0122] Step S81, determining the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity based on the predicted production capacity interval; wherein the maximum production capacity in the production capacity interval is determined as the optimal production capacity;

[0123] Step S82, determining the engineering parameters of the single well to be predicted based on the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity and the design range of the engineering parameters.

[0124] The present invention can accurately analyze the contribution of each geological engineering parameter to the output by establishing a production capacity influencing factor database and normalizing each geological engineering parameter, and thereby determine the main controlling factors, and filter out the factors that have a small impact on the output, thereby reducing the amount of data processing. By calculating the correlation between each main controlling factor and the production capacity, a database of main controlling factors and production capacity correlation coefficients is constructed, and the weight coefficients of each main controlling factor are determined, and a geological engineering comprehensive index formula is constructed, the impact of each main controlling factor on the output can be further determined, and the geological engineering comprehensive index formula is established to achieve quantitative characterization of each main controlling factor, and the integrated combination of geological parameters and engineering parameters is achieved. By constructing an index-production capacity regression curve, the relationship between the geological engineering comprehensive index and the output can be accurately reflected. By determining the design range of each engineering parameter of the single well to be predicted, and calculating the geological engineering comprehensive index range of the single well to be predicted, the production capacity interval of the single well to be predicted can be predicted, thereby determining the engineering parameters corresponding to the optimal production capacity, not only can the production capacity of the single well to be predicted be accurately predicted, but also the optimization of engineering parameters can be guided, and the production capacity optimization of the single well to be predicted of muddy shale oil can be achieved.

[0125] In a specific embodiment, the main control factors of 8 constructed wells are shown in Table 1.

[0126] Table 1 Statistics of main control factors of constructed wells

[0127]

[0128] The normalized results of each main control factor are shown in Table 2.

[0129] Table 2 Statistics of normalized results of main control factors of constructed wells

[0130] hashtag A B C D E F G H Sound Wave 0.9110 0.9657 0.1399 0.9647 0.1165 0.0000 1.0000 0.9019 density 0.0000 0.5000 0.6250 0.5000 1.0000 0.5000 0.1250 0.6250 NMR total porosity 1.0000 0.2903 0.4839 0.2742 0.2097 0.1452 0.0000 0.1613 Total organic carbon content 0.0000 1.0000 0.5417 1.0000 0.7000 0.3083 0.3417 0.1083 Free hydrocarbon content 0.1784 0.9129 1.0000 0.9170 0.8880 0.5851 0.0000 0.2490 Burst pressure 0.9285 0.4488 1.0000 0.0000 0.8808 0.9173 0.9383 0.6858 Liquid addition intensity 0.3010 0.2788 0.0000 1.0000 0.4321 0.3820 0.6378 0.7315 Sand Adding Strength 0.0034 0.0000 0.1379 0.0103 0.0138 0.1172 0.1276 0.0069 Slippery water ratio 0.0000 0.8333 1.0000 0.2319 0.4928 0.1304 0.9565 0.5072

[0131] The correlation between each main controlling factor and production capacity is calculated according to the preset correlation coefficient calculation method, and the calculation results are: total NMR porosity = 0.6311, total organic carbon content = 0.5444, free hydrocarbon content = 0.3588, liquid addition intensity = 0.3600, acoustic wave = 0.2142, sand addition intensity = 0.0723, fracture pressure = -0.1900, density = -0.3400, slick water ratio = -0.3800; among which, positive numbers represent the degree of positive correlation, and negative numbers represent the degree of negative correlation.

[0132] See also Figure 6 As shown, it is an index-capacity regression curve diagram of an embodiment of the present invention; the weight coefficient of each main control factor on the capacity is calculated, and the result is:

[0133] NMR total porosity = 20.9%, total organic carbon content = 18.0%, free hydrocarbon content = 11.9%, liquid addition intensity = 9.6%, sonic wave = 7.1%, sand addition intensity = 2.4%, fracture pressure = 6.3%, density = 11.3%, slick water ratio = 12.5%.

[0134] The calculation formula of the comprehensive geological engineering index is:

[0135]

[0136] See also Figure 7 As shown, it is a comparison diagram of the actual production capacity and the predicted production capacity of three new wells to be predicted in the embodiment of the present invention. The statistics of the main controlling factors of the three new wells to be predicted are shown in Table 3.

[0137] Table 3 Statistics of main controlling factors of new wells

[0138] hashtag I well J Well K Well NMR total porosity, % 14.50 14.80 14.94 Total organic carbon content, % 2.38 2.41 2.00 Free hydrocarbon content, mg / g 9.86 9.13 8.40 <![CDATA[Liquid addition intensity, m 3 / m]]> 48.62 37.17 44.19 Sound wave, μs / ft 108.55 103.47 102.88 <![CDATA[Density, g / cm 3 > 2.48 2.50 2.50 Burst pressure, MPa 60.42 60.70 60.40 <![CDATA[Sand addition strength, m 3 / m]]> 2.46 2.96 2.68 Slippery water ratio, % 35.80 43.90 43.27

[0139] Calculate the comprehensive geological engineering index R of the three new wells to be predicted. The result is R I =0.68, R J =0.46, R K =0.39; R I , R J , R K Substitute them into the index-capacity regression curve respectively, and the capacity (oil and gas equivalent per kilometer per day) of the three new wells to be predicted are predicted as I well = 18.97t / day, J well predicted 15.80t / day, and K well predicted 14.43t / day;

[0140] The actual production capacity (oil and gas equivalent per kilometer per day) of the three new wells to be predicted is respectively I well actual = 17.64t / day, J well actual 14.54t / day, K well actual 15.30t / day. The actual production capacity of the three new wells to be predicted is compared with the predicted production capacity. Figure 6 As shown, the calculated prediction errors are 7.55%, 8.64% and 5.65% respectively, and the average prediction error is only 7.28%. Therefore, the prediction result is accurate with a small error, and the production capacity of new wells can be accurately predicted.

[0141] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for predicting the production capacity of muddy shale oil, characterized in that: include: Step S1, obtaining several geological engineering parameters and corresponding production capacities of several constructed wells of shale oil, and various geological engineering parameters of a single well to be predicted for shale oil; the geological engineering parameters include geological parameters and engineering parameters; Step S2, establishing a production capacity influencing factor database according to the target evaluation system, and normalizing the geological engineering parameters of the constructed wells of muddy shale oil; Step S3, determining the main controlling factors of the constructed wells of muddy shale oil based on the normalized results, and calculating the correlation between each main controlling factor and the production capacity, so as to construct a database of correlation coefficients between the main controlling factors and the production capacity; the main controlling factors include at least one geological parameter and at least one engineering parameter; Step S4, determining the weight coefficient of each main control factor according to the main control factor and production capacity correlation coefficient database, constructing a geological engineering comprehensive index formula, and obtaining the geological engineering comprehensive index of each of the constructed muddy shale oil wells; Step S5, constructing an index-capacity regression curve according to the comprehensive geological engineering index of each constructed shale oil well and the corresponding capacity; Step S6, determining a design reference database of engineering parameters based on the geological parameters of the single well to be predicted for the shale oil, and determining the design range of each engineering parameter of the single well to be predicted according to the geological engineering parameters and corresponding production capacities of each constructed well for the shale oil; Step S7, calculating the geological engineering comprehensive index range of the single well to be predicted according to the geological engineering comprehensive index formula, and regressing the geological engineering comprehensive index range of the single well to be predicted in the index-capacity regression curve to predict the capacity range of the single well to be predicted for muddy shale oil; Step S8, determining the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity based on the predicted production capacity interval, and determining the engineering parameters of the single well to be predicted based on the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity and the design range of the engineering parameters; Among them, the geological parameters include nuclear magnetic total porosity, total organic carbon content, free hydrocarbon content, sound wave, and density; the engineering parameters include liquid addition intensity, sand addition intensity, fracture pressure, and slick water ratio.

2. The method for predicting the production capacity of muddy shale oil according to claim 1, characterized in that: In step S2, each geotechnical engineering parameter is normalized by the following formula: X z =(X * -X min ) / (X max -X min ), Among them, X z is the normalized result of each geological engineering parameter, and its value range is between 0 and 1; X * is the actual value of the normalized parameter; X max is the actual maximum value of the normalized parameter; X min is the actual minimum value of the normalized parameter.

3. The method for predicting the productivity of shale oil according to claim 2, characterized in that: The step S3 comprises: Step S31, calculating the correlation coefficient and positive and negative correlation of each geo-engineering parameter by a preset correlation coefficient calculation method based on the normalization result; Step S32, determining the main controlling factors of the constructed wells of muddy shale oil and the correlation between each main controlling factor and the production capacity according to the correlation calculation result; Step S33, constructing a database of correlation coefficients between main control factors and production capacity according to the correlation coefficients and positive and negative correlations between each main control factor and production capacity.

4. The method for predicting the productivity of shale oil according to claim 3, characterized in that: The step S4 comprises: Step S41, determining the weight coefficient of each main control factor to the capacity based on the main control factor and capacity correlation coefficient database; Step S42, constructing a geological engineering comprehensive index formula according to each main controlling factor and its weight coefficient to the production capacity; Step S43, based on the geological engineering comprehensive index formula, obtain the geological engineering comprehensive index of each of the constructed muddy shale oil wells.

5. The method for predicting the productivity of shale oil according to claim 4, characterized in that: In step S42, the geological engineering comprehensive index formula is: Among them, M1, M2, ..., M i , …, M n is the weight coefficient of the main control factor that has a positive correlation with the production capacity among the main control factors, i = 1, 2, ..., n; n is the number of main control factors that have a positive correlation with the production capacity among the main control factors; X1, X2, ..., X i , …, X n M is the main control factor that has a positive correlation with production capacity among all the main control factors; n+1 , M n+2 , …, M n+j , …, M n+m is the weight coefficient of the main control factor that has a negative correlation with the production capacity among the main control factors, j = 1, 2, ..., m; m is the number of main control factors that have a negative correlation with the production capacity among the main control factors; X n+1 , X n+2 , …, X n+j , …, X n+m is the main controlling factor that has a negative correlation with production capacity among all the main controlling factors; n+m is the number of main controlling factors.

6. The method for predicting the production capacity of muddy shale oil according to claim 5, characterized in that: The step S41 comprises: Step S411, based on the database of correlation coefficients between main control factors and production capacity, the correlation coefficients between each main control factor and production capacity are processed in a preset manner to determine the weight coefficient of each main control factor to production capacity, wherein the weight coefficient is calculated based on the correlation coefficients of each main control factor.

7. The method for predicting the productivity of shale oil according to claim 6, characterized in that: In the step S411, the preset method is implemented by the following formula: Among them, M Z is the calculation result of the weight coefficient of each main control factor on the capacity, and the value range is between 0 and 1; Y is the sum of the absolute values ​​of the correlation coefficients of each main control factor and the capacity; Y * is the actual value of the correlation coefficient between each main control factor and production capacity.

8. The method for predicting the productivity of shale oil according to claim 7, characterized in that: The step S31 comprises: Step S311, determining a preset standard based on the capacity influencing factor database; Step S312, based on the preset standard, the geotechnical engineering parameters that do not meet the preset standard in the normalized results of each geotechnical engineering parameter are filtered out to calculate the correlation coefficient of each geotechnical engineering parameter.

9. The method for predicting the productivity of shale oil according to claim 1, characterized in that: The step S6 comprises: Step S61, based on the geological parameters of the single well to be predicted for the muddy shale oil and a design reference database for determining engineering parameters; Step S62, calculating the matching degree between the geological parameters of the single well to be predicted for the shale oil and the geological parameters of each of the constructed shale oil wells; The matching degree MP is determined by the following formula: MP=sqrt(∑ q p＝1 (YB p -EB p ) 2 ); p = 1, 2, ..., q; sqrt() is a preset square root determination function; YB p is the pth geological parameter of each constructed well of shale oil, EB p is the pth geological parameter of the single well to be predicted for muddy shale oil; q is the number of geological parameters; Step S63, based on the constructed mud shale oil wells whose matching degrees are greater than the preset matching degree threshold and whose production capacity is greater than the preset production capacity threshold, determine the candidate wells, and based on the engineering parameters of the candidate wells, determine the design range of the engineering parameters of the single well to be predicted; wherein the minimum value of the engineering parameters of the candidate wells is determined as the minimum value of the design range of the engineering parameters corresponding to the single well to be predicted, and the maximum value of the engineering parameters of the candidate wells is determined as the maximum value of the design range of the engineering parameters corresponding to the single well to be predicted.

10. The method for predicting the productivity of shale oil according to claim 1, characterized in that: The step S8 comprises: Step S81, determining the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity based on the predicted production capacity interval; wherein the maximum production capacity in the production capacity interval is determined as the optimal production capacity; Step S82, determining the engineering parameters of the single well to be predicted based on the geological engineering comprehensive index of the single well to be predicted corresponding to the optimal production capacity and the design range of the engineering parameters.

Images