CN114595628A - Differential transformation method for volume fracturing of horizontal well - Google Patents
Differential transformation method for volume fracturing of horizontal well Download PDFInfo
- Publication number
- CN114595628A CN114595628A CN202210111563.2A CN202210111563A CN114595628A CN 114595628 A CN114595628 A CN 114595628A CN 202210111563 A CN202210111563 A CN 202210111563A CN 114595628 A CN114595628 A CN 114595628A
- Authority
- CN
- China
- Prior art keywords
- horizontal well
- dessert
- fracturing
- horizontal
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000011426 transformation method Methods 0.000 title 1
- 235000021185 dessert Nutrition 0.000 claims abstract description 91
- 238000013210 evaluation model Methods 0.000 claims abstract description 43
- 235000011850 desserts Nutrition 0.000 claims abstract description 26
- 230000009466 transformation Effects 0.000 claims abstract description 25
- 235000009508 confectionery Nutrition 0.000 claims abstract description 21
- 238000002715 modification method Methods 0.000 claims abstract description 16
- 238000013461 design Methods 0.000 claims abstract description 13
- 238000009826 distribution Methods 0.000 claims abstract description 13
- 238000010586 diagram Methods 0.000 claims abstract description 10
- 238000004519 manufacturing process Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 33
- 230000004048 modification Effects 0.000 claims description 29
- 238000012986 modification Methods 0.000 claims description 29
- 238000010276 construction Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012067 mathematical method Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 5
- YCKRFDGAMUMZLT-UHFFFAOYSA-N Fluorine atom Chemical compound [F] YCKRFDGAMUMZLT-UHFFFAOYSA-N 0.000 claims description 4
- 229910052731 fluorine Inorganic materials 0.000 claims description 4
- 239000011737 fluorine Substances 0.000 claims description 4
- 230000035699 permeability Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 239000011435 rock Substances 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 15
- 230000008901 benefit Effects 0.000 abstract description 11
- 230000000694 effects Effects 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 description 16
- 238000009472 formulation Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000000704 physical effect Effects 0.000 description 3
- 239000007788 liquid Substances 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000014510 cooky Nutrition 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000003079 shale oil Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
- E21B43/25—Methods for stimulating production
- E21B43/26—Methods for stimulating production by forming crevices or fractures
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B49/00—Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Abstract
The invention provides a differential modification method for volume fracturing of a horizontal well, which comprises the steps of sorting data of the horizontal well of a target block; calculating the weight ratio of each parameter in the data to the initial capacity of the horizontal well; establishing a fractured dessert evaluation model of the horizontal well; calculating the average sweet spot degree of the fracturing section of the horizontal well; drawing a scatter diagram of the average dessert content and the initial production energy of the horizontal well fracturing section, and fitting a relation curve; establishing dessert classification standards and value intervals of logging parameters corresponding to various desserts in the dessert classification standards; establishing a volume fracturing differential transformation scheme design template of a horizontal section of the horizontal well; obtaining the distribution of the dessert degrees of various desserts along the horizontal section; and obtaining a differential reconstruction scheme of the horizontal well. Based on the technical scheme of the invention, the transformation effect of volume fracturing is exerted to the maximum extent, the fracturing transformation cost is controlled, and the economic benefit of horizontal well development is further ensured.
Description
Technical Field
The invention relates to the technical field of horizontal well volume fracturing modification, in particular to a volume fracturing differential modification method of a horizontal well.
Background
At present, along with the development of oil and gas resources in China, unconventional oil and gas reservoirs such as low-permeability, extra-low-permeability, compact oil and shale oil are gradually the key points of the development of the oil and gas resources in China; due to the characteristics of the unconventional oil and gas reservoirs, the conventional development means cannot play a good role easily, so that the horizontal well volume fracturing technology becomes a main means for developing the unconventional oil and gas reservoirs at present, and the horizontal section length of the horizontal well is longer and longer along with the development of the technology. However, the developed reservoir has strong heterogeneity, so that the physical properties and the oil content of the reservoir along the horizontal section of the horizontal well have great difference, and meanwhile, the volume fracturing of the horizontal well is high in cost, and the conventional volume fracturing transformation without optimization is carried out, so that the horizontal development productivity is low, the development cost is high, and finally, great development economic benefit loss is caused.
The conventional horizontal well volume fracturing method rarely considers the influence of heterogeneity along a horizontal well section, the seam arrangement mode is carried out according to equal distance, and the design and modification degrees of all positions are basically consistent. According to the conventional modification method, the economic benefit of horizontal well volume fracturing development is difficult to guarantee, and the development effect of the horizontal well volume fracturing technology on the unconventional reservoir is difficult to exert.
In other words, the conventional volume fracturing modification method for the horizontal well has the problem that the development economic benefit of the horizontal well cannot be guaranteed.
Disclosure of Invention
Aiming at the problems in the prior art, the application provides a volume fracturing differential modification method for a horizontal well, and solves the problem that the conventional volume fracturing modification method for the horizontal well cannot guarantee the development economic benefit of the horizontal well.
The invention discloses a differential reconstruction method for volume fracturing of a horizontal well, which comprises the following steps:
step one, data of a horizontal well of a target block are collated;
calculating the weight ratio of each parameter in the data to the initial capacity of the horizontal well according to the data of the horizontal well;
step three, establishing a horizontal well fractured dessert evaluation model according to the weight ratio of each parameter;
calculating the average sweet spot degree of the horizontal well fracturing section by using the horizontal well fracturing sweet spot evaluation model;
drawing a scatter diagram of the average dessert degree and the initial productivity of the horizontal well fracturing section, and fitting a relation curve;
step six, classifying and dividing the average dessert degree of the horizontal well fracturing section according to the initial capacity by referring to the fitting relation curve, and establishing a dessert classification standard;
step seven, establishing value intervals of the logging parameters corresponding to various desserts in the dessert classification standard according to the dessert classification standard of the horizontal well, the corresponding logging characteristics, the geological parameters and the engineering parameter classification standard;
according to the value-taking interval, utilizing a means of numerical reservoir simulation to optimally design the geometric parameters of the fractures of various desserts, and establishing a design template of a volume fracturing differential transformation scheme of the horizontal section of the horizontal well;
step nine, according to the logging data of the horizontal well, obtaining the distribution condition of the dessert degrees of various desserts along the horizontal section by utilizing the horizontal well fractured dessert evaluation model;
and step ten, designing a template according to the established volume fracturing differential reconstruction scheme based on the distribution condition of the dessert degrees of various desserts in the horizontal section, and designing the volume fracturing differential reconstruction scheme of the horizontal well to finally obtain the differential reconstruction scheme of the horizontal well.
In one embodiment, the parameters in the data include geological parameters, engineering parameters, fracture construction parameters, and initial capacity parameters of the horizontal well.
In one embodiment, in the second step, calculating the weight ratio of each parameter in the data to the initial capacity of the horizontal well respectively according to the data of the horizontal well includes calculating the initial weight ratio of each parameter in the data to the initial capacity of the horizontal well respectively by using a plurality of mathematical methods, and performing statistical averaging on the initial weight ratios by using a weighting method to finally obtain the weighted weight ratio of each parameter.
In one embodiment, the plurality of mathematical methods includes at least any two of entropy, grey correlation, analytic hierarchy, and Pearson-Mic.
In one embodiment, the step three of establishing the horizontal well fractured sweet spot evaluation model according to the weight ratio of each parameter comprises the steps of neglecting the parameter with smaller influence weight according to the weight ratio of each parameter in the data, establishing an evaluation relation model of the initial productivity and each parameter in the data by means of BP neural network and multivariate nonlinear fitting, and taking the evaluation relation model as the horizontal well fractured sweet spot evaluation model with the same price.
In one embodiment, the horizontal well fracture sweet spot evaluation model has the formula: dSynthesis of＝D1+D2
Wherein D isSynthesis ofRepresents a synthetic dessert; d1Representing a BP neural network dessert evaluation model; d2A non-linear fit dessert evaluation model is represented.
In one embodiment, in the formulation of the horizontal well fractured dessert evaluation model,
wherein, i represents the serial number of the output layer node of the hidden layer; (x) represents the activation function of the hidden layer; w is a1jl represents the weight from the input layer to the hidden layer node; w is a2 jlRepresenting the weight from the hidden layer to each output layer node; thetajA threshold value representing each node from the hidden layer to the output layer; g (x) the function is an activation function of neurons in the output layer; x is the number oflRepresenting the value of the respective parameter.
In one embodiment, in the formulation of the horizontal well fractured dessert evaluation model,
D2＝1.338-1.214x1+1.122x1 2+0.853x2-0.406x2 2-0.478x3-0.016x3 2-0.954x4+0.461x4 2+1.186x5-2.024x5 2-2.591x6+1.883x6 2-0.117x7+0.191x7 2-0.509x8+0.274x8 2+0.522x9-0.481x9 2
wherein x is1Represents the argillaceous content; x is the number of2Represents porosity; x is the number of3Represents the permeability; x is the number of4Represents the horizontal principal stress difference; x is the number of5Represents the Young's modulus; x is the number of6Represents the Poisson's ratio; x is the number of7Representing the rock brittleness index; x is a radical of a fluorine atom8Represents the oil/gas saturation; x is the number of9Representing the oil layer thickness.
In one embodiment, in step six, the dessert degrees of the horizontal well fracturing section are classified into four categories according to the initial capacity size, wherein the sweetness value D1 of the category I dessert is: d1 is more than 0.59, and the sweetness value D2 of the type II dessert is as follows: d2 is more than or equal to 0.56 and less than or equal to 0.59, and the sweetness value D3 of the type III dessert is as follows: d3 is more than or equal to 0.51 and less than or equal to 0.56, and the sweetness value D4 of the non-dessert is as follows: d4 < 0.51.
In one embodiment, the step one, the step of collating the data of the horizontal well of the target block comprises a step of rearranging the data after each fracturing construction of the horizontal well.
The features mentioned above can be combined in various suitable ways or replaced by equivalent features as long as the object of the invention is achieved.
Compared with the prior art, the differential reconstruction method for the volume fracturing of the horizontal well at least has the following beneficial effects:
the method has the advantages that relevant data of the developed horizontal well are used as sample data, heterogeneous dessert distribution of the horizontal section of the horizontal well is evaluated and analyzed, and then a differential transformation scheme is designed for different dessert regions of the horizontal section of the horizontal well according to physical properties and oil content levels of all positions of the horizontal section, so that the transformation effect of volume fracturing is exerted to the maximum extent, the fracturing transformation cost is controlled, and further the economic benefit of horizontal well development is guaranteed.
Drawings
The invention will be described in more detail hereinafter on the basis of embodiments and with reference to the drawings. Wherein:
fig. 1 shows a method flow diagram of a volumetric fracture differential modification method of a horizontal well of the present invention;
FIG. 2 is a graph showing the weight distribution of the engineering parameters of the well area to the initial capacity;
FIG. 3 is a diagram illustrating a weight distribution of geologic parameters of the well area to initial productivity according to an embodiment of the present invention;
FIG. 4 is a graph showing a fit of initial productivity and sweetness value for a well according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating a cookie type partitioning result for the well zone in an embodiment of the present invention;
FIG. 6 is a graph showing the natural gamma reduction coefficient versus resistivity for the well in an embodiment of the present invention;
FIG. 7 is a graph showing the natural potential vs. resistivity for the well region in an embodiment of the present invention;
FIG. 8 shows various sweet spot profiles for the P17 well horizontal segment in an example of the present invention;
FIG. 9 shows a differential fracture reconstruction scheme for the horizontal section of a P17 well in an example of the invention;
fig. 10 shows a graphical representation of the revenue and investment curves for the differential extent of fracturing modification of the horizontal section of a P17 well in an embodiment of the present invention.
In the drawings, like parts are provided with like reference numerals. The drawings are not to scale.
Detailed Description
The invention will be further explained with reference to the drawings.
As shown in fig. 1, the invention provides a differential reconstruction method for volume fracturing of a horizontal well, which comprises the following steps:
step one, data of a horizontal well of a target block are collated;
calculating the weight ratio of each parameter in the data to the initial capacity of the horizontal well according to the data of the horizontal well;
step three, establishing a horizontal well fractured dessert evaluation model according to the weight ratio of each parameter;
calculating the average sweet spot degree of the horizontal well fracturing section by using the horizontal well fracturing sweet spot evaluation model;
drawing a scatter diagram of the average dessert degree and the initial productivity of the horizontal well fracturing section, and fitting a relation curve;
step six, classifying and dividing the dessert degree of the horizontal fracturing section according to the initial capacity by referring to the fitting relation curve, and establishing a dessert classification standard;
step seven, establishing value intervals of the logging parameters corresponding to various desserts in the dessert classification standard according to the dessert classification standard of the horizontal well, the corresponding logging characteristics, the geological parameters and the engineering parameter classification standard;
step eight, optimally designing geometric parameters of the fractures of various desserts by means of numerical reservoir simulation according to the value interval, and establishing a design template of a volume fracturing differential transformation scheme of the horizontal section of the horizontal well;
step nine, according to the logging data of the horizontal well, obtaining the distribution condition of the dessert degrees of various desserts along the horizontal section by utilizing the horizontal well fractured dessert evaluation model;
and step ten, designing a template according to the established volume fracturing differential reconstruction scheme based on the distribution condition of the dessert degrees of various desserts in the horizontal section, and designing the volume fracturing differential reconstruction scheme of the horizontal well to finally obtain the differential reconstruction scheme of the horizontal well.
According to the steps, related data of the developed horizontal well are used as sample data, heterogeneous dessert distribution of the horizontal section of the horizontal well is evaluated and analyzed, and then a differential transformation scheme is designed for different dessert regions of the horizontal section of the horizontal well according to physical properties and oil content levels of all positions of the horizontal section, so that the transformation effect of volume fracturing is exerted to the maximum extent, the fracturing transformation cost is controlled, and the economic benefit of horizontal well development is further guaranteed.
Specifically, in one embodiment, the parameters in the data include geological parameters, engineering parameters, fracture construction parameters, and initial productivity parameters of the horizontal well.
Specifically, in one embodiment, in the second step, according to the data of the horizontal well, calculating the weight ratio of each parameter in the data to the initial capacity of the horizontal well respectively includes calculating the initial weight ratio of each parameter in the data to the initial capacity of the horizontal well respectively by using a plurality of mathematical methods, and performing statistical averaging on the initial weight ratios by using a weighting method to finally obtain the weighted weight ratio of each parameter after weighting.
In the above steps, the initial weight ratio of each parameter is calculated by various mathematical methods, and then weighted average is performed to obtain the weighted weight ratio of each parameter. Therefore, the accuracy of modeling data is improved, and the modeling precision of the horizontal well fractured dessert evaluation model is further improved.
Specifically, in one embodiment, the plurality of mathematical methods includes at least two of entropy, grey correlation, analytic hierarchy, and Pearson-Mic.
Specifically, in one embodiment, in the third step, the establishing of the horizontal well fractured sweet spot evaluation model according to the weight ratio of each parameter includes the steps of neglecting the parameter with smaller influence weight according to the weight ratio of each parameter in the data, establishing an evaluation relation model of the initial productivity and each parameter in the data by means of a BP neural network and multivariate nonlinear fitting, and taking the evaluation relation model as the horizontal well fractured sweet spot evaluation model at the equivalent value.
In the steps, parameters with smaller influence weight are ignored, so that initial input data of modeling is simplified, the modeling speed of the horizontal well fractured dessert evaluation model is increased, and meanwhile, the error rate of modeling is reduced.
Specifically, in one embodiment, the step one, the collating the data of the horizontal well of the target block includes rearranging the data after each fracturing construction of the horizontal well.
In the steps, the data are rearranged after each horizontal well fracturing construction and added into the database, so that the initial input data of the horizontal well fracturing dessert evaluation model can be updated, the initial input data can be more accurate, and the horizontal well fracturing dessert evaluation model with high accuracy can be established. Namely, a new evaluation model is learned and established again, so that the accuracy of the evaluation model is improved, and the effectiveness of later-stage modification is improved.
In the following, a P17 well (horizontal well) of a certain well zone is taken as an example to explain the differential modification method for volume fracturing of the horizontal well of the present application:
step one, data of a P17 well are collated;
specifically, the data for the P17 well includes:
geological parameters;
the method specifically comprises reservoir thickness, porosity, saturation, shale content, permeability, hydrocarbon content and the like;
engineering parameters;
the material specifically comprises Young modulus, Poisson's ratio, brittleness index, tensile strength, fracture toughness, fracture pressure, horizontal stress difference and the like;
thirdly, fracturing construction parameters;
the method specifically comprises the steps of ground liquid entering amount, sand amount, discharge capacity, horizontal fracturing section length and the like;
fourthly, initial productivity parameters are obtained;
specifically, the method comprises the steps of P17 well initial liquid production, initial oil production and the like.
Step two, calculating the weight ratio of each parameter in the data to the initial capacity of the P17 well according to the data of the P17 well;
specifically, an entropy method calculation method, a grey correlation analysis method and a Person-Mic method are adopted to calculate the initial weight ratio of each parameter in the data to the initial production energy of the P17 well respectively,
(1) the entropy method calculation method comprises the following steps:
calculating the proportion of the ith sample in the index under the j influence factor
In the formula, PijThe proportion of the jth influencing factor to the overall value of the factor;
② calculating entropy of j factor
According to the index proportion calculation result, calculating the entropy value of each influence factor by using the following formula, wherein the formula is shown as (1.2):
in the formula, k-is related to the number of horizontal well samples, and is generally 1/(lnm);
ej-entropy value of the jth factor;
calculating the difference coefficient of the j factor
According to the analysis, the larger the difference coefficient of the influencing factors is, the larger the evaluation effect on the scheme is, and the smaller the entropy value is; therefore, the difference coefficient of the influencing factors is calculated according to the entropy value, as shown in formula (1.3):
gj＝1-ej (1.3)
in the formula, gj-coefficient of difference of the j factor;
weight calculation
Calculating the weight occupied by the jth factor according to the calculation result of the difference coefficient of the jth factor, wherein the formula (1.4) is as follows:
through the calculation process, the influence weights of geological factors, engineering factors, construction parameters and the like on the productivity (initial productivity) can be obtained respectively.
(2) Grey correlation analysis method:
finding a difference sequence
On the basis of normalizing the values of all parameters, the absolute difference between the values of all influencing factors (geological factors, engineering factors and construction parameters) and the evaluation index (horizontal well productivity) in each sample is as follows (1.5):
△i＝|xindex (es)(k)-xi(k)| (1.5)
In the formula, xi is the value of influence factors (geological factors, engineering factors and construction parameters);
x index-evaluation index (horizontal well productivity) value;
Δ i — absolute difference;
② two-stage minimum difference and maximum difference are obtained
According to the absolute difference result calculated above, the minimum value and the maximum value are searched, specifically, the formulas (1.6) and (1.7):
in the formula, Vmin-two levels of minimum difference;
Vmax-a two-level maximum difference;
computing correlation coefficient according to formula
Substituting the above calculation result into a correlation coefficient calculation formula, as shown in equation (1.8):
in the formula, xii(k) The relative difference value of the influence factor i and the value of the horizontal well productivity;
fourthly, calculating the degree of association
Because a plurality of correlation coefficients exist between the influence factors and the evaluation indexes, and the information is too dispersed, the plurality of correlation coefficients are processed in a centralized manner; the specific treatment method is as shown in formula (1.9):
in the formula, N is the number of sample horizontal wells;
through the calculation process, the influence weight of geological factors, engineering factors, construction parameters and the like (all parameters) on the productivity (initial productivity) can be obtained respectively.
(3) The Person-Mic method:
(ii) Pearson correlation coefficient calculation
The Pearson correlation coefficient between two variables is defined as the quotient of the covariance and the standard deviation between the two variables, and the specific calculation formula is shown as the following formula:
where Cov (X, Y) -represents the covariance of the two variables;
SX、SY-represents the standard deviation of the two variables respectively.
Calculation of MIC values
I. Given i and j, meshing a scatter diagram formed by X, Y in i columns and j rows, and solving;
dispersing two variables into a two-dimensional space which is subjected to grid division in the direction of X, Y, and solving a maximum mutual confidence value according to the falling condition of a current point in each square and a mutual information calculation formula.
II, normalizing the maximum mutual information value;
and dividing the maximum mutual information value obtained in the last step by log (min (X, Y)), so as to obtain the normalization process.
Selecting the maximum value of mutual information under different scales as an MIC value;
calculating the value of M (X, Y, D, i, j) in each case, given a large number of values of (i, j); then, the maximum value among all M (X, Y, D, i, j) is judged as the MIC value.
Specifically, in one embodiment, statistically averaging the parameters by a weighting method to finally obtain weighted weight ratios of the weighted parameters includes: .
The three methods are used for carrying out statistical averaging on the calculation results of all the influence factors, and the specific calculation method is as follows:
in the formula, WiRepresents the integrated weight of the i factor in each method, WijThe weighted weight value of the i factor (i parameter) is calculated on behalf of the j method.
The weighted weight ratios of the various parameters of the P17 well are arranged into a graph (see FIGS. 2 and 3)
Step three, establishing a horizontal well fracturing dessert evaluation model of the P17 well according to the weight ratio of each parameter;
specifically, in one embodiment, the formula of the horizontal well fractured sweet spot evaluation model is:
Dsynthesis of＝D1+D2
Wherein D isSynthesis ofRepresents a synthetic dessert; d1Representing a BP neural network dessert evaluation model; d2A non-linear fit dessert evaluation model is represented.
It should be noted that the formula is established by means of BP neural network and multivariate nonlinear fitting, an evaluation relation model of each parameter in the initial productivity and data is established, and the model is used as a horizontal well fractured dessert evaluation model. Therefore, the modeling precision is greatly improved, and a more accurate design result diagram of the differential fracturing transformation scheme of the horizontal well horizontal section can be obtained through the horizontal well fractured dessert evaluation model subsequently. And further, the transformation effect of the volume fracturing is maximally exerted, the fracturing transformation cost is controlled, and the economic benefit of the horizontal well development is further ensured.
In particular, in one embodiment, in the formulation of the horizontal well fractured sweet spot evaluation model,
wherein, i represents the serial number of the output layer node of the hidden layer; (x) represents the activation function of the hidden layer; w is a1 jlRepresenting the weight from the input layer to the hidden layer node; w is a2 jlRepresenting the weight from the hidden layer to each output layer node; thetajA threshold value representing each node from the hidden layer to the output layer; g (x) the function is an activation function of neurons in the output layer; x is the number oflRepresenting the value of the respective parameter.
In particular, in one embodiment, in the formulation of the horizontal well fractured sweet spot evaluation model,
D2＝1.338-1.214x1+1.122x1 2+0.853x2-0.406x2 2-0.478x3-0.016x3 2-0.954x4+0.461x4 2+1.186x5-2.024x5 2-2.591x6+1.883x6 2-0.117x7+0.191x7 2-0.509x8+0.274x8 2+0.522x9-0.481x9 2
wherein x is1Represents the argillaceous content; x is the number of2Represents porosity; x is the number of3Represents the permeability; x is the number of4Represents the horizontal principal stress difference; x is the number of5Represents the Young's modulus; x is a radical of a fluorine atom6Represents the poisson ratio; x is the number of7Representing the rock brittleness index; x is the number of8Represents the oil/gas saturation; x is the number of9Representing the oil layer thickness (see table 1 below).
TABLE 1
Calculating the average sweet spot degree of the horizontal well fracturing section by using the horizontal well fracturing sweet spot evaluation model;
step five, drawing a scatter diagram of the average dessert degree and the initial productivity of the horizontal well fracturing section according to the horizontal well fracturing dessert evaluation model, and fitting a relation curve (see fig. 4);
step six, classifying and dividing the average dessert degree of the horizontal well fracturing section according to the initial capacity by referring to the fitting relation curve, and establishing a dessert classification standard;
in particular, the dessert sorting criteria are characterized by table 2 and fig. 5;
table 2 dessert type partition value range statistical table
Step seven, establishing value intervals of the logging parameters corresponding to various desserts in the dessert classification standard according to the dessert classification standard of the horizontal well, the corresponding logging characteristics, the geological parameters and the engineering parameter classification standard;
specifically, the value intervals of the logging parameters corresponding to various desserts in the desserts classification standard are represented by table 3, fig. 6 and fig. 7;
TABLE 3 interval of values of logging parameters corresponding to various desserts
And step eight, optimally designing the geometric parameters of the fractures of various desserts by means of numerical reservoir simulation according to the value intervals, establishing a design template of a volume fracturing differential transformation scheme of the horizontal section of the horizontal well, and representing the design template in a table form, which is shown in the following table 4.
TABLE 4 volume fracturing differential reconstruction scheme design template
Step nine, according to the logging data of the horizontal well, obtaining the sweetness type distribution condition of each position along the horizontal section by utilizing a horizontal well fractured dessert evaluation model (see fig. 8);
step ten, based on the dessert distribution situation of each position of the horizontal section, designing a template according to the established volume fracturing differential transformation scheme (see table 4), designing the volume fracturing differential transformation scheme of the P17 well, and finally obtaining the differential transformation scheme of the horizontal section of the P17 well (see fig. 9), namely evaluating and calculating the dessert types of different positions of the horizontal section of the P17 well, wherein the dessert types mainly comprise a type III dessert region, a type II dessert region and the like (as shown by marks in the figure), and designing different transformation scales and corresponding parameters (including fracture length and the like) for each dessert type of different regions according to the volume fracturing differential transformation design template.
Based on the research, the problems of insufficient fracturing modification and ineffective fracturing of each horizontal section of the P17 well can be solved, and the purpose of greatly improving the economic benefit of horizontal well volume fracturing is achieved.
Specifically, by means of numerical simulation, the horizontal well profits of the type I dessert area, the type II dessert area and the type III dessert area under different modification degrees are simulated and calculated, and the corresponding modification expenses under different modification degrees are calculated according to a modification cost calculation method, so that as shown in fig. 10, the abscissa of the modification cost is the modification degree, and the ordinate of the modification cost includes not only the income of the various desserts but also the investment of the various desserts.
Specifically, three revenue curves (reflecting the revenue of the three types of dessert at different levels of modification, respectively) are plotted in fig. 10, along with a modification cost line (reflecting the cost invested at different levels of modification).
Specifically, as shown in fig. 10, with increasing scale of modification, the revenue obtained for type I desserts is the greatest, type II desserts are the next lowest, and type III desserts are the least (at the same degree of modification, i.e. the same abscissa); according to the comparison between various dessert income curves and the modification cost, the following can be determined:
1. different types of dessert zones in the horizontal section can correspond to different optimal fracturing modification degrees;
2. the maximum profit value of the type I dessert is obtained under the transformation degree of 0.11;
3. the type II dessert obtains the maximum profit value under the transformation degree of 0.07;
4. the type III dessert obtains the maximum profit value under the transformation degree of 0.03;
it can be seen that as the dessert grade increases, the more optimal modification, for different dessert types of P17 well, a modification scheme (differential modification scheme) is established in match. Therefore, the fine fracturing modification of the horizontal well can be realized by using a differential modification scheme, so that the optimal modification degree can be designed for various dessert regions of the horizontal section of the P17 well, and the optimal economic benefit is realized.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "bottom", "top", "front", "rear", "inner", "outer", "left", "right", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the present invention.
Although the invention herein has been described with reference to particular embodiments, it is to be understood that these embodiments are merely illustrative of the principles and applications of the present invention. It is therefore to be understood that numerous modifications may be made to the illustrative embodiments and that other arrangements may be devised without departing from the spirit and scope of the present invention as defined by the appended claims. It should be understood that various dependent claims and the features described herein may be combined in ways different from those described in the original claims. It is also to be understood that features described in connection with individual embodiments may be used in other described embodiments.
Claims (10)
1. A differential reconstruction method for volume fracturing of a horizontal well is characterized by comprising the following steps:
step one, data of a horizontal well of a target block are collated;
calculating the weight ratio of each parameter in the data to the initial capacity of the horizontal well according to the data of the horizontal well;
step three, establishing a horizontal well fractured dessert evaluation model according to the weight ratio of each parameter;
calculating the average dessert degree of the horizontal well fracturing section by using the horizontal well fracturing dessert evaluation model;
drawing a scatter diagram of the average dessert degree of the horizontal well fracturing section and the initial yield, and fitting a relation curve;
step six, classifying and dividing the dessert degree of the horizontal well fracturing section according to the initial energy production by referring to the fitting relation curve, and establishing a dessert classification standard;
step seven, establishing value intervals of logging parameters corresponding to various desserts in the desserts classification standard according to the desserts classification standard, the corresponding logging characteristics, the geological parameters and the engineering parameter classification standard of the horizontal well;
according to the value-taking interval, utilizing a means of numerical reservoir simulation to optimally design the geometric parameters of the fractures of various desserts, and establishing a design template of a volume fracturing differential transformation scheme of a horizontal section of a horizontal well;
step nine, according to the logging data of the horizontal well, obtaining the distribution condition of the dessert degrees of various desserts along the horizontal section by utilizing the horizontal well fractured dessert evaluation model;
and step ten, designing a volume fracturing differential modification scheme of the horizontal well according to the distribution condition of the dessert degrees of various desserts in the horizontal section and the established volume fracturing differential modification scheme design template, and finally obtaining the differential modification scheme of the horizontal well.
2. The differential reconstruction method for volumetric fracturing of a horizontal well according to claim 1, wherein the parameters in the data include geological parameters, engineering parameters, fracturing construction parameters and initial productivity parameters of the horizontal well.
3. The differential modification method for the volume fracturing of the horizontal well according to claim 1, wherein in the second step, according to the data of the horizontal well, calculating the weight ratio of each parameter in the data to the initial capacity of the horizontal well comprises calculating the initial weight ratio of each parameter in the data to the initial capacity of the horizontal well by adopting a plurality of mathematical methods, performing statistical averaging on the initial weight ratios by using a weighting method, and finally obtaining the weighted weight ratio of each parameter.
4. The differential modification method for volume fracturing of the horizontal well according to claim 3, wherein the plurality of mathematical methods at least comprise any two of entropy method, grey correlation analysis method, analytic hierarchy process and Pearson-Mic method.
5. The differential modification method for the volume fracturing of the horizontal well according to claim 1, wherein the step three of establishing the horizontal well fracturing sweet spot evaluation model according to the weight ratio of each parameter comprises the steps of neglecting the parameter with smaller influence weight according to the weight ratio of each parameter in the data, establishing an evaluation relation model of each parameter in the data and the initial productivity by means of BP neural network and multivariate nonlinear fitting, and taking the equivalence as the horizontal well fracturing sweet spot evaluation model.
6. The differential modification method for the volume fracturing of the horizontal well according to claim 5, wherein the formula of the horizontal well fracturing sweet spot evaluation model is as follows:
Dsynthesis of＝D1+D2
Wherein D isSynthesis ofRepresents a complex dessert; d1Representing a BP neural network dessert evaluation model; d2A non-linear fit dessert evaluation model is represented.
7. The differential modification method for the volume fracturing of the horizontal well according to claim 6, wherein in the formula of the horizontal well fracturing sweet spot evaluation model,
wherein, i represents the serial number of the output layer node of the hidden layer; (x) represents the activation function of the hidden layer;
representing the weight from the input layer to the hidden layer node;
representing the weight from the hidden layer to each output layer node; thetajA threshold value representing each node from the hidden layer to the output layer; g (x) the function is an activation function of neurons in the output layer; x is a radical of a fluorine atomlRepresenting the value of the respective parameter.
8. The differential modification method for the volume fracturing of the horizontal well according to claim 6, wherein in the formula of the horizontal well fracturing sweet spot evaluation model,
D2＝1.338-1.214x1+1.122x1 2+0.853x2-0.406x2 2-0.478x3-0.016x3 2-0.954x4+0.461x4 2+1.186x5-2.024x5 2-2.591x6+1.883x6 2-0.117x7+0.191x7 2-0.509x8+0.274x8 2+0.522x9-0.481x9 2
wherein x is1Represents the argillaceous content; x is the number of2Represents porosity; x is the number of3Represents the permeability; x is the number of4Represents the horizontal principal stress difference; x is the number of5Represents the Young's modulus; x is the number of6Represents the poisson ratio; x is the number of7Representing the rock brittleness index; x is a radical of a fluorine atom8Represents the oil/gas saturation; x is the number of9Representing the oil layer thickness.
9. The horizontal well volume fracturing differentiation modification method according to claim 1, wherein in step six, the dessert degrees of the horizontal well fracturing section are classified into four types according to the initial capacity, wherein the sweetness value D1 of the type I dessert is: d1 is more than 0.59, and the sweetness value D2 of the type II dessert is as follows: d2 is more than or equal to 0.56 and less than or equal to 0.59, and the sweetness value D3 of the type III dessert is as follows: d3 is not less than 0.51 and not more than 0.56, and the sweetness value D4 of the non-dessert is as follows: d4 < 0.51.
10. The differential modification method for the volume fracturing of the horizontal well according to claim 1, wherein the step one of collating the data of the horizontal well of the target block comprises a step of rearranging the data after each fracturing construction of the horizontal well.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210111563.2A CN114595628B (en) | 2022-01-29 | 2022-01-29 | Differential transformation method for volume fracturing of horizontal well |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210111563.2A CN114595628B (en) | 2022-01-29 | 2022-01-29 | Differential transformation method for volume fracturing of horizontal well |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114595628A true CN114595628A (en) | 2022-06-07 |
| CN114595628B CN114595628B (en) | 2024-05-03 |
Family
ID=81806029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210111563.2A Active CN114595628B (en) | 2022-01-29 | 2022-01-29 | Differential transformation method for volume fracturing of horizontal well |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114595628B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116307871A (en) * | 2023-03-06 | 2023-06-23 | 中国地质调查局油气资源调查中心 | Method for evaluating shale microcosmic reservoir space effectiveness |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103835691A (en) * | 2014-04-03 | 2014-06-04 | 北京捷贝通石油技术有限公司 | Natural selection sweet heart temporary plugging volume fracturing method |
| WO2016041189A1 (en) * | 2014-09-19 | 2016-03-24 | 杨顺伟 | Method for evaluating shale gas reservoir and seeking desert area |
| CN106909758A (en) * | 2017-04-10 | 2017-06-30 | 西南石油大学 | A kind of new method of fine and close oil reservoir-level well multistage sub-clustering perforating site optimization design |
| CN107229989A (en) * | 2016-03-25 | 2017-10-03 | 中国石油化工股份有限公司 | A kind of staged fracturing of horizontal well cluster optimization of perforation method |
| CN109063232A (en) * | 2018-06-15 | 2018-12-21 | 中国石油化工股份有限公司江汉油田分公司石油工程技术研究院 | One kind being used for shale gas well reservoir "sweet spot" evaluation method |
| US10677961B1 (en) * | 2019-07-08 | 2020-06-09 | Southwest Petroleum University | Method for optimizing perforation parameters to maintain uniform fracture growth in multi-stage hydraulic fracturing of horizontal well |
| US20210003727A1 (en) * | 2019-07-04 | 2021-01-07 | Chengdu University Of Technology | Optimization design method for volumetric fracturing construction parameters of infilled well of unconventional oil and gas reservoir |
| CN113673771A (en) * | 2021-08-24 | 2021-11-19 | 中国石油化工股份有限公司 | Shale gas horizontal well fracturing segmentation method |
-
2022
- 2022-01-29 CN CN202210111563.2A patent/CN114595628B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103835691A (en) * | 2014-04-03 | 2014-06-04 | 北京捷贝通石油技术有限公司 | Natural selection sweet heart temporary plugging volume fracturing method |
| WO2016041189A1 (en) * | 2014-09-19 | 2016-03-24 | 杨顺伟 | Method for evaluating shale gas reservoir and seeking desert area |
| CN107229989A (en) * | 2016-03-25 | 2017-10-03 | 中国石油化工股份有限公司 | A kind of staged fracturing of horizontal well cluster optimization of perforation method |
| CN106909758A (en) * | 2017-04-10 | 2017-06-30 | 西南石油大学 | A kind of new method of fine and close oil reservoir-level well multistage sub-clustering perforating site optimization design |
| CN109063232A (en) * | 2018-06-15 | 2018-12-21 | 中国石油化工股份有限公司江汉油田分公司石油工程技术研究院 | One kind being used for shale gas well reservoir "sweet spot" evaluation method |
| US20210003727A1 (en) * | 2019-07-04 | 2021-01-07 | Chengdu University Of Technology | Optimization design method for volumetric fracturing construction parameters of infilled well of unconventional oil and gas reservoir |
| US10677961B1 (en) * | 2019-07-08 | 2020-06-09 | Southwest Petroleum University | Method for optimizing perforation parameters to maintain uniform fracture growth in multi-stage hydraulic fracturing of horizontal well |
| CN113673771A (en) * | 2021-08-24 | 2021-11-19 | 中国石油化工股份有限公司 | Shale gas horizontal well fracturing segmentation method |
Non-Patent Citations (3)
| Title |
|---|
| 李旻翾;孙敬;胡佳妮;刘德华;袁博;: "基于组合权重法的页岩气水平井段评价模型及其应用", 数学的实践与认识, no. 13, 8 July 2020 (2020-07-08) * |
| 李旻翾;孙敬;胡佳妮;刘德华;袁博;: "页岩气水平井段甜点优选模型", 科学技术与工程, no. 24, 28 August 2020 (2020-08-28) * |
| 陈桂华;白玉湖;陈晓智;徐兵祥;祝彦贺;冯汝勇;陈岭;: "页岩油气纵向综合甜点识别新方法及定量化评价", 石油学报, no. 11, 25 November 2016 (2016-11-25) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116307871A (en) * | 2023-03-06 | 2023-06-23 | 中国地质调查局油气资源调查中心 | Method for evaluating shale microcosmic reservoir space effectiveness |
| CN116307871B (en) * | 2023-03-06 | 2023-10-27 | 中国地质调查局油气资源调查中心 | Method for evaluating shale microcosmic reservoir space effectiveness |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114595628B (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110674841B (en) | Logging curve identification method based on clustering algorithm | |
| CN104239666B (en) | A kind of Comprehensive Evaluation of Coal Bed Gas method based on analytic hierarchy process (AHP) | |
| CN106703776B (en) | Fracturing parameter optimization method | |
| CN101266299B (en) | Method for forecasting oil gas utilizing earthquake data object constructional features | |
| CN109345007B (en) | Advantageous reservoir development area prediction method based on XGboost feature selection | |
| CN110287516B (en) | Comprehensive evaluation method for compressibility of horizontal fractured well of shale gas reservoir | |
| CN112308269A (en) | Yield prediction method and device for low-permeability oil and gas reservoir | |
| CN114358427B (en) | Method for predicting final recoverable reserves of shale gas well | |
| CN115906675B (en) | Well position and injection and production parameter joint optimization method based on time sequence multi-target prediction model | |
| CN109902881A (en) | The PM2.5 concentration prediction method merged based on multi-variate statistical analysis and LSTM | |
| CN114969953B (en) | Optimized shield underpass tunnel design method and equipment based on Catboost-NSGA-III | |
| CN113240527A (en) | Bond market default risk early warning method based on interpretable machine learning | |
| CN106569272A (en) | Earthquake attribute fusion method based on data property space ascending dimension | |
| CN114595628B (en) | Differential transformation method for volume fracturing of horizontal well | |
| CN113722997A (en) | New well dynamic yield prediction method based on static oil and gas field data | |
| CN113627639A (en) | Well testing productivity prediction method and system for carbonate fracture-cave reservoir | |
| CN107165621A (en) | A kind of method that utilization clustering method recognizes many well sedimentary micros | |
| CN110717270A (en) | Oil and gas reservoir simulation method based on data | |
| CN113762614A (en) | Shale gas well productivity prediction method based on static oil and gas field data | |
| CN113807021A (en) | Gas well productivity grade prediction method based on index analysis and multi-model fusion | |
| CN104143117B (en) | A kind of related coefficient extracting method between power grid specific load and daily load | |
| CN112149922A (en) | Method for predicting severity of accident in exit and entrance area of down-link of highway tunnel | |
| CN107403391A (en) | A kind of optimal screening method for oil field development pre-arranged project | |
| CN116562428A (en) | Fracturing construction parameter optimization method based on machine learning | |
| CN114638147A (en) | Method for determining fracturing process parameters of oil and gas reservoir |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |