CN109214026A - Shale gas horizontal well initial-stage productivity prediction method - Google Patents
Shale gas horizontal well initial-stage productivity prediction method Download PDFInfo
- Publication number
- CN109214026A CN109214026A CN201710551814.8A CN201710551814A CN109214026A CN 109214026 A CN109214026 A CN 109214026A CN 201710551814 A CN201710551814 A CN 201710551814A CN 109214026 A CN109214026 A CN 109214026A
- Authority
- CN
- China
- Prior art keywords
- shale gas
- factors
- horizontal well
- well
- gas horizontal
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000010276 construction Methods 0.000 claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000000556 factor analysis Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000005553 drilling Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 238000003745 diagnosis Methods 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 239000004576 sand Substances 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 229910052500 inorganic mineral Inorganic materials 0.000 claims description 4
- 239000011707 mineral Substances 0.000 claims description 4
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 3
- 229910052799 carbon Inorganic materials 0.000 claims description 3
- 239000012530 fluid Substances 0.000 claims description 3
- 238000002347 injection Methods 0.000 claims description 3
- 239000007924 injection Substances 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 description 20
- 238000004458 analytical method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000007405 data analysis Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000011435 rock Substances 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012097 association analysis method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000011425 standardization method Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting initial productivity of a shale gas horizontal well, and belongs to the field of shale gas development. The method comprises the following steps: acquiring single-well logging information and construction information of a plurality of shale gas horizontal wells of a block to be detected, and extracting influence factors influencing initial productivity of the shale gas horizontal wells from the single-well logging information and the construction information; determining main control factors and secondary control factors influencing the initial productivity of the shale gas horizontal well from the influencing factors by using a multi-factor analysis method, wherein the influence degree of the main control factors to the secondary control factors on the initial productivity of the shale gas horizontal well is gradually reduced; and according to a neural network algorithm, establishing a shale gas horizontal well initial productivity prediction model by using the main control factors and the secondary control factors. The method is not only suitable for analyzing the data of the shale gas horizontal well initial capacity which is in a linear characteristic under the influence of multiple factors, but also suitable for analyzing the data which is in a nonlinear characteristic so as to analyze the initial capacity under the control of the multiple factors.
Description
Technical Field
The invention relates to the field of shale gas development, in particular to a method for predicting initial productivity of a shale gas horizontal well.
Background
In the process of shale gas development of the shale gas horizontal well, accurate prediction of the initial productivity of the shale gas horizontal well has important significance for single well production allocation. Therefore, it is necessary to provide a method for predicting the initial productivity of shale gas horizontal wells.
The prior art provides a method for predicting initial productivity of a shale gas horizontal well, which comprises the following steps: 1) establishing a shale gas drilling, logging interpretation and fracturing parameter database of a block to be tested; 2) analyzing the single influence factor of the shale gas product by using a database; 3) carrying out multi-factor sensitivity analysis by using an orthogonal experiment method, quantitatively grading the sensitivity of the main control factor on the influence of the shale gas horizontal well productivity, and sequencing and determining the most main parameters of the shale gas horizontal well initial productivity according to the sensitivity; 4) and establishing an initial capacity prediction equation of the shale gas horizontal well by adopting a multivariate linear regression fitting method according to the exponential correlation between the capacity and the single factor in the main control factor.
The inventor finds that the prior art has at least the following technical problems:
because the initial productivity influence factors of the shale gas horizontal well are more, and the initial productivity of the shale gas horizontal well does not necessarily have linear correlation with each influence factor, a certain error exists in the shale gas horizontal well initial productivity prediction equation established by the prior art through a multiple linear regression fitting method.
Disclosure of Invention
In order to solve the technical problem, the embodiment of the invention provides a shale gas horizontal well initial productivity prediction method. The specific technical scheme is as follows:
a shale gas horizontal well initial productivity prediction method comprises the following steps: acquiring single-well logging information and construction information of a plurality of shale gas horizontal wells of a block to be detected, and extracting influence factors influencing initial productivity of the shale gas horizontal wells from the single-well logging information and the construction information;
characterized in that the method further comprises: determining main control factors and secondary control factors influencing the initial productivity of the shale gas horizontal well from the influencing factors by using a multi-factor analysis method, wherein the influence degree of the main control factors to the secondary control factors on the initial productivity of the shale gas horizontal well is gradually reduced;
and according to a neural network algorithm, establishing a shale gas horizontal well initial productivity prediction model by using the main control factors and the secondary control factors.
Specifically, preferably, the method further comprises: predicting the initial productivity of the new well by using the shale gas horizontal well initial productivity prediction model to obtain the test yield of the new well;
extracting the main control factors and the secondary control factors from single well logging information and construction information of the new well, and forming a learning sample by matching with the test yield of the new well;
and learning the shale gas horizontal well initial productivity prediction model by using the learning sample so as to obtain the learned shale gas horizontal well initial productivity prediction model.
Specifically, the influencing factors preferably include: the method comprises the following steps of total organic carbon content, reservoir gas content, reservoir porosity, brittle mineral content of a reservoir, effective drilling rate of a type I reservoir, drilling length of a highest-quality small layer in a Longmaxi group shale reservoir, fracturing series, fracturing fluid injection strength during fracturing construction and sand adding strength during fracturing construction.
Specifically, as an optimal selection, the determining, by using a multi-factor analysis method, a main control factor and a secondary control factor which influence the initial productivity of the shale gas horizontal well from the influencing factors includes:
determining a reference series of reaction system behavior characteristics and a comparison series of influence system behaviors, taking a plurality of shale gas horizontal wells as sample wells, taking the test yield of the sample wells as the reference series, and taking the influence factors as the comparison series;
carrying out non-dimensionalization processing on the reference number sequence and the comparison number sequence;
calculating a correlation coefficient of the comparison sequence to the reference sequence according to the reference sequence and the comparison sequence after non-dimensionalization processing aiming at each sample well;
acquiring the association degree of the comparison array to the reference array according to the association coefficient;
and determining the main control factor and the secondary control factor from the influence factors according to the magnitude of the association degree.
Specifically, preferably, the calculation formula of the correlation coefficient is:
wherein y (k) is a dimensionless number corresponding to the reference number sequence in the kth sample well;
xi(k) a dimensionless number, x, corresponding to the comparison array at the kth sample welliIs the ith comparison sequence;
ξi(k) x for the kth sample welliCorrelation coefficient to y;
rho is a resolution coefficient, and is taken as 0.5;
the calculation formula of the correlation degree is as follows:
wherein n is the number of sample wells.
Specifically, preferably, the reference number sequence and the comparison number sequence are subjected to non-dimensionalization processing according to an averaging method.
Specifically, as an optimization, the determining, by using the multi-factor analysis method, the main control factor and the secondary control factor that affect the initial productivity of the shale gas horizontal well from the influencing factors further includes:
presetting a test yield threshold value of a shale gas horizontal well, and classifying a plurality of shale gas horizontal wells into a high yield class and a low yield class by taking the threshold value as a boundary;
dividing each influence factor into a plurality of numerical value intervals;
acquiring the frequency of each numerical interval projected on a high-yield shale gas-like horizontal well and a low-yield shale gas-like horizontal well;
acquiring the average probability frequency of each numerical value interval according to the frequency;
calculating the ratio of the average probability frequencies corresponding to the high-yield shale gas-like horizontal well and the low-yield shale gas-like horizontal well, and acquiring the diagnosis coefficient of each numerical interval according to the ratio;
calculating the information quantity of each influence factor in a plurality of numerical value intervals according to the diagnosis coefficient;
determining the main control factor and the secondary control factor from the influence factors according to the size of the information quantity;
the calculation formula of the average probability frequency is as follows:
wherein,projecting the ith numerical interval on a high-yield shale gas horizontal well or a low-yield shale gas horizontal wellAverage probability frequency;
the calculation formula of the diagnosis coefficient is as follows:
wherein,the average probability frequency corresponding to the low-yield shale gas horizontal well is obtained;
the average probability frequency corresponding to the high-yield shale gas-like horizontal well is obtained;
the calculation formula of the information quantity is as follows:
specifically, as a preferred option, the method further includes, according to the association degree and the information amount, sequentially sorting the influence factors from large to small according to the magnitude of the influence degree;
and averaging the sequence value obtained based on the association degree and the sequence value obtained based on the information amount, and determining the main control factor and the secondary control factor from the influence factors.
Specifically, as an optimal selection, in the process of establishing the shale gas horizontal well initial productivity prediction model according to the neural network algorithm, the main control factor and the secondary control factor are used as input layers, and the test yield is used as an output layer.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the prediction method provided by the embodiment of the invention determines the main control factors and the secondary control factors which influence the initial productivity of the shale gas horizontal well by adopting a multi-factor analysis method, so that the prediction method is not only suitable for data analysis that the initial productivity of the shale gas horizontal well is in a linear characteristic under the influence of the multi-factor, but also suitable for data analysis that the initial productivity of the shale gas horizontal well is in a nonlinear characteristic. On the basis, a shale gas horizontal well initial capacity prediction model is established by utilizing the main control factors and the secondary control factors through a neural network algorithm so as to be suitable for initial capacity analysis under multi-factor control. And the neural network algorithm also has the function of continuous learning, so that the accuracy of the shale gas horizontal well initial productivity prediction model can be improved by utilizing subsequent new well data, and the shale gas horizontal well initial productivity can be predicted more accurately.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1-1 is a schematic diagram of a linear relationship between a test production rate of a production well in a production area of a Sichuan basin A and an average daily production rate in a first year according to an embodiment of the present invention;
fig. 1-2 are schematic diagrams illustrating a linear relationship between a test production of a production well in a production area of a Sichuan basin B and an average daily production in a first year according to an embodiment of the present invention;
fig. 2 is a network structure diagram of the BP neural network algorithm.
Detailed Description
Unless defined otherwise, all technical terms used in the examples of the present invention have the same meaning as commonly understood by one of ordinary skill in the art. In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below.
The embodiment of the invention provides a method for predicting initial productivity of a shale gas horizontal well, which comprises the following steps:
step 101, obtaining single-well logging information and construction information of a plurality of shale gas horizontal wells of a block to be tested, and extracting influence factors influencing initial production performance of the shale gas horizontal wells from the single-well logging information and the construction information.
And 102, determining main control factors and secondary control factors influencing the initial productivity of the shale gas horizontal well from the main control factors to the secondary control factors by using a multi-factor analysis method, wherein the influence degree of the main control factors to the secondary control factors on the initial productivity of the shale gas horizontal well is gradually reduced.
And 103, establishing a shale gas horizontal well initial productivity prediction model by utilizing the main control factors and the secondary control factors according to a neural network algorithm.
The prediction method provided by the embodiment of the invention determines the main control factors and the secondary control factors which influence the initial productivity of the shale gas horizontal well by adopting a multi-factor analysis method, so that the prediction method is not only suitable for data analysis that the initial productivity of the shale gas horizontal well is in a linear characteristic under the influence of the multi-factor, but also suitable for data analysis that the initial productivity of the shale gas horizontal well is in a nonlinear characteristic. On the basis, a shale gas horizontal well initial capacity prediction model is established by utilizing the main control factors and the secondary control factors through a neural network algorithm so as to be suitable for initial capacity analysis under multi-factor control. And the neural network algorithm also has the function of continuous learning, so that the accuracy of the shale gas horizontal well initial productivity prediction model can be improved by utilizing subsequent new well data, and the shale gas horizontal well initial productivity can be predicted more accurately.
Specifically, the method for predicting the initial productivity of the shale gas horizontal well provided by the embodiment of the invention further comprises the following steps:
and 104, predicting the initial productivity of the new well by using the shale gas horizontal well initial productivity prediction model to obtain the test yield of the new well.
105, extracting main control factors and secondary control factors from single well logging data and construction data of the new well, and forming a learning sample by matching with the test yield of the new well;
and 106, learning the shale gas horizontal well initial productivity prediction model by using the learning sample, and further obtaining the learned shale gas horizontal well initial productivity prediction model.
Wherein the new well refers to a new shale gas horizontal well, different from the shale gas horizontal well mentioned in step 101.
The shale gas horizontal well initial-stage capacity prediction model is learned by using single well logging information, construction information and test yield of a new well as a learning sample, so that the accuracy of the prediction model can be gradually improved, the prediction model can be continuously and completely optimized, and the method has important significance for accurately predicting the new well initial-stage capacity.
The following is set forth for each of the above steps:
for step 101, firstly, single-well logging information and construction information of a plurality of shale gas horizontal wells of a block to be tested are obtained, and then influence factors influencing initial productivity of the shale gas horizontal wells are extracted from the single-well logging information and the construction information.
The shale gas horizontal wells are developed and matured, and logging information and construction information of the shale gas horizontal wells are acquired in the development process. And the logging information and the construction information of each shale gas horizontal well are single-well logging information and construction information. It can be understood that the logging data and the construction data refer to various scheme reports and production reports related in the shale gas development process, and influence factors influencing the initial productivity of the horizontal well can be extracted from the logging data and the construction data.
Various logging information and construction information can be extracted from single-well logging information and construction information, and the logging information and the construction information can be influence factors influencing the initial production of the shale gas horizontal well. The shale gas horizontal well, the selection of logging data and construction data of the shale gas horizontal well have important influence on the accuracy of a prediction model.
For the selection of shale gas horizontal wells, in order to improve the accuracy of a prediction model, horizontal wells with complete and as complete wellbores as possible need to be selected, and particularly, the following types of horizontal wells are excluded: horizontal wells with incomplete wellheads due to casing deformation or other reasons, horizontal wells using different fracturing technologies at the early stage, and horizontal wells with missing logging data or construction data.
For the selection of single well logging data and construction data, in order to improve the accuracy of the prediction model, the following factors need to be considered: first, the integrity of the single well log data is considered, and the collection of the data is comprehensive and consistent. Secondly, considering the diversity of the influencing factors, as the initial productivity of the shale gas horizontal well may be influenced by a plurality of factors, the reservoir factors, the drilling factors and the fracturing factors need to be comprehensively analyzed. Thirdly, considering representativeness, selecting common, normative and index data as much as possible for analysis.
Based on the above, in the embodiment of the present invention, the influencing factors include: the method comprises the following steps of total organic carbon content (TOC for short), reservoir gas content, reservoir porosity, brittle mineral content of a reservoir, effective drilling rate of a type I reservoir, drilling length of a small layer with the highest quality in a rock reservoir of the Longmaxi group, fracturing series, fracturing fluid injection strength during fracturing construction and sand adding strength during fracturing construction.
Generally, shale reservoirs are classified according to the quality of the reservoirs. For example, southwestern oil and gas field companies classify shale reservoirs in the Sichuan basin into three categories I, II and III according to reservoir quality, wherein the reservoir quality in category I is the best, and the reservoir quality in category III is the worst.
For the Longmaxi group pageThe highest quality sub-zone in a rock reservoir means that it is the best quality. For example, southwestern oil and gas field division performed a small layer partitioning of the rampart shale of the Sichuan basin shale reservoir, where Longyi is described in industry Standard1 1The small reservoir is best quality.
Step 102 indicates that a main control factor and a secondary control factor which influence the initial productivity of the shale gas horizontal well are determined from the influence factors by using a multi-factor analysis method, wherein the influence degree of the main control factor on the initial productivity of the shale gas horizontal well is greater than the secondary control factor.
Specifically, for data analysis that initial productivity of the shale gas horizontal well is in a nonlinear characteristic under the influence of multiple factors, the main control factor and the secondary control factor can be determined in the following manner:
the first determination method is to adopt a correlation analysis method: if the two factors have consistency in the change trend, namely the synchronous change degree is higher, the correlation degree of the two factors is higher; otherwise, if the degree of synchronous variation is low, the degree of correlation between the two is low.
When the main control factor and the secondary control factor are determined by using the correlation analysis method, a reference series reflecting the behavior characteristics of the system and a comparison series influencing the behavior of the system need to be determined, obviously, each influencing factor is used as the comparison series, and an evaluation index capable of representing the initial capacity of the horizontal well is used as the reference series.
Research shows that for a horizontal well which is already put into production, the corresponding test yield and the average daily yield of the first year are in a good positive correlation relationship, taking a production area built in the Sichuan basin A, B as an example, and referring to the attached drawings 1-1 and 1-2, the test yield and the average daily yield of the first year are in a good positive correlation relationship, which means that the test yield is feasible to be used as an initial productivity evaluation index of the shale gas horizontal well.
The method is characterized in that the test yield is obtained by a productivity test method before the shale gas horizontal well is put into operation, and is an important index for evaluating the horizontal well productivity. For example, Liu hong bin discloses productivity testing and evaluation of gas wells in the Processary Explorer theoretical research, which is not described in detail herein.
Based on the above, determining the primary control factor and the secondary control factor by using the association analysis method includes:
and 1021a, determining a reference series of the behavior characteristics of the reaction system and a comparison series of the influence system behavior, wherein the plurality of shale gas horizontal wells are used as sample wells, the test yield of the sample wells is used as the reference series, and the influence factors are used as the comparison series.
Step 1022a, non-dimensionalizing the reference sequence and the comparison sequence.
And step 1023a, calculating a correlation coefficient of the comparison array to the reference array according to the non-dimensionalized reference array and the comparison array for each sample well.
And step 1024a, acquiring the association degree of the comparison number array to the reference number array according to the association coefficient.
And 1025a, determining a main control factor and a secondary control factor from the influence factors according to the magnitude of the association degree.
The relevance of the comparison array to the reference array is obtained through the method, the greater the relevance, the greater the influence degree of the influence factor on the test yield is, and the smaller the relevance is, so that the main control factor and the secondary control factor can be easily determined from the influence factors by sequencing the relevance.
In step 1022a, the reference number sequence and the comparison number sequence are subjected to non-dimensionalization, and those skilled in the art realize various non-dimensionalization methods, such as a range transformation method, a normalization method, and an averaging method.
Let n values (i ═ 1,2, …, n) be assigned to index x, i.e., x1、…….xn；yiIndicates that the index x is at the secondThe value of i units after non-dimensionalization processing,is xiMean value of (a)iThe standard deviation of index x.
(1) The range conversion method comprises the following steps:
as can be seen from the above formula, when xiWhen the maximum value and the minimum value of (a) are greatly different from each other, y is decreasediThe weight of (c); when x isiWhen the maximum value of (a) is very small in difference from the minimum value of (b), y is increasediThe weight of (c). The maximum and minimum values of the index x have a large influence on its weight.
(2) The standardization method is as follows:
it can be seen from the above formula that the influence of dimension and magnitude can be eliminated by the normalization method, but the difference in the variation degree of each index x can also be eliminated, and the variance of each index is 1.
(3) The averaging method comprises the following steps:
it can be seen from the above knowledge that the method not only eliminates the influence of dimension and magnitude, but also retains the variation degree information of each index x, and is suitable for multi-factor analysis. Therefore, the embodiment of the present invention preferably performs the dimensionless process by using an averaging method.
When the dimensionless reference number sequence is denoted as y, the dimensionless value at the first time is y (1), the dimensionless value at the second time is y (2), and the dimensionless value at the kth time is y (k), the reference number sequence y can be denoted as y ═ y (1), y (2),.. once, y (n)).
The comparative number sequence after the dimensionless processing is recorded as x1，x2，......，xiThe dimensionless number for the first sample well is x (1),... the dimensionless number for the kth sample well is x (k), then the comparison sequence x can be expressed as:
x1＝(x1(1),x1(2),…,x1(k),…,x1(n))，......,xi＝(xi(1),xi(2),...,xi(k),…,xi(n))。
the above relationship between the comparison series and the reference series can be seen in the following table:
specifically, in step 1023a, the calculation formula of the correlation coefficient is:
wherein y (k) is a dimensionless number corresponding to the reference number sequence in the kth sample well;
xi(k) the dimensionless numerical value of the comparison numerical sequence corresponding to the kth sample well is shown, and i is the ith comparison numerical sequence corresponding to x;
ξi(k) x for k sample wellsiCorrelation coefficient to y;
rho is a resolution coefficient and is 0.5.
The calculation formula of the correlation degree is as follows:
wherein n is the number of sample wells.
The second method is to divide the research object into two classes, analyze the frequencies of the different value intervals of each parameter projected on the two classes of objects, and finally compare the distribution and difference conditions of the frequencies of the files belonging to the two classes, wherein the smaller the difference degree, the smaller the description information amount, which means that the influence degree of the parameter on the research object is low, and otherwise, the higher the influence degree is.
Specifically, the method comprises the following steps:
and 1021b, presetting a testing yield threshold value of the shale gas horizontal well, and classifying the shale gas horizontal wells into a high yield class and a low yield class by taking the threshold value as a boundary.
Step 1022b, divide each influencing factor into a plurality of value intervals.
And step 1023b, acquiring the frequency of each numerical value interval projected on the high-yield shale gas-like horizontal well and the low-yield shale gas-like horizontal well.
And step 1024b, acquiring the average probability frequency of each numerical value interval according to the frequency.
And 1025b, calculating the ratio of the average probability frequencies corresponding to the high-yield shale gas-like horizontal well and the low-yield shale gas-like horizontal well, and obtaining the diagnosis coefficient of each numerical interval according to the ratio.
Step 1026b, calculating the information quantity of each influence factor in a plurality of numerical value intervals according to the diagnosis coefficient;
and step 1027b, determining a main control factor and a secondary control factor from the influence factors according to the size of the information quantity.
Wherein, the calculation formula of the average probability frequency (I) is as follows:
wherein,and (4) projecting the average probability frequency of the ith numerical interval on the shale gas horizontal well with high yield or low yield.
The formula for calculating the diagnosis coefficient is as follows:
wherein,the average probability frequency corresponding to the low-yield shale gas horizontal well;
the average probability frequency corresponding to the high-yield shale gas-like horizontal well;
(III) the calculation formula of the information quantity is as follows:
the method comprises the steps of classifying a plurality of shale gas horizontal wells into a high-yield type and a low-yield type by presetting a test yield threshold of the shale gas horizontal wells and taking the threshold as a boundary, dividing the shale gas horizontal wells into a plurality of numerical value intervals based on the fact that each influence factor comprises a plurality of numerical values, respectively calculating the frequency of the numerical value intervals corresponding to the two types of shale gas horizontal wells, and further obtaining the average probability frequency of each numerical value interval, so that the information quantity of each influence factor in the plurality of numerical value intervals can be further obtained, and further the influence degree of each influence factor on the initial productivity of the horizontal wells can be obtained.
When the main control factors and the secondary control factors are determined, the main control factors and the secondary control factors can be determined not only directly through the relevance and the size of the information quantity, but also can be indirectly determined according to the size of the main control factors and the secondary control factors and the size of the influence degree, the influence factors are sequentially sorted from big to small, and the influence degree is represented to be smaller and smaller from front to back.
In order to improve the accuracy of determining the primary control factor and the secondary control factor, the method provided by the embodiment of the invention further comprises the following steps: according to the relevance and the information quantity, sequentially ordering the influence factors from large to small according to the influence degree;
and averaging the sequence value obtained based on the association degree and the sequence value obtained based on the information quantity, and determining the main control factor and the secondary control factor from the influence factors.
The number of the main control factors and the number of the secondary control factors are at least 30% of the number of the influence factors, for example, when the number of the influence factors is 9, the influence factors are sorted according to the influence degree, the first three are selected as the main control factors, and the second three are selected as the secondary control factors.
After the main control factor and the secondary control factor are determined, step 103 is adopted to establish a shale gas horizontal well initial productivity prediction model by utilizing the main control factor and the secondary control factor according to a neural network algorithm.
Specifically, a Back Propagation neural network algorithm (for short, a BP neural network algorithm) is used to establish the prediction model.
As is well known to those skilled in the art, the network structure of the BP neural network based on the error back propagation algorithm is divided into three parts: an input layer, a hidden layer, and an output layer. The working principle is divided into two processes: firstly, a forward transmission process of a working signal; second, the error signal is passed back through the process. When the actual output does not match the desired output, the error back-propagation phase is entered. And the error passes through the output layer, the weight of each layer is corrected in a mode of error gradient reduction, and the weight is reversely transmitted to the hidden layer and the input layer by layer. Through repeated forward information transmission and reverse error transmission, weights of all layers are continuously corrected to achieve the purpose of training the network, and the purpose is shown in the attached figure 2.
In the embodiment of the invention, in the process of establishing the shale gas horizontal well initial productivity prediction model according to the neural network algorithm, the main control factors and the secondary control factors, namely data of all factors, are used as input layers, and the test yield is used as an output layer.
In the process of establishing the shale gas horizontal well initial productivity prediction model, the involved model parameters are as follows:
(1) implicit layer number
Robert Hecht-Nielsen has demonstrated that a continuous function in any closed interval can be approximated by an implicit layer network, so that a three-layer network can accomplish arbitrary m-dimensional to n-dimensional mapping.
(2) Number of hidden layer nodes
An empirical formula is adopted: h 2m +1
Wherein h is the number of hidden layer nodes, and m is the number of input layer nodes.
(3) Transfer function: a tansig function;
(4) learning function: a trainlm function;
(5) training times are as follows: 10000;
(6) training a target: 1 e-6；
(7) Learning rate: 0.01.
after the model parameters are determined, corresponding program codes are compiled based on the model parameters, and then an initial productivity prediction model of the shale gas horizontal well can be established.
In modeling, a plurality of shale gas horizontal wells, for example, 24 shale gas horizontal wells can participate in analysis, for example, 4 wells which have recently completed testing can be used as verification wells (for verifying the accuracy of the prediction model), the remaining 20 wells can be used as samples for establishing the early productivity prediction model, and 14 wells are randomly selected as learning samples, 3 wells are variable samples, and 3 wells are test samples. Namely, 20 wells are used for modeling, 14 wells are used as a basis for modeling, in the neural network algorithm, 3 variable wells are used for correcting the model in the calculation, 3 test samples are used for verifying the model error, and the relative error is as small as possible, for example, less than 30%. After the prediction model is established, the simulated results of the 20 wells can be compared with the actual test yield value to obtain a suitable model.
After the subsequent shale gas horizontal well is tested successively, applying the established shale gas horizontal well initial productivity prediction model, and predicting the initial productivity of the subsequent well: the numerical values of the main control factors are input into the model, so that the yield of the new well from the test can be obtained, the initial productivity of the new well can be predicted, and the production allocation scheme is designed by combining the production effect of the produced well. With the continuous expansion of new well samples, the prediction precision of the model can be continuously increased, so that the method provided by the embodiment of the invention is a dynamic process for predicting the initial productivity of the shale gas horizontal well, and the accuracy of the prediction is gradually improved, and the basis and guidance are provided for the production allocation of a well area single well and the compilation of a gas reservoir engineering scheme.
The present invention will be further described below by way of specific examples. In the following examples, those whose operations are not subject to the conditions indicated, are carried out according to the conventional conditions or conditions recommended by the manufacturer.
Example 1
In this embodiment, taking the zone B of the sichuan basin as an example, 9 influencing factors are selected as analysis targets, that is:
①TOC；
② reservoir gas content;
③ reservoir porosity;
④ brittle mineral content;
⑤ effective drilling rate of type I reservoir;
⑥ Dragon I1 1Drilling a small layer to meet the length;
⑦ fracturing order;
⑧ liquid strength;
⑨ sand strength;
and the well B area has 35 openings of shale gas horizontal wells for completing the test, and the shale gas horizontal wells participating in the analysis have 24 openings according to the integrity of the mineshaft.
In this embodiment, the first determination method and the second determination method are respectively adopted to sort the influence degrees of the 9 factors from large to small (1, 2, 3, 4, 5, 6, 7, 8, and 9 in sequence), and the average values of the two methods are used to perform comprehensive sorting, and the results are shown in table 1:
TABLE 1 comprehensive ranking table of influence factors
As can be seen from Table 1, the main control factors influencing the initial productivity of the shale gas horizontal well of the B well region are the effective drilling rate of the I-type reservoir stratum and Longyi1 1Drilling length and gas content of small layer; the secondary control factors are the sand-adding strength, the fracturing grade number and the porosity.
Of the 24 shale gas horizontal wells participating in analysis, 4 wells which have recently completed testing are used as verification wells (for verifying the accuracy of the prediction model), and the other 20 wells are used as samples for establishing the early-stage capacity prediction model, wherein 14 wells are learning samples, 3 wells are variable samples, and 3 wells are testing samples.
And establishing an initial capacity prediction model aiming at the shale gas horizontal well of the B well area of the Sichuan basin by using the 3 main control factors (the effective drilling rate of the I-type reservoir, the effective drilling length of 11 small layers and the gas content) and the 3 secondary control factors (the sand adding strength, the fracturing grade number and the porosity) obtained by comprehensive sequencing as control factors.
And predicting 4 verification wells by using the established initial productivity prediction model, wherein the prediction result is shown in a table 2.
TABLE 2
| Number of well | 1 | 2 | 3 | 4 | Mean value of |
| Actual value (10)4m3/d) | 15.72 | 19.38 | 21.82 | 20.00 | / |
| Predicted value (10)4m3/d) | 11.60 | 20.16 | 16.21 | 26.57 | / |
| Absolute error (10)4m3/d) | 4.12 | 0.78 | 5.61 | 6.57 | 4.27 |
| Relative error (%) | 26.19 | 4.02 | 25.73 | 32.83 | 22.19 |
As can be seen from Table 2, the average absolute error of 4 verified wells is 4.27, the average relative error is 22.19%, and the prediction precision is good.
In summary, the prediction method provided by the embodiment of the invention utilizes logging information and construction information, and based on a multi-factor analysis method, the main control factors influencing the initial productivity of the shale gas horizontal well are determined, a more applicable shale gas horizontal well initial productivity prediction model is established, the prediction precision is improved, the compilation of a shale gas single well production allocation scheme can be directly guided, and a more reasonable production system is established. And with the continuous increase of the production wells in the later period, the prediction model can be continuously perfected and optimized, so that the prediction precision is continuously improved.
The above description is only exemplary of the present invention and should not be taken as limiting the scope of the present invention, as any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A shale gas horizontal well initial productivity prediction method comprises the following steps: acquiring single-well logging information and construction information of a plurality of shale gas horizontal wells of a block to be detected, and extracting influence factors influencing initial productivity of the shale gas horizontal wells from the single-well logging information and the construction information;
characterized in that the method further comprises: determining main control factors and secondary control factors influencing the initial productivity of the shale gas horizontal well from the influencing factors by using a multi-factor analysis method, wherein the influence degree of the main control factors to the secondary control factors on the initial productivity of the shale gas horizontal well is gradually reduced;
and according to a neural network algorithm, establishing a shale gas horizontal well initial productivity prediction model by using the main control factors and the secondary control factors.
2. The method of claim 1, further comprising: predicting the initial productivity of the new well by using the shale gas horizontal well initial productivity prediction model to obtain the test yield of the new well;
extracting the main control factors and the secondary control factors from single well logging information and construction information of the new well, and forming a learning sample by matching with the test yield of the new well;
and learning the shale gas horizontal well initial productivity prediction model by using the learning sample so as to obtain the learned shale gas horizontal well initial productivity prediction model.
3. The method of claim 1, wherein the influencing factors comprise: the method comprises the following steps of total organic carbon content, reservoir gas content, reservoir porosity, brittle mineral content of a reservoir, effective drilling rate of a type I reservoir, drilling length of a highest-quality small layer in a Longmaxi group shale reservoir, fracturing series, fracturing fluid injection strength during fracturing construction and sand adding strength during fracturing construction.
4. The method of claim 1, wherein the determining the primary control factors and the secondary control factors that affect the initial productivity of the shale gas horizontal well from the influencing factors by using a multi-factor analysis method comprises:
determining a reference series of reaction system behavior characteristics and a comparison series of influence system behaviors, taking a plurality of shale gas horizontal wells as sample wells, taking the test yield of the sample wells as the reference series, and taking the influence factors as the comparison series;
carrying out non-dimensionalization processing on the reference number sequence and the comparison number sequence;
calculating a correlation coefficient of the comparison sequence to the reference sequence according to the reference sequence and the comparison sequence after non-dimensionalization processing aiming at each sample well;
acquiring the association degree of the comparison array to the reference array according to the association coefficient;
and determining the main control factor and the secondary control factor from the influence factors according to the magnitude of the association degree.
5. The method according to claim 4, wherein the correlation coefficient is calculated by:
wherein y (k) is a dimensionless number corresponding to the reference number sequence in the kth sample well;
xi(k) a dimensionless number, x, corresponding to the comparison array at the kth sample welliIs the ith comparison sequence;
ξi(k) x for the kth sample welliCorrelation coefficient to y;
rho is a resolution coefficient, and is taken as 0.5;
the calculation formula of the correlation degree is as follows:
wherein n is the number of sample wells.
6. The method according to claim 4, wherein the reference sequence and the comparison sequence are subjected to non-dimensionalization according to an averaging method.
7. The method of claim 4, wherein the determining the primary control factors and the secondary control factors that affect the initial productivity of the shale gas horizontal well from the influencing factors using a multi-factor analysis method further comprises:
presetting a test yield threshold value of a shale gas horizontal well, and classifying a plurality of shale gas horizontal wells into a high yield class and a low yield class by taking the threshold value as a boundary;
dividing each influence factor into a plurality of numerical value intervals;
acquiring the frequency of each numerical interval projected on a high-yield shale gas-like horizontal well and a low-yield shale gas-like horizontal well;
acquiring the average probability frequency of each numerical value interval according to the frequency;
calculating the ratio of the average probability frequencies corresponding to the high-yield shale gas-like horizontal well and the low-yield shale gas-like horizontal well, and acquiring the diagnosis coefficient of each numerical interval according to the ratio;
calculating the information quantity of each influence factor in a plurality of numerical value intervals according to the diagnosis coefficient;
determining the main control factor and the secondary control factor from the influence factors according to the size of the information quantity;
the calculation formula of the average probability frequency is as follows:
wherein,projecting the average probability frequency of the ith numerical interval on the high-yield or low-yield shale gas horizontal well;
the calculation formula of the diagnosis coefficient is as follows:
wherein,the average probability frequency corresponding to the low-yield shale gas horizontal well is obtained;
the average probability frequency corresponding to the high-yield shale gas-like horizontal well is obtained;
the calculation formula of the information quantity is as follows:
8. the method according to claim 7, further comprising sorting the influence factors in order from big to small according to the degree of influence and the information amount;
and averaging the sequence value obtained based on the association degree and the sequence value obtained based on the information amount, and determining the main control factor and the secondary control factor from the influence factors.
9. The method of claim 1, wherein the primary control factors and the secondary control factors are used as input layers and the test yield is used as an output layer in the process of establishing the shale gas horizontal well initial productivity prediction model according to a neural network algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710551814.8A CN109214026A (en) | 2017-07-07 | 2017-07-07 | Shale gas horizontal well initial-stage productivity prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710551814.8A CN109214026A (en) | 2017-07-07 | 2017-07-07 | Shale gas horizontal well initial-stage productivity prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109214026A true CN109214026A (en) | 2019-01-15 |
Family
ID=64990844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710551814.8A Pending CN109214026A (en) | 2017-07-07 | 2017-07-07 | Shale gas horizontal well initial-stage productivity prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214026A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111396038A (en) * | 2020-04-22 | 2020-07-10 | 中国石油天然气集团有限公司 | Horizontal single well yield prediction method |
| CN111488666A (en) * | 2019-01-28 | 2020-08-04 | 中国石油化工股份有限公司 | Gas reservoir horizontal well productivity prediction model establishing and predicting method and device |
| CN112228054A (en) * | 2020-11-06 | 2021-01-15 | 中国石油大学(北京) | Method, device and equipment for determining shale gas yield based on convolutional neural network |
| CN112308269A (en) * | 2019-07-30 | 2021-02-02 | 中国石油化工股份有限公司 | Yield prediction method and device for low-permeability oil and gas reservoir |
| CN112761628A (en) * | 2021-01-25 | 2021-05-07 | 中国石油大学(北京) | Shale gas yield determination method and device based on long-term and short-term memory neural network |
| CN113153286A (en) * | 2021-05-25 | 2021-07-23 | 中国石油天然气股份有限公司 | Shale gas development main control factor analysis method based on decision tree |
| CN113705878A (en) * | 2021-08-24 | 2021-11-26 | 中海石油(中国)有限公司深圳分公司 | Horizontal well water yield determination method and device, computer equipment and storage medium |
| CN113762614A (en) * | 2021-09-01 | 2021-12-07 | 北京中地金石科技有限公司 | Shale gas well productivity prediction method based on static oil and gas field data |
| CN113837890A (en) * | 2021-08-09 | 2021-12-24 | 中国石油天然气股份有限公司 | Shale gas horizontal well type optimization method based on data statistics |
| CN114021821A (en) * | 2021-11-08 | 2022-02-08 | 四川省科源工程技术测试中心 | Gas reservoir recovery rate prediction method based on multiple regression |
| CN114427432A (en) * | 2020-09-11 | 2022-05-03 | 中国石油化工股份有限公司 | Method for determining development potential of residual gas in gas reservoir |
| CN115539026A (en) * | 2022-09-27 | 2022-12-30 | 西南石油大学 | Fusion prediction method for initial yield of horizontal well of complex reservoir |
| CN115829104A (en) * | 2022-11-24 | 2023-03-21 | 北京科技大学 | Shale gas energy production main control factor analysis method based on convolutional neural network and SHAP value |
| CN115874993A (en) * | 2023-02-21 | 2023-03-31 | 成都工业学院 | Shale gas well production control method, equipment and system based on artificial intelligence |
| CN116128162A (en) * | 2023-04-13 | 2023-05-16 | 中国石油大学(华东) | Method, system and storage medium for predicting initial productivity of fracturing well based on small sample |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104134101A (en) * | 2014-07-23 | 2014-11-05 | 中国石油集团川庆钻探工程有限公司 | Low-permeability reservoir natural gas productivity prediction method |
| CN104832166A (en) * | 2015-03-20 | 2015-08-12 | 中国石油化工股份有限公司江汉油田分公司勘探开发研究院 | Initial productivity prediction method of shale gas horizontal well |
| US20160042272A1 (en) * | 2013-03-15 | 2016-02-11 | Intelligent Solutions, Inc. | Data-driven analytics, predictive modeling & opitmization of hydraulic fracturing in marcellus shale |
-
2017
- 2017-07-07 CN CN201710551814.8A patent/CN109214026A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160042272A1 (en) * | 2013-03-15 | 2016-02-11 | Intelligent Solutions, Inc. | Data-driven analytics, predictive modeling & opitmization of hydraulic fracturing in marcellus shale |
| CN104134101A (en) * | 2014-07-23 | 2014-11-05 | 中国石油集团川庆钻探工程有限公司 | Low-permeability reservoir natural gas productivity prediction method |
| CN104832166A (en) * | 2015-03-20 | 2015-08-12 | 中国石油化工股份有限公司江汉油田分公司勘探开发研究院 | Initial productivity prediction method of shale gas horizontal well |
Non-Patent Citations (4)
| Title |
|---|
| 叶双江 等: "基于灰色关联与神经网络技术的水平井产能预测", 《大庆石油学院学报》 * |
| 梁涛 等: "巴肯致密油藏单井产能参数影响程度排序", 《石油勘探与开发》 * |
| 王威: "致密油藏水平井体积压裂初期产能预测", 《新疆石油地质》 * |
| 赵圣贤 等: "四川盆地页岩气水平井高产地质因素分析", 《2016年全国天然气学术年会论文集》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488666A (en) * | 2019-01-28 | 2020-08-04 | 中国石油化工股份有限公司 | Gas reservoir horizontal well productivity prediction model establishing and predicting method and device |
| CN112308269A (en) * | 2019-07-30 | 2021-02-02 | 中国石油化工股份有限公司 | Yield prediction method and device for low-permeability oil and gas reservoir |
| CN111396038A (en) * | 2020-04-22 | 2020-07-10 | 中国石油天然气集团有限公司 | Horizontal single well yield prediction method |
| CN111396038B (en) * | 2020-04-22 | 2023-10-03 | 中国石油天然气集团有限公司 | Prediction method for horizontal single well yield |
| CN114427432A (en) * | 2020-09-11 | 2022-05-03 | 中国石油化工股份有限公司 | Method for determining development potential of residual gas in gas reservoir |
| CN114427432B (en) * | 2020-09-11 | 2024-04-26 | 中国石油化工股份有限公司 | Method for determining development potential of residual gas in gas reservoir |
| CN112228054A (en) * | 2020-11-06 | 2021-01-15 | 中国石油大学(北京) | Method, device and equipment for determining shale gas yield based on convolutional neural network |
| CN112761628A (en) * | 2021-01-25 | 2021-05-07 | 中国石油大学(北京) | Shale gas yield determination method and device based on long-term and short-term memory neural network |
| CN113153286A (en) * | 2021-05-25 | 2021-07-23 | 中国石油天然气股份有限公司 | Shale gas development main control factor analysis method based on decision tree |
| CN113153286B (en) * | 2021-05-25 | 2024-04-30 | 中国石油天然气股份有限公司 | Shale gas development main control factor analysis method based on decision tree |
| CN113837890A (en) * | 2021-08-09 | 2021-12-24 | 中国石油天然气股份有限公司 | Shale gas horizontal well type optimization method based on data statistics |
| CN113705878A (en) * | 2021-08-24 | 2021-11-26 | 中海石油(中国)有限公司深圳分公司 | Horizontal well water yield determination method and device, computer equipment and storage medium |
| CN113705878B (en) * | 2021-08-24 | 2024-02-09 | 中海石油(中国)有限公司深圳分公司 | Method and device for determining water yield of horizontal well, computer equipment and storage medium |
| CN113762614A (en) * | 2021-09-01 | 2021-12-07 | 北京中地金石科技有限公司 | Shale gas well productivity prediction method based on static oil and gas field data |
| CN113762614B (en) * | 2021-09-01 | 2024-09-13 | 北京中地金石科技有限公司 | Shale gas well productivity prediction method based on static oil-gas field data |
| CN114021821A (en) * | 2021-11-08 | 2022-02-08 | 四川省科源工程技术测试中心 | Gas reservoir recovery rate prediction method based on multiple regression |
| CN115539026B (en) * | 2022-09-27 | 2023-11-14 | 西南石油大学 | Initial yield fusion prediction method for horizontal well of complex reservoir |
| CN115539026A (en) * | 2022-09-27 | 2022-12-30 | 西南石油大学 | Fusion prediction method for initial yield of horizontal well of complex reservoir |
| CN115829104A (en) * | 2022-11-24 | 2023-03-21 | 北京科技大学 | Shale gas energy production main control factor analysis method based on convolutional neural network and SHAP value |
| CN115874993A (en) * | 2023-02-21 | 2023-03-31 | 成都工业学院 | Shale gas well production control method, equipment and system based on artificial intelligence |
| CN116128162A (en) * | 2023-04-13 | 2023-05-16 | 中国石油大学(华东) | Method, system and storage medium for predicting initial productivity of fracturing well based on small sample |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214026A (en) | Shale gas horizontal well initial-stage productivity prediction method | |
| CN108009716B (en) | Multi-level evaluation method for influence factors of horizontal well volume fracturing effect | |
| CN106355030B (en) | A kind of fault detection method based on analytic hierarchy process (AHP) and Nearest Neighbor with Weighted Voting Decision fusion | |
| CN105760673B (en) | A kind of fluvial depositional reservoir seismic-sensitive parameterized template analysis method | |
| CN111046341A (en) | Unconventional natural gas fracturing effect evaluation and capacity prediction method based on principal component analysis | |
| CN112364560B (en) | Intelligent prediction method for working hours of mine rock drilling equipment | |
| CN110569566B (en) | Method for predicting mechanical property of plate strip | |
| CN112529341A (en) | Drilling well leakage probability prediction method based on naive Bayesian algorithm | |
| CN103617147A (en) | Method for identifying mine water-inrush source | |
| CN110472689B (en) | Sucker-rod pump pumping well moving liquid level soft measurement method based on integrated Gaussian process regression | |
| CN103577676A (en) | Grey weighting method for sewage treatment process comprehensive evaluation | |
| CN113379256A (en) | Reservoir evaluation prediction method for Kmeans-random forest | |
| CN104992178A (en) | Tight sandstone fluid type identification method based on support vector machine simulation cross plot | |
| CN104655583A (en) | Fourier-infrared-spectrum-based rapid coal quality recognition method | |
| CN110633504A (en) | Prediction method for coal bed gas permeability | |
| CN115017646A (en) | Fracturing parameter optimization method and device, electronic equipment and storage medium | |
| CN113420795A (en) | Mineral spectrum classification method based on void convolutional neural network | |
| CN113762614A (en) | Shale gas well productivity prediction method based on static oil and gas field data | |
| CN105824785A (en) | Rapid abnormal point detection method based on penalized regression | |
| CN104880737A (en) | Multivariate Logistic method using logging information to identify type of underground fluid | |
| CN117541095A (en) | Agricultural land soil environment quality classification method | |
| CN113157561A (en) | Defect prediction method for numerical control system software module | |
| CN110674868A (en) | Stratum lithology identification system and method based on high-dimensional drilling parameter information | |
| CN113627640B (en) | Production capacity well test prediction method and system for fracture-cavity type oil and gas reservoirs | |
| CN113720952B (en) | Method, device, equipment and medium for generating image plate for reservoir interpretation evaluation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |
|
| RJ01 | Rejection of invention patent application after publication |