CN116658155A - Shale gas well yield prediction method - Google Patents

Shale gas well yield prediction method Download PDF

Info

Publication number
CN116658155A
CN116658155A CN202310646030.9A CN202310646030A CN116658155A CN 116658155 A CN116658155 A CN 116658155A CN 202310646030 A CN202310646030 A CN 202310646030A CN 116658155 A CN116658155 A CN 116658155A
Authority
CN
China
Prior art keywords
shale gas
data
gas well
yield
result
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
Application number
CN202310646030.9A
Other languages
Chinese (zh)
Inventor
梁海波
代继鑫
杨海
邹佳玲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest Petroleum University
Original Assignee
Southwest Petroleum University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southwest Petroleum University filed Critical Southwest Petroleum University
Priority to CN202310646030.9A priority Critical patent/CN116658155A/en
Publication of CN116658155A publication Critical patent/CN116658155A/en
Pending legal-status Critical Current

Links

Classifications

    • E—FIXED CONSTRUCTIONS
    • E21—EARTH OR ROCK DRILLING; MINING
    • E21B—EARTH OR ROCK 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • E—FIXED CONSTRUCTIONS
    • E21—EARTH OR ROCK DRILLING; MINING
    • E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
    • E21B2200/00—Special features related to earth drilling for obtaining oil, gas or water
    • E21B2200/20—Computer models or simulations, e.g. for reservoirs under production, drill bits
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Economics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mining & Mineral Resources (AREA)
  • Human Resources & Organizations (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Geology (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Geochemistry & Mineralogy (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Environmental & Geological Engineering (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Fluid Mechanics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Agronomy & Crop Science (AREA)
  • Animal Husbandry (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Primary Health Care (AREA)

Abstract

The application belongs to the technical field of shale gas reservoir development, and provides a shale gas well yield prediction method, which comprises the following steps: step 1, acquiring geological data, engineering data and production data of a shale gas well to generate basic data; step 2, preprocessing basic data to obtain main control factors influencing the yield of the shale gas well; step 3, constructing a sample set; step 4, establishing a shale gas yield prediction model through an improved B-L-A algorithm And 5, predicting the yield of the fracturing stage of the target zone gas well by using the shale gas yield prediction model established in the step 4. According to the application, the established shale gas yield prediction model is deeply combined with the mathematical method advantages of the BP neural network and the LSTM neural network, and is used as an engineering experience model to carry out constraint, so that the generalization error is effectively reduced, the phenomenon of overfitting is avoided, the model prediction precision is improved, and the reliable yield prediction is provided for the large-scale development of shale gas.

Description

Shale gas well yield prediction method
Technical Field
The application belongs to the technical field of shale gas reservoir development, and particularly relates to a shale gas well yield prediction method.
Background
Shale gas, tight sandstone gas, coalbed methane and the like belong to unconventional natural gas. Shale gas, tight sandstone gas, coal bed gas and the like are unconventional natural gas, and the yield prediction after shale gas fracturing is an important means for determining the development economy of the shale gas, but the traditional yield prediction method is complex in calculation, large in workload and difficult to guarantee precision due to complex fracturing process and numerous influencing factors.
Currently, shale gas well production prediction mainly comprises two types of methods: methods based on engineering experience models and methods based on data. The development of the method based on the physical experience model is mature, and the success of the method is that a concise formula is deduced according to the physical parameters of a certain shale gas well under certain conditions, so that the method is convenient for direct application in engineering. However, there are still great difficulties in predicting parameters in a model, and many times, the most difficult problem to solve is presented. At present, a data-based method mainly adopts a machine learning technology to predict conventional oil gas production, and mainly adopts a related algorithm of machine learning to deeply mine data, but the influence on physical parameters is not fully researched. Data-based methods have been tried with little success in using known shale gas reservoir data to infer unknown data, but because the physical parameters of the gas well itself are not considered, the accuracy of the predictions is greatly affected by how similar the predicted gas well is to the physical properties of the known gas well in various aspects.
The method is characterized in that the method is based on the combination of engineering experience model and data mining, the prediction capability of a machine learning method on unknown things is fully utilized, and meanwhile, by introducing classical experience model control, good prediction accuracy is obtained after actual measurement data training, and more accurate prediction is made on the domestic shale gas well yield.
Disclosure of Invention
The application aims to solve the technical problems in the prior art and provides a shale gas well yield prediction method.
In order to achieve the above purpose, the application adopts the following technical scheme: a method of shale gas well production prediction comprising the steps of:
step 1, acquiring geological data, engineering data and production data of a shale gas well to generate basic data;
step 2, preprocessing basic data to obtain main control factors influencing the yield of the shale gas well;
step 3, constructing a sample set, setting the main control factors affecting the yield obtained in the step 2 as Xi, taking the Xi as a characteristic vector of a target block gas well, selecting the basic data of the collected target block gas well as a sample data set, extracting the sample data in the sample data set according to a certain proportion as a training set, and taking the rest sample data as a test set;
step 4, randomly generating a training set and a testing set in a sample data set through learning and training, combining a mathematical method of an error reverse transfer neural network and a long-term and short-term memory neural network, restraining by utilizing an Arps model to form an improved B-L-A algorithm, and establishing a shale gas yield prediction model through the improved B-L-A algorithm
And 5, predicting the yield of the fracturing stage of the target zone gas well by using the shale gas yield prediction model established in the step 4.
In the further technical scheme, in the step 1, basic data comprise a median value, porosity, total organic carbon content, pressure coefficient, horizontal section length, fracturing transformation section number, average cluster distance, fracturing fluid quantity, supporting dosage, quartz sand dosage, average sand ratio, construction displacement, average section length, sand adding strength and fluid using strength of the vertical depth of a horizontal well, wherein the fracturing fluid is slickwater, and the propping agents are 70/140-mesh quartz sand and 40/70-mesh ceramsite.
In the step 2, the specific mode of preprocessing the basic data is that the basic data is ranked according to the intensity degree of influencing the yield of the gas well by adopting a gray correlation method, so that the main control factor influencing the yield is obtained.
In the further technical scheme, in the step 3, the target attribute of the constructed sample data set is the predicted gas well fracturing stage yield.
In a further technical scheme, in the step 4, the improved B-L-A algorithm comprises the following steps:
step 4-1, training test data by using an error reverse transfer neural network method, and performing new prediction by using an algorithm structure meeting the training error requirement after reaching the accuracy requirement, wherein a gradient descent method is selected as a training function, the maximum training frequency is 1000, and the training accuracy requirement is 0.0001;
step 4-2, before the output layer is converted into the result by combining the long-term and short-term memory artificial neural network method, storing the last result in the operation process, adding a storage layer P on the basis of the original output layer to serve as a final output result, storing the last result, and marking the last storage layer element as P t-1 The current storage layer element is denoted as P t ，
P t-1 ＝(P t-1，1 ，P t-1，2 ，…，P t-1，k )
The output result of this time is given by the error reverse transfer neural network result of this time and the final result of last time together, namely:
Pt＝(z t，1 ，z t，2 ，…，z t，k )+MP t-1
wherein the matrix M is likewise given by the training data;
step 4-3, adopting an Arps model empirical model constraint in a data training stage, adopting an empirical model to reasonably extrapolate and compare the result with an actual predicted value according to the three previous results before finally giving a predicted result, if the deviation exceeds a set deviation range, the result cannot be accepted, and the corresponding coefficient is readjusted, and finally accepting the result as an effective predicted result; the basic equation of the Arps model is:
wherein q (t) is the yield at any time, q i For initial yield, D is decreasing index, D i Is the initial reduction rate.
The principle and the beneficial effects of the application are as follows:
1. compared with the prior art, the method has the advantages that the geological data, engineering data and production data of the shale gas well are collected, the data are preprocessed by adopting a gray correlation method, the main control factors influencing the yield are identified, a nonlinear mathematical model is built, and the yield of the shale gas well can be predicted more accurately.
2. Compared with the prior art, the shale gas yield prediction model established by the application deeply combines the mathematical method advantages of the error reverse transfer neural network and the long-short-period memory neural network, and is constrained by taking the Arps model as an engineering experience model, so that the generalization error is effectively reduced, the overfitting phenomenon is avoided, the model prediction precision is improved, and the reliable yield prediction is provided for the large-scale development of shale gas.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flow chart of a method of shale gas well production prediction of the present application;
FIG. 2 is a flow chart of a modified B-L-A algorithm of the method of shale gas well production prediction of the present application
FIG. 3 is a graph comparing test results of an improved B-L-A algorithm of the method for shale gas well production prediction of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
The application provides a shale gas well yield prediction method, which is characterized by comprising the following steps:
and step 1, acquiring geological data, engineering data and production data of the shale gas well to generate basic data.
And step 2, preprocessing the basic data to obtain a main control factor influencing the yield of the shale gas well.
And 3, constructing a sample set, setting the main control factors affecting the yield obtained in the step 2 as Xi, taking the Xi as a characteristic vector of a target block gas well, selecting the collected basic data of the target block gas well as a sample data set, extracting the sample data in the sample data set according to a certain proportion as a training set, and taking the rest sample data as a test set.
And 4, randomly generating a training set and a testing set in a sample data set through learning and training, combining a mathematical method of an error reverse transfer (BP) neural network and an (LSTM) long-short-term memory neural network, restraining by utilizing an Arps model to form an improved B-L-A algorithm, and establishing a shale gas yield prediction model through the improved B-L-A algorithm.
Wherein, the improved B-L-A algorithm comprises the following steps:
step 4-1, training test data by using an error reverse transfer neural network method, and performing new prediction by using an algorithm structure meeting the training error requirement after reaching the accuracy requirement, wherein a gradient descent method is selected as a training function, the maximum training frequency is 1000, and the training accuracy requirement is 0.0001;
step 4-2, storing the last result in the current operation process before the output layer is converted into the result by combining the long-term memory artificial neural network method, and in order to achieve the goal, storing the last result in the original stateAdding a storage layer P based on the output layer as the final output result, storing the last result, and marking the last storage layer element as P t-1 The current storage layer element is denoted as P t ，
P t-1 ＝(P t-1，1 ，P t-1，2 ，…，P t-1，k )
The output result of this time is given by the error reverse transfer neural network result of this time and the final result of last time together, namely:
Pt＝(z t，1 ，z t，2 ，…，z t，k )+MP t-1
wherein the matrix M is likewise given by the training data;
step 4-3, adopting an Arps model empirical model constraint in a data training stage, carrying out reasonable extrapolation by adopting an empirical model according to the three previous results before finally giving a predicted result, comparing the predicted result with an actual predicted value, if the deviation exceeds a set deviation range, failing to accept the predicted result, and readjusting a corresponding coefficient, and finally accepting the predicted result as an effective predicted result; the basic equation of the Arps model is:
wherein q (t) is the yield at any time, q i For initial yield, D is decreasing index, D i Is the initial reduction rate.
And 5, predicting the yield of the fracturing stage of the target zone gas well by using the shale gas yield prediction model established in the step 4.
The basic principle of the application is further described below in connection with specific examples:
collecting data of shale gas well geology, engineering, production and the like:
the method comprises the steps of collecting geological, engineering, production and other data of a shale gas well of a certain block to generate basic data, wherein factors influencing shale gas yield in the basic data comprise a median value (m) of vertical depth of a horizontal well, porosity), total organic carbon content (TOC,%) and pressure coefficient, horizontal section length (m), fracturing transformation section number, average cluster distance (m), fracturing liquid amount (m & lt 3 & gt), propping agent amount (m & lt 3 & gt), quartz sand consumption (t), average sand ratio (%), construction displacement (m & lt 3 & gt/min), average section length (m), sand adding strength (t/m) and liquid using strength (m & lt 3 & gt/section), and 16 parameters are added. Wherein the fracturing fluid is slick water, and the propping agent is 40/70 mesh ceramsite of 70/140 mesh quartz sand.
Data preprocessing:
the factors influencing the shale gas yield in the basic data are preprocessed by adopting a gray correlation method, specifically, the 16 factors are ranked according to the intensity degree influencing the gas well yield by adopting the gray correlation method, and the factors influencing the gas well yield, 8 bits before the ranking of the correlation degree, are selected to be used as main control factors for analysis, wherein the main control factors are shown in the following table 1.
TABLE 1
Sample set construction is performed:
and setting the main control factors affecting the yield, which are obtained based on gray correlation analysis, as Xi as characteristic vectors of the target block gas well. The target attribute is a predicted gas well fracturing stage yield. The selected well base data is used as a sample data set. And extracting certain sample data as a training set, and taking the rest sample data as a test set.
First, a sample data set is imported, and the sample data set is trained by learning according to 7: the ratio of 3 randomly generates a training set and a test set. Through calculating the correlation coefficient between physical parameters (input layer) and a target well, building a BP neural network, combining an LSTM neural network, taking the constraint of an empirical model Arps model into consideration, forming an improved B-L-A algorithm, building a shale gas yield prediction model, and selecting a decision coefficient and a root mean square error as two evaluation indexes.
And calculating two evaluation indexes of the common BP neural network method and the improved algorithm prediction, wherein the statistics of the evaluation indexes of different algorithms are shown in the following table 2.
TABLE 2
Well number Common BP neural network Improved B-L-A algorithm
R 2 0.792 0.875
MSE 0.443 0.219
As shown in FIG. 3, the predicted value and the true test value of the modified B-L-A algorithm and the classical BP network method are compared (the abscissa is the segment number, the ordinate is the fracturing segment yield, and the unit is m 3 )。
The result shows that the prediction effect of the improved algorithm is obviously improved, and the overall trend and the single-point error value basically meet the requirement on precision. The improved B-L-A method combines the advantages of an empirical model and a neural network model, and the accuracy of the obtained result is greatly improved.
In the description of the present specification, reference to the terms "preferred implementation," "one embodiment," "some embodiments," "example," "a particular example" or "some examples" and the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the application, the scope of which is defined by the claims and their equivalents.

Claims (5)

1. A method for predicting shale gas well production, comprising the steps of:
step 1, acquiring geological data, engineering data and production data of a shale gas well to generate basic data;
step 2, preprocessing basic data to obtain main control factors influencing the yield of the shale gas well;
step 3, constructing a sample set, setting the main control factors affecting the yield obtained in the step 2 as Xi, taking the Xi as a characteristic vector of a target block gas well, selecting the basic data of the collected target block gas well as a sample data set, extracting the sample data in the sample data set according to a certain proportion as a training set, and taking the rest sample data as a test set;
step 4, randomly generating a training set and a testing set in a sample data set through learning and training, combining a mathematical method of an error reverse transfer neural network and a long-term and short-term memory neural network, restraining by utilizing an Arps model to form an improved B-L-A algorithm, and establishing a shale gas yield prediction model through the improved B-L-A algorithm
And 5, predicting the yield of the target zone gas fracturing stage by using the shale gas yield prediction model established in the step 4.
2. The method of shale gas well production prediction as claimed in claim 1, wherein in step 1, the base data comprises median value of vertical depth of horizontal well, porosity, total organic carbon content, pressure coefficient, horizontal segment length, fracturing segment length, number of fracturing modification segments, average cluster spacing, fracturing fluid volume, propping agent amount, quartz sand usage, average sand ratio, construction displacement, average segment length, sand addition strength and fluid use strength, wherein the fracturing fluid is slickwater, and the propping agent is 70/140 mesh quartz sand and 40/70 mesh ceramsite.
3. The method for predicting the production of the shale gas well according to claim 1, wherein in the step 2, the basic data is preprocessed in a specific mode, the basic data is ranked according to the intensity of the influence on the production of the gas well by adopting a gray correlation method, so that a main control factor influencing the production is obtained.
4. The method of shale gas well production prediction as recited in claim 1, wherein in step 3, the constructing a sample dataset target property is predicting gas well fracturing stage production.
5. The method of shale gas well production prediction as claimed in claim 1, wherein in step 4, the improvement of the B-L-a algorithm comprises the steps of:
step 4-1, training test data by using an error reverse transfer neural network method, and performing new prediction by using an algorithm structure meeting the training error requirement after reaching the accuracy requirement, wherein a gradient descent method is selected as a training function, the maximum training frequency is 1000, and the training accuracy requirement is 0.0001;
step 4-2, before the output layer is converted into the result by combining the long-term and short-term memory artificial neural network method, storing the last result in the operation process, adding a storage layer P on the basis of the original output layer to serve as a final output result, storing the last result, and marking the last storage layer element as P t-1 The current storage layer element is denoted as P t ，
P t-1 ＝(P t-1，1 ，P t-1，2 ，…，P t-1，k )
The output result of this time is given by the error reverse transfer neural network result of this time and the final result of last time together, namely:
Pt＝(z t，1 ，z t，2 ，…，z t，k )+MP t-1
wherein the matrix M is likewise given by the training data;
step 4-3, adopting an Arps model empirical model constraint in a data training stage, adopting an empirical model to reasonably extrapolate and compare the result with an actual predicted value according to the three previous results before finally giving a predicted result, if the deviation exceeds a set deviation range, the result cannot be accepted, and the corresponding coefficient is readjusted, and finally accepting the result as an effective predicted result;
the basic equation of the Arps model is:
wherein q (t) is the yield at any time, q i For initial yield, D is decreasing index, D i Is the initial reduction rate.
CN202310646030.9A 2023-06-02 2023-06-02 Shale gas well yield prediction method Pending CN116658155A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310646030.9A CN116658155A (en) 2023-06-02 2023-06-02 Shale gas well yield prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310646030.9A CN116658155A (en) 2023-06-02 2023-06-02 Shale gas well yield prediction method

Publications (1)

Publication Number Publication Date
CN116658155A true CN116658155A (en) 2023-08-29

Family

ID=87723823

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310646030.9A Pending CN116658155A (en) 2023-06-02 2023-06-02 Shale gas well yield prediction method

Country Status (1)

Country Link
CN (1) CN116658155A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116911640A (en) * 2023-09-11 2023-10-20 中国地质大学（北京） Shale reservoir gas content prediction method based on machine deep learning
CN116976146A (en) * 2023-09-22 2023-10-31 中国石油大学(华东) Fracturing well yield prediction method and system coupled with physical driving and data driving

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116911640A (en) * 2023-09-11 2023-10-20 中国地质大学（北京） Shale reservoir gas content prediction method based on machine deep learning
CN116911640B (en) * 2023-09-11 2023-12-26 中国地质大学（北京） Shale reservoir gas content prediction method based on machine learning
CN116976146A (en) * 2023-09-22 2023-10-31 中国石油大学(华东) Fracturing well yield prediction method and system coupled with physical driving and data driving
CN116976146B (en) * 2023-09-22 2024-01-05 中国石油大学(华东) Fracturing well yield prediction method and system coupled with physical driving and data driving

Similar Documents

Publication Publication Date Title
Pan et al. An optimized XGBoost method for predicting reservoir porosity using petrophysical logs
CN109441422B (en) Shale gas well spacing optimization mining method
CN116658155A (en) Shale gas well yield prediction method
CN110334431A (en) A kind of low permeability tight gas reservoir single well controlled reserves calculating and remaining gas analysis method
CN103046914B (en) A kind of low permeability gas reservoirs staged fracturing of horizontal well effect determination methods
CN112561356B (en) Comprehensive evaluation method for production dynamic mode and productivity of shale oil fracturing horizontal well
CN107676085A (en) A kind of marine facies shale gas horizontal wellbore logging PRODUCTION FORECASTING METHODS
CN104458489B (en) Mud shale adsorbed gas content Forecasting Methodology and device
CN114595608B (en) Fracturing construction parameter and working system parameter optimization method and system
CN108416475A (en) A kind of shale gas production capacity uncertainty prediction technique
CN114048695A (en) Effective shale gas seam net volume inversion method based on flowback data
CN108843312A (en) Oilfield reservoir in-layer heterogeneity integrated evaluating method
CN115587674B (en) Dynamic capacity prediction method for gas well in oil reservoir reconstruction gas storage capacity expansion and production process
CN113297740A (en) Horizontal well gel profile control parameter optimization method
Naderi et al. Nonlinear risk optimization approach to water drive gas reservoir production optimization using DOE and artificial intelligence
Wang et al. Application of fuzzy analytic hierarchy process in sandstone aquifer water yield property evaluation
Zhong et al. Study on Co-production compatibility evaluation method of multilayer tight gas reservoir
CN112049629B (en) Fracture-cavity type oil reservoir recovery ratio prediction method based on A-type water drive characteristic curve
Lu et al. Revised inflow performance relationship for productivity prediction and energy evaluation based on stage characteristics of Class III methane hydrate deposits
CN112035993B (en) Bottom constant-pressure carbonate reservoir testing and evaluating method
Yi et al. Spatial correlation-based machine learning framework for evaluating shale gas production potential: A case study in southern Sichuan Basin, China
Ariadji et al. Optimization of vertical well placement for oil field development based on basic reservoir rock properties using a genetic algorithm
Rafiei Improved oil production and waterflood performance by water allocation management
CN114066166A (en) Cltobalite low-permeability reservoir CO2Miscible flooding screening method
CN107869336A (en) Super-viscous oil chemistry auxiliary thermal recovery improves recovery ratio method

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