CN115310357A - Fracturing analysis method based on data-driven decision - Google Patents
Fracturing analysis method based on data-driven decision Download PDFInfo
- Publication number
- CN115310357A CN115310357A CN202210949311.7A CN202210949311A CN115310357A CN 115310357 A CN115310357 A CN 115310357A CN 202210949311 A CN202210949311 A CN 202210949311A CN 115310357 A CN115310357 A CN 115310357A
- Authority
- CN
- China
- Prior art keywords
- data
- fracturing
- analysis
- neural network
- yield
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 19
- 238000004088 simulation Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 7
- 238000007405 data analysis Methods 0.000 claims abstract description 6
- 238000003825 pressing Methods 0.000 claims abstract description 5
- 230000002068 genetic effect Effects 0.000 claims abstract description 4
- 238000002360 preparation method Methods 0.000 claims abstract description 4
- 239000012530 fluid Substances 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 20
- 230000015572 biosynthetic process Effects 0.000 claims description 14
- 238000004519 manufacturing process Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 6
- 230000035699 permeability Effects 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 238000010220 Pearson correlation analysis Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 239000011435 rock Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 230000001364 causal effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Fluid Mechanics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data analysis and processing, in particular to a fracturing analysis method based on data-driven decision making, which comprises the following steps of 1, collecting fracturing historical data, and performing data analysis, optimization and screening; step 2, integrating the analyzed and screened data, and performing modeling preparation by using the analyzed data; step 3, establishing a crack simulation neural network and a productivity simulation neural network expert group; step 4, combining professional knowledge and simultaneously utilizing a data driving strategy to form a STACKING algorithm; step 5, predicting the yield after stress by combining a STACKING algorithm; step 6, after the yield after the completion of the pressing is predicted, the fracturing parameter prediction facing the oil field data is carried out by combining a genetic algorithm; and 7, repeating the steps 1 to 7, so that the technical problem that the data cannot be preprocessed in advance when the noise and incomplete information are oriented in the prior art can be solved.
Description
Technical Field
The invention relates to the technical field of data analysis and processing, in particular to a fracturing analysis method based on data-driven decision-making.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
Two basic problems of artificial intelligence application are the problems of incomplete information and noise, the two basic problems are well processed, the data preprocessing work can be effectively completed, and a standardized and normalized software data processing scheme for oil field data processing is formulated based on the problem processing, so that a basic theoretical basis can be provided for model selection.
In the prior art, when artificial intelligence is applied to 'big data of an oil field', the two problems are more prominent, and are particularly represented as noise problems generated by mutual matching of uncertainty of process, single-well basic information, unstable well testing, perforation data and fracturing data and well history data; the missing value problem of the process, the perforation data, the single well basic information and the fracturing data; the analysis of the correlation degree among the characteristics of each item of data and the three conditions of the Pearson correlation coefficient specifically include: the non-linear relationship causes a problem that the Pearson coefficient is small, and correlation analysis of non-causal relationship and correlation analysis of causal relationship.
Disclosure of Invention
The inventor finds out through research that: the noise problem of noise signal processing mainly occurs in the fitting problem between geological information reflected on the back of capacity before fracturing and fracturing measures and processes, the causal relationship between the two is complex, and uncertain factors such as artificial, sudden and unpredictable exist, and the factors influence the capacity effect after fracturing.
The purpose of the present disclosure is to provide a fracturing analysis method based on data-driven decision, which can solve the technical problem that the prior art cannot perform data preprocessing in advance when facing to noise and incomplete information through the analysis methods of steps 1 to 6; meanwhile, the technical problem that the accuracy of the traditional formula prediction method is not high is solved.
According to one aspect of the present disclosure, there is provided a method comprising the steps of: step 1, collecting fracturing historical data, and performing data analysis, optimization and screening, wherein the optimization and screening contents comprise reservoir parameters, rock mechanics parameters, fracturing construction parameters and productivity parameters; step 2, integrating the analyzed and screened data, and performing modeling preparation by using the analyzed data; step 3, establishing a crack simulation neural network and a productivity simulation neural network expert group; step 4, combining professional knowledge and simultaneously utilizing a data driving strategy to form a STACKING algorithm; step 5, predicting the yield after stress by combining a STACKING algorithm; step 6, predicting the yield after the completion of the pressing, and then predicting the fracturing parameters facing the oil field data by combining a genetic algorithm; and 7, repeating the steps 1 to 7, and finishing the circulation after the corresponding fracturing analysis is finished.
In some embodiments of the present disclosure, the step 1 specifically includes the following steps: the screened data are as follows: porosity Φ, permeability K, virgin oil saturation So, formation fluid viscosity μ, thickness h, virgin formation pressure p, total fracturing fluid, total proppant, pattern type, development interval, fracturing process, fracturing fluid type, proppant type, time, block, bed, initial fluid production, initial oil production, cumulative fluid production, cumulative oil production, strength produced, and oil gain.
In some embodiments of the present disclosure, the step 2 specifically includes: and (3) carrying out Pearson correlation analysis on the data in the step (1) pairwise, separating data items with Pearson correlation larger than 0.45, and carrying out next analysis.
In some embodiments of the present disclosure, the step 3 specifically includes: establishing a fracture simulation neural network, establishing a prediction relation between the porosity phi, the permeability K, the original oil saturation So, the formation fluid viscosity mu, the thickness h, the original formation pressure p, the total fracturing fluid amount, the total proppant amount, the well pattern type, the development well spacing, the fracturing process, the fracturing fluid type, the proppant type, the time, the blocks and the layer system, the initial fluid yield and the initial oil yield, wherein the neural network adopts a fully-connected neural network consisting of four layers of 256 neurons and an input layer and an output layer, the activation function of the middle layer adopts reLu, the final objective function is MSE, the gradient reduction adopts Adam, epoch is 1000, and Batch is 300.
In some embodiments of the present disclosure, the step 4 specifically includes: and (4) connecting the last round of the last layer in the four-layer fully-connected neural network described in the step (3) with the XGBOST algorithm, namely realizing the stacking between the fully-connected network and the XGBOST.
Compared with the prior art, the method has the following advantages and beneficial effects: in the technology disclosed by the invention, the method for predicting the yield after pressing is limited to methods such as cracks, pressure, seam control factors and the like, and the interference caused by data noise cannot be solved, so that the accuracy is low.
Drawings
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
Referring to fig. 1, the present embodiment provides a data-driven decision-based fracture analysis method, which is already in the actual test use stage.
In the following paragraphs, the different aspects of the embodiments are defined in more detail. Aspects so defined may be combined with any other aspect or aspects unless clearly indicated to the contrary. In particular, any feature considered to be preferred or advantageous may be combined with one or more other features considered to be preferred or advantageous. The terms "first", "second", and the like in the present invention are merely for convenience of description to distinguish different constituent elements having the same name, and do not denote a sequential or primary-secondary relationship.
Examples
The present embodiment at least includes the following contents: the method comprises the following steps:
step 1, collecting fracturing historical data, and performing data analysis, optimization and screening, wherein the optimization and screening contents comprise reservoir parameters, rock mechanics parameters, fracturing construction parameters and productivity parameters;
step 2, integrating, analyzing and screening the data, and performing modeling preparation by using the analyzed data;
step 3, establishing a crack simulation neural network and a productivity simulation neural network expert group;
step 4, combining professional knowledge and simultaneously utilizing a data driving strategy to form a STACKING algorithm;
step 5, predicting the yield after stress by combining a STACKING algorithm;
step 6, predicting the yield after the completion of the pressing, and then predicting the fracturing parameters facing the oil field data by combining a genetic algorithm;
and 7, repeating the steps 1 to 7, and finishing the circulation after the corresponding fracturing analysis is finished.
The method specifically comprises the following steps: the step 1 specifically comprises the following steps: the screened data are as follows: porosity Φ, permeability K, virgin oil or gas saturation So, formation fluid viscosity μ, thickness h, virgin formation pressure p, total fracturing fluid, total proppant, well pattern type, development well spacing, fracturing process, fracturing fluid type, proppant type, time, block, formation, initial fluid production, initial oil production, cumulative fluid production, cumulative oil production, strength of production, and oil gain. The step 2 specifically comprises the following steps: and (4) performing Pearson correlation analysis on the data in the step (1) pairwise, separating data items with Pearson correlation larger than 0.45, and performing next analysis. The step 3 specifically comprises the following steps: establishing a fracture simulation neural network, establishing a prediction relation between the porosity phi, the permeability K, the original oil or gas saturation So, the formation fluid viscosity mu, the thickness h, the original formation pressure p, the total fracturing fluid amount, the total proppant amount, the well pattern type, the development well spacing, the fracturing process, the fracturing fluid type, the proppant type, the time, the blocks and the layer system, the initial fluid yield and the initial oil yield, wherein the neural network adopts a fully-connected neural network consisting of four layers of 256 neurons and an input layer and an output layer, the activation function of the middle layer adopts reLu, the final objective function is MSE, the gradient descent adopts Adam, epoch is 1000, and Batch is 300. The step 4 specifically comprises the following steps: connecting the last round of the last layer in the four-layer fully-connected neural network described in the step 3 with the XGBOST algorithm, namely realizing the stacking between the fully-connected network and the XGBOST
The above description is intended to be illustrative of the preferred embodiment of the present invention and should not be taken as limiting the invention, but rather, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
Claims (5)
1. A fracture analysis method using data-driven decision-making, comprising the steps of:
step 1, collecting fracturing historical data, and performing data analysis, optimization and screening, wherein the optimization and screening contents comprise reservoir parameters, rock mechanics parameters, fracturing construction parameters and productivity parameters;
step 2, integrating, analyzing and screening the data, and performing modeling preparation by using the analyzed data;
step 3, establishing a crack simulation neural network;
step 4, combining professional knowledge and simultaneously utilizing a data driving strategy to form a STACKING algorithm;
step 5, predicting the yield after stress by combining a STACKING algorithm;
step 6, after the yield after the completion of the pressing is predicted, the fracturing parameter prediction facing the oil field data is carried out by combining a genetic algorithm;
and 7, repeating the steps 1 to 7, and finishing the circulation after the corresponding fracturing analysis is finished.
2. The method for fracture analysis by data-driven decision-making according to claim 1, wherein the step 1 specifically comprises the following steps: the screened data are as follows: porosity Φ, permeability K, virgin oil saturation So, formation fluid viscosity μ, thickness h, virgin formation pressure p, total fracturing fluid, total proppant, pattern type, development interval, fracturing process, fracturing fluid type, proppant type, time, block, formation, initial fluid production, initial oil production, cumulative fluid production, cumulative oil production, strength of production, and oil gain.
3. The method for fracture analysis by data-driven decision-making according to claim 1, wherein the step 2 specifically comprises: and (4) performing Pearson correlation analysis on the data in the step (1) pairwise, separating data items with Pearson correlation larger than 0.45, and performing next analysis.
4. The method for fracture analysis by data-driven decision-making according to claim 1, wherein the step 3 specifically comprises: establishing a fracture simulation neural network, establishing a prediction relation between the porosity phi, the permeability K, the original oil saturation So, the formation fluid viscosity mu, the thickness h, the original formation pressure p, the total fracturing fluid amount, the total proppant amount, the well pattern type, the development well spacing, the fracturing process, the fracturing fluid type, the proppant type, the time, the block and the bed series, and the initial fluid yield and the initial oil yield, wherein the neural network is a fully-connected neural network consisting of four layers of 256 neurons and an input layer and an output layer, the activation function of the middle layer is reLu, the final objective function is MSE, the gradient descent is Adam, epoch is 1000, and batch is 300.
5. The method for fracture analysis using data-driven decision making according to claim 1, wherein the step 4 specifically comprises: and (4) connecting the last round of the last layer in the four-layer fully-connected neural network described in the step (3) with the XGBOST algorithm, namely realizing the stacking between the fully-connected network and the XGBOST.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210949311.7A CN115310357A (en) | 2022-08-09 | 2022-08-09 | Fracturing analysis method based on data-driven decision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210949311.7A CN115310357A (en) | 2022-08-09 | 2022-08-09 | Fracturing analysis method based on data-driven decision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115310357A true CN115310357A (en) | 2022-11-08 |
Family
ID=83860026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210949311.7A Pending CN115310357A (en) | 2022-08-09 | 2022-08-09 | Fracturing analysis method based on data-driven decision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115310357A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108573078A (en) * | 2017-03-09 | 2018-09-25 | 中国石油化工股份有限公司 | Post-frac effect forecasting method based on data mining |
| WO2021143067A1 (en) * | 2020-05-28 | 2021-07-22 | 平安科技（深圳）有限公司 | Method and apparatus for predicting workpiece quality, and computer device |
| CN114117881A (en) * | 2020-08-31 | 2022-03-01 | 中国石油化工股份有限公司 | Sand production risk prediction method and system |
| CN114429800A (en) * | 2020-10-15 | 2022-05-03 | 中国石油化工股份有限公司 | Methane hydrate generation rate prediction method and system based on model fusion |
| CN114638147A (en) * | 2020-12-16 | 2022-06-17 | 中国石油化工股份有限公司 | Method for determining fracturing process parameters of oil and gas reservoir |
-
2022
- 2022-08-09 CN CN202210949311.7A patent/CN115310357A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108573078A (en) * | 2017-03-09 | 2018-09-25 | 中国石油化工股份有限公司 | Post-frac effect forecasting method based on data mining |
| WO2021143067A1 (en) * | 2020-05-28 | 2021-07-22 | 平安科技（深圳）有限公司 | Method and apparatus for predicting workpiece quality, and computer device |
| CN114117881A (en) * | 2020-08-31 | 2022-03-01 | 中国石油化工股份有限公司 | Sand production risk prediction method and system |
| CN114429800A (en) * | 2020-10-15 | 2022-05-03 | 中国石油化工股份有限公司 | Methane hydrate generation rate prediction method and system based on model fusion |
| CN114638147A (en) * | 2020-12-16 | 2022-06-17 | 中国石油化工股份有限公司 | Method for determining fracturing process parameters of oil and gas reservoir |
Non-Patent Citations (2)
| Title |
|---|
| 吴华: ""基于机器学习的页岩气井压裂优化模型研究"", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
| 王少英: ""基于智能计算的水力压裂施工参数优化"", 《山东工业技术》, pages 79 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113723838B (en) | While-drilling safety risk intelligent identification method based on convolutional neural network | |
| US12135926B2 (en) | Method for quickly optimizing key mining parameters of outburst coal seam | |
| CN108573320B (en) | Method and system for calculating final recoverable reserves of shale gas reservoir | |
| CN111080408B (en) | Order information processing method based on deep reinforcement learning | |
| CN102521694A (en) | Multi-process scheme planning method based on combination weighting method | |
| CN110400006A (en) | Oil well output prediction technique based on deep learning algorithm | |
| CN110287516B (en) | Comprehensive evaluation method for compressibility of horizontal fractured well of shale gas reservoir | |
| CN106599230A (en) | Method and system for evaluating distributed data mining model | |
| CN110647830A (en) | Bearing fault diagnosis method based on convolutional neural network and Gaussian mixture model | |
| CN108595803A (en) | Shale gas well liquid loading pressure prediction method based on recurrent neural network | |
| CN114662793B (en) | Business process remaining time prediction method and system based on interpretable hierarchical model | |
| CN117574755B (en) | Hierarchical multistage optimization method for fracturing parameters of horizontal well of shale reservoir well factory | |
| CN113722997A (en) | New well dynamic yield prediction method based on static oil and gas field data | |
| Zhang et al. | A generic data analytics system for manufacturing production | |
| CN110633504A (en) | Prediction method for coal bed gas permeability | |
| CN115329468A (en) | Drilling machine drilling speed prediction method for improving BP neural network based on BAS algorithm | |
| CN114991757B (en) | A method and system for integrated monitoring of formation pressure while drilling | |
| CN116011234A (en) | Pressure front sleeve change risk level judgment method integrating geomechanics and Bayes | |
| CN115310357A (en) | Fracturing analysis method based on data-driven decision | |
| CN114004100B (en) | Oil reservoir assisted history fitting and optimization simulation method | |
| CN111749675A (en) | Stratum drillability prediction method and system based on cascade model algorithm | |
| CN106530109A (en) | Oilfield development appraisal well decision method based on information value | |
| CN117669795A (en) | Deep learning-based tight gas reservoir yield prediction method and system | |
| CN116522777A (en) | Drilling process drilling rate online prediction method and system based on multi-source information fusion | |
| Mohaghegh et al. | Hydraulic fracture design and optimization of gas storage wells |
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: 20221108 |
|
| RJ01 | Rejection of invention patent application after publication |