CN113283180A - K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application - Google Patents
K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application Download PDFInfo
- Publication number
- CN113283180A CN113283180A CN202110718754.0A CN202110718754A CN113283180A CN 113283180 A CN113283180 A CN 113283180A CN 202110718754 A CN202110718754 A CN 202110718754A CN 113283180 A CN113283180 A CN 113283180A
- Authority
- CN
- China
- Prior art keywords
- data
- svr
- fracturing
- combination
- parameters
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000010276 construction Methods 0.000 claims abstract description 20
- 238000000513 principal component analysis Methods 0.000 claims abstract description 6
- 238000010219 correlation analysis Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000004140 cleaning Methods 0.000 claims abstract description 3
- 239000003921 oil Substances 0.000 claims description 24
- 239000012530 fluid Substances 0.000 claims description 20
- 238000004519 manufacturing process Methods 0.000 claims description 15
- 230000000704 physical effect Effects 0.000 claims description 13
- 230000015572 biosynthetic process Effects 0.000 claims description 8
- 239000010779 crude oil Substances 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 230000035699 permeability Effects 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 239000003795 chemical substances by application Substances 0.000 claims 1
- 230000001186 cumulative effect Effects 0.000 claims 1
- 238000011156 evaluation Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000011161 development Methods 0.000 abstract description 5
- 239000003129 oil well Substances 0.000 abstract description 4
- 238000003064 k means clustering Methods 0.000 abstract 1
- 230000008901 benefit Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010845 search algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
- E21B43/25—Methods for stimulating production
- E21B43/26—Methods for stimulating production by forming crevices or fractures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mining & Mineral Resources (AREA)
- Geology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a compact reservoir horizontal well fracturing capacity combined prediction method and application based on a Support Vector Regression (SVR) combination of k-means, and belongs to the technical field of oil and gas exploration and development. The method comprises obtaining a data set related to capacity impact; carrying out data cleaning and data preprocessing; calculating characteristic weight by a principal component analysis algorithm and carrying out characteristic weighting; finding out main control factors by a gray level correlation analysis algorithm; clustering geological factors and physical factors according to a K-means clustering analysis algorithm; building an SVR algorithm model according to the clustering result and the fracturing construction data, and finding out an optimal precision model for prediction; and performing fracturing construction suggestion guidance on the low-yield oil well by using the SVR model. By adopting the technical scheme, the invention can better solve the main factors of low yield of the oil well and huge economic loss caused by fracturing construction design and the like, and provides a new yield combined prediction mode for predicting the capacity of the compact oil.
Description
Technical Field
The invention relates to a capacity prediction method, in particular to a method for predicting the fracturing capacity of a tight reservoir horizontal well based on K-means and SVR combination and application thereof, and belongs to the technical field of oil and gas exploration and development.
Background
The tight oil reservoir is one of the main sources of the current unconventional oil and gas exploitation, and with the influence of the progress of drilling level and development technology in recent years, most oil fields adopt an exploitation mode of horizontal well matched with volume fracturing technology to replace the original exploitation method so as to achieve the important method of increasing production and improving recovery ratio. Under the mining mode, the main factors of long-time continuous high yield of the compact oil horizontal fracturing well are researched, the oil deposit productivity is accurately predicted, and the method has important guiding significance and economic benefit on efficient development of subsequent compact oil.
The existing methods related to reservoir productivity prediction are roughly divided into two categories: one is longitudinal prediction, mainly deducing a productivity formula based on the non-Darcy seepage; the other type is transverse prediction, and parameters are processed by using mathematical methods such as pattern recognition and the like, so that a capacity prediction model is established. The formula prediction based on mechanism analysis needs to be combined with actual production conditions, the accuracy and the rationality need to be further improved, and the prediction of the capacity of the dense oil by adopting a single machine learning algorithm cannot be solved: 1. the contribution degrees of different characteristic parameters are different; 2. the dense oil productivity has a plurality of influence parameters, and direct introduction may cause overfitting; 3. the geological parameters and the fluid physical parameters belong to static parameters, and the static parameters of the similar block wells are basically consistent. Therefore, from the data mining perspective, the combined model based on the cluster analysis algorithm and the regression algorithm is provided in combination with the actual situation of the site, and the problems can be solved. The main component analysis algorithm is used for performing characteristic weighting, the gray level correlation algorithm is used for analyzing the main control factors, the grid traversal algorithm is used for searching the optimal precision model to improve the model accuracy rate, and the method has important theoretical and practical significance, and can greatly improve the overall development economic benefit of the oil field by researching and optimizing the fracturing construction parameters of the low-yield oil well.
Disclosure of Invention
Aiming at the problems, the invention aims to avoid the great waste of human resources and financial resources caused by the uncertainty of fracturing construction parameters, thereby improving the construction quality and the overall economic benefit of a fracturing construction team of a compact oil field.
In order to achieve the purpose, the invention adopts the following technical scheme: the method for predicting the fracturing capacity of the tight oil reservoir horizontal well based on the combination of K-means and SVR comprises the following steps:
(1) and collecting tight oil reservoir geological data, fluid physical property data, fracturing construction data and post-fracturing energy production data.
(2) And carrying out data cleaning and data preprocessing on the acquired data.
(3) Weights are calculated and weighted for different types of data features.
(4) And finding out the main control factors of different types of data.
(5) And performing cluster analysis modeling on the data after the geological parameters and the fluid physical property parameters are processed.
(6) And (4) modeling the clustering result by a prediction algorithm in combination with the fracturing construction data, and searching for the optimal model parameter.
(7) And constructing an SVR algorithm model.
In the step 1), the collected geological data, fluid physical property data and fracturing construction data are used as model independent variables, and 'production accumulated in the year of production' in the pressed productivity data is selected as a dependent variable.
And 2) removing abnormal data by a mean square error method, and mapping the data to a [0,1] interval by maximum-minimum standardization.
And 3) performing characteristic weighting on factors of geology, fluid physical property and fracturing construction by a principal component analysis algorithm, and replacing original data with weighted data.
And 4) performing relevance sorting on all the characteristic values through a gray level relevance algorithm, so as to screen the characteristic values mainly influencing output in factors of geology, fluid physical property and fracturing construction.
And 5) selecting the characteristics belonging to the geological parameters and the fluid physical property parameters from the reconstructed data volume of the characteristic values selected in the step 4) as a data volume of a k-means model to model. A grid search algorithm is used to find the optimal number of clusters k.
And 6) combining the classification characteristics and the fracturing construction parameters obtained in the step 5) with a reconstruction data body, and selecting the accumulated oil production in the current year of production as an output value of an algorithm to construct an SVR prediction model. A grid search algorithm is used to find the optimal penalty parameter c and the kernel function parameter g.
And 7), setting parameters of the SVR according to the optimal value searched in the step 6), and inputting data into the SVR model to obtain a model with optimal prediction accuracy.
Due to the adoption of the technical scheme, the invention has the following advantages: 1. according to the method, abnormal data are removed through a mean square error method, the accuracy of the data is improved, different characteristics are made to be comparable through removing dimensions in a standardized mode, and the influence of characteristic numerical value levels caused by the dimensions on analysis results is eliminated. 2. Different feature weights are calculated through a principal component analysis algorithm, and the problem of hard clustering of the k-means algorithm is solved. 3. And (3) finding out the most representative characteristic influencing the capacity change by adopting a gray level correlation analysis algorithm, and improving the accuracy of model prediction. 4. The fracturing construction parameters of the low-yield wells of the similar blocks can be optimized and guided.
Drawings
FIG. 1 is a flow chart of a fracturing productivity prediction algorithm for a tight reservoir horizontal well;
FIG. 2 is a schematic view of SVR;
FIG. 3 is a schematic diagram of a combination model.
Detailed Description
In order to more clearly illustrate the technical solution of the present invention, the following detailed description of the present invention is provided with reference to the accompanying drawings and examples.
The method for predicting the fracturing capacity of the tight oil reservoir horizontal well based on the combination of K-means and SVR and the application flow chart are shown in figure 1, and the method is specifically realized through the following steps:
1. geological data, fluid physical property data, fracturing construction data and post-fracturing energy production data of a plurality of blocks of the tight oil reservoir are collected. In particular, the method can be used for obtaining the geological: permeability, porosity, natural gamma, effective thickness; fluid physical Properties: formation crude oil viscosity, formation crude oil density, content saturation; fracturing construction: the proppant usage, the fracturing fluid type, the number of stages, the average sand ratio and the like are used as independent variables required by the algorithm, and the yield after pressing is as follows: and (4) taking the accumulated oil production in the current year of production as a dependent variable required by the algorithm.
2. And carrying out statistics and distribution query on each characteristic data, and screening abnormal data by a mean square error method. Because the oil well data have different dimensions and magnitude levels, if the screened data are directly used for modeling training, the algorithm is greatly influenced by the higher median value of the data, and the characteristic of lower numerical mean value is ignored. Therefore, min-max normalization is performed on the screened data, and each eigenvalue result is mapped to [0,1], and the specific conversion function is as follows:
wherein x, min and max are sample data of the characteristic value, the minimum value in the sample data of the characteristic value and the maximum value in the sample data of the characteristic value respectively.
3. And (3) performing principal component analysis on the data in the step (2), and performing feature weighting on all feature value calculation weights to construct a new data body.
4. And (3) carrying out gray level correlation algorithm analysis on the weighted data in the step (3), carrying out correlation calculation on all characteristic values (subsequences) and accumulated oil production (parent sequence) in the current year of production to obtain correlation degree sorting, and respectively finding out the first 3 characteristic values with the maximum correlation between geological and fluid physical properties and fracturing construction data and oil production as the input of a subsequent model. The calculation method of the correlation coefficient of each index of the subsequence and the parent sequence is as follows:
rho is a resolution coefficient, rho is more than 0 and less than 1, and the smaller rho is, the larger the difference between the correlation coefficients is, and the stronger the distinguishing capability is. Usually ρ is 0.5. x is the number of0(k),xi(k) Respectively representing the kth number of the mother sequence and the kth number of the ith characteristic value of the subsequence. Zetai(k)The correlation coefficient of the kth value representing the ith feature with the kth value of the mother sequence. And calculating the relevance through the relevance coefficient, and then carrying out final sorting. Wherein the degree of association is calculated as follows:
wherein r isiAnd n is the sample number, and is the relevance size of the ith feature and the mother sequence. Finally, for all the advances riAnd (3) obtaining the relevancy ranking by row ranking, wherein the finally selected geological main control factors are as follows: permeability, porosity, effective thickness; the main factors of the physical properties of the fluid are as follows: formation crude oil viscosity, formation crude oil density, oil saturation; the fracturing construction main control factors are as follows: proppant amount, fracturing fluid type, number of stages.
5. And (4) establishing a k-means cluster analysis model for the geological and fluid physical property data selected in the step (4).
6. And (4) constructing a new data body by combining the clustering characteristic value obtained in the step (5) and the fracturing construction type data obtained in the step (4), as shown in a schematic diagram of fig. 3. The method comprises the steps of dividing a training set and a test set for modified samples, carrying out SVR algorithm modeling, traversing kernel function parameters g and penalty parameters c in the SVR algorithm through a grid traversal search algorithm, using mean square error MSE of a predicted value and a true value as performance indexes of a model, setting SVR final model parameters by finding out parameters set by the minimum mean square error, wherein the model is more optimal when the mean square error is smaller. The mean square error MSE calculation mode is as follows:
whereinIs the predicted value of the ith sample, yiIs the actual value of the ith sample, and n is the number of samples.
The above examples are only for illustrating the present invention, and the implementation steps of the methods and the like can be changed, and all equivalent changes and modifications based on the technical scheme of the present invention should not be excluded from the protection scope of the present invention.
Claims (7)
1. The method for predicting the fracturing capacity of the tight oil reservoir horizontal well based on the combination of K-means and SVR comprises the following steps:
1) collecting sample data influencing productivity, wherein the sample data comprises permeability, porosity, formation crude oil viscosity, formation crude oil density, proppant consumption, fracturing fluid type and number of stages;
2) data cleaning is carried out on the collected data, repeated data are removed, and a data body is constructed by singular data;
3) carrying out dimensionless preprocessing on the data volume;
4) calculating the feature weight by adopting a principal component analysis algorithm to perform feature weighting;
5) extracting main control factors by adopting a gray level correlation analysis algorithm;
6) carrying out cluster analysis modeling on the geological parameters and the fluid physical property parameters;
7) and establishing a prediction model based on support vector regression.
2. The method for predicting the fracturing productivity of the tight reservoir horizontal well based on the combination of K-means and SVR as claimed in claim 1 and the application thereof, wherein said step 2) is to perform data screening on the original sample, to perform statistics on the mean and variance of each characteristic value, and to select the value range as [ mean-variance, mean + variance ].
3. The method and the application for predicting the fracturing capacity of the tight reservoir horizontal well based on the combination of K-means and SVR as claimed in claim 1, wherein the step 3) is to perform maximum-minimum standardization preprocessing on the screened data, so that the data are distributed in the interval [0,1 ].
4. The method and application for predicting the fracturing capacity of the tight reservoir horizontal well based on the combination of K-means and SVR as claimed in claim 1, wherein step 4) adopts a principal component analysis algorithm to calculate the feature weight of the normalized data volume, and weights the calculated feature to reconstruct the data volume.
5. The method and application for predicting the fracturing capacity of the tight reservoir horizontal well based on the combination of K-means and SVR as claimed in claim 1, wherein said step 5) adopts a gray level correlation analysis algorithm to calculate and sequence the correlation degree of the normalized data volume, and the final selected geological major factors are: permeability, porosity, effective thickness; the main factors of the physical properties of the fluid are as follows: formation crude oil viscosity, formation crude oil density, oil saturation; the fracturing construction main control factors are as follows: the amount of the propping agent, the amount of the fracturing fluid, the type of the fracturing fluid and the number of stages are used as independent variables, and the cumulative oil production in the current year of production is used as a dependent variable.
6. The method and application for predicting the fracturing productivity of the tight reservoir horizontal well based on the combination of K-means and SVR as claimed in claim 1, wherein the step 6) performs K-means cluster modeling on the geological parameters and the fluid physical parameters.
7. The method for predicting the fracturing productivity of the tight oil reservoir horizontal well based on the combination of the K-means and the SVR and the application thereof as claimed in claim 1 or claim 6, wherein the step 7) is to establish a new data body for algorithm training of the SVR (kernel, C, gamma) by combining the clustered category features and the fracturing parameters, wherein the kernel is a kernel type, C is a penalty coefficient, and gamma is a kernel coefficient, the algorithm traversal parameters are searched through grid traversal, the mean square error MSE is used as a model evaluation standard to determine the optimal parameters, and the parameters are kernel RBF, C is 0.13, and g is 0.035.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110718754.0A CN113283180A (en) | 2021-06-28 | 2021-06-28 | K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110718754.0A CN113283180A (en) | 2021-06-28 | 2021-06-28 | K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113283180A true CN113283180A (en) | 2021-08-20 |
Family
ID=77285778
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110718754.0A Withdrawn CN113283180A (en) | 2021-06-28 | 2021-06-28 | K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113283180A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114320266A (en) * | 2021-11-17 | 2022-04-12 | 陕西延长石油(集团)有限责任公司 | Conventional well yield prediction method for tight oil reservoir based on support vector machine |
CN114461704A (en) * | 2022-04-14 | 2022-05-10 | 浙江理工大学 | Method and system for predicting loom availability based on loom productivity |
CN115828130A (en) * | 2023-02-14 | 2023-03-21 | 中国石油天然气股份有限公司 | Clustering algorithm-based multi-parameter dominant water flow channel automatic identification method and system |
CN117351300A (en) * | 2023-09-14 | 2024-01-05 | 北京市燃气集团有限责任公司 | Small sample training method and device for target detection model |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109871997A (en) * | 2019-02-14 | 2019-06-11 | 国网宁夏电力有限公司经济技术研究院 | A kind of temperature-lowering load combination calculating system adapting to complex environment |
CN112561144A (en) * | 2020-12-07 | 2021-03-26 | 西安石油大学 | Method for evaluating main control factor of productivity of tight oil fracturing horizontal well and predicting productivity |
CN112664184A (en) * | 2020-12-23 | 2021-04-16 | 中国石油大学(华东) | Pumping unit well pump detection period prediction method based on support vector regression algorithm |
-
2021
- 2021-06-28 CN CN202110718754.0A patent/CN113283180A/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109871997A (en) * | 2019-02-14 | 2019-06-11 | 国网宁夏电力有限公司经济技术研究院 | A kind of temperature-lowering load combination calculating system adapting to complex environment |
CN112561144A (en) * | 2020-12-07 | 2021-03-26 | 西安石油大学 | Method for evaluating main control factor of productivity of tight oil fracturing horizontal well and predicting productivity |
CN112664184A (en) * | 2020-12-23 | 2021-04-16 | 中国石油大学(华东) | Pumping unit well pump detection period prediction method based on support vector regression algorithm |
Non-Patent Citations (2)
Title |
---|
王宇: "致密油藏压裂水平井产能模型与应用研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》 * |
郭菊娥 等: "基于GMDH-SVR致密气开发过程参数优化", 《运筹与管理》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114320266A (en) * | 2021-11-17 | 2022-04-12 | 陕西延长石油(集团)有限责任公司 | Conventional well yield prediction method for tight oil reservoir based on support vector machine |
CN114320266B (en) * | 2021-11-17 | 2023-11-28 | 陕西延长石油(集团)有限责任公司 | Dense oil reservoir conventional well yield prediction method based on support vector machine |
CN114461704A (en) * | 2022-04-14 | 2022-05-10 | 浙江理工大学 | Method and system for predicting loom availability based on loom productivity |
CN114461704B (en) * | 2022-04-14 | 2022-06-24 | 浙江理工大学 | Method and system for predicting loom availability based on loom productivity |
CN115828130A (en) * | 2023-02-14 | 2023-03-21 | 中国石油天然气股份有限公司 | Clustering algorithm-based multi-parameter dominant water flow channel automatic identification method and system |
CN117351300A (en) * | 2023-09-14 | 2024-01-05 | 北京市燃气集团有限责任公司 | Small sample training method and device for target detection model |
CN117351300B (en) * | 2023-09-14 | 2024-05-14 | 北京市燃气集团有限责任公司 | Small sample training method and device for target detection model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113283180A (en) | K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application | |
CN108009716B (en) | Multi-level evaluation method for influence factors of horizontal well volume fracturing effect | |
CN109102180B (en) | Comprehensive parameter evaluation method for double-dessert evaluation of tight sandstone reservoir | |
CN110674841B (en) | Logging curve identification method based on clustering algorithm | |
CN104747185A (en) | Heterogeneous reservoir stratum synthetic classifying evaluation method | |
CN111046341A (en) | Unconventional natural gas fracturing effect evaluation and capacity prediction method based on principal component analysis | |
CN113537585B (en) | Oil field production increasing measure recommendation method based on random forest and gradient lifting decision tree | |
CN105005712B (en) | Limestone aquifer watery evaluation methodology | |
CN114997496B (en) | Unsupervised reservoir intelligent segmentation method based on space-time sequence data constraint | |
CN115438823A (en) | Borehole wall instability mechanism analysis and prediction method and system | |
CN109184677A (en) | Reservoir evaluation methods for heterogeneous alternating layers sand body | |
CN107038505A (en) | Ore-search models Forecasting Methodology based on machine learning | |
CN112664184A (en) | Pumping unit well pump detection period prediction method based on support vector regression algorithm | |
CN116384554A (en) | Method and device for predicting mechanical drilling speed, electronic equipment and computer storage medium | |
CN115438090A (en) | Borehole wall instability type analysis and prediction method and system based on lost block image characteristics | |
CN116562428A (en) | Fracturing construction parameter optimization method based on machine learning | |
CN113537706A (en) | Oil field production increasing measure optimization method based on intelligent integration | |
CN117312919A (en) | Rock burst early warning method based on BO-CNN-LSTM model | |
CN110956388A (en) | Method for generating yield increasing scheme of offshore oil and gas reservoir | |
CN116011351A (en) | Oil well reasonable sinking degree determining method based on clustering algorithm and Widedeep network | |
CN117332668A (en) | Shale gas well fracturing effect analysis method and system based on data driving | |
CN113988410A (en) | Cross-region tight oil reservoir oil well productivity prediction method based on KNN algorithm and polynomial regression algorithm combination | |
CN114004151A (en) | Oil pumping well fault prediction method based on LSTM-VGGNet | |
CN113627640A (en) | Productivity well testing prediction method and system for fracture-cavity type oil reservoir oil and gas well | |
CN113344729B (en) | Residual oil submergence digging method based on small sample learning |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210820 |