CN114492153B - Method for predicting high-pressure physical parameters of reservoir fluid - Google Patents
Method for predicting high-pressure physical parameters of reservoir fluid Download PDFInfo
- Publication number
- CN114492153B CN114492153B CN202111146793.4A CN202111146793A CN114492153B CN 114492153 B CN114492153 B CN 114492153B CN 202111146793 A CN202111146793 A CN 202111146793A CN 114492153 B CN114492153 B CN 114492153B
- Authority
- CN
- China
- Prior art keywords
- fluid
- pressure physical
- reservoir
- physical parameters
- formation
- 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.)
- Active
Links
- 239000012530 fluid Substances 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012795 verification Methods 0.000 claims abstract description 24
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 48
- 239000010779 crude oil Substances 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 26
- 230000000704 physical effect Effects 0.000 claims description 15
- 239000003921 oil Substances 0.000 claims description 12
- 239000004215 Carbon black (E152) Substances 0.000 claims description 11
- 229930195733 hydrocarbon Natural products 0.000 claims description 11
- 150000002430 hydrocarbons Chemical class 0.000 claims description 11
- 238000010200 validation analysis Methods 0.000 claims description 7
- 238000002474 experimental method Methods 0.000 claims description 6
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 239000007789 gas Substances 0.000 description 8
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004090 dissolution Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- 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
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- Evolutionary Biology (AREA)
- Fluid Mechanics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Production Of Liquid Hydrocarbon Mixture For Refining Petroleum (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a method for predicting high-pressure physical parameters of a fluid in a reservoir, which comprises the following steps: data collection, sample acquisition, data division, data prediction, result analysis and verification, model optimization and prediction of high-pressure physical parameters of the reservoir fluid. The prediction model established by the invention is reliable and reasonable, and can accurately predict the high-pressure physical parameters of the reservoir fluid by using the model; the invention starts from a microscopic angle, takes the fluid component composition as the input characteristic value of the prediction model, so that the correlation and the interpretability of the prediction model and the high-pressure physical parameters of the stratum fluid are higher, the prediction result is more accurate, the experimental efficiency is improved, and the reserve calculation and the production practice are guided.
Description
Technical Field
The invention relates to the technical field of petroleum and natural gas, in particular to a method for predicting high-pressure physical parameters of a reservoir fluid.
Background
The high-pressure physical parameters of the reservoir fluid are the basis for reservoir calculation, development scheme compilation and scheme adjustment.
The high-pressure physical parameters of the oil and gas reservoir stratum fluid are mainly obtained through conventional PVT test experiments, and the conventional test conditions are demanding, the physical simulation period is long, and the efficiency is low. With the rapid increase of the workload of oil and gas reservoir exploration and development experiments in China, the problem of experimental efficiency is increasingly prominent, and the existing PVT experimental equipment and personnel are difficult to meet the oil and gas reservoir exploration and development requirements.
In addition, the presently disclosed prediction method for the high-pressure physical parameters of the oil and gas reservoir stratum fluid is to establish a prediction model through a neural network, take stratum pressure, stratum temperature, ground crude oil density, gas-oil ratio and natural gas relative density as input layers of the prediction model, and take saturated pressure, crude oil dissolution gas-oil ratio, volume coefficient, stratum crude oil density and stratum crude oil viscosity as output prediction results of the prediction model. The correlation between the high-pressure physical parameters of the fluid in the reservoir and the composition of the fluid is larger, and the neural network lacks of interpretability, so that the prediction result of the disclosed prediction method for the high-pressure physical parameters of the fluid in the reservoir has deviation and irrational property.
Disclosure of Invention
The invention overcomes the defects in the prior art, has strict requirements on conventional PVT test experimental conditions, long physical simulation period and lower efficiency, provides a method for predicting high-pressure physical property parameters of the fluid in the reservoir, starts from a microscopic angle, the fluid component composition is used as the input characteristic value of the prediction model, so that the correlation and the interpretability of the prediction model and the high-pressure physical parameters of the formation fluid are higher, the prediction result is more accurate, the experimental efficiency is improved, and the reserve calculation and the production practice are guided.
The aim of the invention is achieved by the following technical scheme.
A method for predicting high-pressure physical parameters of a fluid in a reservoir is carried out according to the following steps:
Step 1, data collection: collecting historical data composed of formation fluid components of a target reservoir block;
step 2, obtaining a sample: taking the composition of stratum fluid components and high-pressure physical parameters of each well of a target oil and gas reservoir block as one sample, so that n samples of the target block are obtained;
step 3, data division: dividing the collected samples into s groups of training sets m and verification sets p;
Step 4, data prediction: establishing a high-pressure physical property parameter prediction model of the reservoir stratum fluid, taking the composition of the stratum fluid in the training set m as an input characteristic of the model, and obtaining an output result;
step 5, result analysis and verification: comparing the output result with data in the verification set, thereby obtaining error data;
Step 6, model optimization: selecting another group of training set m and verification set p, repeating the steps 4-5, continuously establishing a new prediction model based on XGBoost according to the new training set m and verification set p until the correlation coefficient R 2 of the prediction model is larger than 0.95, regarding the error as meeting the requirement, and completing optimization and establishment of the prediction model;
And 7, predicting high-pressure physical parameters of the fluid in the reservoir: and taking the content of a group of stratum fluid as an input characteristic value of an optimized model, and inputting the optimized model, namely, the predicted high-pressure physical parameters of the stratum fluid of the oil and gas reservoir.
In step 3, the s sets of training set m and validation set p are obtained using a cross validation method.
In step 3, training set m is composed of formation fluid components in m samples, and validation set p is composed of formation fluid high pressure physical parameters in p samples.
In step 4, a reservoir fluid high pressure physical property parameter prediction model is established based on XGBoost.
In step 4, the output results are the formation crude oil viscosity, the formation crude oil density, the saturation pressure and the volume coefficient.
The verification set in the step 5 is in the same group as the training set in the step 6, so that the error comparison is ensured to be effective.
In step 1, the historical data of the composition of the formation fluid in the target hydrocarbon reservoir block is the content of the formation fluid CO2、N2、C1、C2、C3、iC4、nC4、iC5、nC5、C6、C7、C8、C9、C10、C11+ in each well of the block and the high-pressure physical parameters such as the viscosity of the formation crude oil, the density of the formation crude oil, the saturation pressure, the volume coefficient and the like, which are measured by the PVT experiment.
In step 7, the input characteristic value is the content of formation fluid CO2、N2、C1、C2、C3、iC4、nC4、iC5、nC5、C6、C7、C8、C9、C10、C11+.
In step 7, the input characteristic data is collected data, rather than historical data of formation fluid composition of the target reservoir block in step 1.
The beneficial effects of the invention are as follows: the prediction model established by the invention is reliable and reasonable, and can accurately predict the high-pressure physical parameters of the reservoir fluid by using the model; the invention starts from a microscopic angle, takes the fluid component composition as the input characteristic value of the prediction model, so that the correlation and the interpretability of the prediction model and the high-pressure physical parameters of the stratum fluid are higher, the prediction result is more accurate, the experimental efficiency is improved, and the reserve calculation and the production practice are guided.
Drawings
Fig. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical scheme of the invention is further described by specific examples.
As shown in fig. 1, a method for predicting high-pressure physical parameters of a fluid in a reservoir, comprising the steps of:
Data collection
Collecting historical data composed of formation fluid components of a target reservoir block;
ii. Obtaining a sample
Taking the composition of stratum fluid components and high-pressure physical parameters of each well of a target oil and gas reservoir block as one sample, so that n samples of the target block are obtained;
Iii data partitioning
Dividing the collected samples into s groups of training sets m and verification sets p;
iv. Data prediction
Establishing a high-pressure physical property parameter prediction model of the reservoir stratum fluid, taking the composition of the stratum fluid in the training set m as an input characteristic of the model, and obtaining an output result;
v. analysis and verification of results
Comparing the output result with data in the verification set, thereby obtaining error data;
Vi model optimization
Selecting another group of training set m and verification set p, repeating the steps iv-v, continuously establishing a new prediction model based on XGBoost according to the new training set m and verification set p until the correlation coefficient R 2 of the prediction model is larger than 0.95, regarding the error as meeting the requirement, and completing optimization and establishment of the prediction model;
vii. Predicting high pressure physical parameters of reservoir fluids
And taking the content of a group of stratum fluid as an input characteristic value of an optimized model, and inputting the optimized model, namely, the predicted high-pressure physical parameters of the stratum fluid of the oil and gas reservoir.
In step iii, the s training set m and the verification set p are obtained by using a cross verification method.
In step iii, training set m is composed of formation fluid components in m samples, and verification set p is composed of formation fluid high-pressure physical parameters in p samples.
In the step iv, a model for predicting high-pressure physical property parameters of the fluid in the reservoir and the reservoir is built based on XGBoost.
The output result in the step iv is the formation crude oil viscosity, the formation crude oil density, the saturation pressure and the volume coefficient.
And v, the verification set in the step v is in the same group as the training set in the step iv, so that the error comparison is ensured to be effective.
The historical data of the composition of the formation fluid of the target hydrocarbon reservoir block in the step i are the content of the formation fluid CO2、N2、C1、C2、C3、iC4、nC4、iC5、nC5、C6、C7、C8、C9、C10、C11+ of each well of the block, and the high-pressure physical parameters such as the viscosity of the formation crude oil, the density of the formation crude oil, the saturation pressure, the volume coefficient and the like, which are measured through PVT experiments.
The input characteristic value in step vii is the formation fluid CO2、N2、C1、C2、C3、iC4、nC4、iC5、nC5、C6、C7、C8、C9、C10、C11+ content.
The characteristic data input in step vii is collected data, but not historical data of the formation fluid composition of the target hydrocarbon reservoir block in step i.
Examples
First, 220 pieces of PVT experimental sample data are collected, and each piece of sample data further comprises high-pressure physical parameters such as the content of formation fluid CO2、N2、C1、C2、C3、iC4、nC4、iC5、nC5、C6、C7、C8、C9、C10、C11+, the viscosity of formation crude oil, the density of formation crude oil, the saturation pressure, the volume coefficient and the like.
Then, the collected samples were divided into 50 groups each consisting of a random 200 training set and 20 validation sets using a cross validation method; each training set is composed of the content of formation fluid CO2、N2、C1、C2、C3、iC4、nC4、iC5、nC5、C6、C7、C8、C9、C10、C11+ in the corresponding sample data, and each validation set is composed of high-pressure physical parameters such as formation crude oil viscosity, formation crude oil density, saturation pressure, volume coefficient and the like in the corresponding sample data.
And then, establishing a high-pressure physical property parameter prediction model of the reservoir fluid based on XGBoost, selecting a training set and a validation set, taking the composition of the reservoir fluid in the training set as an input characteristic of the model, and taking the viscosity of the crude oil of the stratum, the density of the crude oil of the stratum, the saturation pressure and the volume coefficient as a prediction model output result.
And carrying out error analysis on the output result of the prediction model and historical experimental data of formation crude oil viscosity, formation crude oil density, saturation pressure and volume coefficient in the same group of verification set.
And selecting another group of training set and verification set, repeating the steps until the error meets the requirement, and completing the optimization and establishment of the prediction model.
The content of formation fluid CO2、N2、C1、C2、C3、iC4、nC4、iC5、nC5、C6、C7、C8、C9、C10、C11+ of 10 wells is randomly selected as a model input characteristic value, the established prediction model is utilized to predict the high-pressure physical parameters of the formation crude oil viscosity, the formation crude oil density, the saturation pressure and the volume coefficient, and the prediction result is compared with experimental data of the high-pressure physical parameters of the formation crude oil viscosity, the formation crude oil density, the saturation pressure and the volume coefficient of the 10 wells, as shown in tables 1-4.
Table 1 comparison table of crude oil viscosity test values and predicted values
| Sample of | Actual viscosity value | Predicted viscosity value | Error, percent |
| 1 St well | 22.5 | 23.5 | 4.44 |
| 2 Nd well | 126.2 | 125.6 | 0.48 |
| 3 Rd well | 1.1 | 1.3 | 2.73 |
| 4 Th well | 0.3 | 0.4 | 3.33 |
| 5 Th well | 0.3 | 0.2 | 6.67 |
| 6 Th well | 0.3 | 0.4 | 3.33 |
| 7 Th well | 0.3 | 0.4 | 6.67 |
| 8 Th well | 13.8 | 15.1 | 5.07 |
| No. 9 well | 67.9 | 68.2 | 1.62 |
| 10 Th well | 2.2 | 2.5 | 6.82 |
Table 2 comparison table of crude oil density experimental value and predicted value of stratum
| Sample of | Actual density value | Predicted density value | Error, percent |
| 1 St well | 0.8934 | 0.8859 | 0.84 |
| 2 Nd well | 0.9365 | 0.9158 | 2.21 |
| 3 Rd well | 0.7356 | 0.7158 | 2.69 |
| 4 Th well | 0.6158 | 0.6254 | 1.56 |
| 5 Th well | 0.6159 | 0.5987 | 2.79 |
| 6 Th well | 0.6289 | 0.6157 | 2.10 |
| 7 Th well | 0.6338 | 0.6259 | 1.25 |
| 8 Th well | 0.8894 | 0.8566 | 3.69 |
| No. 9 well | 0.8659 | 0.8235 | 4.90 |
| 10 Th well | 0.8155 | 0.8054 | 1.24 |
Table 3 comparison table of formation crude oil saturation pressure experimental value and predicted value
| Sample of | Actual saturation pressure value | Predicting saturation pressure values | Error, percent |
| 1 St well | 4.60 | 4.52 | 1.74 |
| 2 Nd well | 8.23 | 8.13 | 1.22 |
| 3 Rd well | 14.18 | 13.59 | 4.16 |
| 4 Th well | 27.44 | 25.91 | 5.58 |
| 5 Th well | 28.32 | 27.36 | 3.39 |
| 6 Th well | 21.56 | 20.68 | 4.08 |
| 7 Th well | 36.06 | 34.21 | 5.13 |
| 8 Th well | 5.59 | 5.64 | 0.89 |
| No. 9 well | 6.57 | 6.28 | 4.41 |
| 10 Th well | 14.80 | 14.2 | 4.05 |
Table 4 comparison table of crude oil volume coefficient experiment value and predicted value of stratum
| Sample of | Actual volume coefficient value | Predicted volume coefficient value | Error, percent |
| 1 St well | 1.06 | 1.04 | 1.89 |
| 2 Nd well | 1.05 | 1.03 | 1.90 |
| 3 Rd well | 1.27 | 1.21 | 4.72 |
| 4 Th well | 1.76 | 1.79 | 1.70 |
| 5 Th well | 1.76 | 1.72 | 2.27 |
| 6 Th well | 1.52 | 1.45 | 4.61 |
| 7 Th well | 1.63 | 1.55 | 4.91 |
| 8 Th well | 1.07 | 1.12 | 4.67 |
| No. 9 well | 1.09 | 1.03 | 5.50 |
| 10 Th well | 1.21 | 1.25 | 3.31 |
The prediction model established by the invention is reliable and reasonable, and can accurately predict the high-pressure physical parameters of the reservoir fluid.
The invention starts from a microscopic angle, takes the fluid component composition as the input characteristic value of the prediction model, so that the correlation and the interpretability of the prediction model and the high-pressure physical parameters of the stratum fluid are higher, the prediction result is more accurate, the experimental efficiency is improved, and the reserve calculation and the production practice are guided.
The foregoing has described exemplary embodiments of the invention, it being understood that any simple variations, modifications, or other equivalent arrangements which would not unduly obscure the invention may be made by those skilled in the art without departing from the spirit of the invention.
Claims (7)
1. A method for predicting high-pressure physical parameters of a reservoir fluid, which is characterized in that: the method comprises the following steps of:
Step 1, data collection: collecting historical data composed of formation fluid components of a target reservoir block;
step 2, obtaining a sample: taking the composition of stratum fluid components and high-pressure physical parameters of each well of a target oil and gas reservoir block as one sample, so that n samples of the target block are obtained;
step 3, data division: dividing the collected samples into s groups of training sets m and verification sets p;
Step 4, data prediction: establishing a high-pressure physical property parameter prediction model of the reservoir stratum fluid, taking the composition of the stratum fluid in the training set m as an input characteristic of the model, and obtaining an output result;
step 5, result analysis and verification: comparing the output result with data in the verification set, thereby obtaining error data;
Step 6, model optimization: selecting another group of training set m and verification set p, repeating the steps 4-5, continuously establishing a new prediction model based on XGBoost according to the new training set m and verification set p until the correlation coefficient R2 of the prediction model is larger than 0.95, and finishing optimization and establishment of the prediction model by considering that the error meets the requirement;
and 7, predicting high-pressure physical parameters of the fluid in the reservoir: taking the content of a group of stratum fluid as an input characteristic value of an optimized model, and inputting the optimized model, namely, the predicted high-pressure physical parameters of the stratum fluid of the oil and gas reservoir;
In step 1, historical data of formation fluid composition of a target hydrocarbon reservoir block are high-pressure physical parameters of formation crude oil viscosity, formation crude oil density, saturation pressure and volume coefficient of formation fluids CO2, N2, C1, C2, C3, iC4, nC4, iC5, nC5, C6, C7, C8, C9, C10 and C11+ of each well of the block measured through PVT experiments;
In step 7, the input characteristic values are the contents of formation fluids CO2, N2, C1, C2, C3, iC4, nC4, iC5, nC5, C6, C7, C8, C9, C10, C11+;
in step 7, the input characteristic data is collected data, rather than historical data of formation fluid composition of the target reservoir block in step 1.
2. A method of predicting high pressure physical properties of a hydrocarbon reservoir fluid as recited in claim 1, wherein: in step 3, the s sets of training set m and validation set p are obtained using a cross validation method.
3. A method of predicting high pressure physical properties of a hydrocarbon reservoir fluid as recited in claim 1, wherein: in step 3, training set m is composed of formation fluid components in m samples, and validation set p is composed of formation fluid high pressure physical parameters in p samples.
4. A method of predicting high pressure physical properties of a hydrocarbon reservoir fluid as recited in claim 1, wherein: in step 4, a reservoir fluid high pressure physical property parameter prediction model is established based on XGBoost.
5. A method of predicting high pressure physical properties of a hydrocarbon reservoir fluid as recited in claim 1, wherein: in step 4, the output results are the formation crude oil viscosity, the formation crude oil density, the saturation pressure and the volume coefficient.
6. A method of predicting high pressure physical properties of a hydrocarbon reservoir fluid as recited in claim 1, wherein: the verification set in the step 5 is in the same group as the training set in the step 6, so that the error comparison is ensured to be effective.
7. Use of a method for predicting a high pressure physical property parameter of a hydrocarbon reservoir fluid as claimed in any one of claims 1 to 6 in predicting a high pressure physical property parameter of a hydrocarbon reservoir fluid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111146793.4A CN114492153B (en) | 2021-09-28 | 2021-09-28 | Method for predicting high-pressure physical parameters of reservoir fluid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111146793.4A CN114492153B (en) | 2021-09-28 | 2021-09-28 | Method for predicting high-pressure physical parameters of reservoir fluid |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114492153A CN114492153A (en) | 2022-05-13 |
| CN114492153B true CN114492153B (en) | 2024-11-01 |
Family
ID=81492755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111146793.4A Active CN114492153B (en) | 2021-09-28 | 2021-09-28 | Method for predicting high-pressure physical parameters of reservoir fluid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114492153B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112983409A (en) * | 2021-03-19 | 2021-06-18 | 中海石油(中国)有限公司海南分公司 | Method for predicting mineral components of clastic rock by using machine learning algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021183165A1 (en) * | 2020-03-13 | 2021-09-16 | Landmark Graphics Corporation | Early warning and automated detection for lost circulation in wellbore drilling |
-
2021
- 2021-09-28 CN CN202111146793.4A patent/CN114492153B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112983409A (en) * | 2021-03-19 | 2021-06-18 | 中海石油(中国)有限公司海南分公司 | Method for predicting mineral components of clastic rock by using machine learning algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114492153A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112487582B (en) | Oil-gas drilling machinery drilling speed prediction and optimization method based on CART algorithm | |
| Zhou* et al. | Evaluating gas production performances in marcellus using data mining technologies | |
| CN112561356B (en) | Comprehensive evaluation method for production dynamic mode and productivity of shale oil fracturing horizontal well | |
| CN108959767B (en) | Method for simulating damage numerical values of condensate oil in different well types of narrow-river-channel gas reservoir | |
| CN105386751A (en) | Well logging and productivity prediction method of horizontal well based on oil reservoir seepage flow model | |
| CN110952976A (en) | Single-well exploitation stable yield potential evaluation method under gas reservoir development mode | |
| CN109063403B (en) | Optimal design method for slickwater fracturing | |
| CN116122801A (en) | Shale oil horizontal well volume fracturing compressibility comprehensive evaluation method | |
| CN106125156A (en) | The multifactor means of interpretation of igneous rock well logging | |
| CN113297740A (en) | Horizontal well gel profile control parameter optimization method | |
| CN114492153B (en) | Method for predicting high-pressure physical parameters of reservoir fluid | |
| CN110295895B (en) | Method for dynamically evaluating physical properties of glutenite reservoir by using macroscopic flow coefficient | |
| Ariadji et al. | Optimization of vertical well placement for oil field development based on basic reservoir rock properties using a genetic algorithm | |
| CN112069690A (en) | Evaluation method for test productivity of deep water fault block oil reservoir long horizontal well multistage oil nozzle | |
| CN111460647A (en) | Quantitative allocation method for horizontal well segmented targeted steam injection amount after multi-round huff and puff | |
| CN111335871A (en) | Layer-checking hole-repairing technical method based on layered productivity evaluation | |
| Kalantari-Dahaghi et al. | A new practical approach in modelling and simulation of shale gas reservoirs: application to New Albany Shale | |
| CN111691878A (en) | Lithofacies quality grading evaluation method and device for shale | |
| CN115705452A (en) | Novel recovery ratio prediction method for middle and later stages of integrated sandstone reservoir development | |
| CN111155980A (en) | Water flow dominant channel identification method and device | |
| CN112360446B (en) | Method for judging gas well type based on gas well production dynamic index system | |
| CN110851982B (en) | Method for analyzing feasibility of oxygen reduction air flooding of medium-low permeability oil reservoir | |
| CN112834404A (en) | Method and device for determining gas production capacity of shale reservoir | |
| CN112464136A (en) | Method for predicting yield and development effect of offshore thin interbed sandstone oil field directional well | |
| CN111428375A (en) | Novel high-water-content oilfield layer system recombination and division 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 | ||
| GR01 | Patent grant |