CN109711595A - A kind of hydraulic fracturing operation effect evaluation method based on machine learning - Google Patents
A kind of hydraulic fracturing operation effect evaluation method based on machine learning Download PDFInfo
- Publication number
- CN109711595A CN109711595A CN201811102171.XA CN201811102171A CN109711595A CN 109711595 A CN109711595 A CN 109711595A CN 201811102171 A CN201811102171 A CN 201811102171A CN 109711595 A CN109711595 A CN 109711595A
- Authority
- CN
- China
- Prior art keywords
- data
- machine learning
- well
- value
- capacity
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 61
- 230000000694 effects Effects 0.000 title claims abstract description 56
- 238000011156 evaluation Methods 0.000 title claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 48
- 238000004519 manufacturing process Methods 0.000 claims abstract description 47
- 238000009826 distribution Methods 0.000 claims abstract description 18
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000000342 Monte Carlo simulation Methods 0.000 claims abstract description 8
- 239000007788 liquid Substances 0.000 claims description 15
- 239000004576 sand Substances 0.000 claims description 10
- 238000003066 decision tree Methods 0.000 claims description 8
- 239000012530 fluid Substances 0.000 claims description 8
- 230000001186 cumulative effect Effects 0.000 claims description 6
- 230000035699 permeability Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000011161 development Methods 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000003825 pressing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000003129 oil well Substances 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to fine and close Reservoir Development technical fields, and in particular to a kind of hydraulic fracturing operation effect evaluation method based on machine learning first obtains geologic data, project data and the capacity data of block；It is again training data block, verify data block and test data block these data set random divisions, and these data blocks is handled using a variety of machine learning algorithms, selects the prediction the smallest machine learning algorithm of error；The key data for influencing production capacity is obtained according to the preset value for influencing capacity data different degree further according to the algorithm selected；It enables project data obey probability distribution, in conjunction with the machine learning algorithm of selection and the key data of influence production capacity, generates single well productivity probability distribution curve using Monte Carlo simulation；Single well productivity value corresponding to several probability is obtained respectively further according to the curve；The single well productivity value for comparing the practical production capacity value of individual well and obtaining from probability curve, evaluates the well fracturing effect, and the evaluation of Fracturing Effect on Compact Sandstone of block further can be achieved.
Description
Technical field
The present invention relates to fine and close Reservoir Development technical fields, and in particular to a kind of hydraulic fracturing throwing based on machine learning
Produce effect evaluation method.
Background technique
Fine and close oil-gas reservoir occupies sizable ratio in China and in the world, and rock stratum is fine and close, the porosity on stratum and
Permeability is all relatively low, generally requires to carry out these oil-gas reservoirs artificial hydraulic fracturing to achieve the purpose that volume increase or operation.
Hydraulic fracturing is that high viscosity fracturing fluid is pumped into oil well or gas well using the high pressure pump group on ground, when the liquid pressure of fractured interval
After power reaches certain value, fractured interval will rupture and open crack, as (the generally sand or haydite) of proppant adds
Add, gradually form a high flow conductivity adds sand crack, to achieve the purpose that improve oil and gas production.
Hydraulic fracturing mechanism is complicated, influence factor is numerous, is related to the different field such as geology, engineering, material, and goes into operation
Evaluation of Fracturing Effect on Compact Sandstone is to ensure pressing crack construction success rate, Optimum Fracturing technology, improve after pressure for the purpose of production capacity, according to section
Program and method is systematically analyzed and is commented to the performance of oil/gas well or oil-gas reservoir after pressing crack construction itself and pressure break
Valence provides foundation for Optimum Fracturing design and Reservoir Management decision.Whether operation effect assessment conclusion is credible, depends on oil gas
The selection of well capacity prediction model.The generally existing following problem of evaluation method at present: mould is predicted using single Oil & Gas Productivity
Type does not optimize model, to affect the credibility of evaluation of Fracturing Effect on Compact Sandstone.
Summary of the invention
To solve problems of the prior art, the purpose of the present invention is to provide a kind of waterpower based on machine learning
Fracturing production effect evaluation method, this method establish productivity prediction model with machine learning algorithm, are calculated by preferred machine learning
Method realizes the optimization of productivity prediction model, and the probability assessment technology of Monte Carlo simulation is combined with machine learning method,
It can be realized to individual well evaluation of Fracturing Effect on Compact Sandstone.
The technical solution adopted by the invention is as follows:
A kind of hydraulic fracturing operation effect evaluation method based on machine learning, includes the following steps:
Step 1, the geologic data, project data and capacity data of block are obtained；
It step 2, is training data block, verify data data set random division according to the preset ratio of data amount check
Block and test data block, wherein the data set includes geologic data described in step 1, project data and capacity data；
Step 3, training data block is learnt respectively using a variety of machine learning algorithms, is distinguished with verify data block true
The model parameter of fixed a variety of machine learning algorithms, the machine of a variety of machine learning algorithms is constructed according to model parameter respectively
Device learning model；
Step 4, the machine learning model for being utilized respectively a variety of machine learning algorithms predicts test data block,
According to prediction error, the prediction the smallest machine learning algorithm of error is chosen；
Step 5, the machine learning algorithm that applying step 4 is chosen, according to the influence degree to Oil & Gas Productivity, prime number over the ground
It is ranked up according to project data, the key data for influencing production capacity is obtained according to the preset value for influencing capacity data different degree；
Step 6, project data is enabled to obey known probability distribution, the machine learning algorithm chosen in conjunction with step 4 and step
The key data of the rapid 5 influence production capacities obtained generates single well productivity probability distribution curve using Monte Carlo simulation；
Step 7, the single well productivity probability distribution curve that applying step 6 generates, obtains list corresponding to several probability respectively
Well capacity value P；
Step 8, the single well productivity value P for comparing the practical production capacity value of individual well and being obtained from step 7, according to comparing result to this
The fracturing effect of well is evaluated.
The geologic data includes effective thickness, porosity, permeability, shale content and the gas saturation on stratum.
The project data includes the discharge capacity of fracturing fluid, preposition liquid measure, average sand ratio, mulling liquid measure, fracture pressure and returns
Row leads.
The capacity data includes open-flow capacity, cumulative oil production or cumulative gas.
Data amount check is training data block, verify data block and test data set random division according to the ratio of 7:1:2
Data block.
A variety of machine learning algorithms include random forest, generalized linear model, support vector machines, decision tree, artificial
Neural network and gradient promote decision tree.
In the step 6, project data can be enabled to obey arbitrariness probability distributing.
In the step 7, when obtaining single well productivity value P corresponding to several probability, several probability can be according to actual needs
It is arbitrarily chosen by evaluation personnel.
In the step 7, respectively acquisition probability be 0.8,0.6,0.4 and 0.2 corresponding to single well productivity value P80, P60,
P40 and P20；In the step 8, single well productivity value P80, P60, P40 for comparing the practical production capacity value of individual well and being obtained from step 7
And P20:
As practical production capacity value >=P80 of well, then evaluation of Fracturing Effect on Compact Sandstone is excellent；
As the practical production capacity value < P80 of P60≤well, then evaluation of Fracturing Effect on Compact Sandstone is good；
As the practical production capacity value < P60 of P40≤well, then during evaluation of Fracturing Effect on Compact Sandstone is；
As the practical production capacity value < P40 of P20≤well, then evaluation of Fracturing Effect on Compact Sandstone is to pass；
As the practical production capacity value < P20 of well, then evaluation of Fracturing Effect on Compact Sandstone is poor.
Effect assessment is carried out to all fractured wells of block by step 8, count respectively operation effect be " excellent ", " good ",
" in ", the quantity of " qualifying " and " poor " well, block fracturing effect is evaluated by the quantity of statistics.
The invention has the following beneficial effects:
The present invention is evaluation index with production history situation after individual well pressure by comprehensively considering geologic(al) factor, engineering factor,
To data amount check according to preset ratio geologic data, project data and capacity data random division be training data block, verifying
Data block and test data block then respectively learn training data block using a variety of machine learning methods, with verifying number
The model parameter for determining a variety of machine learning algorithms respectively according to block constructs a variety of engineerings according to model parameter respectively
The machine learning model for practising algorithm, since in different data and application, all kinds of machine algorithms have the performance of different accuracys rate,
Therefore it needs to combine specific application and data in practical applications, selects the machine learning algorithm and its ginseng of the most suitable data
Number, to obtain reaching the algorithm of highest prediction accuracy rate in the data, therefore the present invention is then utilized respectively a variety of machines
The machine learning model of learning algorithm predicts test data block, according to prediction error, chooses the prediction the smallest machine of error
Device learning algorithm realizes the optimization to machine learning algorithm, improves the quality of evaluation of Fracturing Effect on Compact Sandstone；Followed by selection
Machine learning algorithm is ranked up geologic data and project data according to the influence degree to Oil & Gas Productivity, according to influence
The preset value of capacity data different degree obtains the key data for influencing production capacity；Then project data is enabled to obey probability distribution, in conjunction with
It is general to generate single well productivity using Monte Carlo simulation for the key data of the machine learning algorithm of selection and the influence production capacity obtained
Rate distribution curve, Monte Carlo simulation energy comprehensive considering various effects, can not only obtain evaluation result, can also obtain corresponding hair
Raw probability so that evaluation result it is more reliable, closer to reality, facilitate to used pressing crack construction technique, fracturing fluid, support
Agent it is preferred, improve the science of project decision；Then single well productivity probability distribution curve is applied, obtains several probability institutes respectively
Corresponding single well productivity value P, the single well productivity value P for finally comparing the practical production capacity value of individual well and obtaining, according to comparing result pair
The fracturing effect of the well is evaluated；To sum up, evaluation method of the invention commenting using qualitative, quantitative combination and man-computer cooperation
Valence technology, and make evaluation result that there is scientific and objectivity by evaluation index quantificational expression qualitative effect factor.This
Invention is not only to be directed to individual well or individual event fracturing technology, but a kind of fracturing technology the most universal is in the applicable cases of block
Evaluation, the result of evaluation has broad perspectives.
Detailed description of the invention
Fig. 1 is that geologic data and project data influence capacity data different degree schematic diagram in the embodiment of the present invention；
Fig. 2 is the generation flow chart of open-flow capacity probability distribution curve in the embodiment of the present invention；
Fig. 3 is to utilize block fracturing production effect assessment schematic diagram in the embodiment of the present invention；
Fig. 4 is the flow chart of evaluation method of the present invention.
Specific embodiment
It is next with reference to the accompanying drawings and examples that the present invention is further illustrated.
Referring to Fig. 4, the hydraulic fracturing operation effect evaluation method of the invention based on machine learning, including two parts,
It is determining optimal machine learning algorithm that first part, which is from a variety of learning algorithms,；Second part is calculated using optimal study
Method realizes hydraulic fracturing operation effect assessment.Specific step is as follows:
Step 1, geologic data, project data and the Oil & Gas Productivity data geology of evaluation block, geologic data packet are obtained
Include effective thickness, porosity, permeability, shale content and the gas saturation on stratum；Project data include fracturing fluid discharge capacity,
Preposition liquid measure, average sand ratio, mulling liquid measure, fracture pressure and the row of returning lead；Capacity data include open-flow capacity, cumulative oil production or
Cumulative gas；The discharge capacity of fracturing fluid, preposition liquid measure, average sand ratio, mulling liquid measure are known as pressing crack construction data, geologic data and
Project data is referred to as input data, and Oil & Gas Productivity data are known as output data；
It step 2, is training data block, verify data data set random division according to the preset ratio of data amount check
Block and test data block, wherein the data set includes geologic data described in step 1, project data and capacity data；
Step 3, training data block is learnt using a variety of existing machine learning algorithms, is distinguished with verify data block
The model parameter for determining a variety of machine learning algorithms constructs a variety of machine learning algorithms according to model parameter respectively
Machine learning model, these existing machine learning algorithms include random forest, generalized linear model, support vector machines, decision
Tree, artificial neural network and gradient promote decision tree；
Step 4, the machine learning model for being utilized respectively a variety of machine learning algorithms predicts test data block,
According to prediction error, the prediction the smallest machine learning algorithm of error is chosen；
Step 5, the machine learning algorithm that applying step 4 is chosen, according to the influence degree to Oil & Gas Productivity, to geology because
Element and engineering factor are ranked up, and the key data for influencing production capacity is obtained according to the preset value for influencing capacity data different degree；
Step 6, project data is enabled to obey probability distribution, the probability distribution can be existing arbitrariness probability distributing function,
The key data for the influence production capacity that the machine learning algorithm and step 5 chosen in conjunction with step 4 obtain, using Monte Carlo simulation
Generate single well productivity probability distribution curve；
Step 7, the single well productivity probability distribution curve that applying step 6 generates, obtains list corresponding to several probability respectively
Well capacity value P；When obtaining single well productivity value P corresponding to several probability, the number and numerical value of several probability can be according to realities
Border needs arbitrarily to be chosen by evaluation personnel, by the selected descending sequence of probability after choosing, under normal circumstances, chooses probability
Value is 0.8,0.6,0.4 and 0.2, they are expressed as P80, P60, P40 and P20 or probability value at corresponding well capacity value
It is 0.9,0.7,0.5,0.3 and 0.1, corresponding well capacity value is expressed as P90, P70, P50, P30 and P10；
Step 8, the single well productivity value P for comparing the practical production capacity value of individual well and being obtained from step 7, according to comparing result to this
The fracturing effect of well is evaluated；When using probability value such as 0.8,0.6,0.4 and 0.2, according to table 1 to the fracturing effect of the well
It is evaluated；
Table 1
| Fracturing production effect | Comparison of production |
| It is excellent | The practical production capacity of well is more than or equal to P80 value |
| It is good | The practical production capacity of well is between P60 and P80 value |
| In | The practical production capacity of well is between P40 and P60 value |
| It passes | The practical production capacity of well is between P20 and P40 value |
| Difference | The practical production capacity of well is less than or equal to value P20 |
Step 9, effect assessment is carried out to all fractured wells of block according to step 8, count respectively operation effect be " excellent ",
" good ", " in ", the quantity of " qualifying " and " poor " well, to complete the evaluation to block fracturing effect.
Embodiment
The present embodiment carries out in accordance with the following steps:
Step 1, data acquisition:
The key data of acquisition includes the following:
(1) geologic data includes effective thickness, shale content, porosity, permeability and the gas saturation on stratum.
(2) project data includes fracturing fluid discharge capacity, preposition liquid measure, average sand ratio, mulling liquid measure, fracture pressure and the row of returning
Rate；
(3) gas well deliverability is open-flow capacity；
Fractured Gas Wells in the present embodiment including above data have 222 mouthfuls, using the ratio of 7:1:2, by these well data
It is randomly divided into training data block, verify data block and test data block, wherein training data 155, verify data 22, inspection
Measured data 45.
Step 2, machine learning algorithm is preferred:
It is mentioned first using random forest, generalized linear model, support vector machines, decision tree, artificial neural network and gradient
It rises these machine learning algorithms of decision tree to learn training data block, determines these machine learning algorithms with verify data block
Model parameter, construct machine learning model；Then the geologic data and project data of input test data block give these machines
Learning model predicts the open-flow capacity of gas well, using the practical open-flow capacity value of test data block, seeks the prediction of these models
Error.For the data set, it is minimum that gradient promotes the open-flow capacity prediction error that decision making algorithm calculates, therefore gradient is selected to be promoted
Decision making algorithm constructs gas well deliverability prediction model and carries out hydraulic fracturing operation effect assessment.Decision making algorithm is promoted first with gradient
Determine geologic data and project data to the influence degree of open-flow capacity, as shown in Figure 1.
Fig. 1 shows: the influence of geology and project data to open-flow capacity is different, and influences the leading of Absolute Open Flow of Gas Wells
Factor is the effective thickness on stratum, followed by average sand ratio, respectively 39.3% and 14.2%.Effective thickness, the gassiness on stratum
Saturation degree, matrix permeability, porosity and shale content are about 60% to the combined influence of open-flow capacity, and average sand ratio, preceding
Set liquid, mulling liquid, the row of returning lead, discharge capacity and fracture pressure these project data then account for 40%.Influence open-flow capacity data different degree
Preset value be 3%, therefore, all geology and project data be all it is main influence data, for effect assessment of going into operation.
Step 3, individual well hydraulic fracturing operation effect assessment:
The every mouth Absolute Open Flow of Gas Wells probability point that decision making algorithm generates block is promoted in conjunction with Monte Carlo simulation and gradient
Cloth curve, Fig. 2 show the generation process of this curve.In Fig. 2, by assuming that fracturing fluid discharge capacity, preposition liquid measure, average sand ratio,
The probability distribution for mixing the parameters such as liquid measure evaluates influence of these factors variation to open-flow capacity.Utilize the open-flow capacity of generation
Probability distribution curve, obtaining probability is open-flow capacity value corresponding to 0.8,0.6,0.4 and 0.2, respectively with P80, P60, P40 and
P20 is indicated.Individual well hydraulic fracturing operation effect is evaluated by comparing the size relation of practical open-flow capacity and these values, table 1 is given
The standard of evaluation is gone out.By carrying out after so evaluating to all wells of block, hydraulic fracturing operation effect in block is counted respectively
Fruit be " excellent ", " good ", " in ", " qualification ", " poor " well number, the fracturing production effect of block is provided by Fig. 3 mode.Such as figure
Shown in 3, according to the open-flow capacity of Fractured Gas Wells, the fracturing production effect of the gas well of block 23.7% belongs to good level, about
The fracturing production effect of the gas well of half belongs to medium level, and the fracturing production effect of 6.3% gas well is poor.
Claims (7)
1. a kind of hydraulic fracturing operation effect evaluation method based on machine learning, which comprises the steps of:
Step 1, the geologic data, project data and capacity data of block are obtained；
Step 2, according to the preset ratio of data amount check, data set random division be training data block, verify data block and
Test data block, wherein the data set includes geologic data described in step 1, project data and capacity data；
Step 3, training data block is learnt respectively using a variety of machine learning algorithms, determines institute respectively with verify data block
The model parameter for stating a variety of machine learning algorithms constructs the engineering of a variety of machine learning algorithms according to model parameter respectively
Practise model；
Step 4, the machine learning model for being utilized respectively a variety of machine learning algorithms predicts test data block, according to
It predicts error, chooses the prediction the smallest machine learning algorithm of error；
Step 5, the machine learning algorithm that applying step 4 is chosen, according to the influence degree to Oil & Gas Productivity, to geologic data and
Project data is ranked up, and the key data for influencing production capacity is obtained according to the preset value for influencing capacity data different degree；
Step 6, project data is enabled to obey probability distribution, the shadow that the machine learning algorithm and step 5 chosen in conjunction with step 4 obtain
The key data for ringing production capacity generates single well productivity probability distribution curve using Monte Carlo simulation；
Step 7, the single well productivity probability distribution curve that applying step 6 generates obtains the production of individual well corresponding to several probability respectively
It can value P；
Step 8, the single well productivity value P for comparing the practical production capacity value of individual well and being obtained from step 7, according to comparing result to the well
Fracturing effect is evaluated.
2. a kind of hydraulic fracturing operation effect evaluation method based on machine learning according to claim 1, feature exist
In the geologic data includes effective thickness, porosity, permeability, shale content and the gas saturation on stratum.
3. a kind of hydraulic fracturing operation effect evaluation method based on machine learning according to claim 1, feature exist
In the project data includes that discharge capacity, preposition liquid measure, average sand ratio, mulling liquid measure, fracture pressure and the row of returning of fracturing fluid lead.
4. a kind of hydraulic fracturing operation effect evaluation method based on machine learning according to claim 1, feature exist
In the capacity data includes open-flow capacity, cumulative oil production or cumulative gas.
5. a kind of hydraulic fracturing operation effect evaluation method based on machine learning according to claim 1, feature exist
In data amount check is training data block, verify data block and test data data set random division according to the ratio of 7:1:2
Block.
6. a kind of hydraulic fracturing operation effect evaluation method based on machine learning according to claim 1, feature exist
In a variety of machine learning algorithms include random forest, generalized linear model, support vector machines, decision tree, artificial neural network
Network and gradient promote decision tree.
7. a kind of hydraulic fracturing operation effect evaluation method based on machine learning according to claim 1, feature exist
In, in the step 7, respectively acquisition probability be 0.8,0.6,0.4 and 0.2 corresponding to single well productivity value P80, P60, P40 and
P20；In the step 8, compare the practical production capacity value of individual well and single well productivity value P80, P60, P40 for being obtained from step 7 and
P20:
As practical production capacity value >=P80 of well, then evaluation of Fracturing Effect on Compact Sandstone is excellent；
As the practical production capacity value < P80 of P60≤well, then evaluation of Fracturing Effect on Compact Sandstone is good；
As the practical production capacity value < P60 of P40≤well, then during evaluation of Fracturing Effect on Compact Sandstone is；
As the practical production capacity value < P40 of P20≤well, then evaluation of Fracturing Effect on Compact Sandstone is to pass；
As the practical production capacity value < P20 of well, then evaluation of Fracturing Effect on Compact Sandstone is poor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811102171.XA CN109711595A (en) | 2018-09-20 | 2018-09-20 | A kind of hydraulic fracturing operation effect evaluation method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811102171.XA CN109711595A (en) | 2018-09-20 | 2018-09-20 | A kind of hydraulic fracturing operation effect evaluation method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109711595A true CN109711595A (en) | 2019-05-03 |
Family
ID=66253850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811102171.XA Pending CN109711595A (en) | 2018-09-20 | 2018-09-20 | A kind of hydraulic fracturing operation effect evaluation method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711595A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111815121A (en) * | 2020-06-17 | 2020-10-23 | 中建三局绿色产业投资有限公司 | Operation management evaluation method of drainage deep tunnel system based on SWMM model |
| CN112228054A (en) * | 2020-11-06 | 2021-01-15 | 中国石油大学(北京) | Method, device and equipment for determining shale gas yield based on convolutional neural network |
| CN113803042A (en) * | 2020-06-12 | 2021-12-17 | 中国石油化工股份有限公司 | Single-section single-cluster dense fracturing method and system |
| CN113833446A (en) * | 2020-06-23 | 2021-12-24 | 中国石油天然气股份有限公司 | Fracturing effect evaluation method and device |
| US11255184B1 (en) | 2020-10-20 | 2022-02-22 | Saudi Arabian Oil Company | Determining a subterranean formation breakdown pressure |
| US11391135B1 (en) | 2021-01-04 | 2022-07-19 | Saudi Arabian Oil Company | Fracturing a subsurface formation based on the required breakdown pressure |
| US11976540B2 (en) | 2021-02-05 | 2024-05-07 | Saudi Arabian Oil Company | Fracturing a subsurface formation based on a probabilistic determination of the required breakdown pressure |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020096324A1 (en) * | 2000-10-04 | 2002-07-25 | Assignment Branch | Production optimization methodology for multilayer commingled reservoirs using commingled reservoir production performance data and production logging information |
| US20140067353A1 (en) * | 2012-09-05 | 2014-03-06 | Stratagen | Wellbore completion and hydraulic fracturing optimization methods and associated systems |
| CN104616353A (en) * | 2013-11-05 | 2015-05-13 | 中国石油天然气集团公司 | Modeling for random geologic model of reservoir and preferable method |
| CN105488583A (en) * | 2015-11-23 | 2016-04-13 | 中国石油天然气股份有限公司 | Method and device for predicting recoverable reserve of dense oil in region to be evaluated |
| CN106203847A (en) * | 2016-07-14 | 2016-12-07 | 中石化重庆涪陵页岩气勘探开发有限公司 | Shale gas evaluation of Fracturing Effect on Compact Sandstone method |
| CN106651158A (en) * | 2016-12-08 | 2017-05-10 | 中国石油天然气股份有限公司 | Quantitative evaluation method for water injection development effectiveness degree of ultra-low permeability tight reservoir horizontal well |
| CN107676085A (en) * | 2017-09-29 | 2018-02-09 | 中国石油集团川庆钻探工程有限公司 | Sea-phase shale gas horizontal well logging productivity prediction method |
| CN108009716A (en) * | 2017-11-28 | 2018-05-08 | 西南石油大学 | A kind of horizontal well volume fracturing influential effect factor mutiple-stage model method |
| WO2018117890A1 (en) * | 2016-12-21 | 2018-06-28 | Schlumberger Technology Corporation | A method and a cognitive system for predicting a hydraulic fracture performance |
| CN108416475A (en) * | 2018-03-05 | 2018-08-17 | 中国地质大学（北京） | A kind of shale gas production capacity uncertainty prediction technique |
| CN108446797A (en) * | 2018-03-06 | 2018-08-24 | 西南石油大学 | A kind of compact oil reservoir horizontal well volume fracturing initial productivity prediction technique |
-
2018
- 2018-09-20 CN CN201811102171.XA patent/CN109711595A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020096324A1 (en) * | 2000-10-04 | 2002-07-25 | Assignment Branch | Production optimization methodology for multilayer commingled reservoirs using commingled reservoir production performance data and production logging information |
| US20140067353A1 (en) * | 2012-09-05 | 2014-03-06 | Stratagen | Wellbore completion and hydraulic fracturing optimization methods and associated systems |
| CN104616353A (en) * | 2013-11-05 | 2015-05-13 | 中国石油天然气集团公司 | Modeling for random geologic model of reservoir and preferable method |
| CN105488583A (en) * | 2015-11-23 | 2016-04-13 | 中国石油天然气股份有限公司 | Method and device for predicting recoverable reserve of dense oil in region to be evaluated |
| CN106203847A (en) * | 2016-07-14 | 2016-12-07 | 中石化重庆涪陵页岩气勘探开发有限公司 | Shale gas evaluation of Fracturing Effect on Compact Sandstone method |
| CN106651158A (en) * | 2016-12-08 | 2017-05-10 | 中国石油天然气股份有限公司 | Quantitative evaluation method for water injection development effectiveness degree of ultra-low permeability tight reservoir horizontal well |
| WO2018117890A1 (en) * | 2016-12-21 | 2018-06-28 | Schlumberger Technology Corporation | A method and a cognitive system for predicting a hydraulic fracture performance |
| CN107676085A (en) * | 2017-09-29 | 2018-02-09 | 中国石油集团川庆钻探工程有限公司 | Sea-phase shale gas horizontal well logging productivity prediction method |
| CN108009716A (en) * | 2017-11-28 | 2018-05-08 | 西南石油大学 | A kind of horizontal well volume fracturing influential effect factor mutiple-stage model method |
| CN108416475A (en) * | 2018-03-05 | 2018-08-17 | 中国地质大学（北京） | A kind of shale gas production capacity uncertainty prediction technique |
| CN108446797A (en) * | 2018-03-06 | 2018-08-24 | 西南石油大学 | A kind of compact oil reservoir horizontal well volume fracturing initial productivity prediction technique |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113803042A (en) * | 2020-06-12 | 2021-12-17 | 中国石油化工股份有限公司 | Single-section single-cluster dense fracturing method and system |
| CN111815121A (en) * | 2020-06-17 | 2020-10-23 | 中建三局绿色产业投资有限公司 | Operation management evaluation method of drainage deep tunnel system based on SWMM model |
| CN111815121B (en) * | 2020-06-17 | 2023-02-28 | 中建三局绿色产业投资有限公司 | Operation management evaluation method of drainage deep tunnel system based on SWMM model |
| CN113833446A (en) * | 2020-06-23 | 2021-12-24 | 中国石油天然气股份有限公司 | Fracturing effect evaluation method and device |
| CN113833446B (en) * | 2020-06-23 | 2023-08-22 | 中国石油天然气股份有限公司 | Fracturing effect evaluation method and device |
| US11255184B1 (en) | 2020-10-20 | 2022-02-22 | Saudi Arabian Oil Company | Determining a subterranean formation breakdown pressure |
| CN112228054A (en) * | 2020-11-06 | 2021-01-15 | 中国石油大学(北京) | Method, device and equipment for determining shale gas yield based on convolutional neural network |
| US11391135B1 (en) | 2021-01-04 | 2022-07-19 | Saudi Arabian Oil Company | Fracturing a subsurface formation based on the required breakdown pressure |
| US11976540B2 (en) | 2021-02-05 | 2024-05-07 | Saudi Arabian Oil Company | Fracturing a subsurface formation based on a probabilistic determination of the required breakdown pressure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711595A (en) | A kind of hydraulic fracturing operation effect evaluation method based on machine learning | |
| CN112561356B (en) | Comprehensive evaluation method for production dynamic mode and productivity of shale oil fracturing horizontal well | |
| CN109815516A (en) | Method and device for predicting productivity of shale gas well | |
| CN103046914B (en) | A kind of low permeability gas reservoirs staged fracturing of horizontal well effect determination methods | |
| CN111062129B (en) | Shale oil complex fracture network discrete fracture continuous medium mixing numerical simulation method | |
| CN104832166A (en) | Initial productivity prediction method of shale gas horizontal well | |
| CN111222271B (en) | Matrix-fracture-unsteady state fluid channeling oil reservoir fracture numerical simulation method and system | |
| CN108509694B (en) | Proppant paving form prediction method based on BP neural network | |
| CN108416475A (en) | A kind of shale gas production capacity uncertainty prediction technique | |
| CN109063403B (en) | Optimal design method for slickwater fracturing | |
| CN106600440A (en) | Method for profile-control water-shutoff dynamic index well selection for low-permeability reservoir | |
| CN105512366A (en) | Natural-fracture-containing tight-reservoir volume-fracturing tree-shape random fracture net description method | |
| CN104346511A (en) | Bran-new method and bran-new device for dynamically monitoring oil deposit | |
| CN106547934A (en) | Profile control well selection method and device for conglomerate oil reservoir | |
| CN116658155A (en) | Shale gas well yield prediction method | |
| CN111950112B (en) | Carbonate reservoir dynamic analysis method suitable for bottom closure | |
| CN109252855A (en) | Method and device for determining final cumulative yield of gas well | |
| Ren et al. | Shale gas effective fracture network volume prediction and analysis based on flow back data: A case study of southern Sichuan Basin shale | |
| CN114398786B (en) | Fracturing construction pressure prediction model establishing method and device and prediction method and device | |
| CN113503158A (en) | Prediction analysis method for relation between shale gas reservoir soaking time and yield | |
| CN110374573A (en) | A kind of yield potential appraisal procedure for typical pressure break failure well | |
| Chu et al. | Rate transient analysis of a multi-horizontal-well pad with a semi-analytical method | |
| CN111950111B (en) | Dynamic analysis method suitable for open-bottom carbonate reservoir | |
| CN115936232A (en) | Method and system for predicting density and encryption adjustment time of reasonable well pattern of tight gas reservoir | |
| CN110894788A (en) | Oil reservoir production prediction data-based oil reservoir development mode determination method and device |
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: 20190503 |
|
| RJ01 | Rejection of invention patent application after publication |