CN108843312B - Oilfield reservoir in-layer heterogeneity integrated evaluating method - Google Patents
Oilfield reservoir in-layer heterogeneity integrated evaluating method Download PDFInfo
- Publication number
- CN108843312B CN108843312B CN201810564798.0A CN201810564798A CN108843312B CN 108843312 B CN108843312 B CN 108843312B CN 201810564798 A CN201810564798 A CN 201810564798A CN 108843312 B CN108843312 B CN 108843312B
- Authority
- CN
- China
- Prior art keywords
- sample
- permeability
- layer heterogeneity
- reservoir
- samples
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 12
- 238000004519 manufacturing process Methods 0.000 claims abstract description 8
- 238000002347 injection Methods 0.000 claims abstract description 5
- 239000007924 injection Substances 0.000 claims abstract description 5
- 239000010410 layer Substances 0.000 claims description 37
- 230000035699 permeability Effects 0.000 claims description 22
- 238000009826 distribution Methods 0.000 claims description 14
- 238000009830 intercalation Methods 0.000 claims description 8
- 230000002687 intercalation Effects 0.000 claims description 7
- 239000004576 sand Substances 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 5
- 238000012512 characterization method Methods 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 4
- 239000011229 interlayer Substances 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 2
- 239000003129 oil well Substances 0.000 claims description 2
- 230000000704 physical effect Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 15
- 238000011161 development Methods 0.000 abstract description 12
- 238000005516 engineering process Methods 0.000 abstract description 7
- 230000007547 defect Effects 0.000 abstract description 2
- 230000003068 static effect Effects 0.000 abstract 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 6
- 239000007789 gas Substances 0.000 description 5
- 239000003345 natural gas Substances 0.000 description 3
- 239000003208 petroleum Substances 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008595 infiltration Effects 0.000 description 2
- 238000001764 infiltration Methods 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 238000009738 saturating Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000010910 field residue Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B49/00—Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses the in-layer heterogeneity integrated evaluating method based on phase of development higher order neural network, core is the at home and abroad common V of scholark、Tk、Jk、PkAnd DkOn the basis of static geologic parameter, the water injection rate data dynamic parameter of oil field development production, the evaluation index as in-layer heterogeneity are introduced.And higher order neural network method is used, it is studied in depth specifically for each parameters weighting of the above in-layer heterogeneity, effectively improves the accuracy and timeliness of phase of development reservoir in-layer heterogeneity overall merit, overcome defect of the existing technology.
Description
Technical field
The present invention relates to petroleum, a kind of integrated evaluating method of reservoir heterogeneity of natural gas reservoirs geology,
Particular technique is the reservoir in-layer heterogeneity coefficient of colligation acquiring method based on artificial neural network, be can effectively improve to oil
The accuracy of field development phase reservoir in-layer heterogeneity evaluation.
Background technique
Reservoir is the storage in underground of petroleum, natural gas, gathering place, is the direct target of oil-gas exploration, exploitation.Reservoir
Heterogeneity refers to the inhomogeneities of the parameter of characterization reservoir spatially, is the universal feature of reservoir, the accuracy pair of evaluation
There is huge economic value in the production development of accurate instruction petroleum, natural gas.The heterogeneity of reservoir includes that macroscopic view is non-
Matter and microheterogeneity.Wherein, macroscopic heterogeneity is divided by scale is descending: interlayer heterogeneity, plane are non-
Matter and in-layer heterogeneity.
Currently, China major part oil field has entered the mid-later development phase stage, a large amount of oil gas has been plucked out of, but still is had quite
The oil gas of quantity is trapped in underground, we are called remaining oil.Remaining oil with different scales, different form be irregularly distributed in
In oil reservoir.Frequently with the mode of water filling, remaining oil displacement is gone out into stratum, to improve field output.In the process, single sand body stores up
Oil and water zonation and remaining oil distribution in layer become the main problem in production.In-layer heterogeneity hangs down that is, in single sand body scale
Upward reservoir characteristic variation, exactly leads to the immanent cause of oil and water zonation unevenness in sand body, is to directly control note in single sand
Enter swept volume and (injects the oil reservoir volume that water is fed through in water-drive pool from well, size directly affects the effect of water drive oil
Rate.) crucial geologic(al) factor.Therefore, in phase of development, recognize to further increase people to oil and gas and water distribution rule
Know and the rate of oil and gas recovery, the further investigation and accurate evaluation for in-layer heterogeneity are quite crucial.
Currently, the widely used in-layer heterogeneity evaluation index of domestic and foreign scholars includes: coefficient of permeability variation Vk, seep
Saturating rate is advanced by leaps and bounds coefficient Tk, permeability grade Jk, muddy intercalation distribution frequency PkWith distribution density DkDeng.For with water-drive pool
Based on domestic old filed for, since reservoir is washed away by long-period water drive, exacerbate its non-homogeneous degree.At this point, if also using
The V that early stage core measuresk、Tk、Jk、PkAnd DkEqual geologic parameters evaluate in-layer heterogeneity, just necessarily to oil field residue
The understanding of oil generates great deviation.Therefore, the present invention is in Vk、Tk、Jk、PkAnd DkOn the basis of equal geologic parameters, oil is introduced
The water injection rate data V of field development and productionw, evaluation index as in-layer heterogeneity.
In addition, being frequently subjected to complexity, the DATA REASONING of subsurface geology situation when evaluating in-layer heterogeneity
Accuracy and the various aspects factor such as theoretical integrity influence, cause the evaluation result for aforementioned each index often occur mutual
The case where contradiction.In view of this, forefathers, which propose, seeks a composite index to in-layer heterogeneity progress based on mathematical method
Evaluation.The Lorentz curve method of the entropy assessment of such as Yang Shaochun (2004) and Liu superfine (2012), achieves in particular studies area
Good effect.But entropy assessment will depend on enough sample datas and actual Problem Areas, calculate complexity, and participatory is poor,
Judge cannot be embodied to the attention degree of different attribute index, sometimes fixed weight can be with the practical significance level phase of attribute
Difference is larger.Lorentz curve method defines a kind of new in-layer heterogeneity characterization parameter only with permeability data, can not be comprehensive
Reflect the feature of in-layer heterogeneity.
The overall evaluation system of in-layer heterogeneity is a complicated nonlinear system, with time, the passage in space,
Each index can also change to the influence degree of its evaluation problem, and in other words, the weight of most evaluation index can be with evaluation
The development of object, the progress of human knowledge and change.Therefore, it is necessary to the study mechanism of weight is established, it is continually changing to adapt to
Evaluation requires, and this respect is exactly the advantage place that artificial neural network solves the problems, such as.For common multilayer perceptron nerve
(one kind of neural network is most simple most common neural network to network.Generally include an input layer, several hidden layers
With an output layer.) for, since the number of plies and number of nodes of hidden layer are all rule of thumb to be arranged, can be encountered when data volume is big
Convergence rate is slow, and there is the problems such as being easily trapped into local minimum.
Higher order neural network is the extension to multilayer perceptron neural network.It is added on the basic model of perceptron
Enter auxiliary element, input vector is become into n times value that it is combined with each other (by taking second order as an example, in multilayer perceptron neural network
Input parameter x1、x2, it is changing in higher order neural networkx1x2、x1、x2).So that network output and input
Higher order correlation function is corresponding, reduces computation complexity, even if encountering the big situation of data volume, convergence rate also obviously has
There is superiority.And higher order neural network does not include hidden layer, can obtain faster training speed, and be less prone to local minimum
Value, while avoiding the On The Choice of the hidden layer number of plies and number of nodes.
Status based on oil field high production cost, it is necessary to mass data be analyzed in a short time, to reservoir layer
Interior heterogeneity makes accurate evaluation, to instruct next step production measure.Rationally to solve the problems, such as this, the invention proposes one kind
In-layer heterogeneity integrated evaluating method based on higher order neural network is expected to further increase to mid-late oilfield development reservoir
The accuracy and timeliness of in-layer heterogeneity understanding.
Summary of the invention
The purpose of the present invention is to provide a kind of integrated evaluating method of reservoir in-layer heterogeneity, this method is based on artificial
The nonlinear pattern recognition technology of neural network, utilizes Vk、Tk、Jk、Pk、DkAnd VwSix parameters, integrated reservoir geology, oil reservoir
Physics, mathematical statistics etc. are multidisciplinary, and geologic origin analytical technology, various experimental study technologies, geostatistics are studied skill
Art, various mathematical computations technologies, error statistics analytical technology etc. organically combine, specifically for each parameters weighting of in-layer heterogeneity
It is studied in depth, effectively improves the accuracy of phase of development reservoir in-layer heterogeneity overall merit, overcome existing
Defect existing for technology.
To reach the above technical purpose, the present invention provides following technical scheme.
Reservoir in-layer heterogeneity coefficient of colligation acquiring method based on higher order neural network method, core are non-equal in layer
The seeking of each evaluation parameter of matter, Mathematical Statistics Analysis, each parameters weighting are sought.This method successively the following steps are included:
(1) data such as number, thickness of reservoir permeability data and interlayer obtained to the chemical examination of underground core analysis carry out
Statistics, and seek coefficient of permeability variation Vk, leaps and bounds coefficient Tk, permeability grade Jk, muddy intercalation distribution frequency Pk
With distribution density DkAnd the water injection rate V of oilfield development processw；
(2) above data is normalized, determines training sample；
(3) order of neural network is set, converts input sample, and inputted；
(4) setting initial connection is weighed at random；
(5) reality output is calculated；
(6) according to the error of desired output and reality output, connection weight is updated, constantly progress network training；
(7) after all sample trainings terminate and reach neural network accuracy requirement, that is, it can determine the weight of each index.It obtains again
The composite index of all samples.
Detailed description of the invention
Fig. 1 is higher-order neural networks model figure.
Fig. 2 is the in-layer heterogeneity overall merit flow chart based on higher order neural network method.
Specific embodiment
The present invention successively includes step in detailed below:
Step 1: in-layer heterogeneity characterization parameter: coefficient of permeability variation V is soughtk(formula 1), leaps and bounds coefficient Tk
(formula 2), permeability grade JkThe distribution frequency P of (formula 3), muddy intercalationk(formula 4) and distribution density Dk(formula 5), water injection rate VwIt can
Directly obtained from oilfield production data.
F, coefficient of permeability variation
G, leaps and bounds coefficient
H, permeability grade
Jk=Kmax/Kmin (3)
I, interbed distribution frequency
Pk=N/H (4)
J, interbed distribution density
Dk=h/H × 100% (5)
In formula: KiFor the permeability value of single core sample；N is the number of sample；For the average infiltration of all samples
Rate；KmaxFor the permeability maximum value of all samples；KminFor the permeability minimum value of all samples.KmaxAnd KminThree infiltrations
Saturating rate related data can be obtained by physical property measurement or well-log information.N is muddy intercalation number；H is the total thickness of muddy intercalation
Degree, rice；H is the gross reservoir interval of research, rice.N, h interlayer related data and H can observe statistics or well-log information by core
It obtains.
Step 2: to the V of every mouthful of oil well single sand bodyk、Tk、Jk、Pk、DkAnd VwData are counted, and normalized obtains
Several input samples.From first sample X1(formula 6) brings into operation.
X1=(x1,x2,x3,x4,x5,x6) (6)
Wherein, x1=Vk1, x2=Tk1, x3=Jk1, x4=Pk1, x5=Dk1, x6=Vw1。
Step 3: setting higher order neural network converts order into 2, i.e., by input sample X to input parameter1Become X1 *
(formula 7).
Wherein, the quadratic terms of 6 input parameters have 6, and the quadratic term of 6 input parameters product two-by-two has 15,6
Input parameter first order be 6, add last constant 1, total item 28, i.e., by 6 input Parameter Switch for comprising
28 parameters of high-order independent variable.
Step 4: first sample X is set1 *Corresponding desired output is O1, set X1 *With O1Between initial weight vector be
W1, W1Middle element can be set as any value (formula 8) (Fig. 1) between 0-1 at random.
W1=(w1,w2,···,w28)T (8)
Wherein, w1,w2,···,w28For the weight coefficient of each single item in step 3.
Step 5: the reality output Z of first output node is calculated1(formula 9).
Z1=f (W1 TX1 *) (9)
Wherein, f is excitation function, represents the functional relation between input sample and output.Common excitation function includes:
Sigmoid function, tanh function and ReLU function etc..It selects to use Sigmoid function as excitation function herein.
Step 6: according to desired output O1With reality output Z1Error, update connection weight vector W1For W2(formula 10), W2
The initial weight vector of as second sample.
W2=W1+η(O1-Z1)X1 * (10)
In formula, η is that weight coefficient updates step-length.With the increase of the number of iterations, η is gradually reduced.Its general initial value is set at random
It is set to a lesser positive value, sets step-length initial value herein as η1, η1Value is 0.1, its every wheel of iteration 100 is arranged multiplied by 0.1.
I.e. all samples, which repeat step-length after feedback training 100 is taken turns, becomes η2, η2=0.1 η1=0.1*0.1=0.01, and so on.
Step 7: assuming that total sample number be n, circulation step five and step 6, successively obtain each sample initially weigh to
Amount.
Step 8: the mean error E (formula 11) of all samples is calculated.
Wherein, OjAnd ZjThe desired output and reality output of respectively j-th sample.
Step 9: when mean error E≤ε (setting) after, that is, it can determine the weight of each index.Again
Obtain the composite index of all samples.Otherwise, return step five.
The corresponding flow chart of above step is illustrated in fig. 2 shown below.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The skill of the industry
Art personnel it should be appreciated that the present invention is not limited to the above embodiments, the above embodiments and description only describe
The principle of the present invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention,
These changes and improvements all fall within the protetion scope of the claimed invention.The claimed scope of the invention is wanted by appended right
Ask book and its equivalent thereof.
Claims (5)
1. oilfield reservoir in-layer heterogeneity integrated evaluating method, it is characterised in that the following steps are included:
Step 1: in-layer heterogeneity characterization parameter: coefficient of permeability variation V is soughtk, leaps and bounds coefficient Tk, permeability grade
Poor Jk, muddy intercalation distribution frequency PkWith distribution density Dk, water injection rate VwIt can directly be obtained from oilfield production data；
A, coefficient of permeability variation
B, leaps and bounds coefficient
C, permeability grade
Jk=Kmax/Kmin (3)
D, interbed distribution frequency
Pk=N/H (4)
E, interbed distribution density
Dk=h/H × 100% (5)
In formula: KiFor the permeability value of single core sample；N is the number of sample；For the mean permeability of all samples；Kmax
For the permeability maximum value of all samples；KminFor the permeability minimum value of all samples；KmaxAnd KminThree permeability phases
Closing data can be obtained by physical property measurement or well-log information；N is muddy intercalation number；H is the overall thickness of muddy intercalation；H is to grind
The gross reservoir interval studied carefully；N, h interlayer related data and H can observe statistics or well-log information acquisition by core；
Step 2: to the V of every mouthful of oil well single sand bodyk、Tk、Jk、Pk、DkAnd VwData are counted, normalized, are obtained several
A input sample, from first sample X1It brings into operation；
X1=(x1,x2,x3,x4,x5,x6) (6)
Wherein, x1=Vk1, x2=Tk1, x3=Jk1, x4=Pk1, x5=Dk1, x6=Vw1；
Step 3: setting higher order neural network converts order into 2, i.e., by input sample X to input parameter1Become X1 *:
Step 4: first sample X is set1 *Corresponding desired output is O1, set X1 *With O1Between initial weight vector be W1, W1
Middle element can be set as any value between 0-1 at random:
W1=(w1,w2,···,w28)T (8)
Wherein, w1,w2,···,w28For the weight coefficient of each single item in step 3；
Step 5: the reality output Z of first output node is calculated1:
Z1=f (W1 TX1 *) (9)
Wherein, f is excitation function, represents the functional relation between input sample and output；
Step 6: according to desired output O1With reality output Z1Error, update connection weight vector W1For W2, W2As second sample
This initial weight vector；
W2=W1+η(O1-Z1)X1 * (10)
In formula, η is that weight coefficient updates step-length, and with the increase of the number of iterations, η is gradually reduced；
Step 7: assuming that total sample number is n, circulation step five and step 6, the initial weight vector of each sample is successively obtained；
Step 8: the mean error E of all samples is calculated:
Wherein, OjAnd ZjThe desired output and reality output of respectively j-th sample；
Step 9: after mean error E≤ε, that is, it can determine the weight of each index；The composite index of all samples is obtained again, it is no
Then, return step five.
2. oilfield reservoir in-layer heterogeneity integrated evaluating method according to claim 1, it is characterised in that: in step 3
The quadratic terms of 6 input parameters have 6, and the quadratic term of 6 input parameters product two-by-two has 15,6 input parameters it is primary
Item is 6, in addition last constant 1, total item 28, i.e., inputting Parameter Switch for 6 is 28 comprising high-order independent variable
A parameter.
3. oilfield reservoir in-layer heterogeneity integrated evaluating method according to claim 1, it is characterised in that: in step 5
The excitation function is Sigmoid function.
4. oilfield reservoir in-layer heterogeneity integrated evaluating method according to claim 1, it is characterised in that: in step 6
If step-length initial value is η1, η1Value is 0.1, its every wheel of iteration 100 is arranged multiplied by 0.1；I.e. all samples repeat feedback training
100, which take turns step-length later, becomes η2, η2=0.1 η1=0.1*0.1=0.01, and so on.
5. oilfield reservoir in-layer heterogeneity integrated evaluating method according to claim 1, it is characterised in that: in step 9
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810564798.0A CN108843312B (en) | 2018-06-04 | 2018-06-04 | Oilfield reservoir in-layer heterogeneity integrated evaluating method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810564798.0A CN108843312B (en) | 2018-06-04 | 2018-06-04 | Oilfield reservoir in-layer heterogeneity integrated evaluating method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108843312A CN108843312A (en) | 2018-11-20 |
| CN108843312B true CN108843312B (en) | 2019-04-30 |
Family
ID=64210129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810564798.0A Active CN108843312B (en) | 2018-06-04 | 2018-06-04 | Oilfield reservoir in-layer heterogeneity integrated evaluating method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108843312B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800954B (en) * | 2018-12-19 | 2021-08-20 | 中国石油化工股份有限公司 | Reservoir evaluation method based on logging data |
| CN110659685B (en) * | 2019-09-23 | 2022-03-08 | 西南石油大学 | Well position optimization method based on statistical error active learning |
| CN111027882A (en) * | 2019-12-18 | 2020-04-17 | 延安大学 | Method for evaluating brittleness index by utilizing conventional logging data based on high-order neural network |
| CN111058840A (en) * | 2019-12-18 | 2020-04-24 | 延安大学 | Organic carbon content (TOC) evaluation method based on high-order neural network |
| CN112253087A (en) * | 2020-10-20 | 2021-01-22 | 河南理工大学 | Biological disturbance reservoir physical property calculation method based on multi-source logging data |
| CN112489736A (en) * | 2020-12-09 | 2021-03-12 | 中国石油大学(北京) | Mineral content analysis method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106812522A (en) * | 2015-12-01 | 2017-06-09 | 中国石油化工股份有限公司 | Reservoir heterogeneity research method based on three-dimensional geological model |
| CN107327299A (en) * | 2017-08-01 | 2017-11-07 | 中国石油天然气股份有限公司 | Method and device for determining reservoir compressibility |
| CN107590550A (en) * | 2017-07-26 | 2018-01-16 | 长江大学 | The method evaluated and predicted about super-low permeability reservoir oil field production capacity |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484573B (en) * | 2014-12-30 | 2017-09-15 | 中国石油天然气股份有限公司 | Method for determining formation rigidity coefficient |
-
2018
- 2018-06-04 CN CN201810564798.0A patent/CN108843312B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106812522A (en) * | 2015-12-01 | 2017-06-09 | 中国石油化工股份有限公司 | Reservoir heterogeneity research method based on three-dimensional geological model |
| CN107590550A (en) * | 2017-07-26 | 2018-01-16 | 长江大学 | The method evaluated and predicted about super-low permeability reservoir oil field production capacity |
| CN107327299A (en) * | 2017-08-01 | 2017-11-07 | 中国石油天然气股份有限公司 | Method and device for determining reservoir compressibility |
Non-Patent Citations (3)
| Title |
|---|
| 储层非均质性研究方法进展;陈欢庆等;《高校地质学报》;20170331(第01期);104-114 |
| 利用神经网络技术在储层非均质性上的研究;路杨等;《江苏地质》;20070328(第01期);50-57 |
| 层内非均质性参数在储层综合评价中的应用――以南梁西区三叠系长4+5油层组为例;任江丽等;《地下水》;20150925(第05期);250-252 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108843312A (en) | 2018-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108843312B (en) | Oilfield reservoir in-layer heterogeneity integrated evaluating method | |
| Zeng et al. | A new-structure grey Verhulst model for China’s tight gas production forecasting | |
| Pan et al. | An optimized XGBoost method for predicting reservoir porosity using petrophysical logs | |
| CN109543828B (en) | Water absorption profile prediction method based on small sample condition | |
| CN109447532B (en) | Oil reservoir inter-well connectivity determination method based on data driving | |
| CN110807557B (en) | BP neural network-based drilling rate prediction method and BP neural network-based particle swarm optimization method | |
| Xue et al. | A new fracture prediction method by combining genetic algorithm with neural network in low-permeability reservoirs | |
| CN104239666B (en) | A kind of Comprehensive Evaluation of Coal Bed Gas method based on analytic hierarchy process (AHP) | |
| CN113610945B (en) | Ground stress curve prediction method based on hybrid neural network | |
| Wang et al. | Fast history matching and optimization using a novel physics-based data-driven model: an application to a diatomite reservoir | |
| Arigbe et al. | Real-time relative permeability prediction using deep learning | |
| Karkevandi-Talkhooncheh et al. | Application of hybrid adaptive neuro-fuzzy inference system in well placement optimization | |
| Zolotukhin et al. | Machine learning in reservoir permeability prediction and modelling of fluid flow in porous media | |
| CN105760673A (en) | Fluvial facies reservoir earthquake sensitive parameter template analysis method | |
| CN111027882A (en) | Method for evaluating brittleness index by utilizing conventional logging data based on high-order neural network | |
| Cheng et al. | LSTM based EFAST global sensitivity analysis for interwell connectivity evaluation using injection and production fluctuation data | |
| CN112541571A (en) | Injection-production connectivity determination method based on machine learning of double parallel neural networks | |
| CN111048163A (en) | Shale oil hydrocarbon retention amount (S1) evaluation method based on high-order neural network | |
| Ma et al. | A novel method for favorable zone prediction of conventional hydrocarbon accumulations based on RUSBoosted tree machine learning algorithm | |
| Gubanova et al. | Proxy capacitance-resistance modeling for well production forecasts in case of well treatments | |
| CN109655394B (en) | Nuclear magnetic resonance T2 spectrum permeability calculation method under constraint of throat structure parameters | |
| Huang et al. | Dynamic interwell connectivity analysis of multi-layer waterflooding reservoirs based on an improved graph neural network | |
| Stopa et al. | Empirical modeling of two-phase CBM production using analogy to nature | |
| Goda et al. | The Development of an Optimal Artificial Neural Network Model for Estimating Initial, Irreducible Water Saturation–Australian Reservoirs | |
| Maniglio et al. | Physics Informed Neural Networks Based on a Capacitance Resistance Model for Reservoirs Under Water Flooding Conditions |
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 | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210721 Address after: 610500, Xindu Avenue, Xindu District, Sichuan, Chengdu, 8 Patentee after: SOUTHWEST PETROLEUM University Patentee after: Hainan Special Economic Zone Zhongzhi Falcon intelligent Survey Technology Co.,Ltd. Address before: 610500, Xindu Avenue, Xindu District, Sichuan, Chengdu, 8 Patentee before: SOUTHWEST PETROLEUM University Patentee before: SICHUAN ZHONGZHI DINGFENG EXPLORATION TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |