CN112348350B - Layer system recombination method, computer equipment and storage medium in later stage of oilfield development - Google Patents
Layer system recombination method, computer equipment and storage medium in later stage of oilfield development Download PDFInfo
- Publication number
- CN112348350B CN112348350B CN202011215850.5A CN202011215850A CN112348350B CN 112348350 B CN112348350 B CN 112348350B CN 202011215850 A CN202011215850 A CN 202011215850A CN 112348350 B CN112348350 B CN 112348350B
- Authority
- CN
- China
- Prior art keywords
- layer
- clustering
- small
- oil
- layer system
- 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 67
- 230000006798 recombination Effects 0.000 title claims abstract description 49
- 238000005215 recombination Methods 0.000 title claims abstract description 49
- 238000011161 development Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims abstract description 7
- 238000004519 manufacturing process Methods 0.000 claims abstract description 25
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000005065 mining Methods 0.000 claims abstract description 8
- 239000004576 sand Substances 0.000 claims abstract description 7
- 238000002347 injection Methods 0.000 claims abstract description 6
- 239000007924 injection Substances 0.000 claims abstract description 6
- 239000003921 oil Substances 0.000 claims description 46
- 230000018109 developmental process Effects 0.000 claims description 31
- 230000008521 reorganization Effects 0.000 claims description 17
- 230000035699 permeability Effects 0.000 claims description 13
- 230000001186 cumulative effect Effects 0.000 claims description 10
- 239000012530 fluid Substances 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 6
- 239000010779 crude oil Substances 0.000 claims description 6
- 238000003064 k means clustering Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000003672 processing method Methods 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 239000007788 liquid Substances 0.000 claims description 4
- 230000001965 increasing effect Effects 0.000 claims description 3
- 239000003129 oil well Substances 0.000 claims description 3
- 230000032683 aging Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 1
- 239000010410 layer Substances 0.000 abstract description 125
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000009826 distribution Methods 0.000 abstract description 4
- 238000011084 recovery Methods 0.000 abstract description 4
- 230000000630 rising effect Effects 0.000 abstract description 2
- 239000002356 single layer Substances 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000007418 data mining Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012067 mathematical method Methods 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 239000013043 chemical agent Substances 0.000 description 1
- 238000003776 cleavage reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000979 retarding effect Effects 0.000 description 1
- 230000007017 scission Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B43/00—Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells
- E21B43/14—Obtaining from a multiple-zone well
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mining & Mineral Resources (AREA)
- Marketing (AREA)
- Geology (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Environmental & Geological Engineering (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fluid Mechanics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of oil and gas resource development, and discloses a layer system recombination method, computer equipment and a storage medium in the later stage of oil field development, and physical characteristic statistics of an oil reservoir layer system and a small layer; analyzing the small-seam mining dynamic and residual potential; determining the technical limit standard of layer system recombination; normalizing the dynamic indexes, and establishing a spatial clustering attribute table; and (4) carrying out layer series recombination by using an improved spatial clustering algorithm. The layer system recombination method based on the spatial clustering at the later stage of the oil field development provided by the invention is based on the property of the oil layer of a single layer and the dynamic production condition, and considers the spatial position distribution of the layer system or sand body, provides a practical and scientific path and method for the layer system recombination, can realize the expansion of the water injection wave and volume, controls the water content rising speed, improves the water drive recovery ratio and the economic benefit of the oil field to the maximum extent by improving the water drive wave and volume, and has important significance for excavating the potential at the later stage of the oil field development and slowing down the yield decrement.
Description
Technical Field
The invention belongs to the technical field of oil and gas resource development, and particularly relates to a layer system recombination method, computer equipment and a storage medium in the later stage of oil field development.
Background
Most old oil fields in the east of China are multi-oil-layer sandstone oil reservoirs, most oil fields enter the later stage of oil field development at present, and the oil reservoirs are subjected to multiple adjustment measures such as layer series subdivision, well pattern encryption, layered water injection and the like in too many rounds and enter an ultrahigh water-cut stage. Under the international environmental background of long-term low oil price, the main task of exploiting the residual potential and improving the ultimate recovery rate of old oil fields under the conditions of not using expensive chemical agents, not drilling new wells or only drilling a small amount of adjustment wells is to develop the oil fields.
On the basis of reservoir evaluation, well pattern and layer system recombination is an important method for realizing the task. For oil reservoirs entering a high water-cut period or an extra high water-cut period, the difference between layers is more prominent, the difference is not limited to the difference of permeability, but is also large in the difference of the output degree or the water absorption degree of each layer due to the difference of the permeability between the layers, the oil field development and adjustment at the moment is not simple subdivision adjustment of development layer series, and the layers with similar physical properties and development conditions are recombined by combining the output dynamics and the residual recoverable reserves of each layer, namely layer series recombination is carried out. The system recombination based on the spatial clustering method is greatly different from the common clustering method, the longitudinal spatial position distribution and the deposition rule of each small layer must be considered, and the spatial physical limitation of one well on oil layer control cannot be broken through, so the system recombination needs to carry out scientific demonstration and a scientific optimization algorithm.
The traditional spatial clustering K-Means method only calculates a clustering center from Euclidean distance without considering the influence of spatial non-mean, and when the series is recombined, certain small layers with larger span cannot be combined together, so that space limitation conditions exist, and in addition, in some cases, the small layers of different geological units cannot be classified into the same development series. When the traditional K-Means method is used for spatial clustering, the samples are generally assumed to be direct, the similarity between the samples or clusters is generally measured by a straight-line Euclidean distance, and the constraint effect of a spatial entity is ignored. If a fault exists in the formation, the oil-bearing zone on one side of the fault cannot converge to the cluster center on the other side of the fault.
In the recombination process of a well pattern and a layer system, the scientific mathematical method or the intelligent optimization method is lacked as a theoretical basis based on human experience and general fuzzy comprehensive evaluation. Therefore, a new method for reorganizing the strata system in the later period of oil field development based on spatial clustering is needed.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) The traditional spatial clustering K-Means method only calculates a clustering center from Euclidean distance without considering the influence of spatial non-mean, and when the series is recombined, certain small layers with larger span cannot be combined together, so that a spatial limitation condition exists, and in addition, in some cases, the small layers of different geological units cannot be classified into the same development series.
(2) When the traditional K-Means method is used for spatial clustering, the samples are generally assumed to be directly accessible, the similarity between the samples or clusters is generally measured by a straight-line Euclidean distance, and the constraint effect of a spatial entity is ignored. If a fault exists in the formation, the oil-bearing zone on one side of the fault cannot aggregate to the cluster center on the other side of the fault.
(3) In the recombination process of a well pattern and a layer system, the scientific mathematical method or the intelligent optimization method is lacked as a theoretical basis based on human experience and general fuzzy comprehensive evaluation.
The difficulty in solving the above problems and defects is:
on the basis of multi-source information analysis, a line target space clustering algorithm which is topologically related and similar in non-space attribute needs to be established by considering not only the space topological relation of each small layer of an oil reservoir but also the non-space attribute.
The significance of solving the problems and the defects is as follows:
optimizing the layer series recombination process through an improved spatial clustering algorithm, realizing the balanced displacement of the oil reservoir and improving the final recovery ratio; meanwhile, the system layer recombination and transformation scheme is ensured to be within the construction capacity range of the oil extraction process measures, so that the scheme measures have high feasibility.
Disclosure of Invention
The invention provides a layer system recombination method, computer equipment and a storage medium in the later stage of oil field development, and particularly relates to a layer system recombination method in the later stage of oil field development based on spatial clustering.
The invention is realized in such a way that the oil field development later-stage system layer recombination method based on the spatial clustering comprises the following steps:
step one, counting physical characteristics of an oil reservoir layer system and a small layer.
And step two, analyzing the small-layer mining dynamic and residual potential.
And step three, determining the technical limit standard of layer system recombination.
And step four, normalizing the dynamic indexes and establishing a spatial clustering attribute table.
And step five, performing layer system recombination by using an improved spatial clustering algorithm, and giving a layer system recombination result.
Further, in the first step, the method for counting physical characteristics of the reservoir strata and the small strata comprises the following steps:
(1) Establishing a small layer physical characteristic table by taking the interpretation serial number of the drilled small layer of each well as an index number; the physical characteristic table of the small layer comprises geological reserves, permeability, sand layer thickness, jetting thickness and crude oil viscosity;
(2) And (4) updating the division of the small layer by combining geological interpretation data, and renaming the small layer, wherein the interpretation sequence number of the small layer is unchanged.
Further, in step two, the method for analyzing the small seam mining dynamics and the residual potential comprises the following steps:
and (4) carrying out small-layer yield splitting on the block by using a reasonable yield splitting method, and calculating the cumulative oil yield, the cumulative water yield and the cumulative water injection rate of the small layer.
Further, in the process of yield splitting, for special cases, a special treatment method needs to be given:
(1) Measuring the fluid production profile only in a certain horizon time period: splitting the production periods of other layers by using flow coefficients;
(2) Between two fluid production profiles: interpolation of a fluid production profile or interpolation of a fluid production profile and a flow coefficient;
(3) Hole repairing and hole repeating: 1) Adjusting splitting coefficients of the new and old producing zones according to the yield increasing effect; 2) Establishing a manual liquid production profile;
(4) Water plugging of an oil well: 1) Adjusting the weight of the flow coefficient according to the aging of water plugging; 2) And establishing a manual fluid production profile.
Further, the formula of the special processing method is expressed as follows:
q o (k)＝ΔQ o ，q w (k)＝ΔQ w 。
further, in step three, the method for determining the technical limit standard of layer system recombination comprises:
and analyzing the influence of the permeability level difference, the crude oil viscosity, the formation coefficient, the number of small layers, the depth difference, the effective thickness lower limit and the permeability variation coefficient on the extraction degree, and determining the theoretical policy limit of each parameter in the layer series recombination adjustment.
Further, in the fifth step, the K-Means clustering method is improved and applied to residual oil potential evaluation, and the algorithm is as follows: selecting k objects as initial k clustering centers; then calculating the distance from each remaining sample to each clustering center, classifying the sample to the class of the clustering center closest to the sample, and calculating a new clustering center for the adjusted new class by using an average value method; if the cluster centers of two adjacent clusters do not have any change, the sample adjustment is finished and the cluster average error criterion function is converged.
The K-means clustering problem described based on minimizing the sum of squared euclidean distances is: for a given data space R m The n data targets in the cluster are respectively distributed into K clusters, so that the sum of squared Euclidean distances from each target to the center of the cluster where the target is located is minimum:
wherein, the first and the second end of the pipe are connected with each other,
n is the number of data objects, K is the number of clusters, x i Representing the object i, c j Represents a cluster C j C = { C = { C) 1 ,...,C K Denotes a set of K clusters, W = [ W = ij ]Is a 0-1 matrix of nxK, n j Is a cluster C j The number of targets in (1).
Further, the improved method of the spatial clustering algorithm comprises the following steps:
(1) Extracting dynamic and static parameters of each small layer, and carrying out normalization processing;
(2) Randomly selecting initial value points as clustering original data;
(3) Setting the number k of layer series recombination as the number of clustering levels;
(4) Setting the iteration times t =0, and searching k initial clustering centers
(5) For the t-th iteration, the distance between each entity and each cluster center is calculated
(6) If there is
Then sample S i Is assigned to j 0 Go in each cluster domain;
(7) Calculating a new clustering center;
(8) If it is
The iteration is stopped, otherwise t = t +1, go (4).
Further, the k initial cluster centers
Wherein S is j Is the number of the oil group, and the distance D (S) between any two centers i ,S j ) Greater than the allowable distance.
The calculation formula of the new clustering center is as follows:
further, in the fifth step, when the layer system recombination is carried out on the small layer according to the improved spatial clustering method, a single-factor decision or a multi-factor decision is selected, the weight coefficient of each factor is given, the weight coefficient value is between 1 and 10, and the normalization is automatically completed by a program.
It is a further object of the invention to provide a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of:
counting physical characteristics of an oil reservoir stratum and a small layer;
analyzing the small-seam mining dynamic and residual potential;
determining the technical limit standard of layer system recombination;
normalizing the dynamic indexes, and establishing a spatial clustering attribute table;
and (4) performing layer system reorganization by using an improved spatial clustering algorithm, and giving a layer system reorganization result.
It is another object of the present invention to provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of:
counting physical characteristics of the reservoir strata and the small strata;
analyzing the small-layer mining dynamic and residual potential;
determining the technical limit standard of layer system recombination;
normalizing the dynamic indexes, and establishing a spatial clustering attribute table;
and (4) performing layer system reorganization by using an improved spatial clustering algorithm, and giving a layer system reorganization result.
By combining all the technical schemes, the invention has the advantages and positive effects that: the method for reorganizing the stratum system in the later period of the oilfield development based on the spatial clustering is an important research direction in the fields of spatial data mining and knowledge discovery, and is different from the traditional clustering method in that a spatial distance dimension is introduced, so that the spatial clustering is realized on a research object with a spatial distribution attribute. The invention considers the oil layer property of single layer and the production dynamic state, and processes the splitting optimization of the small layer output, and describes the production dynamic state of the small layer; and the spatial position distribution of the layer system or the sand body is considered, and the layer system recombination result is scientific. The invention provides a practical and scientific path and method for the layer system recombination, can realize the expansion of water injection swept volume, control the water content rising speed, and furthest improve the water drive recovery ratio and the economic benefit of the oil field by improving the water drive swept volume, thereby having important significance for excavating the potential in the later development stage of the oil field and retarding the yield decrease.
The invention relates to potential excavation, scheme adjustment or secondary development scheme design at the later stage of multi-oil-layer sandstone reservoir development, and introduces a spatial clustering algorithm on the basis of attribute research and dynamic research and potential analysis of each small layer of a reservoir, and determines a reasonable layer system recombination mode by a clustering method. Spatial clustering analysis is an important Means for spatial pattern recognition and spatial data mining, spatial clustering refers to clustering according to the feature similarity of spatial objects, and multiple indexes such as permeability, stratum thickness, geological reserve, extraction degree and the like need to be considered when oil reservoirs are subjected to layer series recombination, so that a multi-dimensional spatial K-Means clustering method is introduced for recombining layer series, and other factors such as stratum depth and the like need to be considered when the layer series are combined, so that the traditional spatial clustering method is improved, and on the basis of improving the K-Means clustering method, the permeability, the stratum thickness, the geological reserve, the extraction degree, the layer depth and the like are comprehensively considered, and different layer series combined patterns can be given.
Drawings
Fig. 1 is a flow chart of a method for reorganizing a layer system in a late stage of oilfield development based on spatial clustering according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a layer system reorganization method in the later period of oil field development based on spatial clustering according to an embodiment of the present invention.
Fig. 3 is a flow chart of the splitting of the small layer yield provided by the embodiment of the present invention.
FIG. 4 shows the result of layer system reorganization without spatial property provided by an embodiment of the present invention.
Fig. 5 is a series of layer recombination results based on improved spatial clustering according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a spatial clustering-based oil field development later-stage system layer recombination method, which is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for reorganizing a layer system in a late stage of oil field development based on spatial clustering provided by the embodiment of the present invention includes the following steps:
s101, counting physical characteristics of the reservoir strata and the small strata.
And S102, analyzing the small-seam mining dynamics and the residual potential.
S103, determining the technical limit standard of the layer series recombination.
And S104, normalizing the dynamic indexes, and establishing a spatial clustering attribute table.
S105, carrying out layer system recombination by using an improved spatial clustering algorithm, and giving a layer system recombination result.
The present invention will be further described with reference to the following examples.
As shown in fig. 2, the method for reorganizing a layer system in a late stage of oil field development based on spatial clustering provided by the embodiment of the present invention includes the following steps:
(1) Reading in basic information of single well small layer
Reading in basic information of a single well by connecting a static database, and establishing a small-layer physical characteristic table comprising geological reserves, permeability, sand layer thickness, jetting thickness and crude oil viscosity by taking a well name and an interpretation sequence number as index numbers;
(2) Splitting of small layer yield
The yield splitting is performed according to the flow shown in fig. 3, which is a key step for evaluating the dynamics of the small layer, and for some special cases, a special processing method is needed to make the yield splitting result more accurate.
In the case of mass splitting, special treatment methods are required for special cases (see Table 1).
TABLE 1 Special treatment of small layer cleavage
The abnormal change of the yield after the layer is changed, special treatment measures are adopted, under the condition of layer change, the attribution proportion of the increment generated when the yield of the oil well is abnormally changed to a new layer position must be considered, and splitting can not be carried out according to a conventional flow coefficient. Like east 7-24 wells, after replenishing the 42 th layer in 9 months 2002, the yield increased by as much as 10 times, while the 42 th layer had no significant change in physical properties and was even thinner than the 40 th layer. For the situation, a manual liquid production profile method can be adopted to correct the split yield coefficient, and the change of the yield can also be mainly attributed to a new layer number through automatic judgment of a computer.
TABLE 2 examples of layer yield changes
| Number of well | Year and month | Monthly water yield | Monthly oil production | Production layer number |
| East 7-24 | 200207 | 440 | 192 | 40 |
| East 7-24 | 200208 | 376 | 151 | 40 |
| East 7-24 | 200209 | 237 | 1621 | 40,42 |
| East 7-24 | 200210 | 350 | 1740 | 40,42 |
The formula of the special processing method is expressed as follows:
q o (k)＝ΔQ o ，q w (k)＝ΔQ w 。
(3) Single well dynamic and static indicators summary
Summarizing the static and dynamic indicators shown in the following table (for data privacy, only 10 pieces of data are shown)
TABLE 3 Small layer static data sheet
TABLE 4 Small layer dynamic data sheet
| Serial number | Single sand layer | Cumulative water injection amount | Cumulative water yield | Cumulative oil production | Cumulative injection- |
| 1 | NmⅡ-10-1 | 107055.26 | 248044.48 | 23201.09 | 0.395 |
| 2 | NmⅢ-2-1 | 0 | 468636.75 | 31794.58 | 0 |
| 3 | NmⅢ-3-1 | 184.37 | 6620.69 | 3030.74 | 0.019 |
| 4 | NmⅢ-3-2 | 0 | 21346.43 | 1477.81 | 0 |
| 5 | NmⅢ-4-2 | 179314.81 | 82131.87 | 2927.18 | 2.108 |
| 6 | NmⅢ-5-1 | 163655.7 | 223190.13 | 28926.29 | 0.649 |
| 7 | NmⅢ-5-2 | 3145 | 752405.83 | 31327.11 | 0.004 |
| 8 | NmⅢ-6-1 | 492479.49 | 1041757.94 | 73657.77 | 0.442 |
| 9 | NmⅢ-6-2 | 14404.24 | 280671.18 | 33740.83 | 0.046 |
| 10 | NmⅢ-7-1 | 90561.75 | 316778.42 | 47623.49 | 0.249 |
(3) Series system reorganization by improved space clustering method
According to the improved spatial clustering method, the layer system recombination is carried out on the small layers. The normalization can be automatically completed by a program by selecting a single-factor decision or a multi-factor decision and giving a weight coefficient of each factor, wherein the weight coefficient value is between 1 and 10.
The results are exemplified as follows:
layer system 1: nmII-10-1, nmIII-4-2, nmIII-5-1, \ 8230
Layer system 2: nm III-2-1, nm III-3-1, nm III-5-2, \8230
Layer system 3: nm III-6-1, nm III-6-2, nm III-7-1, \ 8230
(4) Technical policy and space verification
And (3) checking the layer system recombination result, namely whether each index combination meets the technical policy boundary of the table 5, checking whether the spatial feasibility is met according to the spatial longitudinal position combination, and if not, recombining the indexes or changing the number of layer system recombination (cluster centers).
TABLE 5 boundary indicator for layer combinations
| Parameter(s) | Boundary of |
| Difference in permeability grade | 3 |
| Coefficient of permeability variation | 0.7 |
| Grade difference of crude oil viscosity | 2.5 |
| Difference in thickness | 4 |
| Difference in flow coefficient | 5 |
| Upper limit of number of small layers | 15 |
| Effective lower limit of thickness | 9m |
| Difference in depth | 120m |
According to the invention, the dynamic production data of a small layer of a certain block obtained by the analysis of the algorithm flow is shown in a table 6, the number of the layer system recombination sets is determined to be three sets after the comprehensive analysis of geology and a mine field, and then three clustering centers are set for carrying out layer system recombination design, the comparison result of the spatial clustering algorithm and the algorithm without considering the spatial attribute is shown in a figure 4 and a figure 5, so that the layer system recombination is only the comprehensive classification of attribute comparison under the condition without considering the spatial attribute, spans different sand layer groups, and has low performability; under the spatial clustering rule, based on the strengthened spatial constraint, the combined result of the cross-layer section can not occur.
TABLE 6 dynamic production data table for main power small layer of a certain block
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. An oilfield development late layer system reorganization method based on spatial clustering is characterized by comprising the following steps:
counting physical characteristics of an oil reservoir stratum and a small layer;
analyzing the small-layer mining dynamic and residual potential;
determining the technical limit standard of layer system recombination;
normalizing the dynamic indexes, and establishing a spatial clustering attribute table;
using an improved spatial clustering algorithm to carry out layer system recombination and giving out a layer system recombination result;
the improved method of the spatial clustering algorithm comprises the following steps:
(1) Extracting dynamic and static parameters of each small layer, and carrying out normalization treatment;
(2) Randomly selecting initial value points as clustering original data;
(3) Setting the number k' of layer series recombination as the number of clustering levels;
(4) Setting the iteration times t =0, and searching k initial clustering centers
(5) For the t-th iteration, the distance between each entity and each cluster center is calculated
(6) If there is
Then the sample S i Is assigned to j 0 Removing in each cluster domain;
(7) Calculating a new clustering center;
(8) If it is
The iteration is stopped, otherwise t = t +1, go (4).
2. The method for late-stage system series reorganization of oil field development based on spatial clustering as claimed in claim 1, wherein the method for reservoir system series and small-layer physical characteristic statistics comprises:
(1) Establishing a small layer physical characteristic table by taking the explanation serial number of the drilled small layer of each well as an index number; the physical characteristic table of the small layer comprises geological reserves, permeability, sand layer thickness, jetting thickness and crude oil viscosity;
(2) Updating the division of the small layer by combining geological interpretation data, renaming the small layer, and keeping the interpretation sequence number of the small layer unchanged;
the method for analyzing the small seam mining dynamic and residual potential comprises the following steps:
and (4) carrying out small-layer yield splitting on the block by using a reasonable yield splitting method, and calculating the cumulative oil yield, the cumulative water yield and the cumulative water injection rate of the small layer.
3. The oil field development later-stage layer system recombination method based on the spatial clustering as claimed in claim 2, characterized in that in the process of yield splitting, for special cases, a special processing method is required to be given:
(1) Measuring the fluid production profile only in a certain horizon time period: splitting the production time periods of other layers by using a flow coefficient;
(2) Between two fluid production profiles: interpolation of a fluid production section or interpolation of a fluid production section and a flow coefficient;
(3) Hole repairing and hole repeating: 1) Adjusting splitting coefficients of new and old layers according to the yield increasing effect; 2) Establishing a manual liquid production profile;
(3) Water plugging of an oil well: 1) Adjusting the weight of the flow coefficient according to the aging of water plugging; 2) Establishing a manual liquid production profile;
the formula of the special processing method is expressed as follows:
q o (k)＝ΔQ o ，q w (k)＝ΔQ w 。
4. the method for system series reorganization later in oil field development based on spatial clustering as claimed in claim 1, wherein the method for determining the technical boundary standard of system series reorganization comprises:
and analyzing the influence of the permeability grade difference, the viscosity of crude oil, the formation coefficient, the number of small layers, the depth difference, the lower limit of effective thickness and the permeability variation coefficient on the production degree, and determining the theoretical policy limit of each parameter in the layer system recombination adjustment.
5. The method for late-stage system series reorganization of oil field development based on spatial clustering as claimed in claim 1, wherein the K-Means clustering method is improved and applied to residual oil potential evaluation, and the algorithm is as follows: selecting k objects as initial k clustering centers; then calculating the distance from each remaining sample to each clustering center, classifying the sample to the class of the clustering center closest to the sample, and calculating a new clustering center for the adjusted new class by using an average value method; if the clustering centers of two adjacent times do not change, the sample adjustment is finished and the clustering average error criterion function is converged;
the K-means clustering problem described based on minimizing the sum of squared euclidean distances is: for a given data space R m The n data targets in the cluster are respectively distributed into K clusters, so that the sum of squared Euclidean distances from each target to the center of the cluster where the target is located is minimum:
wherein the content of the first and second substances,
n is the number of data objects, K is the number of clusters, x i Representing the object i, c j Represents a cluster C j C = { C = { C) 1 ,...,C K Denotes a set of K clusters, W = [ W = [ W = } ij ]Is a 0-1 matrix of nxK, n j Is a cluster C j The number of targets in (1).
6. The method of spatial clustering based oilfield development late-phase system reorganization of claim 1, wherein the k initial cluster centers
Wherein S is j Is the number of the oil group, and the distance D (S) between any two centers i ,S j ) Greater than an allowable distance;
the calculation formula of the new clustering center is as follows:
7. the oil field development later-stage layer system reorganization method based on spatial clustering as claimed in claim 1, wherein when the layer system reorganization is performed on the small layers according to the improved spatial clustering method, single-factor decision or multi-factor decision is selected, and the weight coefficient of each factor is given, the weight coefficient value is between 1 and 10, and the normalization is automatically completed by a program.
8. A computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the method of spatial clustering based late field development system layer system reorganization of any one of claims 1 to 7.
9. A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the method of late system series reorganization of oilfield development based on spatial clustering according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011215850.5A CN112348350B (en) | 2020-11-04 | 2020-11-04 | Layer system recombination method, computer equipment and storage medium in later stage of oilfield development |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011215850.5A CN112348350B (en) | 2020-11-04 | 2020-11-04 | Layer system recombination method, computer equipment and storage medium in later stage of oilfield development |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112348350A CN112348350A (en) | 2021-02-09 |
| CN112348350B true CN112348350B (en) | 2022-10-28 |
Family
ID=74356823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011215850.5A Active CN112348350B (en) | 2020-11-04 | 2020-11-04 | Layer system recombination method, computer equipment and storage medium in later stage of oilfield development |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112348350B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118014312A (en) * | 2024-04-08 | 2024-05-10 | 西安思坦仪器股份有限公司 | Effective allocation method for underground layered flow of intelligent wave code separate injection well |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103924966A (en) * | 2013-01-10 | 2014-07-16 | 中国石油化工股份有限公司 | Bed set well pattern reconstruction method based on reservoir physical property time varying model |
| CN104100243A (en) * | 2013-04-08 | 2014-10-15 | 中国石油化工股份有限公司 | Three-stage subdivision method for retarding interlayer interference of fault-block oil reservoir with ultrahigh water-cut stage and multiple oil layers |
| CN105822269A (en) * | 2015-04-09 | 2016-08-03 | 中国石油化工股份有限公司 | Distribution mode and development regulation method for oil left after binary flooding of multilayer reservoir |
| CN111428375A (en) * | 2020-03-31 | 2020-07-17 | 中国石油大学(华东) | Novel high-water-content oilfield layer system recombination and division method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8793111B2 (en) * | 2009-01-20 | 2014-07-29 | Schlumberger Technology Corporation | Automated field development planning |
-
2020
- 2020-11-04 CN CN202011215850.5A patent/CN112348350B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103924966A (en) * | 2013-01-10 | 2014-07-16 | 中国石油化工股份有限公司 | Bed set well pattern reconstruction method based on reservoir physical property time varying model |
| CN104100243A (en) * | 2013-04-08 | 2014-10-15 | 中国石油化工股份有限公司 | Three-stage subdivision method for retarding interlayer interference of fault-block oil reservoir with ultrahigh water-cut stage and multiple oil layers |
| CN105822269A (en) * | 2015-04-09 | 2016-08-03 | 中国石油化工股份有限公司 | Distribution mode and development regulation method for oil left after binary flooding of multilayer reservoir |
| CN111428375A (en) * | 2020-03-31 | 2020-07-17 | 中国石油大学(华东) | Novel high-water-content oilfield layer system recombination and division method |
Non-Patent Citations (1)
| Title |
|---|
| 高含水率油田开发层系的重组;鲍敬伟 等;《新疆石油地质》;20100630;第31卷(第3期);第291-294页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112348350A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009716B (en) | Multi-level evaluation method for influence factors of horizontal well volume fracturing effect | |
| CN111441767B (en) | Oil reservoir production dynamic prediction method and device | |
| CN115345378B (en) | Shale gas well yield evaluation method based on machine learning | |
| CN108643875B (en) | Water injection development adjustment method, device and system for low-permeability clastic rock oil reservoir | |
| CN103912248A (en) | Method for predicting water contents of water-drive oilfields | |
| CN110717301A (en) | Flow unit information classification and identification method based on support vector machine algorithm | |
| CN105386751A (en) | Well logging and productivity prediction method of horizontal well based on oil reservoir seepage flow model | |
| CN109958413B (en) | Dynamic flow unit dividing method for oil reservoir in ultrahigh water cut period | |
| CN112348350B (en) | Layer system recombination method, computer equipment and storage medium in later stage of oilfield development | |
| CN112576238B (en) | System, method and application for determining position and content of residual oil in low-permeability reservoir | |
| Yi et al. | Spatial correlation-based machine learning framework for evaluating shale gas production potential: A case study in southern Sichuan Basin, China | |
| CN116562428A (en) | Fracturing construction parameter optimization method based on machine learning | |
| Ariadji et al. | Optimization of vertical well placement for oil field development based on basic reservoir rock properties using a genetic algorithm | |
| CN111079341B (en) | Intelligent well completion and oil reservoir unsteady state coupling method based on iterative algorithm | |
| CN115705452A (en) | Novel recovery ratio prediction method for middle and later stages of integrated sandstone reservoir development | |
| Chen et al. | Machine Learning Based Shale Gas Proration Synchronized Computing Method | |
| CN111706323A (en) | Water flooded layer fine interpretation and evaluation method based on GWO-LSSVM algorithm | |
| Liu et al. | Optimizing construction parameters for fractured horizontal wells in shale oil | |
| CN111335871A (en) | Layer-checking hole-repairing technical method based on layered productivity evaluation | |
| CN114169616A (en) | Method for distinguishing low-yield and low-efficiency well | |
| CN113361111B (en) | Partitioning method of low-permeability reservoir characteristic model | |
| Aslam et al. | Capacitance Resistance Clustered Model for Mature Peripheral Waterflood Performance Prediction & Optimization | |
| Hua et al. | Application of Fuzzy Comprehensive Evaluation Method in the Development Performance Evaluation Work of Overseas Oilfields | |
| CN113818859B (en) | Limiting well spacing determining method, judging method and device for low-permeability oil reservoir | |
| Wang et al. | The Optimal Development Strategy Selected for Layered Sandstone Reservoir by Creating a System Economic Model |
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 |