CN107330578A - Sand body Connectivity Evaluation method and device - Google Patents
Sand body Connectivity Evaluation method and device Download PDFInfo
- Publication number
- CN107330578A CN107330578A CN201710376308.XA CN201710376308A CN107330578A CN 107330578 A CN107330578 A CN 107330578A CN 201710376308 A CN201710376308 A CN 201710376308A CN 107330578 A CN107330578 A CN 107330578A
- Authority
- CN
- China
- Prior art keywords
- sand body
- sample
- sand
- connective
- forecast model
- 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.)
- Granted
Links
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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Agronomy & Crop Science (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Animal Husbandry (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application provides a kind of sand body Connectivity Evaluation method and device, and methods described includes：The cross connection sand body sample, vertical communication sand body sample and internal connectivity sand body sample in work area are set up respectively, and will be divided into training sample and test sample per class sand body sample；The training sample of every class sand body sample is trained using default machine learning algorithm, the connective forecast model of corresponding sand body is set up；The connective forecast model of corresponding sand body is optimized according to the test sample of every class sand body sample, so that corresponding sand body predicting the outcome for forecast model of connectedness meets preparatory condition；According to the connective forecast model of sand body after optimization, sand body data corresponding to sand body to be identified in the work area carry out sand body Connectivity Evaluation, obtain evaluation result.The embodiment of the present application can improve the degree of accuracy and the efficiency of sand body Connectivity Evaluation.
Description
Technical field
The application is related to sand body Connectivity Evaluation technical field in reservoir description, is commented more particularly, to a kind of sand body connectedness
Valency method and device.
Background technology
Sandstone reservoir connectedness refer generally to genetic unit sand body on vertical with contact with each other on the side the mode that connects and
Degree, is the key factor for the exploitation for influenceing oil gas field.In oilfield exploitation procedure, the deployment of flooding pattern, development scheme
Selection and taping the latent power etc. for later stage remaining oil be required for setting up on the basis of certain sandstone reservoir connectivity analysis.But by
In the general all complex distributions of subsurface reservoir sand body, anisotropism is strong, especially fluvial sandstone, and frequently transition cause each phase in river course
Sand body mutually cuts stacked, and the connection situation of each river channel sand is sufficiently complex, and often difficulty is big for the prediction of sand body connectedness.
At present traditional sand body connectivity analysis methods majority be by the sedimentation type of sand body, development degree and scale,
The comprehensive analysis of phase transformation contact relation judges the connection situation between all kinds of sand bodies, but this method is often comparatively laborious, when
Just seem unable to do what one wishes during in face of the work area of large area.Also there are some scholars to do sand body Connectivity Evaluation research both at home and abroad, such as
Allen (1979) and Qiu Yinan (1987) determine the connectedness of sand body, Pranter by the critical value of Channel sandstone density
According to sandbody width, sandy ground, when well spacing differentiates quality that sand body is connective to and Sommer (2011).However, influence river course
The connective factor of sand body is more, when considering multiple influence factors simultaneously, efficiently and accurately evaluate sand body connectedness just than
It is more difficult.
The content of the invention
The purpose of the embodiment of the present application is to provide a kind of sand body Connectivity Evaluation method and device, accurate to realize efficiently
True evaluation sand body connectivity.
To reach above-mentioned purpose, on the one hand, the embodiment of the present application provides a kind of sand body Connectivity Evaluation method, including：
The cross connection sand body sample, vertical communication sand body sample and internal connectivity sand body sample in work area are set up respectively
This, and training sample and test sample will be divided into per class sand body sample；
The training sample of every class sand body sample is trained using default machine learning algorithm, corresponding sand body is set up
Connective forecast model；
The connective forecast model of corresponding sand body is optimized according to the test sample of every class sand body sample, so that correspondence
Connective the predicting the outcome for forecast model of sand body meet preparatory condition；
According to the connective forecast model of sand body after optimization, the corresponding sand body data of sand body to be identified in the work area are entered
Row sand body Connectivity Evaluation, obtains evaluation result.
The sand body Connectivity Evaluation method of the embodiment of the present application, described is normalized sand body sample per class sand body sample.
The sand body Connectivity Evaluation method of the embodiment of the present application, described is to sequentially pass through normalized per class sand body sample
With the sand body sample obtained after dimension-reduction treatment.
The sand body Connectivity Evaluation method of the embodiment of the present application, described machine learning algorithm is calculated including SVMs
Method.
The sand body Connectivity Evaluation method of the embodiment of the present application, described dimension-reduction treatment is real by Principal Component Analysis Algorithm
It is existing.
On the other hand, the embodiment of the present application additionally provides a kind of sand body Connectivity Evaluation device, including：
Sample Establishing module, cross connection sand body sample, vertical communication sand body sample for setting up work area respectively
With internal connectivity sand body sample, and training sample and test sample will be divided into per class sand body sample；
Model building module, for being instructed using default machine learning algorithm to the training sample of every class sand body sample
Practice, set up the connective forecast model of corresponding sand body；
Model optimization module, for the test sample according to every class sand body sample to the connective forecast model of corresponding sand body
Optimize, so that corresponding sand body predicting the outcome for forecast model of connectedness meets preparatory condition；
Model prediction module, for according to the connective forecast model of sand body after optimization, to sand to be identified in the work area
The corresponding sand body data of body carry out sand body Connectivity Evaluation, obtain evaluation result.
The sand body Connectivity Evaluation device of the embodiment of the present application, described is normalized sand body sample per class sand body sample.
The sand body Connectivity Evaluation device of the embodiment of the present application, described is to sequentially pass through normalized per class sand body sample
With the sand body sample obtained after dimension-reduction treatment.
The sand body Connectivity Evaluation device of the embodiment of the present application, described machine learning algorithm is calculated including SVMs
Method.
The sand body Connectivity Evaluation device of the embodiment of the present application, described dimension-reduction treatment is real by Principal Component Analysis Algorithm
It is existing.
The technical scheme provided from above the embodiment of the present application, the embodiment of the present application is divided sand body connected relation
Class is described so that more fully, and to select each influence connective good for all types of connectednesses for the connective analysis and research of sand body
Bad Dominated Factors, set up respective prediction and evaluation model, because the connecting degree of different sand body connectivity types is not by
Same geologic parameter influence, such classification processing, can preferably lift the degree of accuracy of sand body Connectivity Evaluation, and due to machine
Learning algorithm can solve small sample problem, and not fear the vector data of high dimension, therefore, and the embodiment of the present application is by machine
Learning algorithm applies to sand body Connectivity Evaluation, and it is not very sufficient situation relatively not only to go in work area data,
Go in sand body Connectivity Evaluation, while the situation of multiple property parameters is considered, without its is right with excessive worry
The influence of evaluation effect.And machine learning algorithm general speed is quickly, and sand body is fast and accurately determined so as to be advantageously implemented
Connecting degree, it is significant to oil field development.
Brief description of the drawings
, below will be to embodiment or existing in order to illustrate more clearly of the embodiment of the present application or technical scheme of the prior art
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments described in application, for those of ordinary skill in the art, are not paying the premise of creative labor
Under, other accompanying drawings can also be obtained according to these accompanying drawings.In the accompanying drawings：
Fig. 1 is the flow chart of the sand body Connectivity Evaluation method of the embodiment of the application one；
Fig. 2 is the sand body schematic diagram with cross connection in the embodiment of the application one；
Fig. 3 is the sand body schematic diagram with vertical communication in the embodiment of the application one；
Fig. 4 is the sand body schematic diagram with internal connectivity in the embodiment of the application one；
Fig. 5 is the sample data feature variance schematic diagram in the embodiment of the application one after PCA dimensionality reductions；
Fig. 6 is shown for the two dimensional surface result obtained in the embodiment of the application one based on the progress parameter optimization of cross validation algorithm
It is intended to；
Fig. 7 is illustrated for the 3 D stereo result obtained in the embodiment of the application one based on the progress ginseng optimizing of cross validation algorithm
Figure；
Fig. 8 is the actual classification and prediction comparison of classification figure of cross connection test sample collection in the embodiment of the application one；
Fig. 9 is the actual classification and prediction comparison of classification figure of vertical communication test sample collection in the embodiment of the application one；
Figure 10 is the actual classification and prediction comparison of classification figure of internal connectivity test sample collection in the embodiment of the application one；
Figure 11 is the structured flowchart of the sand body Connectivity Evaluation device of the embodiment of the application one.
Embodiment
In order that those skilled in the art more fully understand the technical scheme in the application, it is real below in conjunction with the application
The accompanying drawing in example is applied, the technical scheme in the embodiment of the present application is clearly and completely described, it is clear that described implementation
Example only some embodiments of the present application, rather than whole embodiments.Based on the embodiment in the application, this area is common
The every other embodiment that technical staff is obtained under the premise of creative work is not made, should all belong to the application protection
Scope.
With reference to shown in Fig. 1, the sand body Connectivity Evaluation method of the embodiment of the present application can include：
S101, cross connection sand body sample, vertical communication sand body sample and the internal connectivity for setting up work area respectively
Sand body sample, and training sample and test sample will be divided into per class sand body sample.
In the embodiment of the present application, the cross connection sand body sample that work area is set up respectively, vertical communication sand body sample
This and internal connectivity sand body sample may comprise steps of：
First, sand body connectedness is divided into three types by genetic type, contact mode and the distribution mode according to sand body：
Cross connection, vertical communication and internal connectivity.Wherein, cross connection can refer to be located at same sedimentation time unit
It is interior, connected relation between the single sand body of the close adjacent identical or different origin cause of formation on the side, as shown in Figure 2；Vertical communication can be with
Refer to be located in different sedimentation time units, connected relation between neighbouring single sand body, as shown in Figure 3；And internal connectivity
The connected relation inside single sand body can be referred to, as shown in Figure 4.Wherein, described distribution mode can include planar distribution form
And/or section distribution mode etc..
In the embodiment of the present application, the genetic type of sand body can be understood as the sedimentary micro type of sand body, different origins class
The sand body of type is all different in terms of form, scale, physical property, endo conformation and connectedness, and these are all by sedimentary micro control
System.There is Exemplary deposition microfacies sand body in meandering stream：Point bar, abandoned channel, natural levee, alluvial flat；Exemplary deposition is micro- in braided stream
Phase sand body has：Braided channel, channel bar.), distinguishing mark (refer to the distinguishing mark of time river channel sand of single phase, by recognizing these points
Boundary mark will to carry out combination channel sand body single river channel sand division.The distinguishing mark of single river channel can be divided into vertical to be indicated by stages
With lateral two kinds of boundary sign, vertical mark by stages is mainly the interlayer developed between sand body, including muddy intercalation, physical property interlayer and
Calcareous interlayer；Lateral boundary sign includes abandoned channel deposit, discontinuous interchannel deposition, river channel sand top coat position depth displacement
Different, river channel sand difference in thickness, river course edge sand thickness be thinned etc..
In the embodiment of the present application, sand body contact mode refers to that forefathers are total on the basis of a large amount of sand body contact relation researchs
The a set of pattern come is born, contact relation between sand body can preferably be studied based on this set pattern.Contacted in river course between single sand body
Relation mainly has stand alone, docking style, cuts stack-type and 4 kinds of patterns of superimposed type.
Secondly, suitable sand body sample is chosen.In the embodiment of the present application, the selection of the sand body sample in work area is very crucial
, to ensure the authenticity and representativeness of the sand body sample selected.In the application one embodiment, it is contemplated that from Dynamic Water
Flood in the more rich wellblock of data and select the connective sample of sand body, ensure that sand body sample authenticity and representative as far as possible
Property.In the application one embodiment, sand body sample can be mainly by sand body and the property parameters of sand body spacer interlayers, and therewith
The connective situation composition of corresponding sand body；Wherein, the property parameters selected by the connective sample data of different type can not
Together.The property parameters that for example cross connection is chosen can include well spacing, sand body porosity, sandy ground ratio, sand body permeability, interlayer
Density etc.；The property parameters that vertical communication is chosen can include, and sand body porosity, sand body permeability, compartment thickness, interlayer ooze
Saturating rate etc.；Internal connectivity choose property parameters can include sand body porosity, sandy ground ratio, sand body permeability, interlayer density,
Interlayer frequency etc..In the application one embodiment, the connective situation of sand body is specifically as follows the connective quality of sand body
It is divided into several grades, for example, is divided into 3 grades：Connective good, connective medium and poor connectivity, its corresponding distinguishing mark
Can be 1,2 and 3.
Then, for every kind of sand body type of connectivity, according to the rock core and well-log information in work area, therefrom select to sand body
The larger property parameters of connectedness influence, and the connectedness quality of dynamic and static data analyzes test result as even in work area
General character sample, so as to obtain the sand body sample of every kind of sand body type of connectivity, that is, establishes the cross connection sand body sample in work area
Originally, vertical communication sand body sample and internal connectivity sand body sample.
The embodiment of the present application, will can substantially be divided into two groups per class sand body sample at random, one of which as training sample,
It is used to train study, so that for setting up the connective forecast model of sand body；Another group as test samples, i.e., for testing mould
Type, examines its classifying quality, so that for model optimization.In view of requirement of the machine learning algorithm for training data quantity,
The data of the training sample of each class should be at least more than 10.
S102, using default machine learning algorithm the training sample of every class sand body sample is trained, sets up correspondence
The connective forecast model of sand body.
In the embodiment of the present application, sand body connectedness is divided into three types, from three angles inside transverse direction, longitudinal direction, sand body
Classified description is carried out to sand body connected relation so that the connective analysis and research of sand body more fully, and all types of connectedness
The Dominated Factors of the connective quality of each influence are selected, respective prediction and evaluation model is set up, because different sand bodies connects
The connecting degree of logical type is influenceed by different geologic parameters, such classification processing, can preferably lift commenting for sand body connectedness
Valency effect.
In the embodiment of the present application, because machine learning algorithm can solve small sample problem, and high dimension is not feared
Vector data, therefore, sand body Connectivity Evaluation is applied to by machine learning algorithm, is not only gone for relative in work area data
It is not very sufficient situation；It is readily applicable in sand body Connectivity Evaluation, while consider the situation of multiple property parameters, and
Worry its influence to evaluation effect without excessive.And machine learning algorithm general speed is quickly, so as to be advantageously implemented
Sand body connecting degree is fast and accurately determined, it is significant to oil field development.
In the application some embodiments, default machine learning algorithm for example can be SVMs (Support
Vector Machine, SVM), decision tree, random forests algorithm, logistic regression, naive Bayesian, K nearest neighbor algorithms, K averages
Algorithm, Adaboost algorithm, neutral net, markov etc..
, specifically can be using algorithm of support vector machine to every class sand body sample in one exemplary embodiment of the application
Training sample is trained, to set up the connective forecast model of corresponding sand body.Wherein it is possible to select Radial basis kernel function conduct
The kernel function of supporting vector machine model, then according to the structure of system inputoutput data the characteristic study algorithm of support vector machine,
And using the optimal SVMs punishment parameter (C) of grid data service combination cross-validation method selection and kernel functional parameter
(g), as shown in Figure 6 and Figure 7.Training sample is used for training pattern, and set up using optimal punishment parameter and kernel functional parameter
Support vector cassification forecast model, that is, set up the connective forecast model of sand body per class training sample.
SVMs (SVM) is a kind of algorithm for pattern recognition based on sample learning, is set up by the study to sample
SVM models, then to the data progress category division of unknown classification.SVM models be by constantly learn and calculate one
Individual decision function, and SVM modelings are the solution procedure of decision function.
Simple non-linear two classification can finally be converted into the solution to a convex quadratic programming problem：
In formula, K (xi, is x) the inner product kernel function of realizing Nonlinear Mapping, and K (xi, x)=Φ (xi) Φ (x), most
Solving obtained decision function afterwards is：
In one exemplary embodiment of the application, programmed using matlab, introduce LIBSVM function kit, realized
SVM forecast models set up process.The kit provides two crucial functions, svmtrain and svmpredict, wherein
Svmtrain is the function of training study, when setting up model using Gaussian kernel, and the function needs to input two parameters：Punishment ginseng
Number C and kernel functional parameter g.Sample data and two parameters determined are substituted into SVM training functions, operation program obtains SVM
Decision function：
Model=svmtrain (train_Y, train_scale_X' ,-c12-g1')
Wherein, punishment parameter C and nuclear parameter g determination：
K- rolls over cross validation：In order to improve the Generalization Ability of disaggregated model, it will usually extract a part from sample and examine
Sample is not involved in learning training, and the popularization performance of disaggregated model is then detected using test samples, and k- folding cross validations are basic
Exactly above-mentioned thought is implemented.Training sample is randomly divided into the k sons for mutually disjointing and being substantially equal to the magnitudes by it first
Collection, i.e. k- foldings：S1, S2, Sk；Si is selected as test set, remaining S1, Si-1, Si+1,
The training sample set that Sk intersection is used as algorithm, support vector cassification model is set up with this, is tested by test set Si
Disaggregated model, obtains the training points of mistake classification；Said process is repeated k times, and the obtained mistake after k iteration is classified
The ratio of number sum and total training points is used as an estimation of the algorithm model error rate, i.e. k- folding cross validation errors.
Grid data service is a kind of most direct method for finding parameter, and its basic thought is setup parameter C scope
[C1, C2], change step is Cx, and parameter g scope is [g1, g2], and change step is gx, and so all C and g parameters are to structure
Thrown the net lattice into one, and every a pair of parameters one grid node of correspondence.All grid nodes are traveled through, cross validation precision highest is found out
A node.Usually first scanned in real process in a wide range of interior search, then in a small range with small step length.
Example：By taking sand body vertical communication evaluation model as an example, determine that the process of parameter is as follows with the above method：
(1) one group of penalty factor and nuclear parameter σ scope are selected by rule of thumb, and such as C and the σ region of search are set to [2-
10,210], step-size in search is 3；
(2) 10 folding cross-validation methods are used, Training Support Vector Machines simultaneously carry out inspection, obtain one group of optimized parameter C=32,
σ=2.8284, cross validation precision is 86.3014%；
(3) selected scope is constantly adjusted, and progressively reduces step-length and tested, it is final determine C interval be [2-4,
28], σ interval is [2-8,26], and step-length is 0.5, obtains optimized parameter C=16, and σ=1.4142, cross validation precision reaches
90.411%.
So, optimal parameter combination is C=16, σ=1.4142.
The test sample of S103, basis per class sand body sample is optimized to the connective forecast model of corresponding sand body, with
Connective the predicting the outcome for forecast model of corresponding sand body is set to meet preparatory condition.
In the embodiment of the present application, test sample of the basis per class sand body sample is predicted corresponding sand body connectedness
Model is optimized, test sample that will be per class sand body sample respectively as the connective forecast model of correspondence sand body input,
Predict the outcome whether meet preparatory condition with the connective forecast model output of detection correspondence sand body.Described satisfaction presets bar
Part, that is, contrasting SVM prediction result will match with sand body connecting degree actual in corresponding all；If do not kissed
Closing then can suitably adjust the parameter of the connective forecast model of sand body, then be detected again, until current model is exported
Predict the outcome and to be matched with sand body connecting degree actual in corresponding sample untill.
S104, according to the connective forecast model of sand body after optimization, to the corresponding sand body of sand body to be identified in the work area
Data carry out sand body Connectivity Evaluation, obtain evaluation result.
In the embodiment of the present application, can be by the work area after the connective forecast model of sand body after being optimized
The connective forecast model of the corresponding sand body of the corresponding sand body data input of sand body to be identified, so as to obtain corresponding evaluation result.Institute
The corresponding sand body data of sand body to be identified in work area are stated it is to be understood that the connective forecast model A of sand body after for example optimizing
When training is set up, the training sample that inputs is that the property parameters chosen in A1, wherein A1 are a1, a2 and a3, then, can when evaluating
Using the data of property parameters a1, a2 and a3 of sand body to be identified in the work area as the connective forecast model A of sand body input.
In the embodiment of the present application, the evaluation result can include the connective degree of sand body (such as level belonging to quality
Not).
In the application other embodiments, described can be normalized sand body sample per class sand body sample, to avoid
Each parameter dimension difference is adversely affected to predicting the outcome., can be using maximum most in the exemplary embodiment of the application one
Small normalization mode, its functional form is Y=(X-Xmin)/(Xmax-Xmin), and normalized effect is that initial data is regular
To in the range of [0,1].
, as needed can also be to normalizing after will be per class sand body samples normalization in the application other embodiments
Every class sand body sample after change carries out dimension-reduction treatment, to improve the accuracy of identification of model, reduces the identification caused by redundancy
Error.In the exemplary embodiment of the application one, can using principal component analysis (Principal Components Analysis,
PCA), linear Dimension Reduction Analysis (Linear Discriminant Analysis, LDA), be locally linear embedding into (Locally
Linear Embedding) or the dimension-reduction algorithm such as laplacian eigenmaps (Laplacian Eigenmaps) to normalization after
Every class sand body sample carry out dimension-reduction treatment.Data vector after dimensionality reduction is the compression fusion of former multidimensional data, as shown in figure 5,
Original property parameters have 8, after PCA dimension-reduction treatment, and data vector is fused to 5 dimensions, wherein data vector after fusion
5th component variance very little, possibly even removes as needed.Experiment shows, passes through dimension-reduction treatment in the embodiment of the present application
Sample data set up model compared to the processing speed without dimension-reduction treatment faster, and prediction and evaluation accuracy rate more
It is high.
Although above-described steps flow chart includes the multiple operations occurred with particular order, it should however be appreciated that understand,
Each steps flow chart is in the way of helping to understand embodiment described herein, to be described as multiple discrete steps successively
's.However, the order of description is not necessarily to be construed as implying that these operations must be order dependent.Specifically, these are operated
More or less operations may not necessarily can also be included with the sequentially executed of presentation, such as these these processes.
In order to verify whether the embodiment of the present application is capable of the various features parameter of comprehensive analysis influence connectedness, below with big
Illustrated exemplified by the oil reservoir group (PI) of grape flower one in celebrating Saar oil field.
The work area that the present exemplary embodiment is chosen is area western part in Saertu Oilfield in Daqing, and selected reservoir interval is PI oil
The substratums of PI 2 and the substratums of PI 3 in layer group, the wherein substratums of PI 2 development meandering stream deposit, the substratums of PI 3 development braided stream deposit.
Area has just put into exploitation western part nineteen sixty in Saar oil field, and current Sa Portugal oil reservoir is divided into four sets of Grouping of Sand Members And Well exploitations, one group of Portugal
The aqueous rise stage is in, but because its water flooding degree is uneven, river channel sand variation position, poor thin layer etc. still suffer from certain ratio
Example remaining oil, it is necessary to which scrutiny is carried out to river channel sand connection situation.
The present exemplary embodiment is chosen the attribute larger on connective influence and joined on the basis of the division of sand body connectivity types
The supplemental characteristic as sample is counted, the parameter that wherein cross connection is chosen includes, well spacing, sand body porosity, sandy ground ratio, sand body
Permeability, interlayer density；The parameter that vertical communication is chosen includes, sand body porosity, sand body permeability, compartment thickness, interlayer
Permeability；The parameter that internal connectivity is chosen includes, sand body porosity, sandy ground ratio, sand body permeability, interlayer density, interlayer frequency
Rate.Present exemplary embodiment embodiment carries out data statistics to company's well profile by 59 mouthfuls of wells, obtains 71 cross connections
Sample, 146 vertical communication samples and 136 internal connectivity samples, it is as shown in table 1 below.
Table 1
| Connective good sample number | Connective moderate sample number | Poor connectivity sample number | Total sample number | |
| Cross connection sample | 33 | 17 | 21 | 71 |
| Vertical communication sample | 83 | 30 | 33 | 146 |
| Internal connectivity sample | 97 | 25 | 14 | 136 |
The Sand-body Prediction model set up using the embodiment of the present application differentiated to the supplemental characteristic in test samples, as a result
As shown in Fig. 8, Fig. 9 and Figure 10, wherein the accuracy rate of cross connection is 87.8%, and the accuracy rate of vertical communication is
91.8%, the rate of accuracy reached 92.4% of internal connectivity shows that the application can be good at sentencing the connective quality of sand body
Not, sand body is evaluated connective.
With reference to shown in Figure 11, the sand body Connectivity Evaluation device of the embodiment of the present application can include：
Sample Establishing module 111, can be used for cross connection sand body sample, the vertical communication sand for setting up work area respectively
Body sample and internal connectivity sand body sample, and training sample and test sample will be divided into per class sand body sample.
Model building module 112, can be used for the training sample to every class sand body sample using default machine learning algorithm
Originally it is trained, sets up the connective forecast model of corresponding sand body.
Model optimization module 113, can be used for connective to corresponding sand body according to the test sample per class sand body sample
Forecast model is optimized, so that corresponding sand body predicting the outcome for forecast model of connectedness meets preparatory condition.
Model prediction module 114, can be used for according to the connective forecast model of sand body after optimization, to being treated in the work area
Recognize that the corresponding sand body data of sand body carry out sand body Connectivity Evaluation, obtain evaluation result.
The device of the embodiment of the present application is corresponding with the method for above-described embodiment, therefore, is related to the device details of the application,
The method for referring to above-described embodiment, will not be repeated here.
In the 1990s, for a technology improvement can clearly distinguish be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (for the improvement of method flow).So
And, with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow is programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, PLD
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, its logic function is determined by user to device programming.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, without asking chip maker to design and make
Special IC chip.Moreover, nowadays, substitution manually makes IC chip, and this programming is also used instead mostly " patrols
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but have many kinds, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed are most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also should
This understands, it is only necessary to slightly programming in logic and be programmed into method flow in integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method flow can be just readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
Device and storage can by the computer of the computer readable program code (such as software or firmware) of (micro-) computing device
Read medium, gate, switch, application specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and embedded microcontroller, the example of controller includes but is not limited to following microcontroller
Device：ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320, are deposited
Memory controller is also implemented as a part for the control logic of memory.It is also known in the art that except with
Pure computer readable program code mode is realized beyond controller, can be made completely by the way that method and step is carried out into programming in logic
Obtain controller and come real in the form of gate, switch, application specific integrated circuit, programmable logic controller (PLC) and embedded microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and various for realizing to including in it
The device of function can also be considered as the structure in hardware component.Or even, can be by for realizing that the device of various functions is regarded
For that not only can be the software module of implementation method but also can be the structure in hardware component.
For convenience of description, it is divided into various units during description apparatus above with function to describe respectively.Certainly, this is being implemented
The function of each unit can be realized in same or multiple softwares and/or hardware during application.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram are described.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which is produced, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and internal memory.
Internal memory potentially includes the volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only storage (ROM) or flash memory (flash RAM).Internal memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moved
State random access memory (DRAM), other kinds of random access memory (RAM), read-only storage (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only optical disc read-only storage (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic cassette tape, the storage of tape magnetic rigid disk or other magnetic storage apparatus
Or any other non-transmission medium, the information that can be accessed by a computing device available for storage.Define, calculate according to herein
Machine computer-readable recording medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, commodity or equipment including a series of key elements are not only including those key elements, but also wrap
Include other key elements being not expressly set out, or also include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described
Also there is other identical element in process, method, commodity or the equipment of element.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product.
Therefore, the application can be using the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.Deposited moreover, the application can use to can use in one or more computers for wherein including computer usable program code
The shape for the computer program product that storage media is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
The application can be described in the general context of computer executable instructions, such as program
Module.Usually, program module includes performing particular task or realizes routine, program, object, the group of particular abstract data type
Part, data structure etc..The application can also be put into practice in a distributed computing environment, in these DCEs, by
Remote processing devices connected by communication network perform task.In a distributed computing environment, program module can be with
Positioned at including in the local and remote computer-readable storage medium including storage device.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the difference with other embodiment.It is real especially for system
Apply for example, because it is substantially similar to embodiment of the method, so description is fairly simple, related part is referring to embodiment of the method
Part explanation.
Embodiments herein is the foregoing is only, the application is not limited to.For those skilled in the art
For, the application can have various modifications and variations.It is all any modifications made within spirit herein and principle, equivalent
Replace, improve etc., it should be included within the scope of claims hereof.
Claims (10)
1. a kind of sand body Connectivity Evaluation method, it is characterised in that including：
The cross connection sand body sample, vertical communication sand body sample and internal connectivity sand body sample in work area are set up respectively,
And training sample and test sample will be divided into per class sand body sample；
The training sample of every class sand body sample is trained using default machine learning algorithm, corresponding sand body connection is set up
Property forecast model；
The connective forecast model of corresponding sand body is optimized according to the test sample of every class sand body sample, so that corresponding sand
Body predicting the outcome for forecast model of connectedness meets preparatory condition；
According to the connective forecast model of sand body after optimization, sand body data corresponding to sand body to be identified in the work area carry out sand
Body Connectivity Evaluation, obtains evaluation result.
2. sand body Connectivity Evaluation method as claimed in claim 1, it is characterised in that described is normalization per class sand body sample
Sand body sample.
3. sand body Connectivity Evaluation method as claimed in claim 1, it is characterised in that described is to pass through successively per class sand body sample
Cross the sand body sample obtained after normalized and dimension-reduction treatment.
4. sand body Connectivity Evaluation method as claimed in claim 1, it is characterised in that described machine learning algorithm includes branch
Hold vector machine algorithm.
5. sand body Connectivity Evaluation method as claimed in claim 3, it is characterised in that described dimension-reduction treatment passes through principal component
Parser is realized.
6. a kind of sand body Connectivity Evaluation device, it is characterised in that including：
Sample Establishing module, for setting up the cross connection sand body sample in work area, vertical communication sand body sample and interior respectively
Portion's connectedness sand body sample, and training sample and test sample will be divided into per class sand body sample；
Model building module, for being trained using default machine learning algorithm to the training sample of every class sand body sample,
Set up the connective forecast model of corresponding sand body；
Model optimization module, for being carried out according to the test sample per class sand body sample to the connective forecast model of corresponding sand body
Optimization, so that corresponding sand body predicting the outcome for forecast model of connectedness meets preparatory condition；
Model prediction module, for according to the connective forecast model of sand body after optimization, to sand body pair to be identified in the work area
The sand body data answered carry out sand body Connectivity Evaluation, obtain evaluation result.
7. sand body Connectivity Evaluation device as claimed in claim 6, it is characterised in that described is normalization per class sand body sample
Sand body sample.
8. sand body Connectivity Evaluation device as claimed in claim 6, it is characterised in that described is to pass through successively per class sand body sample
Cross the sand body sample obtained after normalized and dimension-reduction treatment.
9. sand body Connectivity Evaluation device as claimed in claim 6, it is characterised in that described machine learning algorithm includes branch
Hold vector machine algorithm.
10. sand body Connectivity Evaluation device as claimed in claim 8, it is characterised in that described dimension-reduction treatment by it is main into
Parser is divided to realize.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710376308.XA CN107330578B (en) | 2017-05-25 | 2017-05-25 | Sand body connectivity evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710376308.XA CN107330578B (en) | 2017-05-25 | 2017-05-25 | Sand body connectivity evaluation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107330578A true CN107330578A (en) | 2017-11-07 |
| CN107330578B CN107330578B (en) | 2020-07-10 |
Family
ID=60193954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710376308.XA Active CN107330578B (en) | 2017-05-25 | 2017-05-25 | Sand body connectivity evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330578B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108386185A (en) * | 2018-01-17 | 2018-08-10 | 中国石油天然气股份有限公司 | A kind of method and device of determining sand body connectivity |
| CN109324354A (en) * | 2018-08-30 | 2019-02-12 | 中国石油天然气股份有限公司 | A kind of method, apparatus and system of determining sand body connectivity |
| CN111027249A (en) * | 2019-12-10 | 2020-04-17 | 北京科技大学 | Machine learning-based inter-well connectivity evaluation method |
| CN111426813A (en) * | 2019-01-10 | 2020-07-17 | 中国石油天然气股份有限公司 | Method and device for determining sand body communication quality and storage medium |
| CN111766635A (en) * | 2019-04-02 | 2020-10-13 | 中国石油天然气股份有限公司 | Sand body communication degree analysis method and system |
| CN114594526A (en) * | 2020-12-03 | 2022-06-07 | 中国石油化工股份有限公司 | Quantitative evaluation method for inter-well plane connectivity of river facies sand body |
| CN116341925A (en) * | 2023-02-23 | 2023-06-27 | 成都理工大学 | System, method, equipment and terminal for evaluating continuity of high-quality reservoir of compact sandstone |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002092264A (en) * | 2000-09-14 | 2002-03-29 | Tokyo Electric Power Co Inc:The | Disaster prevention system for autonomous community or the like |
| CN104680244A (en) * | 2014-12-24 | 2015-06-03 | 中国石油天然气股份有限公司 | Oil and gas field production capacity prediction method and device |
| CN106405637A (en) * | 2015-07-28 | 2017-02-15 | 中国石油化工股份有限公司 | Method and system for predicting sand body thickness of thin sand-shale interbed |
| CN106485223A (en) * | 2016-10-12 | 2017-03-08 | 南京大学 | The automatic identifying method of rock particles in a kind of sandstone microsection |
-
2017
- 2017-05-25 CN CN201710376308.XA patent/CN107330578B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002092264A (en) * | 2000-09-14 | 2002-03-29 | Tokyo Electric Power Co Inc:The | Disaster prevention system for autonomous community or the like |
| CN104680244A (en) * | 2014-12-24 | 2015-06-03 | 中国石油天然气股份有限公司 | Oil and gas field production capacity prediction method and device |
| CN106405637A (en) * | 2015-07-28 | 2017-02-15 | 中国石油化工股份有限公司 | Method and system for predicting sand body thickness of thin sand-shale interbed |
| CN106485223A (en) * | 2016-10-12 | 2017-03-08 | 南京大学 | The automatic identifying method of rock particles in a kind of sandstone microsection |
Non-Patent Citations (4)
| Title |
|---|
| 栗亮等: "《基于模糊数学方法的砂体连通性评价》", 《中州煤炭》 * |
| 沈加刚等: "《基于地震属性的支持向量机河道砂体厚度预测》", 《西南石油大学学报（自然科学版）》 * |
| 王琳: "《基于支持向量机算法的数据分类验证研究》", 《四川文理学院学报》 * |
| 章琳云: "《中国核心通货膨胀的估算与预测研究》", 31 May 2016, 浙江工商大学出版社 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108386185A (en) * | 2018-01-17 | 2018-08-10 | 中国石油天然气股份有限公司 | A kind of method and device of determining sand body connectivity |
| CN108386185B (en) * | 2018-01-17 | 2022-05-06 | 中国石油天然气股份有限公司 | Method and device for determining sand body connectivity |
| CN109324354A (en) * | 2018-08-30 | 2019-02-12 | 中国石油天然气股份有限公司 | A kind of method, apparatus and system of determining sand body connectivity |
| CN111426813A (en) * | 2019-01-10 | 2020-07-17 | 中国石油天然气股份有限公司 | Method and device for determining sand body communication quality and storage medium |
| CN111766635A (en) * | 2019-04-02 | 2020-10-13 | 中国石油天然气股份有限公司 | Sand body communication degree analysis method and system |
| CN111027249A (en) * | 2019-12-10 | 2020-04-17 | 北京科技大学 | Machine learning-based inter-well connectivity evaluation method |
| CN111027249B (en) * | 2019-12-10 | 2021-02-26 | 北京科技大学 | Machine learning-based inter-well connectivity evaluation method |
| CN114594526A (en) * | 2020-12-03 | 2022-06-07 | 中国石油化工股份有限公司 | Quantitative evaluation method for inter-well plane connectivity of river facies sand body |
| CN116341925A (en) * | 2023-02-23 | 2023-06-27 | 成都理工大学 | System, method, equipment and terminal for evaluating continuity of high-quality reservoir of compact sandstone |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107330578B (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330578A (en) | Sand body Connectivity Evaluation method and device | |
| CN108010103A (en) | The quick fine generation method of river with complicated landform | |
| CN108629687A (en) | A kind of anti money washing method, apparatus and equipment | |
| US20070265815A1 (en) | Method for optimal gridding in reservoir simulation | |
| CN105467449B (en) | Deep layer Thin oil sandwich quantitatively characterizing method based on earthquake classification Sensitive Attributes fusion | |
| CN107678059A (en) | A kind of method, apparatus and system of reservoir gas-bearing identification | |
| CN110414723B (en) | Method, device and system for fracture hydrocarbon reservoir history fitting based on microseismic event | |
| Zhu et al. | Rapid identification of high-quality marine shale gas reservoirs based on the oversampling method and random forest algorithm | |
| Song et al. | Geologist-level wireline log shape identification with recurrent neural networks | |
| US20230178399A1 (en) | Systems and methods for systematic physical failure analysis (pfa) fault localization | |
| CN108829804A (en) | Based on the high dimensional data similarity join querying method and device apart from partition tree | |
| CN105096159A (en) | Method and device for predicting regional electricity sales | |
| CN109684477A (en) | A kind of patent text feature extracting method and system | |
| Liu et al. | Predictive model for water absorption in sublayers using a machine learning method | |
| Zhu et al. | Modelling spatial patterns using graph convolutional networks (short paper) | |
| Ayati et al. | Machine Learning–Assisted Model for Leak Detection in Water Distribution Networks Using Hydraulic Transient Flows | |
| CN108090656B (en) | Method and device for determining sand body connectivity | |
| SA515360901B1 (en) | A method of monitoring the behaviour of a subsurface volume | |
| Santos et al. | An artificial intelligence method for improving upscaling in complex reservoirs | |
| CN105608460A (en) | Method and system for fusing multiple classifiers | |
| CN111413731B (en) | Earthquake recognition method and device for carbonate rock fracture-cave body | |
| CN105956658A (en) | Data processing method, data processing device and chip | |
| CN104598662B (en) | The implantation method and system of circuit design | |
| Sun et al. | Optimization of models for rapid identification of oil and water layers during drilling-a win-win strategy based on machine learning | |
| Zhang et al. | An initial guess for the Levenberg–Marquardt algorithm for conditioning a stochastic channel to pressure data |
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 |