CN114943015A - Oil reservoir analogy method and device based on similarity calculation model - Google Patents

Oil reservoir analogy method and device based on similarity calculation model Download PDF

Info

Publication number
CN114943015A
CN114943015A CN202210666291.2A CN202210666291A CN114943015A CN 114943015 A CN114943015 A CN 114943015A CN 202210666291 A CN202210666291 A CN 202210666291A CN 114943015 A CN114943015 A CN 114943015A
Authority
CN
China
Prior art keywords
oil
reservoir
parameters
field
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210666291.2A
Other languages
Chinese (zh)
Inventor
宋来明
卢川
丁祖鹏
张雨晴
刘振坤
陈冠中
王帅
杨烁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Research Center of CNOOC China Ltd
CNOOC China Ltd
Original Assignee
Beijing Research Center of CNOOC China Ltd
CNOOC China Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Research Center of CNOOC China Ltd, CNOOC China Ltd filed Critical Beijing Research Center of CNOOC China Ltd
Priority to CN202210666291.2A priority Critical patent/CN114943015A/en
Publication of CN114943015A publication Critical patent/CN114943015A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/901—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9035—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/904—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/906—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Marketing (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Educational Administration (AREA)
  • Animal Husbandry (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Mining & Mineral Resources (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Agronomy & Crop Science (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to an oil reservoir analogy method based on a similarity calculation model, which comprises the following steps: establishing an oil field evaluation index by using parameters of the established capacity block, wherein the oil field evaluation index comprises a static parameter and a production dynamic parameter, and carrying out quantitative analysis on the static parameter and the production dynamic parameter to obtain an oil reservoir analog oil and gas field database; establishing a target oil field parameter table; according to the characteristics of geological oil reservoirs of target oil fields, preliminarily screening the oil fields in the oil reservoir analog oil and gas field database through multi-attribute filtering setting; taking static parameters and production dynamic parameters corresponding to the current time sequence as patterns, searching similar patterns in historical data, and performing pattern matching by using similarity to obtain a pattern matching model; predicting reservoir characteristics of the target field according to parameters of the pattern matching model. The difficulty of a similarity method is reduced, and the working efficiency is improved; the multiple methods integrate comparative analysis, and improve the accuracy of the method.

Description

Oil reservoir analogy method and device based on similarity calculation model
Technical Field
The invention relates to the field of reservoir analogy, in particular to a reservoir analogy calculation method and device based on a similarity calculation model.
Background
Because oil and gas field geological parameters, production parameters and mining parameters are various, the importance of oil reservoir characteristics under different geological conditions has different influences on production, and how to define/judge whether oil reservoirs are similar is a difficult problem.
Disclosure of Invention
In view of the above problems, the present invention provides a reservoir analogy calculation method and device based on a similarity calculation model.
In order to realize the purpose, the invention adopts the following technical scheme:
a reservoir analogy method based on a similarity calculation model comprises the following steps:
establishing an oil reservoir analog oil and gas field database: establishing an oil field evaluation index by using the parameters of the established capacity block, wherein the oil field evaluation index comprises a static parameter and a production dynamic parameter, and carrying out quantitative analysis on the static parameter and the production dynamic parameter to obtain an oil reservoir analog oil and gas field database;
establishing a target oil field parameter table: collecting geological oil reservoir characteristic parameters of a target oil field to establish a target oil field parameter table;
primary screening: according to the characteristics of geological oil reservoirs of target oil fields, preliminarily screening oil fields in an oil reservoir analog oil and gas field database through multi-attribute filtering setting, and outputting filtering results;
establishing a pattern matching model: taking static parameters and production dynamic parameters corresponding to the current time sequence as patterns, searching similar patterns in historical data, and performing pattern matching by using similarity to obtain a pattern matching model;
predicting reservoir properties of a target field: reservoir characteristics of the target field are predicted from parameters of the pattern matching model.
The static parameters include at least one of the group formed by: constructing, sedimentary facies, pressure systems, reservoir types, pore saturation, well logging curves and interpreting result data; the production dynamic parameter comprises at least one of the group formed by: daily output, cumulative output, moisture content and extraction degree.
The parameters of the established capacity block include at least one of the following: reservoir type, geological reserve, oil-bearing area, reservoir depth, permeability, and crude oil viscosity.
The reservoir analogy field database includes at least one of the following parameters: common heavy oil, thermal recovery heavy oil, permeability, fault block, fracture-cavity carbonate rock and offshore oil reservoir.
The preliminary screening comprises the steps of determining geological profiles, structural characteristics, reservoir characteristics and oil reservoir characteristics of the target oil fields, and preliminarily classifying the target oil fields according to at least one of the following standards: oil reservoirs, gas reservoirs, condensate gas reservoirs, clastic rock reservoirs, carbonate rock reservoirs, and tight sandstone reservoirs.
The preliminary screening comprises selecting filtering parameters, setting a threshold value and removing oil reservoir information outside a selection range.
Establishing a pattern matching model comprises: and setting weights for the attributes and time in the matching process, and adjusting the proportion of each parameter.
A reservoir analogy apparatus based on a similarity calculation model, comprising:
the oil reservoir analog oil and gas field database module is configured to establish oil field evaluation indexes by using parameters of the established productivity blocks, wherein the oil field evaluation indexes comprise static parameters and production dynamic parameters, and the static parameters and the production dynamic parameters are subjected to quantitative analysis to obtain an oil reservoir analog oil and gas field database;
the collection module is configured to collect the geological oil reservoir characteristic parameters of the target oil field and establish a parameter table of the target oil field;
the preliminary screening module is configured to preliminarily screen the oil fields in the oil reservoir analog oil and gas field database through multi-attribute filtering setting according to the geological oil reservoir characteristics of the target oil field and output filtering results;
the pattern matching module is configured to take the static parameters and the production dynamic parameters corresponding to the current time sequence as patterns, search similar patterns in historical data, and perform pattern matching by using similarity to obtain a pattern matching model;
a prediction module configured to predict reservoir characteristics of the target field from parameters of the phase pattern matching model.
An oil reservoir analog analysis device, comprising:
one or more processors configured to perform the above-described steps.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, performs the above-mentioned steps.
Due to the adoption of the technical scheme, the invention has the following advantages: the difficulty of the class comparison method is reduced, and the working efficiency is improved; the multiple methods integrate comparative analysis, and improve the accuracy of the method.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Like parts are designated with like reference numerals throughout the drawings. In the drawings:
FIG. 1 is a schematic diagram of a reservoir analogy method based on a similarity calculation model according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
SEC (Securities and Exchange Commission) of 1 month and 1 day 2010 formally promulgates a reservoir analogy new criterion, similar reservoirs have similar reservoir and fluid properties, reservoir conditions (depth, temperature, pressure) and driving mechanisms, but the development phase is further (development is relatively mature, and continuous development takes longer time) compared with the target reservoir. The new standards of SEC recognize the role of simulated reservoirs in evaluating the undeveloped production dynamics of newly developed reservoirs. The oil reservoir with the same or similar geological characteristics and development modes as the target oil reservoir can be searched through the oil reservoir analogy method, the oil reservoir with long development time and good development effect can be searched, and guidance is provided for the dynamic evaluation of the production of the newly-exploited oil reservoir under limited data.
The defects of the existing oil reservoir analogy method are as follows:
the similarity of oil fields is difficult to define, and the similarity degree is difficult to quantify;
when the analog parameters to be considered are more, the reservoir analog difficulty is larger;
no system is provided in China to realize the oil reservoir analogy method.
The invention establishes a set of oil reservoir analogy method and system based on a similarity calculation model, and the method and system mainly have the following characteristics:
and establishing a set of algorithm model for evaluating the similarity of the oil fields by using the similarity, realizing the sequencing of the similarity of a plurality of oil fields, and visually displaying the similarity of each oil field and the target oil field.
A set of analog parameter system is established, and ninety-six parameters can be simultaneously applied to participate in the calculation of reservoir analog similarity.
A set of oil reservoir analogy research system is formed, the oil reservoir analogy research system comprises seven oil reservoir analogy algorithm models, and synchronous calculation and comparative analysis of multiple algorithms can be realized.
The national scholars have carried out a great deal of work on the research and application of the oil field analogy method.
In 2008, the Wangchining and the like apply the analogy method to exploration of a recessed lithologic oil reservoir in the subsurface river, roughly divide an oil-gas reservoir into a structural oil reservoir and a stratum oil reservoir, and summarize three key factors as analogy indexes according to working experience of a multi-year work area, on the basis, the three key factors are focused, a peripheral 30-well is drilled on a peripheral 21-north fault-lithologic ring closure, and a high-yield industrial oil flow with the daily yield of 12.9 tons is obtained by putting a 2.4m/1 layer of the latent 3-oil group into production.
Royal haijiang et al in 2012 proposed that we should pay attention to the main factors of the analogy and the root causes affecting this factor when building the analogy model. And a reasonable mathematical calculation method is adopted, so that all factors are visualized and digitalized, and the application is convenient. After the model is established, the model needs to be checked, corrected and perfected according to the actual situation, and the model is ensured to be consistent with the actual production situation.
According to the new SEC criterion in 2013, Zhaohui combines the actual situation of the Daqing low-permeability oilfield reserve evaluation, an oil reservoir which is reliable in dynamic and static data, reasonable in water injection mode, complete in well pattern, long in development time, stable in development, good in development, strong in rule and reasonable in recovery rate evaluation is selected, and a Daqing peripheral oilfield analog library is established.
And the Yuan-based learning in 2014 and the like can formulate different analogy key parameters according to different types of oil reservoirs. For the ultra-low-permeability water injection sandstone reservoir, the air permeability, the formation crude oil viscosity, the fluidity, the porosity and the well pattern density are taken as key parameters, and main parameters such as the average single-well stable yield, the effective thickness oil-gas ratio and the like are added. When the flow of crude oil is poor, if the oil-gas ratio is high and the oil layer thickness is large, the defect can be compensated, and higher yield and recovery ratio can be obtained. That is, in evaluating the recovery factor, a correlation between various factors is noted.
In 2015, Liu Ji Yuan and the like play a positive role of a class-proportion method in the case of lack of more exploitation data in oil field production dynamic data, and are applied to the initial exploitation stage or the development of relatively mature oil reservoirs. The analogy method is applied to analogy evaluation on few data such as fluid composition, temperature, well spacing, rock physical property, driving mechanism and the like.
Luxiao in 2018 adopts more than five hundred standardized parameters to characterize the process of the mining and production dynamics of the static and different mining stages of an oil reservoir. Establishing an oil reservoir analog library, and screening analog oil reservoir samples according to the reservior sedimentary property, fluid property, energy driving mechanism and the like.
At present, no similarity-based oil reservoir analogy system exists in China.
The prior art mainly has the following defects:
the oil reservoir analogy library has more parameters and oil reservoir analogy difficulty, and the oil reservoir analogy efficiency is lower;
no system for realizing oil reservoir analogy exists in China;
the conventional analogy method cannot be popularized and applied.
The invention aims to realize multi-parameter and multi-oil-field analogy by establishing an oil reservoir analogy system and applying six oil field analogy methods based on similarity calculation models, and the oil reservoir analogy system is established according to the method, so that a large number of historical oil reservoirs similar to a newly-opened oil reservoir can be effectively and quickly screened out, and through statistical analysis of the historical oil reservoirs, the oil reservoir management method and EOR information of the whole development process and different development stages are obtained, and the production state evaluation and the production dynamic decision can be further provided for the newly-developed oil reservoir.
Oil and gas field analogy technical idea
For analogy purposes: predicting key indexes of the oil-gas well of the new block, and providing decision basis for making development indexes (productivity and recovery ratio);
analog range: fields similar to the target field (global, national);
analogy content: an oil field evaluation index system; static parameters such as structure, sedimentary facies, pressure system, oil reservoir type, reservoir physical properties (pore saturation), logging curve and interpretation result data; daily output, cumulative output, water content, extraction degree and other production dynamic parameters.
An analogy model: establishing an oil field characteristic evaluation model, establishing an oil field analogy model and establishing a development index recommendation model.
Establishing an oil field evaluation index system
The method adopts a statistical analysis method to deeply analyze related data of the oilfield productivity construction at home and abroad, thereby establishing oilfield evaluation indexes by utilizing parameters such as the type of an oil deposit, the geological reserve, the oil-bearing area, the oil deposit burial depth, the permeability, the crude oil viscosity and the like of an established productivity block, realizing qualitative analysis to quantitative analysis, and obtaining 8 types of oil deposit analog oil-gas field databases such as common heavy oil, thermal recovery heavy oil, common low permeability, ultra-low permeability, common fault blocks, complex fault blocks, fracture-cavity carbonate rocks, offshore oil deposits and the like.
Establishing an evaluation index system principle:
and realizing the conversion from the qualitative evaluation to the quantitative evaluation of the type of the oil-gas field. The research utilizes advanced computers, mathematical statistical analysis and system analysis to deeply develop, and changes from extensive type to fine type.
Systematization of
The similarity of oil and gas fields is systematically evaluated from multiple angles, multiple levels and all directions.
Science and technology
By applying advanced computer technology, the function of basic data is fully exerted, internal relation is excavated, and scientific, reliable and practical guiding basis is provided for management decision-making.
Performing main control factor analysis according to the oil field characterization parameters to establish an oil field evaluation index system:
basic parameters: reservoir type, longitudinal reservoir characteristics (basin, group, segment), planar reservoir characteristics (dephasing, subphase), depth in reservoir, geological reserves, formation pressure, formation temperature, effective reservoir thickness, etc.;
physical property parameters: porosity, core permeability, logging permeability, well testing permeability, formation crude oil viscosity, formation natural gas viscosity, crude oil volume coefficient, natural gas volume coefficient, saturation pressure, crude oil solidifying point, crude oil wax precipitation temperature and the like;
real-time parameters: bottom hole flowing pressure, oil production, gas production, oil relative density, gas relative density and the like;
capacity parameters: oil recovery index, gas recovery index, unimpeded flow, production pressure differential, and the like;
testing parameters: well testing permeability, production pressure difference, fault distance, skin factor, well storage coefficient and the like;
establishing analog oilfield screening algorithm model
Establishing a global oil reservoir digital analogy knowledge base
The method adopts a statistical analysis method to deeply analyze related data of oilfield capacity construction at home and abroad, thereby establishing oilfield evaluation indexes by using parameters such as oil deposit type, geological reserve, oil-bearing area, oil deposit burial depth, permeability, crude oil viscosity and the like of the established capacity blocks, realizing qualitative analysis to quantitative analysis, and obtaining eight types of oil deposit analog oil-gas field databases such as common heavy oil, thermal recovery heavy oil, common low permeability, ultra-low permeability, common fault blocks, complex fault blocks, fracture-cavity carbonate rocks, offshore oil deposits and the like.
The steps of primarily screening the oil fields in the oil reservoir analog oil and gas field database through multi-attribute filtering setting are as follows:
and analyzing the geological characteristics of the target oil reservoir, and knowing the oil reservoir type, the structure type and the variation range of key parameters of the target oil field.
The multi-attribute filtering parameter items are selected according to the target reservoir analysis result, and may include offshore/onshore, hydrocarbon type, reservoir type, tectonic type, sedimentary facies, and some parameters included in the target reservoir.
Setting filtering parameter screening threshold value to eliminate oil deposit information outside the selection range
And visualizing the result, and displaying the list of the oil reservoir information searched by the multi-attribute filtering.
Pattern matching model building
Pattern matching of the measures: on the basis of the data model, dynamic and static data corresponding to the current time sequence are taken as a mode, similar modes are searched in historical data, and the similarity is used for carrying out mode matching to obtain the similar modes. In the matching process, weights are set for attributes and time, the proportion of each parameter is adjusted, and the important parameters and the non-important parameters after data flattening are prevented from being in the same position.
Attribute importance degree weight: different attributes have different importance degrees, and different weight values are set to distinguish the importance degrees.
Time weight: for a period of recording, the farther the recording weight is from the time of recording to be predicted, the smaller the importance.
Oil reservoir parameter weight: in the analogy process, different oil reservoir parameters have different influence degrees on the oil reservoir similarity, and the larger the influence degree is, the larger the weight is.
Similar field recommendations
On the basis of judging the similarity of the oil fields, sorting and pushing (the similarity is from high to low) similar oil fields are carried out, the number of the pushed oil fields can be customized by a user, and all-round information of the similar oil fields can be selected and checked according to needs.
The oil field analogy accuracy evaluation index uses the similarity as the oil field analogy evaluation index. Similarity is the similarity of two things. Generally, the distance between the features of the object is calculated, and if the distance is small, the similarity is large; if the distance is large, the similarity is small.
Problem definition: there are two objects X, Y, both containing N-dimensional features, X ═ X1, X2, X3,. times, xn), Y ═ Y1, Y2, Y3,. times, yn, the similarity of X and Y is calculated.
The current oil field analog similarity algorithm has the following methods: cosine similarity, Euclidean distance, a cluster analysis method, a fuzzy matter element method and a comprehensive evaluation method.
System implementation
Oilfield evaluation index management
The function is an oil field evaluation index management module, and the addition, deletion and classification management of the analogy parameters can be realized.
Target oilfield input and settings
The oil field analogy method firstly needs to set a target oil field, namely the oil field needing development scheme design. There is a need for a preliminary understanding of the profile, formation characteristics, reservoir characteristics, fluid characteristics, etc. of the target field. And inputting the collected target oilfield data into the system as a data basis for oilfield analogy implementation.
Setting analogy system
For different oil reservoir types of oil fields, such as heavy oil sandstone, low permeability sandstone, natural gas and the like, key evaluation index systems of similar oil fields are different, so that different analogy systems need to be set. The system provides a system template and a weight setting result table. The parameter content in the analogy system can be added, deleted and modified. And reconfiguring the weight and membership function of each parameter in the system.
The weight configuration of the analogy parameters provides three configuration schemes, namely an expert scoring method, an analytic hierarchy process and a Principal Component Analysis (PCA) method. Principal Component Analysis (PCA) is one of the most commonly used dimension reduction methods, and has wide applications in data compression and redundancy elimination. The PCA method is a dimension reduction algorithm of unsupervised learning, and the purpose of dimension reduction can be realized only by calculating a covariance matrix of sample data.
Similar oil field screening
The system provides six similarity calculation model algorithms which comprise a fuzzy matter element method, an expert scoring method, an analytic hierarchy process, a PCA method, a cosine similarity method and an Euclidean distance method. The calculation results are synchronously displayed, and the user can conveniently perform comparative analysis. And simultaneously clicking any algorithm, and sequencing the oil fields from large to small according to the similarity calculated by the algorithm. Meanwhile, the calculation result can be stored.
The key innovation points of the technical scheme are as follows:
the method is used for screening six algorithms of similar oil fields. And (5) calculating the similarity of the oil fields by adopting Kmeans clustering and utilizing big data.
A parametric system for analogy is established. Including the dynamic parameters of the nine major oil reservoirs.
The application of the analytic hierarchy process in the parameter weight.
The mass data of the database is utilized, the data range is far larger than the use data range of the traditional model, the reliability is higher, and the coverage is wider.
Embodiments of the present application will be described below with reference to the accompanying drawings.
Example 1:
FIG. 1 is a schematic diagram of a reservoir analogy calculation method based on a similarity calculation model according to an embodiment of the present application. As shown in fig. 1, a reservoir analogy calculation method based on a similarity calculation model includes the following steps: s1: establishing an oil reservoir analog oil and gas field database: establishing an oil field evaluation index by using parameters of the established capacity block, wherein the oil field evaluation index comprises a static parameter and a production dynamic parameter, and carrying out quantitative analysis on the static parameter and the production dynamic parameter to obtain an oil reservoir analog oil and gas field database; s2: establishing a target oil field parameter table: collecting geological oil reservoir characteristic parameters of a target oil field to establish a target oil field parameter table; s3: primary screening: according to the characteristics of geological oil reservoirs of target oil fields, preliminarily screening the oil reservoirs by multi-attribute filtering setting in an oil-gas field database, and outputting filtering results; s4: establishing a pattern matching model: taking static parameters and production dynamic parameters corresponding to the current time sequence as patterns, searching similar patterns in historical data, and performing pattern matching by using similarity to obtain a pattern matching model; s5: predicting reservoir properties of a target field: predicting reservoir characteristics of the target field according to parameters of the pattern matching model.
Table 1 is a schematic table of an oil field evaluation index system in a reservoir analogy calculation method based on a similarity calculation model.
TABLE 1
Figure BDA0003693082780000081
According to one embodiment of the application, pattern matching model building includes data preparation, model training, and prediction processes. In the data preparation process, preprocessing the data near the total extraction well of the oil deposit data to obtain sample data so as to obtain characteristic construction data; and finding rock attributes and oiliness attributes from the well data to obtain reservoir distribution, and obtaining the reservoir distribution data represented by time through time-depth conversion. In the model training process, the obtained characteristic construction data and the time-representation reservoir distribution data are input into a labeled sample set, and model training is carried out through a classifier. In the prediction process, the data obtained by the classifier is matched with unlabeled sample data to predict the reservoir sequence.
According to one embodiment of the application, the addition, deletion and classification of the analogy parameters can be realized by carrying out classification management on the analogy parameters. The analogy parameters include but are not limited to: pump frequency, geological storage oil, hydrocarbon type, flow coefficient, volume compression coefficient, production time, gas layer temperature, oil layer temperature, injection mode, water content, acid sensitivity, stress sensitivity, test productivity, production date, well opening time, pump inlet pressure, thickness measurement, ground density, production pressure difference, fluidity, saturation pressure and the like. Classifications include, but are not limited to: fluid properties, reservoir engineering, warm-pressing systems, reservoir characteristics, formation characteristics, and the like.
According to one embodiment of the application, a profile of the target field may be entered, including: formation characteristics, reservoir characteristics, fluid characteristics, and the like. Reservoir characteristics include, but are not limited to: reservoir heterogeneity, reservoir microscopic characteristics, and the like. Reservoir heterogeneity includes, but is not limited to: coefficient of variation, sand-to-ground ratio, permeability range, slip coefficient, etc.; reservoir characteristics include, but are not limited to: throat radius, pore throat volume ratio, pore type, displacement pressure, median pressure, average reservoir thickness, effective reservoir thickness, oil saturation, and the like.
According to one embodiment of the application, different analogy systems can be set for different reservoir type oil fields. According to one embodiment of the present application, the index parameters include, but are not limited to: reserve abundance, effective thickness of the reservoir, formation crude oil density, formation crude oil viscosity, oil bearing area, effective porosity, recovery ratio, permeability, trap type, formation type, oil API gravity, surface crude oil viscosity, and the like. Oil API gravity is a measure of the density of petroleum and petroleum products produced by the American Petroleum institute (API for short).
Table 2 is an example table of parameter weight configuration results according to an embodiment of the present application.
TABLE 2
Figure BDA0003693082780000091
Table 3 is an example table of membership function configuration results according to an embodiment of the present application.
TABLE 3
Figure BDA0003693082780000092
Figure BDA0003693082780000101
According to the reservoir analogy method based on the similarity calculation model, the weight allocation calculation is performed through at least one of an expert scoring method, an analytic hierarchy process and a PCA method. According to an embodiment of the application, a reservoir analogy method based on a similarity calculation model comprises at least one of the group formed by the following methods: fuzzy matter element method, expert scoring method, analytic hierarchy process, PCA method, cosine similarity method and Euclidean distance method.
According to one embodiment of the present application, selection may be made among configuration characteristics, reserves, drive types, reservoir types, fluid properties, and the like. According to one embodiment of the application, the importance degree of each parameter in the system is scored by an expert, the score is between 0 and 1, and then the parameter scoring is normalized to obtain the weight value of each parameter in the analog system. Including but not limited to scoring the following parameters: oil area, effective porosity, reserve abundance, effective thickness of an oil layer, number of oil layers, pressure saturation difference and the like.
Table 4 is an example table of the analogy parameter weight configuration expert scoring method according to an embodiment of the present application.
TABLE 4
Figure BDA0003693082780000102
According to one embodiment of the present application, the similarity calculation model algorithm may include: fuzzy matter element method, expert scoring method, analytic hierarchy process, PCA method, cosine similarity method and Euclidean distance method. The similarity calculated according to the algorithm is sorted from large to small, and can be visually displayed by using a histogram and/or a sector graph and the like.
Table 5 is an example table of similar field screens according to embodiments of the present application.
TABLE 5
Figure BDA0003693082780000103
Figure BDA0003693082780000111
Example 2:
establishing analog oilfield screening algorithm model
(1) Establishing a global oil reservoir digital analogy knowledge base
The method adopts a statistical analysis method to deeply analyze related data of the oilfield productivity construction at home and abroad, thereby establishing oilfield evaluation indexes by utilizing parameters such as the type of an oil deposit, the geological reserve, the oil-bearing area, the oil deposit burial depth, the permeability, the crude oil viscosity and the like of an established productivity block, realizing qualitative analysis to quantitative analysis, and obtaining 8 types of oil deposit analog oil-gas field databases such as common heavy oil, thermal recovery heavy oil, common low permeability, ultra-low permeability, common fault blocks, complex fault blocks, fracture-cavity carbonate rocks, offshore oil deposits and the like.
(2) Oil field preliminary screening by applying multi-attribute filtering method
Because the global oil deposit digital analogy knowledge base comprises a large number of oil field samples at home and abroad, and a plurality of oil fields which are completely different from the basic geological characteristics of the hydrocarbon type, the oil deposit type, the deposit type and the like of a target oil field exist among the oil fields, the oil fields are mixed in the sample base, and if the oil fields participate in the calculation and screening of similar oil fields, the calculation efficiency can be influenced. Therefore, it is necessary to perform preliminary screening on the oil fields in the global reservoir analogy knowledge base by a multi-attribute filtering method before similar oil field screening.
The screening steps are as follows:
1) target field determination and data collection
The method aims to provide a primary understanding for geological profile, structural characteristics, reservoir characteristics, oil reservoir characteristics and the like of a target oil field through data collection, and can further classify the target oil field according to standards on the basis. Such as whether the field is an oil, gas or condensate reservoir; whether it is a clastic, carbonate or tight sandstone reservoir, etc.
2) Reservoir filtration parameter selection and parameter setting
By recognizing the target oil field, selecting key filtering parameters and setting the threshold value, the oil reservoir information outside the selection range can be excluded, and the purpose of primary screening is achieved.
(3) Pattern matching model building
On the basis of the data model, the dynamic and static data corresponding to the current time sequence are taken as a pattern, a similar pattern is searched in the historical data, and the pattern matching is carried out by using the similarity to obtain a pattern matching model. In the matching process, weights are set for attributes, time and similarity, the proportion of each parameter is adjusted, and the situation that important parameters and non-important parameters are the same after data flattening is prevented. Attribute importance degree weight: different attributes have different importance degrees, and different weight values are set to distinguish the importance degrees. Time weight: the longer a recording is recorded at a time, the longer the recording is from the time of the recording to be predicted, the smaller the weight is, the smaller the importance is. Similarity weight: and after pattern matching is carried out, n similar time records are obtained, similarity sorting is carried out, and the more similar weight is larger.
(4) Similar field recommendations
On the basis of oil field similarity judgment, similar analog oil field sequencing and pushing (similarity is from high to low) are carried out, the number of pushing can be customized by a user, and all-round information of the analog oil field is selected to be checked according to needs.
Evaluation index for oil field analogy accuracy
And applying the similarity as an oil field analogy evaluation index. Similarity is the similarity of two things. Generally, the distance between the features of the object is calculated, and if the distance is small, the similarity is large; if the distance is large, the similarity is small.
Problem definition: there are two objects X, Y, each containing N-dimensional features, X ═ X1, X2, X3, Y., xn), Y ═ Y1, Y2, Y3, Y, and N, the similarity between X and Y is calculated.
The oil field analog similarity algorithm has the following six methods: cosine similarity method, Euclidean distance method, fuzzy matter element method, expert scoring method, analytic hierarchy process and PCA method.
System implementation
Oilfield evaluation index management
The function is an oil field evaluation index management module, and the addition, deletion and classification management of the analogy parameters can be realized.
Target oilfield input and settings
The oil field analogy method firstly needs to set a target oil field, namely the oil field needing development scheme design. There is a need for a preliminary understanding of the profile, formation characteristics, reservoir characteristics, fluid characteristics, etc. of the target field. And inputting the collected target oil field data into the system as a data base for realizing the oil field analogy.
Preliminary screening of oil fields
Through the preliminary knowledge of the target oil field, the oil field in the knowledge base is preliminarily screened by applying a multi-attribute filtering method, so that the analogy range is further reduced, and the operation efficiency is improved.
Setting analogy system
For different oil reservoir types of oil fields, such as heavy oil sandstone, low permeability sandstone, natural gas and the like, key evaluation index systems of similar oil fields are different, so that different analogy systems need to be set. The system provides a system template and a weight setting result table. The parameter content in the analogy system can be added, deleted and modified. And reconfiguring the weight and membership function of each parameter in the hierarchy.
The technical scheme of the invention has the following effects:
a set of algorithm model application method for evaluating the similarity of the oil fields by using the similarity is established, and the similarity sequencing of a plurality of oil fields is realized by establishing a system, configuring weight and calculating the similarity, and the similarity of each oil field and a target oil field is visually displayed. Provides a foundation and method guidance for the wide application of the oil field development scheme guidance of the analogy method.
A set of analogy parameter system is established, ninety-six parameters can be simultaneously applied to participate in oil reservoir analogy similarity calculation, and custom addition and deletion of the analogy system are supported. Compared with the traditional analogy method, the difficulty of the analogy method is reduced, and the working efficiency is improved.
A set of oil reservoir analogy research system is formed, the oil reservoir analogy research system comprises six oil reservoir analogy algorithm models, and synchronous calculation and comparative analysis of multiple algorithms can be realized.
The multiple methods integrate comparative analysis, and improve the accuracy of the method.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A reservoir analogy method based on a similarity calculation model comprises the following steps:
establishing an oil reservoir analog oil and gas field database: establishing an oil field evaluation index by using parameters of the established capacity block, wherein the oil field evaluation index comprises a static parameter and a production dynamic parameter, and carrying out quantitative analysis on the static parameter and the production dynamic parameter to obtain an oil reservoir analog oil and gas field database;
establishing a target oil field parameter table: collecting geological oil reservoir characteristic parameters of a target oil field to establish a target oil field parameter table;
primary screening: according to the geological oil reservoir characteristics of a target oil field, preliminarily screening the oil fields in the oil reservoir analog oil and gas field database through multi-attribute filtering setting, and outputting filtering results;
establishing a pattern matching model: taking static parameters and production dynamic parameters corresponding to the current time sequence as patterns, searching similar patterns in historical data, and performing pattern matching by using similarity to obtain a pattern matching model;
predicting reservoir properties of a target field: predicting reservoir characteristics of the target field according to parameters of the pattern matching model.
2. The similarity computation model-based reservoir analogy method according to claim 1, wherein the static parameters comprise at least one of the group formed by: constructing, sedimentary facies, pressure systems, reservoir types, pore saturation, well logging curves and interpreting result data; the production dynamic parameter comprises at least one of the group formed by: daily output, cumulative output, moisture content and extraction degree.
3. The method of claim 1, wherein the parameters of the established capacity blocks comprise at least one of: reservoir type, geological reserve, oil bearing area, reservoir depth, permeability, and crude oil viscosity.
4. The reservoir analogy method based on the similarity computation model of claim 1, wherein the reservoir analogy field database comprises at least one of the following parameters: common heavy oil, thermal recovery heavy oil, permeability, fault block, fracture-cavity carbonate rock and offshore oil reservoir.
5. The method of similarity computation model-based reservoir analogy of claim 1, wherein the preliminary screening comprises determining geological profiles, tectonic features, reservoir features and reservoir features of a target field, and preliminarily classifying the target field according to at least one of the following criteria: oil reservoirs, gas reservoirs, condensate gas reservoirs, clastic rock reservoirs, carbonate rock reservoirs, and tight sandstone reservoirs.
6. The reservoir analogy method based on the similarity computation model of claim 5, wherein the preliminary screening comprises selecting filtering parameters and performing threshold setting to exclude reservoir information outside a selection range.
7. The reservoir analogy method based on the similarity calculation model according to claim 1, wherein the establishing a pattern matching model comprises: and setting weights for the attributes and time in the matching process, and adjusting the proportion of each parameter.
8. A reservoir analogy device based on a similarity calculation model is characterized by comprising:
the oil reservoir analog oil and gas field database module is configured to establish an oil field evaluation index by using parameters of an established capacity block, wherein the oil field evaluation index comprises a static parameter and a production dynamic parameter, and the static parameter and the production dynamic parameter are subjected to quantitative analysis to obtain an oil reservoir analog oil and gas field database;
the collection module is configured to collect the geological oil deposit characteristic parameters of the target oil field and establish a target oil field parameter table;
the preliminary screening module is configured to preliminarily screen the oil fields in the oil reservoir analog oil and gas field database through multi-attribute filtering setting according to the geological oil reservoir characteristics of the target oil field and output filtering results;
the pattern matching module is configured to take the static parameters and the production dynamic parameters corresponding to the current time sequence as patterns, search similar patterns in historical data, and perform pattern matching by using similarity to obtain a pattern matching model;
a prediction module configured to predict reservoir characteristics of the target field from parameters of the pattern matching model.
9. An oil reservoir analog analysis device, comprising:
one or more processors configured to perform the steps recited in any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of any of claims 1-7.
CN202210666291.2A 2022-06-14 2022-06-14 Oil reservoir analogy method and device based on similarity calculation model Pending CN114943015A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210666291.2A CN114943015A (en) 2022-06-14 2022-06-14 Oil reservoir analogy method and device based on similarity calculation model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210666291.2A CN114943015A (en) 2022-06-14 2022-06-14 Oil reservoir analogy method and device based on similarity calculation model

Publications (1)

Publication Number Publication Date
CN114943015A true CN114943015A (en) 2022-08-26

Family

ID=82909149

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210666291.2A Pending CN114943015A (en) 2022-06-14 2022-06-14 Oil reservoir analogy method and device based on similarity calculation model

Country Status (1)

Country Link
CN (1) CN114943015A (en)

Similar Documents

Publication Publication Date Title
Huang et al. Well performance prediction based on Long Short-Term Memory (LSTM) neural network
CN110674841B (en) Logging curve identification method based on clustering algorithm
CN104747185A (en) Heterogeneous reservoir stratum synthetic classifying evaluation method
Zhu et al. Rapid identification of high-quality marine shale gas reservoirs based on the oversampling method and random forest algorithm
CN105760673A (en) Fluvial facies reservoir earthquake sensitive parameter template analysis method
CN108732620A (en) A kind of non-supervisory multi-wave seismic oil and gas reservoir prediction technique under supervised learning
He et al. Shale gas production evaluation framework based on data-driven models
Lu et al. Lithology identification using graph neural network in continental shale oil reservoirs: A case study in Mahu Sag, Junggar Basin, Western China
CN112576238B (en) System, method and application for determining position and content of residual oil in low-permeability reservoir
CN114117881A (en) Sand production risk prediction method and system
CN113283180A (en) K-means and SVR combination-based tight reservoir horizontal well fracturing productivity prediction method and application
CN105005712A (en) Method for evaluating water yield property of limestone aquifer
CN113033648A (en) Method for realizing logging interpretation by using machine learning algorithm
CN115438823A (en) Borehole wall instability mechanism analysis and prediction method and system
Purbey et al. Machine learning and data mining assisted petroleum reservoir engineering: a comprehensive review
CN114635682A (en) Multi-layer commingled production capacity prediction method based on shaft multi-permeability coupling
Wei et al. Characterization of saturation and pressure distribution based on deep learning for a typical carbonate reservoir in the Middle East
Feng et al. Interpretable Lost Circulation Analysis: Labeled, Identified, and Analyzed Lost Circulation in Drilling Operations
Mutalova et al. Machine learning on field data for hydraulic fracturing design optimization
Abbas et al. Unsupervised machine learning technique for classifying production zones in unconventional reservoirs
Wang et al. The integrated geosciences and engineering production prediction in tight reservoir based on deep learning
CN114943015A (en) Oil reservoir analogy method and device based on similarity calculation model
Huang et al. Quantitative analysis of the main controlling factors of oil saturation variation
Ma et al. Design and development of intelligent well logging interpretation system
CN113627640A (en) Productivity well testing prediction method and system for fracture-cavity type oil reservoir oil and gas well

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