CN104881435B - A kind of research process automation logging evaluation expert system based on data mining - Google Patents
A kind of research process automation logging evaluation expert system based on data mining Download PDFInfo
- Publication number
- CN104881435B CN104881435B CN201510223200.8A CN201510223200A CN104881435B CN 104881435 B CN104881435 B CN 104881435B CN 201510223200 A CN201510223200 A CN 201510223200A CN 104881435 B CN104881435 B CN 104881435B
- Authority
- CN
- China
- Prior art keywords
- data
- research
- node
- logging
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The present invention provides a kind of research process automation logging evaluation expert systems based on data mining, belong to geophysical well logging technology field.The present invention includes data meta-model storehouse, classical knowledge base, artificial intelligence knowledge base, user's application interface module, regional study module and processing interpretation and evaluation module, data mining technology is combined with traditional logging evaluation technology, the classical knowledge base model and artificial intelligence knowledge base of Establishing process automation, for user carry out the quick logging evaluation of block provide in real time, comprehensively flow guiding with expert's technical support, realization process automation logging evaluation expert system.
Description
Technical field
The present invention relates to geophysical well logging technology field, specifically a kind of research flow based on data mining is certainly
Dynamicization logging evaluation expert system.
Background technology
With deepening constantly for offshore exploration development, the existing external log interpretation system introduced is more and more inadaptable
The complex hydrocarbons such as increasing " three-lows ", high thermal, non-hydrocarbons layer evaluates well log interpretation proposed technological challenge.
Log data data type is various, more and more with the quantity of well-digging, and data separate storage in the database, counts
It is not interrelated according to, and when regional evaluation and research is done, it is necessary to comprehensive various data and the various data of extraction it
Between implication relation, go to search by manual operation and carry out a required basic data of research and not only need rich experiences,
And it takes, leakiness, fallibility.
The experience for combining rock physics data and the expert that logs well accumulates for many years is needed when doing well logging rock physics research, it will
Specific experience " plate ", the perceptual recognition and region experience become in expert's brains are recognized into the rationality in researcher's real work
Know so that researcher is model selects, parameter determines etc. to reduce interference from human factor to greatest extent during well log interpretations.
Regional historical data is needed to refer in the process that processing explanation is carried out to well data, including logging data, formation testing number
According to this and Production development data, analyzed by artificial contrast, reduce explanation efficiency, and the instrument of data mining can be according to going through
History data automatically extracts valuable historical summary, realizes automatic identification.
In regional study, some summarized for many years by the expert that logs well study flows, do not form system, for new hand not
Can quick left-hand seat, so need one can according to research contents, automatically determine research flow system.
Current data digging method used in the industry does not combine with expert knowledge library, and traditional logging evaluation
The method that method is not bound with data mining again lacks data mining and expertise intersecting the cyberneticist combined
System.
The content of the invention
The present invention using integration data meta-model storehouse, the content of meta-model library management include Professional Model, logical model,
Physical model；Data listings data is excavated；By the input data type of default polyalgorithm node respectively with the metadata
In input data type matched, determine the algorithm node of successful match；According to default node relationships table, recursive lookup
Each the algorithm node of successful match is all preceding to node and backward node, determines the calculation with each successful match respectively
Corresponding multiple data mining paths of method node optimize using human-computer interaction and establish research flow；According to default flow
Node algorithm parameter template is automatically performed corresponding research work；Such as carry out automation well logging " lithology-electrically-physical property-oil-containing
Property " relation research；Reservoir effective thickness lower limit research etc.；Above-mentioned each achievement in research enters classical knowledge base in expert knowledge library
System provides processing model and parameter for tradition logging evaluation, and division has automatically under the guide of knowledge base effective thickness lower limit
Imitate reservoir（The sub- patent of this project）；To the individual layer of AUTOMATIC ZONING, surveyed, surveyed using the actual well logging gas in Data Mining Tools combination oil field
Pressure measurement, formation testing and storage facility located at processing plant are tried, automatically generating multi-method using association analysis, cluster analysis, neural network method intersects, parallel
Contrast verification oil-gas layer identification conclusion, effectively improve hydrocarbon zone interpretation evaluation precision, and by human-computer interaction connection lay down a definition into
One step improves difficult layer and explains reliability.System, which is combined together, to be provided in real time for user's progress quick logging evaluation of block
Ground, comprehensively flow guiding and expert's technical support.
In order to solve the above technical problems, the present invention provides a kind of research process automation Logging Evaluations based on data mining
Valency expert system, including In Oil Field Exploration And Development database, integration data meta-model storehouse, user's application interface module, region is ground
Study carefully module and interpretation and evaluation module, wherein：
The content of meta-model library management includes：Professional Model, logical model, physical model；
User's application interface module realizes the importing of data, user interactive, algorithm flow man-machine interactively and visual
The effect of change is shown；
Regional study module realizes that four sexual intercourse research of region, reservoir parameter automation research, effective thickness lower limit are ground
Study carefully, fluid identification research, litho-electric parameters research, lower limit sensitivity analysis, regional study provides technology for interpretation and evaluation module
It supports；
Interpretation and evaluation module realizes that Automatic interpretation and man-machine interactively are explained, Automatic interpretation is by regional study achievement
The artificial intelligence knowledge base that the classical knowledge base and data digging method established are established calls engine automatic by knowledge
It realizes fluid identification of reservoir, and two results is compared, cross validation, more technology branch are provided for the evaluation of well data interpretation
It holds；And explain that personnel are modified Automatic interpretation result by man-machine interactively mode according to confidence level, while interpretation and evaluation
Module realizes Real-time Feedback to regional study again.
As the preferred embodiment of this programme, the method for building up of the classical knowledge base is as follows：
1. the sources numbers such as assay data, well logging firsthand information, the dynamic static data of exploration are extracted from basic database
According to；According to default expert's research contents and flow in Professional Model in data meta-model storehouse and logical model, algorithm section is established
Point matching list, algorithm node and research flow relation table, research flow plate and its relation table；
2. the correlation rule between logging program and core data is established using Data Mining Tools, by correlation rule and in advance
If polyalgorithm node matched, determine the algorithm node of successful match, formation algorithm node matching table is included in table
Critical field has:Node ID, node index, search range, algorithm node, algorithm description；
3. according to default node relationships table, the algorithm node of recursive lookup to each successful match it is all before to section
Point and backward node determine more research flows corresponding with the algorithm node of each successful match respectively.Formation algorithm
Node has with studying flow relation table, the critical field included in table：Node ID, node index, search range, flow section
Point, flow algorithm description；
4. using data mining algorithm instrument, created according to default node parameter and flowed with the multiple data mining research
The corresponding multiple automation knowledge research flows of journey.Establish logging program and rock core assay (A) and algorithm node matching mould
Block (B), algorithm flow (R), the correlation rule of algorithm template (L)：A—>B—>R—>L、A—>B、A—>R、B—>R、B—>
L、R—>L；
5. man-machine interactively is confirmed and is corrected to the correlation rule of foundation and by the algorithm flow that correlation rule is established,
And be put in storage the rule and flow of foundation, it is established using Data Mining Tools between algorithm node and research flow and flow plate
Correlation rule, formation algorithm node, research flow with research flow plate relation table, the critical field wherein included in table
Have：Node ID, node index, search range, template type, template description；
6. by process（5）Chart and model of research needs etc. can be generated automatically according to template, may be selected to know into classics
Know in storehouse and preserve, explain that research is called for logging data processing.
As the preferred embodiment of this programme, the method for building up of the artificial intelligence knowledge base is as follows：
Go out 1. extracting test, formation testing, pressure measurement sampling and Production development data etc. from basic database and having proven to stratum
Oil, water outlet information data；
2. the data of pair extraction carry out online analysis and processing, ensure the quality and integrality of data；
3. using the statistical analysis of data mining, association analysis, neural network method, cluster analysis to the data of extraction
It is analyzed, according to the classification of knowledge, the individual layer automatic modeling to AUTOMATIC ZONING such as lithology is divided in region-by-region, layering position, and to building
Mould result carries out Confidence Analysis；
4. by knowledge acquisition card, knowledge acquisition is carried out to the knowledge model of foundation, forms artificial intelligence knowledge base.
As the preferred embodiment of this programme, the artificial intelligence knowledge base and classical knowledge base are called by knowledge
Engine is called automatically by upper layer application, and knowledge base is applied to fluid identification, logging data processing is explained, effective reservoir division.
As the preferred embodiment of this programme, the knowledge calls engine, possesses and is manually entered Keywords matching calling
And flow calls two big functions automatically.
As the preferred embodiment of this programme, the logging program excavates module according to logging program in database purchase
Data, the correlation rule of logging program is established using a variety of data digging methods such as cluster analysis and model tree, realizes user
Input keyword is inquired about, and provides association for the generation of subsequent automatic flow.
As the preferred embodiment of this programme, the rock core laboratory analysis of data excavates module according to core experiment analysis
With reference to logging program, core data correlation rule is set up by using data digging method for data.
As the preferred embodiment of this programme, the algorithm node matching module is defeated by default polyalgorithm node
Enter, output data type respectively in the metadata input, output data type matched, determine the calculation of successful match
Method node.
As the preferred embodiment of this programme, the field exploration and development database, storage content covers Geophysical-chemical, bores
Well, well logging, well logging, oil and gas well testing, analytical test, stratigraphy study, tectonic cycle period, Evaluation of source rocks research, evaluating reservoir, lid
Layer research, evaluation of trap, oil-gas migration research, reservoir-forming study, the design of prospect pit well location, reserves management, hydrocarbon reservoir evaluation, oil reservoir are opened
Send out pre feasibility study, oil reservoir development feasibility study, ODP design and implementations, development well design, Reservoir Development dynamic analysis
With adjustment, oil recovery and injection production management, underground work, dynamic monitoring, using integration data meta-model library management, number is realized
According to integrated management and shared service.
One or more technical solutions provided herein, at least have the advantages that：
Data mining technology is combined with traditional logging evaluation technology, the classical knowledge base mould of Establishing process automation
Type and artificial intelligence knowledge base, for user carry out the quick logging evaluation of block provide in real time, comprehensively flow guiding with specially
Family's technical support, realization process automation logging evaluation expert system.
Description of the drawings
It in order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this hair
Some bright embodiments, for those of ordinary skill in the art, without having to pay creative labor, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the system construction drawing of the embodiment of the present application.
Specific embodiment
In order to better understand the above technical scheme, in conjunction with appended figures and specific embodiments to upper
Technical solution is stated to be described in detail.
Embodiment 1
As shown in Figure 1, a kind of research process automation logging evaluation expert system based on data mining, is surveyed including oil field
Visit exploitation database, classical knowledge base, artificial intelligence knowledge base, user's application interface module, regional study module and explanation
Evaluation module, wherein：
User's application interface module realizes the importing of data, user interactive, algorithm flow man-machine interactively and visual
The effect of change is shown.
Regional study module, realize region in four sexual intercourse researchs, reservoir parameter automation research, effective thickness lower limit
Research, fluid identification research, litho-electric parameters research, lower limit sensitivity analysis etc., regional study provides for interpretation and evaluation module
Technical support.
Interpretation and evaluation module realizes that Automatic interpretation and man-machine interactively are explained, Automatic interpretation is by regional study achievement
The artificial intelligence knowledge base that the classical knowledge base and data digging method established are established calls engine automatic by knowledge
It realizes fluid identification of reservoir, and two results is compared, cross validation, more technology branch are provided for the evaluation of well data interpretation
It holds；And it explains personnel and Automatic interpretation result is modified by man-machine interactively mode according to confidence level.Interpretation and evaluation simultaneously
Module realizes Real-time Feedback to regional study again.
Evaluating expert system technology route is：
A kind of research process automation logging evaluation expert system based on data mining, including man-machine interactively data mining
Two technology paths of technology and artificial intelligence automatic technology combined with expertise knowledge, wherein：
The technology path that man-machine interactively data mining is combined with expertise knowledge, the route are built by data digging method
The correlation rule of logging program, rock core laboratory analysis of data etc. and expertise algorithm node is erected, while passes through data mining
Algorithm establishes the correlation rule between expertise algorithm node and flow template, parameterized template, drawing template.By walking above
Suddenly knowledge study on classics flow is set up, such as four sexual intercourse, reservoir parameter automation research, the research of effective thickness lower limit, fluid
Flow is studied in Study of recognition, litho-electric parameters research, lower limit sensitivity analysis etc., realizes the foundation of classical knowledge base model.
Artificial intelligence automatic technology, using data mining algorithm from test data, formation testing data and Production development number
The automatic learning knowledge in, and the knowledge model learnt is acquired storage, form artificial intelligence knowledge base.
The classical knowledge base and artificial intelligence database established according to two technology paths are drawn by unified knowledge calling
Calling, the two cross-application are held up, cross validation is realized and is combined expertise with the artificial intelligence technology automated, and will
It is applied in the applications such as logging data processing and explanation, fluid identification of reservoir, computing permeability, so as to establish research process automation
Logging evaluation expert system.
Evaluate expert system data source：
Exploration-development integration database of the data from oily company large size, covers physical prospecting, drilling well, well logging, well logging, oil gas
Well test, analytical test, stratigraphy study, tectonic cycle period, Evaluation of source rocks research, evaluating reservoir, cap rock research, evaluation of trap,
Oil-gas migration research, reservoir-forming study, the design of prospect pit well location, reserves management, hydrocarbon reservoir evaluation, oil reservoir development pre feasibility study,
Oil reservoir development feasibility study, ODP design and implementations, development well design, Reservoir Development dynamic analysis and adjustment, oil recovery and note
Enter production management, underground work, dynamic monitoring etc., there are in unified hub database.
Evaluate expert system data management：
The management of data source uses integration data meta-model storehouse, including Professional Model, logical model, physical model, throwing
Shadow model, implementation model management, Data Migration, data safety, data access, data general-purpose are inquired about, using functions such as supports, built
Be based on the data service of data service platform.
Expert system data source is evaluated to arrange and screen：
Evaluation system combination data digging method and expertise knowledge are realized, it is therefore desirable to data source arrange and
Screening, such as when establishing fluid identification of reservoir data mining model, it is necessary to select the data that formation testing is verified as training
Sample；When establishing the correlation rule of logging program and algorithm node, it is necessary to ensure the integrality and reliability of data.
Expert system is evaluated, classics knowledge base model therein includes the step of foundation：
The data sources such as logging program, rock core laboratory analysis of data are screened from database and are screened；
Algorithm node table is established according to expertise knowledge；
Research flow concordance list is established according to expertise knowledge；
Parameterized template, drawing template and algorithm template are established according to expertise knowledge, such as " four property " relation of logging well,
The research of well logging reserves research associated reservoir parameter automatization, the research of effective thickness lower limit, fluid identification research, litho-electric parameters are ground
Study carefully, the templates such as effective thickness lower limit sensitivity analysis；
Establish the relation table of logging program and algorithm node；
Establish the relation table of rock core laboratory analysis of data and algorithm node；
Algorithm node is established with studying the relation table of flow；
Establish the relation table between algorithm node, research flow and template；
The correlation rule of logging program and algorithm node is established using Data Mining Tools；
The correlation rule of rock core laboratory analysis of data and algorithm node is established using Data Mining Tools；
Algorithm node is established with studying the correlation rule of flow using Data Mining Tools；
The correlation rule between algorithm node and template is established using Data Mining Tools；
The correlation rule between research flow and template is established using Data Mining Tools；
It establishes from logging program, rock core laboratory analysis of data, curve data to algorithm node, grind using Data Mining Tools
The integral automation for studying carefully flow to template library studies flow；
It gathers at the correlation rule of foundation and all kinds of Well Data Processing model formations of foregoing schemes generation, well logging
Understanding releases the storage such as key parameter into database, classical knowledge base model is established, when being provided with rear region research and new exploration areas
With reference to utilization.
Expert system is evaluated, artificial intelligence knowledge base therein includes the step of foundation：
It is screened and is arranged to AUTOMATIC SORTING IN LAYERS BY WELL-LOGGING CURVES, and to individual-layer data；
On the basis of log effective reservoir divides explanation automatically, to the existing test oil test data of research block, survey
The pressure data such as sampling data and oil field Production development information are excavated, and pass through statistical analysis, association analysis, neutral net side
Method, clustering method etc., according to the classification of knowledge, region-by-region, layering position, point lithology divide the list to AUTOMATIC ZONING such as thickness
Layer automatic modeling；And Confidence Analysis is carried out to modeling result, storage is acquired after human-computer interaction, establishes artificial intelligence
Knowledge base.
Artificial intelligence knowledge and classical knowledge are established into knowledge base by knowledge acquisition.
Evaluate expert system, wherein man-machine interactively explanation：
For the research flow that automation is established, if it is less consistent with researcher's demand, pass through man-machine interactively
Mode, supervised learning until meeting the requirements, are evaluated for well data interpretation, compare classical knowledge base model and artificial intelligence
Two kinds of explanation results of knowledge base, by inconsistent local man-machine interactively amendment.
Illustrate application flow and application effect by taking effective reservoir evaluation of logging well as an example：
During Well Data Processing, engine is called by knowledge, automatic call in classical knowledge base handles model, such as saturation degree
The model of calculating needs and wherein key parameter, such as a b m n litho-electric parameters；A well has handled rear, it is necessary to effectively be stored up
The division of layer and fluid properties judge, during to this flow, system automatic start layering value module, and quote classical knowledge base
Middle effective thickness lower limit divides effective reservoir automatically, and forms quantification well log interpretation achievement chart；
It is explained according to keyword evaluating reservoir and is forwardly and rearwardly searched in knowledge base, recurrence finds matched algorithm
Node and algorithm flow.
Shale content, porosity, water saturation, permeability etc. are calculated according to matched algorithm node.
Recursive search Reservoir Parameter Research model, acquisition in classical knowledge base model according to keywords such as region, layer groups
Effective thickness lower limit studies parameter.
According to effective thickness lower limit parameter, layering value submodule divides effective reservoir automatically.
It is automated according to matched algorithm flow and obtains evaluating reservoir explanation template visualization display evaluation result, the above are
The quantitative logging data processing of a set of classics explains flow.
Well logging expert carries out man-machine interactively amendment, while can play back interpretation and evaluation according to the evaluation result of above-mentioned flow
Knowledge model in flow if the flow automatically generated is unsatisfactory for requiring, is formulated by man-machine interactively and explains flow.
Meanwhile when carrying out quantitative effective reservoir division to oil, gas and water layer, well logging scholar is frequently run onto some effective
Reservoir near lower thickness limit standard, the explanation of these layers cannot simply go to judge fluid properties according to lower limit standard, even more need
Substantial amounts of theoretical foundation and region is wanted to put into practice, by the assurance degree to all kinds of data of local area particular problem is gone to make a concrete analysis of, this
Sample utilizes knowledge base and Data Mining Tools, it is possible to play a role, the system is provided for using artificial intelligence and knowledge base
Carry out the function of qualitative well log interpretation evaluation；
To well logs section, thickness is divided to carry out data Classification Management.
According to well-log information affiliated area, all models of the affiliated area in artificial intelligence knowledge base are obtained.
According to the corresponding model of the acquisitions such as the contained interval of well-log information, thickness in acquired model.
According to the model of acquisition, corresponding well-log information, automatic decision fluid type of reservoir through, and calculating results are inputted
Confidence level.
Quantification interpretation and evaluation result and the qualitative solution of data mining artificial intelligence knowledge base under classical knowledge base is guided
It releases evaluation result and carries out Comprehensive Correlation.
According to the result cross validation of the two, for the inconsistent evaluation result of conclusion, implement man-machine interactively evaluation, complete
Effective reservoir evaluation.
The above described is only a preferred embodiment of the present invention, not make limitation in any form to the present invention, though
So the present invention is demonstrated as above with preferred embodiment, however is not limited to the present invention, any to be familiar with this professional technology people
Member, without departing from the scope of the present invention, you can make a little change or modification using the technology contents of the disclosure above
For the equivalent embodiment of equivalent variations, as long as being the content without departing from technical solution of the present invention, technical spirit according to the invention
To any simple modification, equivalent change and modification that above example is made, in the range of still falling within technical solution of the present invention.
Claims (10)
1. a kind of research process automation logging evaluation expert system based on data mining, it is characterised in that：Including data element
Model library, classical knowledge base, artificial intelligence knowledge base, user's application interface module, regional study module and processing are explained and commented
Valency module, wherein：
The content of meta-model library management includes：Professional Model, logical model, physical model；
User's application interface module realizes that data import, user interactive, algorithm flow man-machine interactively and visual effect
Fruit shows；
Regional study module realizes four sexual intercourse research of region, reservoir parameter automation research, the research of effective thickness lower limit, stream
Body Study of recognition, litho-electric parameters research, lower limit sensitivity analysis, regional study can form classical knowledge base, explain and comment for processing
Valency module provides key parameter, model supports；
Interpretation and evaluation module is handled, realizes that automatic business processing is explained and man-machine interactively is explained, automatic business processing, which is explained, utilizes warp
Allusion quotation knowledge base and artificial intelligence knowledge base call engine to realize logging data processing explanation and fluid identification automatically by knowledge, and will
As a result compared, cross validation, explained for the processing of well data and technical support is provided；And it explains personnel and passes through people according to confidence level
Work interactive mode is modified Automatic interpretation result；Interpretation and evaluation module is again realized regional study knowledge base real-time simultaneously
Feedback.
2. a kind of research process automation logging evaluation expert system based on data mining according to claim 1,
It is characterized in that：The method for building up of the classical knowledge base is as follows：
（1）Assay data, well logging firsthand information, exploration sound state data source data are extracted from basic database；Foundation
Default expert's research contents and flow in Professional Model and logical model in data meta-model storehouse, establish algorithm node matching
Table, algorithm node and research flow relation table, research flow plate and its relation table；
（2）Establish the correlation rule between logging program and core data using Data Mining Tools, by correlation rule with it is default
Polyalgorithm node is matched, and determines the algorithm node of successful match, formation algorithm node matching table, the key included in table
Field has:Node ID, node index, search range, algorithm node, algorithm description；
（3）According to default node relationships table, the algorithm node of recursive lookup to each successful match it is all before to node and
Backward node determines more research flows corresponding with the algorithm node of each successful match respectively, formation algorithm node
With studying flow relation table, the critical field included in table has：Node ID, node index, search range, flow nodes, stream
Journey algorithm description；
（4）Using data mining algorithm instrument, created according to default node parameter and study flow with the multiple data mining
Corresponding multiple automation knowledge research flows, establish logging program and rock core assay (A) and algorithm node matching module
(B), algorithm flow (R), the correlation rule of algorithm template (L)：A—>B—>R—>L、A—>B、A—>R、B—>R、B—>L、
R—>L；
（5）Man-machine interactively confirmed and corrected to the correlation rule of foundation and by the algorithm flow that correlation rule is established, and
By rule and the flow storage of foundation, established using Data Mining Tools between algorithm node and research flow and flow plate
Correlation rule, with research flow plate relation table, the critical field wherein included in table has for formation algorithm node, research flow：
Node ID, node index, search range, template type, template description；
（6）By process（5）Chart and model that research needs can be generated automatically according to template, may be selected into classical knowledge base
It preserves, explains that research is called for logging data processing.
3. a kind of research process automation logging evaluation expert system based on data mining according to claim 1,
It is characterized in that：The method for building up of the artificial intelligence knowledge base is as follows：
（1）Test is extracted from basic database, formation testing, pressure measurement sampling and Production development data have proven to that stratum is fuel-displaced, goes out
Water information data；
（2）Online analysis and processing is carried out to the data of extraction, ensures the quality and integrality of data；
（3）The data of extraction are carried out using the statistical analysis of data mining, association analysis, neural network method, cluster analysis
Analysis, according to the classification of knowledge, region-by-region, layering position divide the individual layer automatic modeling to AUTOMATIC ZONING such as lithology, and modeling are tied
Fruit carries out Confidence Analysis；
（4）By knowledge acquisition card, knowledge acquisition is carried out to the knowledge model of foundation, forms artificial intelligence knowledge base.
4. a kind of research process automation logging evaluation expert system based on data mining according to claim 1,
It is characterized in that：The artificial intelligence knowledge base and classical knowledge base, call engine to be called automatically by upper layer application by knowledge,
Knowledge base is applied to fluid identification, logging data processing is explained, effective reservoir division.
5. a kind of research process automation logging evaluation expert system based on data mining according to claim 4,
It is characterized in that：The knowledge calls engine, possesses and is manually entered Keywords matching calling and flow two big work(of calling automatically
Energy.
6. a kind of research process automation logging evaluation expert system based on data mining according to claim 2,
It is characterized in that：The logging program excavate module according to logging program database purchase data, using cluster analysis and
A variety of data digging methods such as model tree establish the correlation rule of logging program, realize that user inputs keyword and inquired about, and
Association is provided for the generation of subsequent automatic flow.
7. a kind of research process automation logging evaluation expert system based on data mining according to claim 2,
It is characterized in that：The rock core laboratory analysis of data excavates module according to core experiment analysis data, with reference to logging program, passes through
Core data correlation rule is set up using data digging method.
8. a kind of research process automation logging evaluation expert system based on data mining according to claim 2,
It is characterized in that：The algorithm node matching module by the input of default polyalgorithm node, output data type respectively with
Input, output data type in metadata are matched, and determine the algorithm node of successful match.
9. a kind of research process automation logging evaluation expert system based on data mining according to claim 1,
It is characterized in that：The generation of the data mining research flow, according to default node relationships table, recursive lookup to each matching
All front nodal points and posterior nodal point of successful algorithm node are determined respectively corresponding to the algorithm node with each successful match
Multiple data mining paths；And the multiple data digging flow is determined according to verification result and default assessment rule, it looks for
Flow is excavated to optimal data.
10. a kind of research process automation logging evaluation expert system based on data mining according to claim 1,
It is characterized in that：By data mining mathematical tool, realize that artificial intelligence is organically combined with expertise knowledge；By artificial intelligence with
Expertise knowledge, which combines, establishes automation research flow, establishes classical knowledge base；Learn automatically using data mining simultaneously
Mechanism is excavated and learnt to well logging information storehouse, is gathered model of mind, is established artificial intelligence knowledge base, and the two carries out parallel,
It influences each other again, cross-application, cross validation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510223200.8A CN104881435B (en) | 2015-05-05 | 2015-05-05 | A kind of research process automation logging evaluation expert system based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510223200.8A CN104881435B (en) | 2015-05-05 | 2015-05-05 | A kind of research process automation logging evaluation expert system based on data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104881435A CN104881435A (en) | 2015-09-02 |
| CN104881435B true CN104881435B (en) | 2018-05-25 |
Family
ID=53948929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510223200.8A Active CN104881435B (en) | 2015-05-05 | 2015-05-05 | A kind of research process automation logging evaluation expert system based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104881435B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11900070B2 (en) | 2020-02-03 | 2024-02-13 | International Business Machines Corporation | Producing explainable rules via deep learning |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105443122B (en) * | 2015-12-28 | 2019-01-18 | 中国石油天然气股份有限公司 | A kind of processing method and processing device of log interpretation model |
| US10990882B2 (en) * | 2017-07-28 | 2021-04-27 | International Business Machines Corporation | Stratigraphic layer identification from seismic and well data with stratigraphic knowledge base |
| CN109841285B (en) * | 2017-11-28 | 2021-01-08 | 北京市眼科研究所 | Clinical research collaboration system and method |
| CN108802816A (en) * | 2018-04-11 | 2018-11-13 | 中石化石油工程技术服务有限公司 | Urban underground space exploitation method and system |
| CN109508880A (en) * | 2018-11-12 | 2019-03-22 | 西南石油大学 | Cementing quality appraisal procedure based on ontology |
| CN109558393B (en) * | 2018-11-28 | 2023-08-22 | 中国海洋石油集团有限公司 | Data model construction method, device, equipment and storage medium |
| CN109611087B (en) * | 2018-12-11 | 2021-10-08 | 中国石油大学(北京) | Volcanic oil reservoir parameter intelligent prediction method and system |
| CN111472751B (en) * | 2019-12-27 | 2020-11-13 | 北京国双科技有限公司 | Logging interpretation method, knowledge graph construction method and related device |
| CN112084553A (en) * | 2020-08-06 | 2020-12-15 | 重庆市市政设计研究院有限公司 | Surveying method for tunnel planning |
| CN113722358B (en) * | 2021-08-20 | 2023-11-17 | 河北环鼎石油设备有限责任公司 | Large file playback algorithm, system and device for pump-out logging mode |
| CN117273411B (en) * | 2023-11-23 | 2024-02-02 | 杨凌职业技术学院 | Agricultural information service system based on agricultural big data management |
| CN117406972B (en) * | 2023-12-14 | 2024-02-13 | 安徽思高智能科技有限公司 | RPA high-value flow instance discovery method and system based on fitness analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101145235A (en) * | 2007-06-29 | 2008-03-19 | 中国石化集团胜利石油管理局 | Oil field development decision-making system |
| CN101630161A (en) * | 2009-08-05 | 2010-01-20 | 北方工业大学 | Intelligent system for complex industrial production and construction method thereof |
| CN102830441A (en) * | 2012-05-16 | 2012-12-19 | 陶冶 | Comprehensive interpretation and evaluation method of hydrocarbon reservoir including data mining |
| CN103761678A (en) * | 2014-01-06 | 2014-04-30 | 中国石油大学(华东) | Block rapid well logging evaluation linkage platform system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8380642B2 (en) * | 2008-12-03 | 2013-02-19 | Schlumberger Technology Corporation | Methods and systems for self-improving reasoning tools |
-
2015
- 2015-05-05 CN CN201510223200.8A patent/CN104881435B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101145235A (en) * | 2007-06-29 | 2008-03-19 | 中国石化集团胜利石油管理局 | Oil field development decision-making system |
| CN101630161A (en) * | 2009-08-05 | 2010-01-20 | 北方工业大学 | Intelligent system for complex industrial production and construction method thereof |
| CN102830441A (en) * | 2012-05-16 | 2012-12-19 | 陶冶 | Comprehensive interpretation and evaluation method of hydrocarbon reservoir including data mining |
| CN103761678A (en) * | 2014-01-06 | 2014-04-30 | 中国石油大学(华东) | Block rapid well logging evaluation linkage platform system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11900070B2 (en) | 2020-02-03 | 2024-02-13 | International Business Machines Corporation | Producing explainable rules via deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104881435A (en) | 2015-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104881435B (en) | A kind of research process automation logging evaluation expert system based on data mining | |
| US20070016389A1 (en) | Method and system for accelerating and improving the history matching of a reservoir simulation model | |
| CA2695207C (en) | Method and system for performing oilfield operations based on contextual information of oilfield projects | |
| McCarthy et al. | A GIS-based borehole data management and 3D visualization system | |
| CN106529667A (en) | Logging facies identification and analysis method based on fuzzy depth learning in big data environment | |
| SA109300022B1 (en) | Evaluation of Acid Fracturing Treatments in An Oil filed | |
| CN110060173A (en) | A kind of deep gold deposit method of prospecting | |
| CN105426645B (en) | A kind of automatic control methods in the stratum ASC and system | |
| CN107038505A (en) | Ore-search models Forecasting Methodology based on machine learning | |
| CN104199092A (en) | Multi-level framework based three-dimensional full-horizon automatic tracking method | |
| Tan et al. | Evaluation of complex petroleum reservoirs based on data mining methods | |
| CN113033648A (en) | Method for realizing logging interpretation by using machine learning algorithm | |
| CN109948825A (en) | Favorable Reservoir development area prediction technique based on improvement PSO in conjunction with Adaboost | |
| NO20171058A1 (en) | Integrated a priori uncertainty parameter architecture in simulation model creation | |
| CN110927793A (en) | Reservoir prediction method and system based on sequential random fuzzy simulation | |
| CN116307123B (en) | Knowledge graph driving-based mineral resource prediction method and storage medium | |
| Maschio et al. | Integration of geostatistical realizations in data assimilation and reduction of uncertainty process using genetic algorithm combined with multi-start simulated annealing | |
| CN113722412B (en) | Method for inquiring and predicting rock parameters in space dimension | |
| He et al. | Optimize Well Placement Based on Genetic Algorithm and Productivity Potential Maps | |
| Rafi et al. | Preliminary prioritization on steam flood injection in oil field using random forest regression method | |
| Yu et al. | Machine Learning Empowered Well Placement in a Large Unconventional Tight Gas Field in China | |
| Bentley et al. | Model-Based Uncertainty Handling | |
| Lopes et al. | An Overview of Evolutionary Computing for Interpretation in the Oil and Gas Industry | |
| Al Tandi et al. | An AI-Driven Multiwell Placement and Scheduling Method | |
| Singh | Basin analog approach answers characterization challenges of unconventional gas potential in frontier basins |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 100010 Beijing, Chaoyangmen, North Street, No. 25, No. Applicant after: China Offshore Oil Group Co., Ltd. Applicant after: CNOOC (China) Limited Zhanjiang Branch Address before: Chinese CNOOC Building No. 25 Beijing 100010 Dongcheng District Chaoyangmen North Street Applicant before: China National Offshore Oil Corporation Applicant before: CNOOC (China) Limited Zhanjiang Branch |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |