CN112132369A - Petroleum geology evaluation index assignment method - Google Patents
Petroleum geology evaluation index assignment method Download PDFInfo
- Publication number
- CN112132369A CN112132369A CN201910550011.XA CN201910550011A CN112132369A CN 112132369 A CN112132369 A CN 112132369A CN 201910550011 A CN201910550011 A CN 201910550011A CN 112132369 A CN112132369 A CN 112132369A
- Authority
- CN
- China
- Prior art keywords
- geological
- index
- evaluated
- value
- neural network
- 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
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000003208 petroleum Substances 0.000 title claims abstract description 27
- 238000013528 artificial neural network Methods 0.000 claims abstract description 77
- 238000012549 training Methods 0.000 claims abstract description 47
- 239000004215 Carbon black (E152) Substances 0.000 claims description 25
- 229930195733 hydrocarbon Natural products 0.000 claims description 25
- 150000002430 hydrocarbons Chemical class 0.000 claims description 25
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 4
- 229910052799 carbon Inorganic materials 0.000 claims description 4
- 239000005416 organic matter Substances 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 239000011435 rock Substances 0.000 description 12
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000012854 evaluation process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 2
- 208000010392 Bone Fractures Diseases 0.000 description 1
- 206010017076 Fracture Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 239000003079 shale oil Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention discloses a petroleum geology evaluation index assignment method, which comprises the following steps: determining the type of a geological unit to be evaluated, and selecting geological parameters and evaluation criteria according to the type; obtaining a first reference value of an index to be evaluated by applying a neural network algorithm according to various geological parameters and evaluation standards through a pre-established neural network training sample library; obtaining a second reference value of the index to be evaluated through manual assignment by taking the comparison area data as reference through a pre-established comparison area database and according to the evaluation standard; when the difference value between the first reference value and the second reference value is smaller than a set first threshold value, selecting the first reference value or the second reference value as the value of the index to be evaluated; and when the difference value of the first reference score and the second reference score is larger than a first threshold value, selecting the second reference score as the score of the index to be evaluated. The work efficiency of evaluation index assignment is improved through the comparison area and the neural network comprehensive assignment, and the scientificity and the objectivity are improved.
Description
Technical Field
The invention relates to the field of petroleum geology research, in particular to a petroleum geology evaluation index assignment method.
Background
The oil and gas exploration and evaluation is a process of gradually deepening from surface to point, and gradually develops from basin → zone → trap → oil reservoir, along with continuous deepening of oil and gas-containing basin exploration in China, a corresponding more perfect evaluation system and method [ guo autumn, Dian Guang, Shiguanren ] improved zone comprehensive evaluation model and a realization method thereof are established for geological units of different levels, the petroleum institute, 2004 and 25(2) ], and at present, the evaluation methods for basins, traps and oil reservoirs at home and abroad are more systematic and mature, and multiple versions of 'basin evaluation technical specification (SY/T5519 + 1996) "and' trap evaluation technical specification (SY/T5520 + 1996)" are also provided. Although the algorithms and parameters adopted when geological comprehensive evaluation is carried out on the geological units of different levels have differences, the evaluation process is assigned by the geological comprehensive indexes, and then the comprehensive score of the evaluation object is calculated by the index scores. Therefore, the geological index assignment process aiming at the object to be evaluated (evaluation unit) is a key process of geological comprehensive evaluation. In the past, in the evaluation index assignment work, an 'off-line consulting geological data and on-line manual assignment' mode is adopted, namely, when a geological scientific researcher evaluates and assigns values, the evaluation index assignment is finally given by consulting related data, further analyzing the content of the related data and combining work experience.
The index assignment mode has the following disadvantages:
(1) in the evaluation process, index assignment processes of a large number of geological evaluation units are involved, scientific research personnel need to repeatedly look up comparison data, and the working efficiency is extremely low;
(2) the manual assignment has strong subjectivity, and even if the same or similar geological evaluation unit indexes are assigned, a large difference possibly exists;
(3) the index is assigned without quantitative reference.
Therefore, a petroleum geological evaluation index assignment method capable of improving index assignment efficiency of a petroleum geological evaluation unit, enhancing objectivity of index assignment and providing quantitative reference is needed.
Disclosure of Invention
The invention aims to provide a petroleum geological evaluation index assignment method, which can improve the index assignment efficiency of a petroleum geological evaluation unit, enhance the objectivity of index assignment and provide quantitative reference for assignment.
In order to achieve the aim, the invention provides a petroleum geology evaluation index assignment method, which comprises the following steps:
step 1: determining the type of a geological unit to be evaluated, and selecting corresponding geological parameters and evaluation standards according to the type, wherein the geological unit to be evaluated corresponds to a plurality of indexes to be evaluated, and each index to be evaluated corresponds to a plurality of geological parameters;
step 2: extracting each geological parameter of one index to be evaluated, and obtaining a first reference value of the index to be evaluated by applying a neural network algorithm according to each geological parameter and the evaluation standard through a pre-established neural network training sample library;
and step 3: selecting comparison area data corresponding to each geological parameter of the index to be evaluated through a pre-established comparison area database, and obtaining a second reference score of the index to be evaluated based on the comparison area data;
and 4, step 4: when the difference value between the first reference value and the second reference value is smaller than a set first threshold value, selecting the first reference value or the second reference value as the value of the index to be evaluated; when the difference value between the first reference value and the second reference value is larger than the first threshold value, selecting the second reference value as the value of the index to be evaluated;
and 5: and repeating the step 2 to the step 4 to obtain the score of each index to be evaluated corresponding to the geological unit to be evaluated.
Optionally, before the step 1, the method further comprises: and establishing the comparison area database, dissecting each geological index of at least one typical geological evaluation unit through geological analysis to obtain the parameter value and index score of each geological parameter corresponding to each geological index, and adding each geological parameter and the parameter value and index score thereof into the comparison area database.
Optionally, before the step 1, the method further comprises: establishing a neural network training sample library, and adding geological parameters, parameter values and index values of geological parameters in the geological units and the comparison area database which are evaluated in the early stage into the neural network training sample library;
and training the neural network algorithm by applying the neural network training sample library.
Optionally, the step 2 further includes: when the number of sample data in the neural network training sample library is larger than or equal to a set second threshold value, calculating the first reference score through the neural network algorithm.
Optionally, the step 2 further includes: when the number of sample data in the neural network training sample library is smaller than the second threshold value, the first reference score is 0.
Optionally, the step 4 further includes: and when the first reference score is 0, taking the second reference score as the score of the index to be evaluated.
Optionally, the step 4 further includes: and when the difference value between the first reference value and the second reference value is smaller than the first threshold value, adding the geological parameter corresponding to the index to be evaluated and the parameter value thereof, the first reference value or the second reference value into the comparison area database and the neural network sample database.
Optionally, the step 4 further includes: and when the difference value between the first reference value and the second reference value is larger than the first threshold value, adding the geological parameter of the index to be evaluated, the parameter value of the geological parameter and the second reference value into the neural network sample database.
Optionally, the neural network algorithm includes a back propagation neural network algorithm, a deep learning algorithm.
Optionally, the to-be-evaluated index comprises a hydrocarbon source condition, a reservoir condition and a trap condition; and geological parameters corresponding to the hydrocarbon source conditions comprise lithology, thickness, total organic carbon, organic matter maturity and kerogen type of the hydrocarbon source.
The invention has the beneficial effects that:
(1) the method can be applied to the evaluation of different exploration areas and different fields, the reliability of the evaluation result is predicted to be higher through artificial intelligence (neural network algorithm), the artificial assignment can be replaced to a certain degree, and the working efficiency of the evaluation index assignment is improved; the comprehensive evaluation assignment has better objectivity through artificial intelligence assignment and comparison of comparison area data, reduces the difference of geological evaluation unit index assignment with the same or similar geological parameters, and can provide quantitative reference for artificial comprehensive index assignment.
(2) By supplementing the data of the geological unit to be evaluated into the comparison area database and the neural network training sample library, the geological index can be continuously evaluated in the comparison area database and the neural network training sample library, and the evaluation process is more scientific and objective.
Partial data detailed evaluation units can be added as comparison area and neural network training sample data to enrich the comparison area database and the neural network training sample database, so that the objectivity and scientificity of evaluation can be obviously improved.
The method of the present invention has other features and advantages which will be apparent from or are set forth in detail in the accompanying drawings and the following detailed description, which are incorporated herein, and which together serve to explain certain principles of the invention.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts.
FIG. 1 shows a step diagram of a petroleum geology evaluation index assignment method according to the invention.
FIG. 2 shows a flow chart of the assignment of the petroleum geological evaluation index assignment method according to the invention.
Detailed Description
The invention will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present invention are shown in the drawings, it should be understood that the present invention may 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.
In the technical field, different evaluation systems often have partial differences, but the geological parameters of indexes to be evaluated are similar in structure mode. In a geological comprehensive selected area, multiple groups of comprehensive geological evaluation indexes are often applied, such as hydrocarbon source conditions, reservoir conditions, trapping conditions and the like in a conventional geological selected area, and the indexes are composed of specific geological parameters (geological parameters), such as the geological parameters of the hydrocarbon source conditions include: source lithology, thickness, Total Organic Carbon (TOC), organic matter maturity (Ro), kerogen type, etc., geological parameters of reservoir conditions include: the lithology, physical property, permeability and fracture development degree of the reservoir, and the geological parameters of the trap condition include: degree of implementation, type, area, magnitude, depth of destination layer, etc. For the purpose of more conveniently illustrating the scheme of the invention, the specific embodiment of the invention is illustrated by taking the hydrocarbon source condition as an example of the evaluation index without loss of generality.
FIG. 1 shows a flow chart of steps of a petroleum geological evaluation index assignment method according to the present invention, and FIG. 2 shows a flow chart of a petroleum geological evaluation index assignment method according to the present invention.
As shown in fig. 1 and 2, the petroleum geology evaluation index assignment method according to the invention comprises the following steps:
step 1: determining the type of a geological unit to be evaluated, and selecting corresponding geological parameters and evaluation standards according to the type, wherein the geological unit to be evaluated corresponds to a plurality of indexes to be evaluated, and each index to be evaluated corresponds to a plurality of geological parameters;
step 2: extracting each geological parameter of an index to be evaluated, and obtaining a first reference value of the index to be evaluated by applying a neural network algorithm according to each geological parameter and an evaluation standard through a pre-established neural network training sample library;
and step 3: selecting comparison area data corresponding to each geological parameter of the index to be evaluated through a pre-established comparison area database, and obtaining a second reference score of the index to be evaluated based on the comparison area data;
and 4, step 4: when the difference value between the first reference value and the second reference value is smaller than a set first threshold value, selecting the first reference value or the second reference value as the value of the index to be evaluated; when the difference value between the first reference value and the second reference value is larger than a first threshold value, selecting the second reference value as the value of the index to be evaluated;
and 5: and (4) repeating the step 2 to the step 4 to obtain the score of each index to be evaluated corresponding to the geological unit to be evaluated.
In one embodiment, step 1 is preceded by: and establishing a contrast area database and a neural network training sample library.
Wherein, the establishment of the comparison area database comprises the following steps: and (3) dissecting each geological index of at least one typical geological evaluation unit through geological analysis to obtain the parameter value and the score of each geological parameter corresponding to each geological index, and adding each geological parameter and the parameter value and the score thereof into a comparison area database. In the specific implementation process, a data table (table 1) of geological parameters of hydrocarbon source conditions of a database of a comparison area is referred, hydrocarbon source conditions of a typical geological evaluation unit are analyzed and dissected through geology, parameter values of the corresponding geological parameters are obtained, the parameter values of the geological parameters and geological index scores are filled in the table 1, the types of exploration areas, fields, lithology and kerogen in the table 1 are limited enumeration data types, and the types of thickness, TOC and Ro are numerical types. A comparison zone data table of geological parameters of reservoir conditions or trap conditions may be set with reference to table 1.
Table 1: data table for comparing geological parameters of hydrocarbon source condition in database of area
The establishment of the neural network training sample library comprises the following steps: adding the geological parameters, parameter values and index values in the evaluated geological evaluation unit and the comparison area database into a neural network training sample library; and training the neural network algorithm by applying a neural network training sample library. In the specific implementation process, referring to the table 2, geological parameters and parameter values of a geological evaluation unit and an anatomical contrast area which are developed in the early stage and evaluated geological index scores are collected, a neural network training sample data table (table 2) is established in a classification mode, a data table is established in a classification mode according to enumeration types in the classification process, and a neural network algorithm is trained according to data in the training sample data table. The training sample data table for the reservoir condition or trap condition geological parameters may be set with reference to table 2.
Table 2: training sample data table of hydrocarbon source conditional geological parameters in neural network sample database
In step 1: and determining the type of the geological unit to be evaluated, and selecting corresponding geological parameters and evaluation standards according to the type. Specifically, each geocellular type corresponds to different evaluation parameters and different evaluation criteria, and the geocellular types include but are not limited to: east clastic rock field unit, west clastic rock field unit, south clastic rock field unit, sea clastic rock field unit, south carbonate field unit, west carbonate field unit, shale oil field unit, shale gas field unit etc. specifically can further refine or merge according to actual research needs. Evaluation criteria are criteria common in the art and include, for different types of geocellular evaluation criteria: the technical specifications of basin evaluation (SY/T5519-. The geological unit to be evaluated comprises a plurality of indexes to be evaluated, each index to be evaluated comprises a plurality of geological parameters, in one example, the indexes to be evaluated of the geological unit to be evaluated comprise hydrocarbon source conditions, reservoir conditions and trap conditions, wherein the geological parameters of the hydrocarbon source conditions comprise hydrocarbon source rock lithology, thickness, total organic carbon, organic matter maturity and kerogen type.
In step 2: extracting each geological parameter of the index to be evaluated, obtaining a first reference score of the index to be evaluated by applying a neural network algorithm according to each geological parameter and an evaluation standard through a pre-established neural network training sample library, calculating to obtain the first reference score through the neural network algorithm when the number of sample data in the neural network training sample library is larger than or equal to a set second threshold, and obtaining the first reference score to be 0 when the number of the sample data in the neural network training sample library is smaller than the second threshold. Specifically, geological parameter values of hydrocarbon source conditions of an object to be evaluated are extracted, the index value to be evaluated of a geological unit to be evaluated is calculated through an artificial intelligence neural network algorithm, the neural network algorithm can adopt the existing Back Propagation neural network algorithm (Back Propagation network), deep learning and other mature algorithms, a prediction model is established through one-time training under the condition that a sample base is not changed, and multiple applications are provided. In specific implementation, the second threshold may be set to 10, that is, when the number of sample data in the sample library is less than 10, the score of the predicted value is directly given to be 0, which indicates that the predicted value cannot be referred to, the amount of sample data in the sample library needs to be increased, and when the number of sample data exceeds (or is equal to) 10, the first reference score predicted by the neural network is given.
In step 3: and selecting comparison area data which are the same as or similar to each geological parameter of the index to be evaluated through a pre-established comparison area database, and obtaining a second reference score of the index to be evaluated through manual assignment by taking the comparison area data as reference according to an evaluation standard. Specifically, the index to be evaluated is compared with the geological parameters of the comparison area database, the score of the data in the comparison area is referred to in combination with the definition of the evaluation standard, and the score of the index to be evaluated (second reference score) is given manually. It should be noted that, in the process of performing manual assignment by using comparison area data, first, each parameter data of the evaluation index of the unit to be evaluated is retrieved, then, each parameter data of the corresponding index of the corresponding geological unit type and the corresponding index score (for example, the same or similar comparison area data are retrieved) are extracted from the comparison area library, and a reasonable score of the evaluation index of the unit to be evaluated is given by manual experience comparison and judgment in combination with the index assignment standard of the geological unit type.
In step 4: when the difference value between the first reference value and the second reference value is smaller than a set first threshold value, selecting the first reference value or the second reference value as the value of the index to be evaluated; and when the difference value of the first reference score and the second reference score is larger than a first threshold value, selecting the second reference score as the score of the index to be evaluated. In a specific implementation process, when the first reference score is 0 (which indicates that the data amount in the neural network sample library is too small to give a predicted first reference score), the second reference score may be directly used as the score of the index to be evaluated, that is, when the first reference score calculated by the neural network is 0 or has a large deviation from the score of the geological index reflected by the actual geological parameter, the predicted score of the neural network is ignored, for example, the first threshold is set to 0.1, that is, when the deviation between the first reference score and the second reference score exceeds ± 0.2, the first reference score given by the neural network is ignored, and the second reference score is directly used as the final value of the index to be evaluated.
The method also comprises the following steps: when the difference value between the first reference value and the second reference value is smaller than a first threshold value (for example, smaller than 0.1), adding the geological parameters corresponding to the geological index to be evaluated into the comparison area database and the neural network sample database; and adding the corresponding first reference value or second reference value of the index to be evaluated into the comparison area database and the neural network sample database. When the difference value of the first reference value and the second reference value is larger than a first threshold value, adding the geological parameters of the index to be evaluated into a neural network sample database; and adding the corresponding second reference value of the index to be evaluated into a neural network sample database. Specifically, when the first reference score and the second reference score are substantially consistent (the difference is less than 0.1), it is indicated that the score predicted by the neural network algorithm (artificial intelligence) is substantially consistent with the manually calculated score, and the geological parameter corresponding to the evaluation index is relatively detailed, so that the geological parameter corresponding to the evaluation index assigned this time and the finally obtained score can be added to the comparison area database and the neural network training sample database. If the deviation between the first reference value predicted by the neural network algorithm and the geological index value (manually calculated second reference value) reflected by the actual geological parameters is large, namely the first reference value predicted by the neural network algorithm is not accurate, the fact that the geological parameter related data of the type is lacked in the neural network training sample database indicates that the geological parameters related to the geological unit to be evaluated at this time are used as training sample data and added into the neural network training sample database, and the second reference value is assigned by manual synthesis according to the value of the evaluation index when the geological parameters are added. Through the method, the comparison area database can be continuously improved, the training data of the neural network algorithm is increased, the accuracy of the subsequent geological unit index assignment is improved, and the quantitative reference data is increased.
And (4) the processes from step 2 to step 4 are circulated to finish the assignment process of other indexes to be evaluated of the geological unit to be evaluated, so that the evaluation score of each geological index in the geological unit to be evaluated can be obtained.
To further illustrate the scheme, the application also provides a specific application example of the petroleum geology evaluation index assignment method, which specifically comprises the following contents:
by applying the method, evaluation and assignment are carried out on hydrocarbon source conditions of 10 geological evaluation units in the field of clastic rocks in the east exploration area, the types of the hydrocarbon source rocks of the geological units to be evaluated are clastic rocks, the lithology is mudstone, and the type of kerogen is I, II 1. The pre-evaluation comparison area database comprises 2 pieces of relevant comparison area data, reference table 3, 7 pieces of mudstone type I kerogen source rock data, 3 pieces of type II source rock data, 10 pieces of training sample data and reference table 4 in the field of the debris rocks in the eastern exploration area in the neural network training sample library.
Table 3: training sample data table for comparing geological parameters of hydrocarbon source condition in regional database
Table 4: training sample data table of hydrocarbon source conditional geological parameters in neural network sample database
After one evaluation assignment is executed, 10 evaluation unit hydrocarbon source condition score values (table 5) are obtained, in a general view, a comparison area provides a reference for geological index evaluation assignment, the total error between the score value predicted by a neural network algorithm and the comprehensive assignment is 0.03<0.1 (wherein the intelligent prediction value is obtained after the unit 4, the unit 9 and the unit 10 are added to a training sample library), meanwhile, 1 is added to the comparison area database (table 6), and 3 training samples are added to the neural network training sample library (table 7). Therefore, the method has better application effect by comprehensively adopting the contrast area and the neural network algorithm assignment.
Table 5: comparison table of hydrocarbon source conditional neural network algorithm assignment and artificial comprehensive assignment of 10 geological evaluation units in east exploration area
Table 6: comparison area data table of hydrocarbon source conditional geological parameters in comparison area database after assignment
Table 7: training sample data table of hydrocarbon source conditional geological parameters in neural network sample database after assignment
The above examples show that:
(1) the evaluation application of 10 geological evaluation units in the field of debris rocks in the east exploration area by the method of the invention shows that: the total error of the value predicted by the neural network algorithm (artificial intelligence) and the artificial comprehensive assignment is 0.03<0.1, the reliability of the artificial intelligence prediction result is high, the artificial assignment can be replaced to a certain degree, and the working efficiency of evaluation index assignment is improved.
(2) The method can be applied to the evaluation of different exploration areas and different fields, and can continuously enrich the geological index evaluation comparison area database and the neural network training sample database, so that the evaluation process is more scientific and objective.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
Claims (10)
1. A petroleum geology evaluation index assignment method is characterized by comprising the following steps:
step 1: determining the type of a geological unit to be evaluated, and selecting corresponding geological parameters and evaluation standards according to the type, wherein the geological unit to be evaluated corresponds to a plurality of indexes to be evaluated, and each index to be evaluated corresponds to a plurality of geological parameters;
step 2: extracting each geological parameter of one index to be evaluated, and obtaining a first reference value of the index to be evaluated by applying a neural network algorithm according to each geological parameter and the evaluation standard through a pre-established neural network training sample library;
and step 3: selecting comparison area data corresponding to each geological parameter of the index to be evaluated through a pre-established comparison area database, and obtaining a second reference score of the index to be evaluated based on the comparison area data;
and 4, step 4: when the difference value between the first reference value and the second reference value is smaller than a set first threshold value, selecting the first reference value or the second reference value as the value of the index to be evaluated; when the difference value between the first reference value and the second reference value is larger than the first threshold value, selecting the second reference value as the value of the index to be evaluated;
and 5: and repeating the step 2 to the step 4 to obtain the score of each index to be evaluated corresponding to the geological unit to be evaluated.
2. The petroleum geology evaluation index assignment method according to claim 1, further comprising, before step 1: and establishing the comparison area database, dissecting each geological index of at least one typical geological evaluation unit through geological analysis to obtain the parameter value and index score of each geological parameter corresponding to each geological index, and adding each geological parameter and the parameter value and index score thereof into the comparison area database.
3. The petroleum geologic evaluation index assignment method of claim 2, further comprising, prior to step 1:
establishing a neural network training sample library, and adding the geological parameters, parameter values and index values of the geological parameters in the evaluated geological units and the comparison area database into the neural network training sample library;
and training the neural network algorithm by applying the neural network training sample library.
4. The petroleum geology evaluation index assignment method of claim 1, wherein the step 2 further comprises: when the number of sample data in the neural network training sample library is larger than or equal to a set second threshold value, calculating the first reference score through the neural network algorithm.
5. The petroleum geology evaluation index assignment method of claim 4, wherein the step 2 further comprises: when the number of sample data in the neural network training sample library is smaller than the second threshold value, the first reference score is 0.
6. The petroleum geology evaluation index assignment method of claim 5, wherein step 4 further comprises: and when the first reference score is 0, taking the second reference score as the score of the index to be evaluated.
7. The petroleum geology evaluation index assignment method of claim 1, wherein the step 4 further comprises: and when the difference value between the first reference score and the second reference score is smaller than the first threshold value, adding the geological parameter corresponding to the index to be evaluated, the parameter value of the geological parameter, the first reference score or the second reference score into the comparison area database and the neural network sample database.
8. The petroleum geology evaluation index assignment method of claim 7, wherein step 4 further comprises: and when the difference value between the first reference value and the second reference value is larger than or equal to the first threshold value, adding the geological parameter of the index to be evaluated, the parameter value of the geological parameter and the second reference value into the neural network sample database.
9. The petroleum geology evaluation index assignment method of claim 1, wherein the neural network algorithm comprises a back propagation neural network algorithm, a deep learning algorithm.
10. The petroleum geological evaluation index assignment method according to claim 1, wherein the index to be evaluated comprises hydrocarbon source conditions, reservoir conditions and trapping conditions; and geological parameters corresponding to the hydrocarbon source conditions comprise lithology, thickness, total organic carbon, organic matter maturity and kerogen type of the hydrocarbon source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910550011.XA CN112132369A (en) | 2019-06-24 | 2019-06-24 | Petroleum geology evaluation index assignment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910550011.XA CN112132369A (en) | 2019-06-24 | 2019-06-24 | Petroleum geology evaluation index assignment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112132369A true CN112132369A (en) | 2020-12-25 |
Family
ID=73849272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910550011.XA Pending CN112132369A (en) | 2019-06-24 | 2019-06-24 | Petroleum geology evaluation index assignment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112132369A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432534A (en) * | 2023-04-18 | 2023-07-14 | 中海石油(中国)有限公司上海分公司 | Data-driven TOC sample prediction method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6490573B1 (en) * | 2000-04-11 | 2002-12-03 | Philip Chidi Njemanze | Neural network for modeling ecological and biological systems |
| CN103426027A (en) * | 2013-07-24 | 2013-12-04 | 浙江大学 | Intelligent normal pool level optimal selection method based on genetic neural network models |
| US20170254910A1 (en) * | 2016-03-04 | 2017-09-07 | General Electric Company | Expert guided knowledge acquisition system for analyzing seismic data |
| CN107463991A (en) * | 2017-06-28 | 2017-12-12 | 西南石油大学 | A kind of Regional Landslide method for evaluating hazard based on slopes unit and machine learning |
| CN108520345A (en) * | 2018-03-29 | 2018-09-11 | 华南农业大学 | Evaluation for cultivated-land method and system based on GA-BP neural network models |
-
2019
- 2019-06-24 CN CN201910550011.XA patent/CN112132369A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6490573B1 (en) * | 2000-04-11 | 2002-12-03 | Philip Chidi Njemanze | Neural network for modeling ecological and biological systems |
| CN103426027A (en) * | 2013-07-24 | 2013-12-04 | 浙江大学 | Intelligent normal pool level optimal selection method based on genetic neural network models |
| US20170254910A1 (en) * | 2016-03-04 | 2017-09-07 | General Electric Company | Expert guided knowledge acquisition system for analyzing seismic data |
| CN107463991A (en) * | 2017-06-28 | 2017-12-12 | 西南石油大学 | A kind of Regional Landslide method for evaluating hazard based on slopes unit and machine learning |
| CN108520345A (en) * | 2018-03-29 | 2018-09-11 | 华南农业大学 | Evaluation for cultivated-land method and system based on GA-BP neural network models |
Non-Patent Citations (1)
| Title |
|---|
| 孙淑霞等: "《人工神经网络在生烃条件评价中的应用》", 《石油与天然气地质》, vol. 17, no. 1, pages 68 - 70 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432534A (en) * | 2023-04-18 | 2023-07-14 | 中海石油(中国)有限公司上海分公司 | Data-driven TOC sample prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shaw et al. | Screening, evaluation, and ranking of oil reservoirs suitable for CO2-flood EOR and carbon dioxide sequestration | |
| Gherabati et al. | The impact of pressure and fluid property variation on well performance of liquid-rich Eagle Ford shale | |
| CN110288258B (en) | High-water-content oil reservoir residual oil submergence excavating method | |
| CN110276827B (en) | Effectiveness evaluation method based on shale reservoir | |
| CN104747185A (en) | Heterogeneous reservoir stratum synthetic classifying evaluation method | |
| CN111461386B (en) | Shale gas dessert prediction method based on BP neural network | |
| CN111046585B (en) | Shale gas dessert prediction method based on multiple linear regression analysis | |
| CN105426645B (en) | A kind of automatic control methods in the stratum ASC and system | |
| CN110413952B (en) | Method and device for predicting exploration degree of oil-gas-containing basin | |
| Zhang et al. | Uncertainty Analysis and Assisted History Matching Workflow in Shale Oil Reservoirs | |
| CN112576238B (en) | System, method and application for determining position and content of residual oil in low-permeability reservoir | |
| Purbey et al. | Machine learning and data mining assisted petroleum reservoir engineering: a comprehensive review | |
| CN112132369A (en) | Petroleum geology evaluation index assignment method | |
| Sun et al. | An empirical analog benchmarking workflow to improve hydrocarbon recovery | |
| AlQassab et al. | Estimating the size and orientation of hydraulic fractures using microseismic events | |
| CN110940790A (en) | Method and device for identifying efficient hydrocarbon source rock | |
| CN110930020B (en) | Method for determining economic recoverable resource amount of unconventional oil and gas resources | |
| Jung | Application of History Matching Quality Index with Moving Linear Regression Analysis | |
| CN112282751A (en) | Geological engineering three-dimensional coupling tight oil gas horizontal well exploitation detection method | |
| Schiozer et al. | Integration of history matching and uncertainty analysis | |
| Wang et al. | Rock typing from cored intervals to all wells with method of decision tree | |
| CN114676631B (en) | Shale gas reservoir fracturing horizontal well fracturing transformation parameter recommendation method | |
| Wang et al. | Identification of watered-out zones in carbonate reservoirs using resistivity curve reconstruction based on reservoir classification | |
| RU2206911C2 (en) | Process of search, prospecting, examination of deposit of mineral wealth and of construction of its model | |
| CN116401849A (en) | Multi-factor coupled prediction method for thick-layer strong water heavy oil reservoir potential area |
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 |