CN116627963A - Intelligent construction method and system for reconnaissance stratum data set based on generalized SR algorithm - Google Patents
Intelligent construction method and system for reconnaissance stratum data set based on generalized SR algorithm Download PDFInfo
- Publication number
- CN116627963A CN116627963A CN202310419918.9A CN202310419918A CN116627963A CN 116627963 A CN116627963 A CN 116627963A CN 202310419918 A CN202310419918 A CN 202310419918A CN 116627963 A CN116627963 A CN 116627963A
- Authority
- CN
- China
- Prior art keywords
- data
- stratum
- drilling
- virtual
- fitting
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 69
- 238000010276 construction Methods 0.000 title claims abstract description 54
- 238000005553 drilling Methods 0.000 claims abstract description 94
- 239000011159 matrix material Substances 0.000 claims abstract description 35
- 230000015572 biosynthetic process Effects 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 19
- 230000009897 systematic effect Effects 0.000 abstract description 3
- 238000011835 investigation Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The embodiment of the invention provides a method and a system for intelligently constructing a reconnaissance stratum data set based on a generalized SR algorithm, wherein the method comprises the following steps: dividing the drilling data in layers to construct a layered picture data matrix, and carrying out virtual drilling construction by combining a bilinear interpolation algorithm to obtain quick virtual drilling data; constructing an SR model, performing data fitting through the SR model until the data fitting passes, generating precision virtual drilling data, and generating a stratum surface discrete point set table through the quick virtual drilling data/the precision virtual drilling data; determining stratum trend data based on the stratum discrete point set table as initial data in combination with drilling data to generate a stratum trend table; and acquiring geological data of geological survey data to generate a stratum foundation information table, and constructing a corresponding geological database. By adopting the method, the three-dimensional geological database can be built, systematic complete data can be provided, meanwhile, virtual drilling construction is also carried out based on an SR algorithm, and the stratum data precision is improved.
Description
Technical Field
The invention belongs to the technical field of geological survey data processing, and particularly relates to an intelligent construction method and system for a survey stratum data set based on a generalized SR algorithm.
Background
In the geological exploration process, a large amount of geological exploration data are often acquired, corresponding geological data are obtained, subsequent geological analysis and business processing are facilitated, for example, in mineral exploration, geological entities and attributes thereof are identified, separated and collected through outcrop observation, drilling, pit exploration, core identification, hydrogeological investigation and the like, so that source data which can be processed are obtained.
The traditional survey data has various kinds, the obtained data is interpreted by combining tables, drawings and working experience on the basis of limited data, the mode is abstract, the interpretation of the survey data is difficult, and engineering geological information is difficult to understand deeply. The investigation result provided to the subsequent profession in the form of text report and map is too specialized, and the possibility of converting the investigation result into data required for design, construction, operation and maintenance is low, thus causing unnecessary loss and waste. The original data of various investigation are mutually evidence and analysis can only be judged by means of human experience, and the efficiency is low. Part of investigation data is deduced manually through drilling data and geologic time and according to experience, the data is often low in precision, reference value for design and construction is low, and design and construction cannot be guided accurately.
Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the invention provides an intelligent construction method and system for a reconnaissance stratum data set based on a generalized SR algorithm.
The embodiment of the invention provides an intelligent construction method for a reconnaissance stratum data set based on a generalized SR algorithm, which comprises the following steps:
acquiring drilling data in geological survey data, acquiring layering positions corresponding to the drilling data, dividing the drilling data according to the layering positions, constructing a corresponding data set for the drilling data of each stratum layer, and constructing a corresponding picture data matrix according to the data set;
judging the data precision requirement of target data, when the data precision requirement of the target data is lower than a preset standard, performing virtual drilling construction by combining a bilinear interpolation algorithm based on the picture data matrix to obtain corresponding quick virtual drilling data, and generating a first stratum discrete point set table through the quick virtual drilling data;
when the data precision requirement of the target data is higher than a preset standard, constructing dimension information of output data based on the data precision requirement, constructing a corresponding SR model according to the dimension information, inputting the drilling data into the SR model, performing data fitting through the SR model until the data fitting is passed, generating corresponding precision virtual drilling data, and generating a second stratum discrete point set table through the precision virtual drilling data;
based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, combining the drilling data, carrying out nearest neighbor point solving by using a KNN algorithm, determining stratum trend data according to a solving result, and generating a stratum trend table according to the stratum trend data pair;
and acquiring geological data of geological survey data to generate a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table.
In one embodiment, the method further comprises:
pre-constructing virtual data dimensions of a virtual stratum of a virtual drilling hole, determining a corresponding target pixel point in the picture data matrix based on the virtual data dimensions, and combining four points around the target pixel point to perform pre-virtual drilling;
and carrying out KNN algorithm calculation through geophysical prospecting data and stratum contour line data in the drilling data, comparing an algorithm calculation result with the pre-virtual drilling result, and when the comparison result is larger than a preset error value, using the geophysical prospecting data and the stratum contour line data as weights, recalculating influence coefficients of a target pixel point and four points around, and carrying out pre-virtual drilling again until the comparison result is smaller than the preset error value.
In one embodiment, the method further comprises:
acquiring geophysical prospecting data and stratum contour line data in the drilling data, fitting the geophysical prospecting data as weight factors of a first-layer fitting function, fitting the stratum contour line data as weight factors of a second-layer fitting function, and updating corresponding weight factors through feed-forward when a fitting result does not meet preset standards in two-layer fitting;
and after the two layers of fitting pass is detected, outputting the precision virtual drilling data after the fitting pass.
In one embodiment, the method further comprises:
correspondingly generating the picture attribute data in the picture data matrix through the attribute data in the drilling data, wherein the picture attribute data comprises the following steps:
and generating coordinate system coordinates of the picture data matrix through the abscissa and the ordinate of the drilling data, and generating R, G, B channel values and transparency of picture pixels in the picture data matrix through stratum coding, temperature, humidity and stress of the drilling data.
In one embodiment, the borehole data includes:
basic information including borehole number, orifice elevation, depth of hole, layering location, layering thickness, formation property information;
multisource data including geophysical prospecting data, formation contour line data, fault data, profile data.
The embodiment of the invention provides an intelligent construction system for a reconnaissance stratum data set based on a generalized SR algorithm, which comprises the following steps:
the acquisition module is used for acquiring drilling data in geological survey data, acquiring layering positions corresponding to the drilling data, dividing the drilling data according to the layering positions, constructing a corresponding data set for the drilling data of each stratum layer, and constructing a corresponding picture data matrix according to the data set;
the judging module is used for judging the data precision requirement of the target data, and when the data precision requirement of the target data is lower than a preset standard, virtual drilling construction is carried out by combining a bilinear interpolation algorithm based on the picture data matrix to obtain corresponding quick virtual drilling data, and a first stratum surface discrete point set table is generated through the quick virtual drilling data;
the SR model module is used for constructing dimension information of output data based on the data precision requirement when the data precision requirement of the target data is higher than a preset standard, constructing a corresponding SR model according to the dimension information, inputting the drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum discrete point set table through the precision virtual drilling data;
the stratum trend module is used for carrying out nearest neighbor point solving by using a KNN algorithm in combination with the drilling data based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, determining stratum trend data through a solving result, and generating a stratum trend table through the stratum trend data pair;
and the database module is used for acquiring geological data of geological survey data, generating a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table.
In one embodiment, the system further comprises:
the virtual drilling module is used for pre-constructing virtual data dimensions of a virtual stratum of the virtual drilling, determining corresponding target pixel points in the picture data matrix based on the virtual data dimensions, and carrying out pre-virtual drilling by combining four points around the target pixel points;
and the iteration module is used for carrying out KNN algorithm calculation through geophysical prospecting data and stratum contour line data in the drilling data, comparing an algorithm calculation result with the pre-virtual drilling result, taking the geophysical prospecting data and the stratum contour line data as weights when the comparison result is larger than a preset error value, and recalculating influence coefficients of a target pixel point and four surrounding points, and carrying out pre-virtual drilling again until the comparison result is smaller than the preset error value.
In one embodiment, the system further comprises:
the fitting module is used for acquiring geophysical prospecting data and stratum contour line data in the drilling data, fitting the geophysical prospecting data as a weight factor of a first-layer fitting function, fitting the stratum contour line data as a weight factor of a second-layer fitting function, and updating the corresponding weight factor through feed-forward when the fitting result does not meet a preset standard in two-layer fitting;
and the detection module is used for outputting the precision virtual drilling data after the two layers of fitting pass.
The embodiment of the invention provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the intelligent construction method for the reconnaissance stratum data set based on a generalized SR algorithm when executing the program.
The embodiment of the invention provides a non-transitory computer readable storage medium, on which a computer program is stored, which when being executed by a processor, realizes the steps of the intelligent construction method for the investigation stratum data set based on the generalized SR algorithm.
According to the intelligent construction method and system for the investigation stratum data set based on the generalized SR algorithm, provided by the embodiment of the invention, drilling data in geological investigation data are collected, layering positions corresponding to the drilling data are obtained, the drilling data are divided according to the layering positions, a corresponding data set is constructed for the drilling data of each stratum, and a corresponding picture data matrix is constructed according to the data set; judging the data precision requirement of the target data, and when the data precision requirement of the target data is lower than a preset standard, performing virtual drilling construction by combining a bilinear interpolation algorithm based on a picture data matrix to obtain corresponding quick virtual drilling data, and generating a first stratum discrete point set table through the quick virtual drilling data; when the data precision requirement of the target data is higher than a preset standard, constructing dimension information of output data based on the data precision requirement, constructing a corresponding SR model according to the dimension information, inputting drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum surface discrete point set table through the precision virtual drilling data; based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, combining drilling data, carrying out nearest neighbor point solving by using a KNN algorithm, determining stratum trend data according to a solving result, and generating a stratum trend table according to stratum trend data pairs; and acquiring geological data of geological survey data to generate a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table. Therefore, the three-dimensional geological database can be built, systematic complete data can be provided, meanwhile, virtual drilling construction is also carried out based on an SR algorithm, and the stratum data precision is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for intelligently constructing a survey stratum data set based on a generalized SR algorithm in an embodiment of the invention;
FIG. 2 is a flow chart of a fast virtual drilling construction in accordance with an embodiment of the present invention;
FIG. 3 is a flow chart of a high precision virtual drilling configuration in accordance with an embodiment of the present invention;
FIG. 4 is a block diagram of an intelligent construction system for a survey stratum data set based on a generalized SR algorithm in an embodiment of the invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a schematic flow chart of an intelligent construction method for a survey stratum data set based on a generalized SR algorithm according to an embodiment of the present invention, as shown in fig. 1, and the embodiment of the present invention provides an intelligent construction method for a survey stratum data set based on a generalized SR algorithm, including:
step S101, drilling data in geological survey data are collected, layering positions corresponding to the drilling data are obtained, the drilling data are divided according to the layering positions, a corresponding data set is constructed for the drilling data of each stratum, and a corresponding picture data matrix is constructed according to the data set.
Specifically, drilling data in drawings and records such as a drilling plan view, a drilling histogram, a drilling construction record and the like in a geological investigation process are collected, wherein the drilling data can be divided into two types, drilling basic data, including data directly collected by drilling numbers, orifice elevations, hole depths, layering positions, layering thicknesses, formation property information and the like, and multi-source data, including geophysical data, stratum contour line data, fault data, profile data and the like, which are required to be subjected to relevant system for carrying out multi-item basic data overall calculation, or data which are not quite accurate through algorithm operation, are collected, the drilling data are then divided layer by layer according to layering positions, each stratum is used as a data set, the data set is constructed into a matrix similar to picture data, a specific construction method can be used for mapping X, Y coordinates of the drilling data into XY coordinates of pixels of picture data, Z coordinates, stress, temperature and humidity are abstract into R, G, B and transparency of picture pixels, and thus the drilling data of each layer can be regarded as an equivalent picture data set.
Step S102, judging the data precision requirement of target data, and when the data precision requirement of the target data is lower than a preset standard, performing virtual drilling construction by combining a bilinear interpolation algorithm based on the picture data matrix to obtain corresponding quick virtual drilling data, and generating a first stratum surface discrete point set table through the quick virtual drilling data.
Specifically, determining the data precision requirement of the target data required for geological survey, and when the data precision requirement of the target data is lower than a preset standard, adopting rapid virtual drilling construction, wherein the method comprises the following steps: the new layer data dimension containing the virtual drilling data is built, then the bilinear interpolation algorithm is utilized to carry out virtual drilling construction, namely four points around the target pixel are utilized to predict, the point weight which is closer to the target position is larger, the quick virtual drilling construction mode is fast, the calculated amount is not large, but the drilling precision of the construction is not high, and errors possibly exist in practice.
In addition, when the construction error of the quick virtual drilling is overlarge, the geophysical prospecting data and the stratum contour line data can be used for calculating the parameter value of the corresponding point by using a KNN algorithm, if the parameter error is in a reasonable range, the parameter weight is adjusted by using a feedback adjustment mechanism, the virtual drilling is constructed by reusing an activation function, the required quick virtual drilling data is obtained through reciprocating calculation, as shown in fig. 2, and then a first stratum discrete point set table is generated by the quick virtual drilling data, wherein the content of the stratum discrete point set table can be shown in table 1, and the discrete point data of each stratum surface extracted from the drilling data mainly comprises coordinate information, stress, temperature, humidity and other data. And the method also comprises virtual drilling data generated by an algorithm from the initial drilling data and other investigation data, and the addition of the virtual data improves the accuracy of the data and the accuracy of the subsequent correlation analysis capability:
| field name | Remarks | Type(s) |
| X | x-coordinate system | Double |
| Y | y-coordinate | Double |
| Z | z-coordinate | Double |
| Code | Formation coding | String |
| Temp | Temperature (temperature) | Double |
| Humidity | Humidity of the water | Double |
| Stress | Stress | Double |
TABLE 1
Step S103, when the data precision requirement of the target data is higher than a preset standard, constructing dimension information of output data based on the data precision requirement, constructing a corresponding SR model according to the dimension information, inputting the drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum discrete point set table through the precision virtual drilling data.
Specifically, judging the data precision requirement of the target data required by geological investigation, and adopting high-precision virtual drilling construction when the data precision requirement of the target data is higher than a preset standard, wherein the method comprises the following steps: the method comprises the steps of constructing dimension information of output data based on data precision requirements, and training and calculating related data in drilling data by using an SR model as input parameters, wherein the related data can comprise geophysical prospecting data and stratum contour line data, the geophysical prospecting data is used as a weight factor of a first-layer fitting function, the stratum contour line data is used as a weight factor of a second-layer fitting function, double-layer feedback is carried out, and in addition, multi-source data conforming to a model framework can be added into nodes of the fitting function to be used as new fitting factors such as fault data, profile data and the like. A transformation function of the stratigraphic discrete point data to the high density stratigraphic discrete point data is constructed. By continuously forward activating the learning process, a high-precision stratum discrete point data set can be constructed, and then a second stratum discrete point set table is generated through precision virtual drilling data, as shown in fig. 3.
Step S104, based on each layered data in the first stratum surface discrete point set table/the second stratum surface discrete point set table as initial data, carrying out nearest neighbor point solving by using a KNN algorithm in combination with the drilling data, determining stratum trend data through a solving result, and generating a stratum surface trend table through the stratum trend data pair.
Specifically, based on each stratum data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, combining geophysical prospecting data and stratum contour line data, performing nearest point solving by using a KNN algorithm, determining stratum trend data of characteristic point positions of the stratum contour line according to a solving result, generating a stratum trend table according to stratum trend data pairs, and predicting a data set of special conditions such as faults, folds, unconformities and the like of the stratum, as shown in table 2:
| field name | Remarks | Type(s) |
| X | x-coordinate system | Double |
| Y | y-coordinate | Double |
| Z | z-coordinate | Double |
| X_R | Inclination angle in X direction | Double |
| Y_R | Inclination angle in Y direction | Double |
| Z_R | Inclination angle in Z direction | Double |
| Code | Formation coding | String |
TABLE 2
Step S105, geological data of geological survey data are collected to generate a stratum basic information table, and a corresponding geological database is constructed according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table.
Specifically, the geological data of the collected geological survey data is used for generating a stratum basic information table, which comprises stratum names, formation years, stratum categories, stratum numbers, geological causes, layering sequences and other professional stratum information data, and the method is mainly used as a dictionary table to be associated with a stratum discrete point set table through the stratum numbers, as shown in table 3:
| field name | Remarks | Type(s) |
| Name | Formation name | String |
| Code | Formation coding | String |
| Year | Age of formation | String |
| Type | Formation class | String |
| Number | Stratum numbering | String |
| Origin | Geological causes | String |
TABLE 3 Table 3
And then, the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table are stored, and a corresponding geological database is constructed.
According to the intelligent construction method for the investigation stratum data set based on the generalized SR algorithm, provided by the embodiment of the invention, drilling data in geological investigation data are collected, layering positions corresponding to the drilling data are obtained, the drilling data are divided according to the layering positions, a corresponding data set is constructed for the drilling data of each stratum, and a corresponding picture data matrix is constructed according to the data set; judging the data precision requirement of the target data, and when the data precision requirement of the target data is lower than a preset standard, performing virtual drilling construction by combining a bilinear interpolation algorithm based on a picture data matrix to obtain corresponding quick virtual drilling data, and generating a first stratum discrete point set table through the quick virtual drilling data; when the data precision requirement of the target data is higher than a preset standard, constructing dimension information of output data based on the data precision requirement, constructing a corresponding SR model according to the dimension information, inputting drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum surface discrete point set table through the precision virtual drilling data; based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, combining drilling data, carrying out nearest neighbor point solving by using a KNN algorithm, determining stratum trend data according to a solving result, and generating a stratum trend table according to stratum trend data pairs; and acquiring geological data of geological survey data to generate a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table. Therefore, the three-dimensional geological database can be built, systematic complete data can be provided, meanwhile, virtual drilling construction is also carried out based on an SR algorithm, and the stratum data precision is improved.
Fig. 4 is a schematic diagram of an intelligent construction system for a survey stratum data set based on a generalized SR algorithm according to an embodiment of the present invention, including: the system comprises an acquisition module S201, a judgment module S202, an SR model module S203, a stratum surface trend module S204 and a database module S205, wherein:
the acquisition module S201 is used for acquiring drilling data in geological survey data, acquiring layering positions corresponding to the drilling data, dividing the drilling data according to the layering positions, constructing a corresponding data set for the drilling data of each stratum layer, and constructing a corresponding picture data matrix according to the data set.
And the judging module S202 is used for judging the data precision requirement of the target data, and performing virtual drilling construction by combining a bilinear interpolation algorithm based on the picture data matrix when the data precision requirement of the target data is lower than a preset standard to obtain corresponding quick virtual drilling data, and generating a first stratum surface discrete point set table through the quick virtual drilling data.
And the SR model module S203 is used for constructing dimension information of output data based on the data precision requirement when the data precision requirement of the target data is higher than a preset standard, constructing a corresponding SR model according to the dimension information, inputting the drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum discrete point set table through the precision virtual drilling data.
And the stratum trend module S204 is used for carrying out nearest neighbor point solving by using a KNN algorithm in combination with the drilling data based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, determining stratum trend data according to a solving result, and generating a stratum trend table according to the stratum trend data pair.
The database module S205 is configured to collect geological data of geological survey data, generate a stratum base information table, and construct a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table, and the stratum base information table.
In one embodiment, the system further comprises:
and the virtual drilling module is used for pre-constructing virtual data dimensions of a virtual stratum of the virtual drilling, determining corresponding target pixel points in the picture data matrix based on the virtual data dimensions, and combining four points around the target pixel points to perform pre-virtual drilling.
And the iteration module is used for carrying out KNN algorithm calculation through geophysical prospecting data and stratum contour line data in the drilling data, comparing an algorithm calculation result with the pre-virtual drilling result, taking the geophysical prospecting data and the stratum contour line data as weights when the comparison result is larger than a preset error value, and recalculating influence coefficients of a target pixel point and four surrounding points, and carrying out pre-virtual drilling again until the comparison result is smaller than the preset error value.
In one embodiment, the system further comprises:
the fitting module is used for acquiring geophysical prospecting data and stratum contour line data in the drilling data, fitting the geophysical prospecting data as a weight factor of a first layer of fitting function, fitting the stratum contour line data as a weight factor of a second layer of fitting function, and updating the corresponding weight factor through feed-forward when the fitting result does not meet a preset standard in two layers of fitting.
And the detection module is used for outputting the precision virtual drilling data after the two layers of fitting pass.
Specific limitations regarding the intelligent construction system for the survey formation data set based on the generalized SR algorithm can be found in the above description of the intelligent construction method for the survey formation data set based on the generalized SR algorithm, and will not be described herein. The modules in the intelligent construction system for the exploration stratum data set based on the generalized SR algorithm can be fully or partially realized by software, hardware and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: a processor (processor) 301, a memory (memory) 302, a communication interface (Communications Interface) 303 and a communication bus 304, wherein the processor 301, the memory 302 and the communication interface 303 perform communication with each other through the communication bus 304. The processor 301 may call logic instructions in the memory 302 to perform the following method: acquiring drilling data in geological investigation data, acquiring layering positions corresponding to the drilling data, dividing the drilling data according to the layering positions, constructing a corresponding data set for the drilling data of each stratum layer, and constructing a corresponding picture data matrix according to the data set; judging the data precision requirement of the target data, and when the data precision requirement of the target data is lower than a preset standard, performing virtual drilling construction by combining a bilinear interpolation algorithm based on a picture data matrix to obtain corresponding quick virtual drilling data, and generating a first stratum discrete point set table through the quick virtual drilling data; when the data precision requirement of the target data is higher than a preset standard, constructing dimension information of output data based on the data precision requirement, constructing a corresponding SR model according to the dimension information, inputting drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum surface discrete point set table through the precision virtual drilling data; based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, combining drilling data, carrying out nearest neighbor point solving by using a KNN algorithm, determining stratum trend data according to a solving result, and generating a stratum trend table according to stratum trend data pairs; and acquiring geological data of geological survey data to generate a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table.
Further, the logic instructions in memory 302 described above may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present invention further provide a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the transmission method provided in the above embodiments, for example, including: acquiring drilling data in geological investigation data, acquiring layering positions corresponding to the drilling data, dividing the drilling data according to the layering positions, constructing a corresponding data set for the drilling data of each stratum layer, and constructing a corresponding picture data matrix according to the data set; judging the data precision requirement of the target data, and when the data precision requirement of the target data is lower than a preset standard, performing virtual drilling construction by combining a bilinear interpolation algorithm based on a picture data matrix to obtain corresponding quick virtual drilling data, and generating a first stratum discrete point set table through the quick virtual drilling data; when the data precision requirement of the target data is higher than a preset standard, constructing dimension information of output data based on the data precision requirement, constructing a corresponding SR model according to the dimension information, inputting drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum surface discrete point set table through the precision virtual drilling data; based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, combining drilling data, carrying out nearest neighbor point solving by using a KNN algorithm, determining stratum trend data according to a solving result, and generating a stratum trend table according to stratum trend data pairs; and acquiring geological data of geological survey data to generate a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table.
The system embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent construction method for a reconnaissance stratum data set based on a generalized SR algorithm is characterized by comprising the following steps:
acquiring drilling data in geological survey data, acquiring layering positions corresponding to the drilling data, dividing the drilling data according to the layering positions, constructing a corresponding data set for the drilling data of each stratum layer, and constructing a corresponding picture data matrix according to the data set;
judging the data precision requirement of target data, when the data precision requirement of the target data is lower than a preset standard, performing virtual drilling construction by combining a bilinear interpolation algorithm based on the picture data matrix to obtain corresponding quick virtual drilling data, and generating a first stratum discrete point set table through the quick virtual drilling data;
when the data precision requirement of the target data is higher than a preset standard, constructing dimension information of output data based on the data precision requirement, constructing a corresponding SR model according to the dimension information, inputting the drilling data into the SR model, performing data fitting through the SR model until the data fitting is passed, generating corresponding precision virtual drilling data, and generating a second stratum discrete point set table through the precision virtual drilling data;
based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, combining the drilling data, carrying out nearest neighbor point solving by using a KNN algorithm, determining stratum trend data according to a solving result, and generating a stratum trend table according to the stratum trend data pair;
and acquiring geological data of geological survey data to generate a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table.
2. The intelligent construction method of a survey stratum data set based on a generalized SR algorithm according to claim 1, wherein the virtual drilling construction is performed by combining a bilinear interpolation algorithm based on the picture data matrix to obtain corresponding fast virtual drilling data, comprising:
pre-constructing virtual data dimensions of a virtual stratum of a virtual drilling hole, determining a corresponding target pixel point in the picture data matrix based on the virtual data dimensions, and combining four points around the target pixel point to perform pre-virtual drilling;
and carrying out KNN algorithm calculation through geophysical prospecting data and stratum contour line data in the drilling data, comparing an algorithm calculation result with the pre-virtual drilling result, and when the comparison result is larger than a preset error value, using the geophysical prospecting data and the stratum contour line data as weights, recalculating influence coefficients of a target pixel point and four points around, and carrying out pre-virtual drilling again until the comparison result is smaller than the preset error value.
3. The intelligent construction method of a survey formation data set based on a generalized SR algorithm of claim 1, wherein the inputting the borehole data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual borehole data, comprises:
acquiring geophysical prospecting data and stratum contour line data in the drilling data, fitting the geophysical prospecting data as weight factors of a first-layer fitting function, fitting the stratum contour line data as weight factors of a second-layer fitting function, and updating corresponding weight factors through feed-forward when a fitting result does not meet preset standards in two-layer fitting;
and after the two layers of fitting pass is detected, outputting the precision virtual drilling data after the fitting pass.
4. The intelligent construction method of a survey stratum data set based on a generalized SR algorithm according to claim 1, wherein the constructing a corresponding picture data matrix from the data set comprises:
correspondingly generating the picture attribute data in the picture data matrix through the attribute data in the drilling data, wherein the picture attribute data comprises the following steps:
and generating coordinate system coordinates of the picture data matrix through the abscissa and the ordinate of the drilling data, and generating R, G, B channel values and transparency of picture pixels in the picture data matrix through stratum coding, temperature, humidity and stress of the drilling data.
5. The intelligent construction method of a survey formation dataset based on a generalized SR algorithm of claim 1, wherein the borehole data comprises:
basic information including borehole number, orifice elevation, depth of hole, layering location, layering thickness, formation property information;
multisource data including geophysical prospecting data, formation contour line data, fault data, profile data.
6. An intelligent construction system for a survey stratum data set based on a generalized SR algorithm, the system comprising:
the acquisition module is used for acquiring drilling data in geological survey data, acquiring layering positions corresponding to the drilling data, dividing the drilling data according to the layering positions, constructing a corresponding data set for the drilling data of each stratum layer, and constructing a corresponding picture data matrix according to the data set;
the judging module is used for judging the data precision requirement of the target data, and when the data precision requirement of the target data is lower than a preset standard, virtual drilling construction is carried out by combining a bilinear interpolation algorithm based on the picture data matrix to obtain corresponding quick virtual drilling data, and a first stratum surface discrete point set table is generated through the quick virtual drilling data;
the SR model module is used for constructing dimension information of output data based on the data precision requirement when the data precision requirement of the target data is higher than a preset standard, constructing a corresponding SR model according to the dimension information, inputting the drilling data into the SR model, performing data fitting through the SR model until the data fitting passes, generating corresponding precision virtual drilling data, and generating a second stratum discrete point set table through the precision virtual drilling data;
the stratum trend module is used for carrying out nearest neighbor point solving by using a KNN algorithm in combination with the drilling data based on each layered data in the first stratum discrete point set table/the second stratum discrete point set table as initial data, determining stratum trend data through a solving result, and generating a stratum trend table through the stratum trend data pair;
and the database module is used for acquiring geological data of geological survey data, generating a stratum basic information table, and constructing a corresponding geological database according to the first stratum discrete point set table/the second stratum discrete point set table, the stratum trend table and the stratum basic information table.
7. The intelligent construction method for a survey formation dataset based on a generalized SR algorithm of claim 6, wherein the system further comprises:
the virtual drilling module is used for pre-constructing virtual data dimensions of a virtual stratum of the virtual drilling, determining corresponding target pixel points in the picture data matrix based on the virtual data dimensions, and carrying out pre-virtual drilling by combining four points around the target pixel points;
and the iteration module is used for carrying out KNN algorithm calculation through geophysical prospecting data and stratum contour line data in the drilling data, comparing an algorithm calculation result with the pre-virtual drilling result, taking the geophysical prospecting data and the stratum contour line data as weights when the comparison result is larger than a preset error value, and recalculating influence coefficients of a target pixel point and four surrounding points, and carrying out pre-virtual drilling again until the comparison result is smaller than the preset error value.
8. The intelligent construction method for a survey formation dataset based on a generalized SR algorithm of claim 6, wherein the system further comprises:
the fitting module is used for acquiring geophysical prospecting data and stratum contour line data in the drilling data, fitting the geophysical prospecting data as a weight factor of a first-layer fitting function, fitting the stratum contour line data as a weight factor of a second-layer fitting function, and updating the corresponding weight factor through feed-forward when the fitting result does not meet a preset standard in two-layer fitting;
and the detection module is used for outputting the precision virtual drilling data after the two layers of fitting pass.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the generalized SR algorithm-based survey formation dataset intelligent construction method according to any one of claims 1 to 5 when the program is executed.
10. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the generalized SR algorithm-based survey formation dataset intelligent construction method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310419918.9A CN116627963A (en) | 2023-04-18 | 2023-04-18 | Intelligent construction method and system for reconnaissance stratum data set based on generalized SR algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310419918.9A CN116627963A (en) | 2023-04-18 | 2023-04-18 | Intelligent construction method and system for reconnaissance stratum data set based on generalized SR algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116627963A true CN116627963A (en) | 2023-08-22 |
Family
ID=87601609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310419918.9A Pending CN116627963A (en) | 2023-04-18 | 2023-04-18 | Intelligent construction method and system for reconnaissance stratum data set based on generalized SR algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116627963A (en) |
-
2023
- 2023-04-18 CN CN202310419918.9A patent/CN116627963A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110284873B (en) | Method and device for detecting oil well reservoir properties | |
| CN112784980B (en) | Intelligent logging horizon dividing method | |
| CN114358427B (en) | Method for predicting final recoverable reserves of shale gas well | |
| AU2015411591A1 (en) | History matching of hydrocarbon production from heterogenous reservoirs | |
| CN109613623B (en) | Lithology prediction method based on residual error network | |
| CN110705179A (en) | Water guide crack belt height accurate prediction method and system based on fusion neural network | |
| CN116245013A (en) | Geological prediction model construction method, modeling method, equipment and storage medium | |
| CN114549774A (en) | Three-dimensional stratum modeling method based on drilling data | |
| US20130132055A1 (en) | Method for optimizing the development of an underground medium by means of a reservoir study comprising optimized upscaling | |
| CN116721227A (en) | Automatic modeling method for three-dimensional geologic model of complex geologic body | |
| CN116627963A (en) | Intelligent construction method and system for reconnaissance stratum data set based on generalized SR algorithm | |
| US20200308934A1 (en) | Automatic calibration of forward depositional models | |
| CN114036829B (en) | Geological profile generation method, system, equipment and storage medium | |
| US8942966B2 (en) | Method for parameterizing and morphing stochastic reservoir models | |
| CN113447997B (en) | Reservoir fracture identification method, identification device and identification system | |
| CN108074282B (en) | Thickness correction method of physical property parameters based on three-dimensional geological modeling software | |
| CN114764546A (en) | Method for predicting residual oil of fault block oil reservoir based on generation of antagonistic neural network | |
| Chen et al. | The improved Kriging interpolation algorithm for local underwater terrain based on fractal compensation | |
| WO2024040801A9 (en) | Transverse wave time difference prediction method and apparatus | |
| CN117633658B (en) | Rock reservoir lithology identification method and system | |
| US20230142526A1 (en) | Systems and methods of predictive decline modeling for a well | |
| US20230376658A1 (en) | Systems and methods for performing drilling rig operations | |
| CN117574269B (en) | Intelligent identification method and system for natural cracks of land shale reservoir | |
| CN116204965B (en) | Working method for embedding two-dimensional rock and soil investigation information into three-dimensional building model | |
| US20220228483A1 (en) | Systems and methods for updating reservoir static models |
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 |