CN116047598B - Oil exploration method and system based on artificial intelligence - Google Patents
Oil exploration method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN116047598B CN116047598B CN202211385134.0A CN202211385134A CN116047598B CN 116047598 B CN116047598 B CN 116047598B CN 202211385134 A CN202211385134 A CN 202211385134A CN 116047598 B CN116047598 B CN 116047598B
- Authority
- CN
- China
- Prior art keywords
- exploration
- stratum
- data
- oil
- groups
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/30—Analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/30—Analysis
- G01V1/301—Analysis for determining seismic cross-sections or geostructures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/30—Analysis
- G01V1/306—Analysis for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles
Abstract
The invention provides an artificial intelligence-based petroleum exploration method and system, which relate to the technical field of petroleum exploration, wherein seismic exploration survey lines are optimized according to the landform characteristics of a sedimentary basin, a plurality of seismic exploration survey lines are generated and are explored, a plurality of groups of seismic exploration data are collected, the obtained data are processed to generate a stratum profile, the stratum profile is subjected to feature analysis to generate a plurality of stratum features, the stratum features are input into an oil-containing probability calibration table to generate an oil-containing probability evaluation result, the oil content is evaluated according to the stratum boundary features to generate an evaluation result, and the evaluation result is added into the petroleum exploration result. The invention solves the technical problems of low decision efficiency caused by most expert experience decision making in petroleum exploration in the prior art, realizes data acquisition from multiple parties and strict data mining, uses an intelligent model to evaluate the oil content and the oil-containing area, and achieves the technical effects of determining a reliable exploration survey line and improving exploration accuracy and efficiency.
Description
Technical Field
The invention relates to the technical field of petroleum exploration, in particular to an artificial intelligence-based petroleum exploration method and system.
Background
In 2020, a complex well drilling matching technology at 8000 m deep layer in China is used for creating a plurality of records, and under the diligence of scientists, the petroleum exploration technology is far away and leading in the global scope. The conventional petroleum exploration method has certain defects, and certain liftable space exists for petroleum exploration.
In the existing petroleum exploration method, most of data are judged and decided by expert experience due to high complexity, so that the decision efficiency is low.
Disclosure of Invention
The embodiment of the application provides an artificial intelligence-based oil exploration method and system, which are used for solving the technical problems that most of expert experience judgment decisions are caused by higher complexity of various data of oil exploration in the prior art, so that the decision efficiency is lower.
In view of the above problems, the embodiments of the present application provide an artificial intelligence-based oil exploration method and system.
In a first aspect, an embodiment of the present application provides an artificial intelligence-based oil exploration method, the method including: optimizing the seismic exploration survey lines according to the geomorphic characteristics of the sedimentary basin to generate a plurality of seismic exploration survey lines; exploration is carried out according to the plurality of seismic exploration survey lines, and a plurality of groups of seismic exploration data are collected; processing the plurality of groups of seismic exploration data to generate a stratum profile; performing feature analysis according to the stratum profile to generate stratum age features, stratum lithology features, stratum thickness features and stratum boundary features; inputting the stratum age characteristic, the stratum lithology characteristic and the stratum thickness characteristic into an oil-containing probability calibration table to generate an oil-containing probability evaluation result; when the oil content probability evaluation result meets the preset oil content probability, carrying out oil content evaluation according to the stratum boundary characteristics to generate an oil content evaluation result and an oil content area evaluation result; and adding the oil content evaluation result and the oil-containing area evaluation result into an oil exploration result.
In a second aspect, embodiments of the present application provide an artificial intelligence based oil exploration system, the system comprising: the exploration survey line optimizing module is used for optimizing the seismic exploration survey lines according to the landform characteristics of the sedimentary basin to generate a plurality of seismic exploration survey lines; the exploration data acquisition module is used for carrying out exploration according to the plurality of seismic exploration survey lines and acquiring a plurality of groups of seismic exploration data; the stratum profile determining module is used for processing the plurality of groups of seismic exploration data to generate stratum profile diagrams; the stratum feature extraction module is used for carrying out feature analysis according to the stratum profile to generate stratum age features, stratum lithology features, stratum thickness features and stratum boundary features; the oil-containing probability calibration module is used for inputting the stratum age characteristic, the stratum lithology characteristic and the stratum thickness characteristic into an oil-containing probability calibration table to generate an oil-containing probability evaluation result; the oil content parameter evaluation module is used for carrying out oil content evaluation according to the stratum boundary characteristics when the oil content probability evaluation result meets the preset oil content probability to generate an oil content evaluation result and an oil content area evaluation result; and the exploration data uploading module is used for adding the oil content evaluation result and the oil content area evaluation result into the petroleum exploration result.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
the embodiment of the application provides an artificial intelligence-based petroleum exploration method, which relates to the technical field of petroleum exploration, and comprises the steps of optimizing seismic exploration survey lines according to the landform characteristics of a sedimentary basin to generate a plurality of seismic exploration survey lines, exploration according to the plurality of seismic exploration survey lines, collecting a plurality of groups of seismic exploration data, processing the plurality of groups of seismic exploration data to generate a stratum profile, carrying out feature analysis according to the stratum profile to generate a plurality of stratum features, inputting the plurality of stratum features into an oil-containing probability calibration table to generate an oil-containing probability evaluation result, carrying out oil content evaluation according to the stratum boundary features when the oil-containing probability evaluation result meets preset oil-containing probability, generating an evaluation result, and adding the evaluation result into the petroleum exploration result. The technical problems that most of expert experience judgment decisions are caused by high complexity of various data of petroleum exploration in the prior art, so that the decision efficiency is low are solved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow diagram of an artificial intelligence-based oil exploration method according to an embodiment of the application;
FIG. 2 is a schematic diagram of a flow chart of generating a plurality of seismic exploration survey lines in an artificial intelligence based oil exploration method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a formation profile generated in an artificial intelligence based oil exploration method according to an embodiment of the present application;
fig. 4 is a schematic diagram of a petroleum exploration system based on artificial intelligence according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an exploration survey line optimization module 10, an exploration data acquisition module 20, a stratum profile determination module 30, a stratum feature extraction module 40, an oil content probability calibration module 50, an oil content parameter evaluation module 60 and an exploration data uploading module 70.
Detailed Description
The embodiment of the application provides an artificial intelligence-based oil exploration method, which is used for solving the technical problems that most of expert experience judgment decisions are caused by higher complexity of various data of oil exploration in the prior art, so that the decision efficiency is lower.
Example 1
As shown in fig. 1, an embodiment of the present application provides an artificial intelligence-based oil exploration method, which includes:
Step S100: optimizing the seismic exploration survey lines according to the geomorphic characteristics of the sedimentary basin to generate a plurality of seismic exploration survey lines;
specifically, the oil exploration method based on the artificial intelligence is applied to an oil exploration system based on the artificial intelligence. Firstly, petroleum exploration personnel use geological knowledge to directly observe and research the bottom layer and rock exposed on the ground in the field to know the sedimentary stratum and structural characteristics, and the sedimentary stratum and structural characteristics are used as the landform characteristics of the sedimentary basin. Acquiring past multiple groups of seismic exploration record data through big data according to the geomorphic characteristics of a sedimentary basin, wherein the multiple groups of seismic exploration record data comprise exploration line record data and stratum profile deviation record data, strictly mining the exploration line record data and the stratum profile deviation record data to generate multiple groups of exploration line mining results and multiple exploration line confidence levels, wherein the multiple groups of exploration line mining results and the multiple exploration line confidence levels are in one-to-one correspondence, and generating the multiple seismic exploration lines according to the exploration line mining results corresponding to the maximum value of the multiple exploration line confidence levels.
Step S200: exploration is carried out according to the plurality of seismic exploration survey lines, and a plurality of groups of seismic exploration data are collected;
specifically, when a well is drilled and blasted at a certain point on the ground survey line according to one seismic exploration line, the seismic waves are generated to propagate to the underground, and the seismic waves are reflected by the interface of two strata, such as the interface of sandstone and mudstone, and then downwards propagate to the interface of two rocks, such as the interface of mudstone and limestone. During blasting, the condition of ground vibration caused by reflected waves from all stratum interfaces is recorded by a detector on the ground, then the propagation time of the seismic waves from the ground downwards, namely the explosion time and the arrival time of the reflected waves from the stratum interfaces at the ground are obtained according to the time when the seismic waves from the ground downwards reach the stratum interfaces, the propagation time of the reflected waves reflected back to the ground is obtained, the propagation speed v of the seismic waves in the stratum is measured, and the burial depth of the stratum interfaces can be calculated, and the propagation position of the reflected waves is marked. And arranging a plurality of measuring lines in a work area to form a measuring line network, observing on each measuring line to obtain a plurality of groups of time t and propagation speed v, and combining the propagation positions of reflected waves to obtain a plurality of groups of seismic exploration data.
Step S300: processing the plurality of groups of seismic exploration data to generate a stratum profile;
acquiring a plurality of groups of first-stage reflection wave propagation duration record data and a plurality of groups of first-stage reflection wave propagation position record data according to the plurality of groups of first-stage reflection wave propagation duration record data and the plurality of groups of first-stage reflection wave propagation position record data, determining a first-stage interface relief profile, acquiring a plurality of groups of N-stage reflection wave propagation duration record data and a plurality of groups of N-stage reflection wave propagation position record data according to the plurality of groups of seismic survey data, determining an N-stage interface relief profile according to the plurality of groups of N-stage reflection wave propagation duration record data and the plurality of groups of N-stage reflection wave propagation position record data, and arranging the first-stage interface relief profile up to the N-stage interface relief profile from top to bottom to generate the stratum profile.
The method solves the technical problem that most of the earth surface is covered by modern deposition to limit geological exploration, realizes excitation of seismic waves by using an artificial method, and obtains underground geological conditions by utilizing different characteristics of seismic wave propagation rules in different rocks.
Step S400: performing feature analysis according to the stratum profile to generate stratum age features, stratum lithology features, stratum thickness features and stratum boundary features;
Specifically, the stratum profile is a profile obtained by tangential to the terrain along a certain direction of the ground surface by an imaginary vertical plane, and the intersecting line of the profile and the ground surface is called a section line, so as to record and reveal the correlation between the morphology and the internal structure of the profile in the certain direction. The principal content of the stratum profile includes the profile direction, topography and lithology, thickness, age and production of the stratum, which may exhibit a wrinkled morphology, fault properties, morphology of igneous rock and ore bodies, and may represent their location and scale, etc.
The stratum characteristic, the stratum lithology characteristic, the stratum thickness characteristic and the stratum boundary characteristic are obtained from the obtained stratum profile, wherein the stratum characteristic is divided according to the biological evolution stage, and the stratum is divided into units with different levels from large to small as universe, generation, century, generation and period due to different phylum types of living beings and the length of the evolution stage, and the generation and period are chronostratigraphic units in one-to-one correspondence with the stratum units: space, world, system, order; the stratum lithology characteristics and stratum lithology characteristics refer to stratum bodies formed by rocks with uniform lithology, lithology or deterioration degree, namely, the stratum bodies are mainly divided by the lithology and the lithology; the formation thickness is characterized by the distance between two layers, and can be divided into: true thickness, apparent thickness, plumb thickness; the stratum boundary features are used for dividing stratum according to identifiable geological events to obtain stratum boundaries. Through the characteristic analysis of the stratum profile, the field geological condition can be truly known, and a foundation is laid for subsequent oil content evaluation.
Step S500: inputting the stratum age characteristic, the stratum lithology characteristic and the stratum thickness characteristic into an oil-containing probability calibration table to generate an oil-containing probability evaluation result;
specifically, a plurality of interaction parties with trust degree are constructed based on big data to provide exploration data, when a preset updating period is met, oil exploration record data are obtained, wherein the oil exploration record data comprise a plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, any one group of the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values is parallelly sent to a plurality of expert groups, a plurality of oil-containing probability initial calibration results are obtained, an average value is obtained for the plurality of oil-containing probability initial calibration results, an oil-containing probability expected calibration result is generated, and the oil-containing probability calibration table is constructed according to a plurality of oil-containing probability expected calibration results. And inputting the stratum age characteristic, the stratum lithology characteristic and the stratum thickness characteristic into an oil-containing probability calibration table, and matching with data in the oil-containing probability calibration table to obtain a generated oil-containing probability evaluation result. Through judging historical data by a plurality of experts and taking an average value of the judging results, professional judgment on the historical data is realized, and then reliable judging standards are obtained.
Step S600: when the oil content probability evaluation result meets the preset oil content probability, carrying out oil content evaluation according to the stratum boundary characteristics to generate an oil content evaluation result and an oil content area evaluation result;
specifically, a preset oil probability is set, for example, to be 50%, that is, the oil probability of the survey area is too low to be worth further mining when the obtained oil probability evaluation result is less than 50%, and the next step can be performed when the oil probability evaluation result is more than 50%. The oil exploration record data further comprises a plurality of groups of oil reservoir exploitation record data and a plurality of groups of stratum boundary record characteristic values, a plurality of groups of oil yield record data and a plurality of groups of oil yield area record data are obtained according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil yield record data are subjected to supervised learning, an oil content evaluation layer is constructed, an oil content area evaluation layer is constructed similarly, the oil content evaluation layer and the oil content area evaluation layer are combined as two parallel nodes, an oil content parameter evaluation model is generated, and the oil content evaluation result and the oil content area evaluation result are output according to the oil content parameter evaluation model. The oil content and the oil-containing area are evaluated by using an intelligent model, so that the effect of improving the treatment efficiency is achieved.
Step S700: and adding the oil content evaluation result and the oil-containing area evaluation result into an oil exploration result.
Specifically, preferably, the oil exploration results include the obtained oil content evaluation results and the oil-containing area evaluation results. The method has the advantages of improving exploration quality, accuracy and depth, and achieving the technical effect of improving oil finding efficiency.
Further, as shown in fig. 2, step S100 of the present application further includes:
step S110: collecting a plurality of groups of seismic exploration record data according to the geomorphic characteristics of the sedimentary basin, wherein the plurality of groups of seismic exploration record data comprise exploration survey line record data and stratum profile deviation record data;
step S120: performing strict data mining on the exploration line record data and the stratum profile deviation degree record data to generate a plurality of groups of exploration line mining results and a plurality of exploration line confidence degrees, wherein the plurality of groups of exploration line mining results and the plurality of exploration line confidence degrees are in one-to-one correspondence;
step S130: and generating the plurality of seismic exploration lines according to exploration line mining results corresponding to the maximum value of the confidence degrees of the plurality of exploration lines.
Specifically, petroleum exploration personnel obtain the sedimentary basin landform characteristics of a to-be-explored area through observation and research, and acquire exploration survey line record data and stratum profile deviation record data through geological data of the related landform characteristics, wherein the exploration survey line record data are survey line data when historical exploration personnel conduct exploration on the sedimentary basin landform characteristics, and comprise exploration line tracks, exploration line drilling depths and drilling positions, and the stratum profile deviation record data are deviation conditions of actual stratum profile and calculated stratum profile after exploration is conducted by the historical exploration personnel according to the survey line data.
Constructing an m-term support degree calculation formula according to the frequency sum of the co-occurrence of m-term test lines in the exploration test line record data under the deviation degree of a plurality of stratum sections, setting a deviation degree threshold, wherein the deviation degree threshold is the lowest deviation degree of test lines meeting the screening requirement, constructing an m-term confidence degree calculation formula according to the frequency sum of the co-occurrence of m-term test lines meeting the deviation degree threshold, and the frequency sum of the co-occurrence of m-term test lines in the multi-group data of a certain stratum section deviation degree, traversing the exploration test line record data and the stratum section deviation degree record data according to the m-term support degree calculation formula and the m-term confidence degree calculation formula, and generating the plurality of exploration test line confidence degrees. Matching the exploration line confidence with the exploration line record data to obtain a plurality of groups of exploration line mining results corresponding to each exploration line confidence, wherein the exploration line confidence and the exploration line record data are in one-to-one correspondence.
Sequencing the obtained survey line confidence coefficient to obtain a maximum value, and matching the corresponding survey line mining results with the maximum value of the survey line confidence coefficient according to the one-to-one correspondence between the survey line confidence coefficient and the survey line mining results to generate the plurality of seismic survey lines. The historical data is used for screening and optimizing a plurality of measuring lines, so that the accurate grasp of the seismic exploration measuring lines is realized, and a foundation is laid for subsequent seismic exploration.
Further, step S120 of the present application further includes:
step S121: building an m-term support degree calculation formula:
A ij ＝<x j1 ,x j2 ,x j3 ,…x jk ,…>
wherein A is ij Recording data, x, of the j-th group exploration survey line of the ith stratum section deviation degree jk A kth line representing recorded data of a jth set of survey lines, n representing a total number of recorded sets of ith formation profile deviations,in n groups of data representing the degree of deviation of the section of the ith stratum, x k →x k+m The sum of the frequencies of co-occurrence of the m lines in total,characterizing m item support degrees;
step S122: building an m-term confidence coefficient calculation formula:
wherein x is yk →x y(k+m) Characterization of x k →x k+m The sum of the frequency of co-occurrence of a certain group of m lines meeting the deviation threshold,in n groups of data representing the degree of deviation of the section of the ith stratum, x yk →x y(k+m) The sum of the frequencies of the co-occurrence of the m lines in total,/->Characterizing m item confidence;
step S123: traversing the exploration line record data and the stratum profile deviation degree record data according to the m item support degree calculation formulas and the m item confidence degree calculation formulas, and generating the multi-group exploration line mining results and the multi-exploration line confidence degrees.
Specifically, an m-term support degree calculation formula is obtained according to the formula and used for representing the frequency of the co-occurrence of m-term measuring lines in n groups of data under the ith stratum profile deviation degree, and an m-term confidence degree calculation formula is obtained according to the formula and used for representing the proportion of the sum of the frequency of the co-occurrence of m-term measuring lines meeting the deviation degree threshold to the frequency of the co-occurrence of m-term measuring lines in n groups of data. Integrating the exploration line record data and the stratum profile deviation degree record data into an array, sequentially calculating each data in the array according to the obtained formula to obtain a plurality of exploration line confidence degrees, and matching the exploration line confidence degrees with the exploration line record data to obtain a plurality of groups of exploration line mining results corresponding to each exploration line confidence degree, wherein the two groups of exploration line mining results are in one-to-one correspondence. Through strict data mining, the determination of reliable exploration survey lines is realized, and the exploration efficiency is improved.
Further, as shown in fig. 3, step S300 of the present application further includes:
step S310: acquiring a plurality of groups of first-order reflected wave propagation time length record data and a plurality of groups of first-order reflected wave propagation position record data according to the plurality of groups of seismic exploration data;
step S320: determining a first-level interface fluctuation profile according to the multiple sets of first-level reflected wave propagation duration record data and the multiple sets of first-level reflected wave propagation position record data;
step S330: acquiring a plurality of groups of N-level reflected wave propagation time length record data and a plurality of groups of N-level reflected wave propagation position record data according to the plurality of groups of seismic exploration data;
step S340: determining an N-level interface relief profile according to the plurality of groups of N-level reflected wave propagation time length record data and the plurality of groups of N-level reflected wave propagation position record data;
step S350: and arranging the primary interface relief profile until the N-level interface relief profile from top to bottom to generate the stratum profile.
Specifically, one exploration line is selected from multiple groups of seismic exploration data, multiple measurement data are arranged at multiple positions on the exploration line, the measurement data comprise reflected wave propagation time length and reflected wave propagation position marks, the first-order reflected wave propagation time length and the first-order reflected wave propagation position of the exploration line are recorded, multiple exploration lines are selected from multiple groups of seismic exploration data, and multiple groups of first-order reflected wave propagation time length recording data and multiple groups of first-order reflected wave propagation position recording data are obtained. The propagation time of the reflected wave is related to the property and structure of the underground rock stratum through which the seismic wave passes, an interface fluctuation profile on a certain exploration line is drawn according to the property and structure of the underground rock stratum, the exploration line is taken as a transverse axis, exploration positions on the exploration line are selected, the corresponding first-level reflected wave propagation time can be obtained by exploration at each exploration position, the propagation time is taken as a longitudinal axis, the point of the corresponding wave propagation time at each exploration position is connected with a smooth curve, and the curve represents the first-level interface fluctuation profile on the exploration line.
Illustratively, if the propagation time lengths of the reflected waves at the exploration positions are consistent, the drawn line is a straight line, which indicates that the interface a is a plane; if an interface b is raised, the propagation time of the reflected wave from the interface b varies at various points, and is short at the shallow point of the interface and long at the deep point of the interface, and the contoured profile of the interface corresponds to the shape of the interface 2.
And adjusting the reflected wave, obtaining an N-level interface relief profile by the same method, and arranging the first-level interface relief profile until the N-level interface relief profile is arranged from top to bottom to generate the stratum profile. The method solves the technical problem that most of the earth surface is covered by modern deposition to limit geological exploration, realizes excitation of seismic waves by using an artificial method, and obtains underground geological conditions by utilizing different characteristics of seismic wave propagation rules in different rocks.
Further, the step S500 of the present application further includes:
step S510: acquiring petroleum exploration record data when a preset updating period is met, wherein the petroleum exploration record data comprises a plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values;
Step S520: any one group of the formation age record characteristic values, the formation lithology record characteristic values and the formation thickness record characteristic values is parallelly transmitted to a plurality of expert groups, and a plurality of initial calibration results of oil-containing probability are obtained;
step S530: calculating an average value of the plurality of initial calibration results of the oil-containing probability to generate an expected calibration result of the oil-containing probability;
step S540: and constructing the oil-containing probability calibration table according to a plurality of expected oil-containing probability calibration results.
Specifically, a plurality of interaction parties with trust degree are constructed based on big data to provide exploration data, wherein the interaction parties comprise petroleum exploration experts, databases of other companies and the like, and the obtained exploration data are integrated to be used as petroleum exploration record data, wherein the petroleum exploration record data comprises a plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values. The expert groups are professionals in the petroleum exploration field, and each expert group is not connected with each other, so that judgment of other people is not affected. And (3) transmitting any one of the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values to a plurality of expert groups in parallel, and carrying out subjective judgment on oil-containing probabilities under different stratum characteristics by the expert groups according to professional knowledge to obtain a plurality of oil-containing probability initial calibration results. Because different experts judge the stratum differently, a plurality of initial calibration results of the oil-containing probability can be obtained under the same stratum, and the average value of the obtained initial calibration results of the oil-containing probability is calculated, so that the expected calibration result of the oil-containing probability can be obtained. And matching a plurality of corresponding expected oil-bearing probability calibration results according to a plurality of stratum features in the petroleum exploration record data, so as to construct the oil-bearing probability calibration table. Through judging historical data by a plurality of experts and taking an average value of the judging results, professional judgment on the historical data is realized, and then reliable judging standards are obtained.
Further, step S600 of the present application includes:
step S610: the petroleum exploration record data also comprises a plurality of groups of oil deposit exploitation record data and a plurality of groups of stratum boundary record characteristic values;
step S620: acquiring a plurality of groups of oil output record data and a plurality of groups of oil output area record data according to the plurality of groups of oil reservoir exploitation record data;
step S630: performing supervised learning according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values, stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil yield record data to construct an oil content evaluation layer;
step S640: performing supervised learning according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values, stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil outlet area record data to construct an oil-containing area evaluation layer;
step S650: combining the oil content evaluation layer and the oil content area evaluation layer as two parallel nodes to generate an oil content parameter evaluation model;
step S660: and outputting the oil content evaluation result and the oil content area evaluation result according to the oil content parameter evaluation model.
Specifically, supervised learning is a machine learning task that extrapolates functions from a labeled training dataset, the training dataset consisting of a set of training instances, analyzes the training data through a supervised learning algorithm, and generates an extrapolated function that can be used to map new instances. And performing supervised learning based on a feedforward neural network according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil yield record data, constructing a first sub-model, constructing a plurality of simpler sub-models which are easy to converge through the idea of integrated learning, combining the plurality of sub-models, and generating the oil yield evaluation layer. Only the construction process of the oil content evaluation layer is described here, and the construction process of the oil content area evaluation layer is identical and will not be described here again. And combining the oil content evaluation layer and the oil content area evaluation layer as two parallel nodes to generate an oil content parameter evaluation model. And taking the obtained stratum boundary characteristics in the exploration area as input data, and outputting the oil content evaluation result and the oil content area evaluation result through an oil content evaluation layer and an oil content area evaluation layer.
The oil content and the oil-containing area are evaluated by using an intelligent model, so that the effect of improving the treatment efficiency is achieved.
Further, step S630 of the present application further includes:
step S631: performing supervised learning based on a feedforward neural network according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil yield record data to construct a first sub-model;
step S632: recording the multi-group stratum age record characteristic values, stratum lithology record characteristic values, stratum thickness record characteristic values and the oil yield record data of which the first sub-model does not meet the preset accuracy as a first loss data set;
step S633: judging whether the data volume of the first loss data set is smaller than or equal to a data volume threshold value;
step S634: if the data is larger than the first loss data set, performing supervised learning based on a feedforward neural network, and constructing a second sub-model;
step S635: and when the data volume of the H-th loss data set is smaller than or equal to the data volume threshold, merging the first sub-model and the second sub-model until the H-th sub-model to generate the oil volume evaluation layer, wherein the oil volume evaluation layer is an output weighted average value of all the sub-models.
Specifically, the feedforward neural network is the simplest neural network, each neuron is arranged in layers, each neuron is only connected with neurons of the previous layer, receives output of the previous layer and outputs the output to the next layer, each layer has no feedback, and is one of the most widely applied and rapidly developed artificial neural networks, no feedback exists in the whole network, and a signal is transmitted unidirectionally from an input layer to an output layer and can be represented by a directed acyclic graph.
And taking the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil output volume record data as training sets to establish a mathematical model, predicting an unknown sample by using the established model, namely, a supervised learning process, so as to establish a first sub-model, setting preset accuracy, wherein the accuracy is the ratio of actual exploration oil output volume to predicted oil output volume, taking the training set which does not meet the preset accuracy of the first sub-model as a first loss data set, setting a data volume threshold, and taking the data volume threshold as preset training convergence point data volume, and if the training set is larger than the first loss data set, performing supervised learning based on a feedforward neural network, and establishing a second sub-model, wherein the feedforward neural network has the effects of high accuracy and easy convergence because of simplicity. And constructing a plurality of sub-models until the data volume of the H-th lost data set is smaller than or equal to a data volume threshold, combining the obtained plurality of sub-models, and taking a weighted average value of the outputs of all the sub-models, namely that the output weight of each sub-model=the data volume of the lost data set/the total data volume is 100%, so as to construct the oil output volume evaluation layer.
Through the idea of integrated learning, a plurality of simpler sub-models which are easy to converge are built, and the sub-models are combined, so that the model construction with better processing accuracy and training speed is realized.
Example two
Based on the same inventive concept as the oil exploration method based on artificial intelligence in the previous embodiment, as shown in fig. 4, the present application provides an oil exploration system based on artificial intelligence, the system comprising:
the exploration survey line optimizing module 10 is used for optimizing the seismic exploration survey lines according to the landform features of the sedimentary basin to generate a plurality of seismic exploration survey lines;
the exploration data acquisition module 20 is used for carrying out exploration according to the plurality of seismic exploration survey lines and acquiring a plurality of groups of seismic exploration data;
the stratum profile determining module 30 is used for processing the plurality of groups of seismic exploration data to generate a stratum profile;
the stratum feature extraction module 40 is used for carrying out feature analysis according to the stratum profile to generate stratum age features, stratum lithology features, stratum thickness features and stratum boundary features;
The oil-containing probability calibration module 50 is used for inputting the stratum age characteristic, the stratum lithology characteristic and the stratum thickness characteristic into an oil-containing probability calibration table to generate an oil-containing probability evaluation result;
the oil content parameter evaluation module 60, wherein the oil content parameter evaluation module 60 is configured to perform oil content evaluation according to the formation boundary characteristics when the oil content probability evaluation result meets a preset oil content probability, so as to generate an oil content evaluation result and an oil content area evaluation result;
and the exploration data uploading module 70 is used for adding the oil content evaluation result and the oil-containing area evaluation result into an oil exploration result by the exploration data uploading module 70.
Further, the system further comprises:
the seismic exploration record data acquisition module is used for acquiring a plurality of groups of seismic exploration record data according to the geomorphic characteristics of the sedimentary basin, wherein the plurality of groups of seismic exploration record data comprise exploration survey line record data and stratum profile deviation record data;
the data mining module is used for carrying out strict data mining on the exploration line record data and the stratum profile deviation degree record data to generate a plurality of groups of exploration line mining results and a plurality of exploration line confidence degrees, wherein the plurality of groups of exploration line mining results and the plurality of exploration line confidence degrees are in one-to-one correspondence;
The seismic exploration line generation module is used for generating the plurality of seismic exploration lines according to exploration line mining results corresponding to the maximum value of the confidence coefficient of the plurality of exploration lines.
Further, the system further comprises:
the support degree calculation formula construction module is used for constructing an m-term support degree calculation formula;
the confidence coefficient calculation formula construction module is used for constructing an m-term confidence coefficient calculation formula;
the recorded data traversing module is used for traversing the exploration line recorded data and the stratum profile deviation degree recorded data according to the m item support degree calculation formulas and the m item confidence degree calculation formulas to generate the multi-group exploration line mining results and the multi-exploration line confidence degrees.
Further, the system further comprises:
the first-stage reflected wave record data acquisition module is used for acquiring a plurality of groups of first-stage reflected wave propagation duration record data and a plurality of groups of first-stage reflected wave propagation position record data according to the plurality of groups of seismic exploration data;
the primary interface relief profile acquisition module is used for determining a primary interface relief profile according to the multiple groups of primary reflection wave propagation duration record data and the multiple groups of primary reflection wave propagation position record data;
The N-level reflected wave record data acquisition module is used for acquiring a plurality of groups of N-level reflected wave propagation duration record data and a plurality of groups of N-level reflected wave propagation position record data according to the plurality of groups of seismic exploration data;
the N-level interface fluctuation profile acquisition module is used for determining an N-level interface fluctuation profile according to the plurality of groups of N-level reflection wave propagation time length record data and the plurality of groups of N-level reflection wave propagation position record data;
and the stratum profile acquisition module is used for arranging the primary interface relief profile to the N-level interface relief profile from top to bottom to generate the stratum profile.
Further, the system further comprises:
the petroleum exploration record data acquisition module is used for acquiring petroleum exploration record data when a preset updating period is met, wherein the petroleum exploration record data comprises a plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values;
the petroleum exploration record data processing module is used for parallelly transmitting any one group of the formation age record characteristic values, the formation lithology record characteristic values and the formation thickness record characteristic values to a plurality of expert groups to obtain a plurality of initial calibration results of oil-containing probability;
The oil-containing probability expected calibration result generation module is used for solving the average value of the plurality of oil-containing probability initial calibration results to generate an oil-containing probability expected calibration result;
the oil-containing probability calibration table construction module is used for constructing the oil-containing probability calibration table according to a plurality of expected oil-containing probability calibration results.
Further, the system further comprises:
the oil outlet record data acquisition module is used for acquiring a plurality of groups of oil outlet volume record data and a plurality of groups of oil outlet area record data according to the plurality of groups of oil reservoir exploitation record data;
the oil content evaluation layer construction module is used for performing supervised learning according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil content record data to construct an oil content evaluation layer;
the oil-containing area evaluation layer construction module is used for performing supervised learning according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil-yielding area record data to construct an oil-containing area evaluation layer;
The oil-containing parameter evaluation model generation module is used for combining the oil-containing evaluation layer and the oil-containing area evaluation layer as two parallel nodes to generate an oil-containing parameter evaluation model;
and the oil content evaluation result output module is used for outputting the oil content evaluation result and the oil content area evaluation result according to the oil content parameter evaluation model.
Further, the system further comprises:
the first sub-model construction module is used for performing supervised learning based on the feedforward neural network according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil output record data to construct a first sub-model;
the first loss data set acquisition module is used for recording the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values, stratum thickness record characteristic values and the oil output volume record data which do not meet the preset accuracy of the first sub-model as a first loss data set;
a first loss data set judging module, configured to judge whether a data amount of the first loss data set is less than or equal to a data amount threshold;
The second sub-model building module is used for performing supervised learning based on a feedforward neural network according to the first loss data set if the first loss data set is larger than the first loss data set, and building a second sub-model;
and the submodel merging module is used for merging the first submodel and the second submodel until the H-th submodel to generate the oil output quantity evaluation layer when the data quantity of the H-th lost data set is smaller than or equal to the data quantity threshold value, wherein the oil output quantity evaluation layer is an output weighted average value of all submodels.
The foregoing detailed description of an artificial intelligence-based oil exploration method and system will be apparent to those skilled in the art, and the device disclosed in this embodiment is relatively simple in description and relevant places refer to the description of the method section because it corresponds to the method disclosed in the embodiment.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. An artificial intelligence based oil exploration method, comprising:
optimizing the seismic exploration survey lines according to the geomorphic characteristics of the sedimentary basin to generate a plurality of seismic exploration survey lines;
exploration is carried out according to the plurality of seismic exploration survey lines, and a plurality of groups of seismic exploration data are collected;
processing the plurality of groups of seismic exploration data to generate a stratum profile;
performing feature analysis according to the stratum profile to generate stratum age features, stratum lithology features, stratum thickness features and stratum boundary features;
inputting the stratum age characteristic, the stratum lithology characteristic and the stratum thickness characteristic into an oil-containing probability calibration table to generate an oil-containing probability evaluation result;
when the oil content probability evaluation result meets the preset oil content probability, carrying out oil content evaluation according to the stratum boundary characteristics to generate an oil content evaluation result and an oil content area evaluation result;
adding the oil content evaluation result and the oil content area evaluation result into an oil exploration result;
optimizing the seismic exploration survey line according to the sedimentary basin landform characteristics to generate a plurality of seismic exploration survey lines, including:
Collecting a plurality of groups of seismic exploration record data according to the geomorphic characteristics of the sedimentary basin, wherein the plurality of groups of seismic exploration record data comprise exploration survey line record data and stratum profile deviation record data;
performing strict data mining on the exploration line record data and the stratum profile deviation degree record data to generate a plurality of groups of exploration line mining results and a plurality of exploration line confidence degrees, wherein the plurality of groups of exploration line mining results and the plurality of exploration line confidence degrees are in one-to-one correspondence;
generating a plurality of seismic exploration lines according to exploration line mining results corresponding to the maximum value of the confidence coefficients of the plurality of exploration lines;
the strictly data mining is performed on the exploration line record data and the stratum profile deviation degree record data to generate a plurality of groups of exploration line mining results and a plurality of exploration line confidence degrees, wherein the plurality of groups of exploration line mining results and the plurality of exploration line confidence degrees are in one-to-one correspondence, and the method comprises the following steps:
building an m-term support degree calculation formula:
wherein (1)>Recording data of a j-th group exploration survey line of the section deviation degree of an i-th stratum,/and>the kth line representing the recorded data of the jth exploration line group, n representing the total number of recorded groups of the ith formation section deviation degree,/for the data of the jth exploration line group >In the n sets of data characterizing the degree of deviation of the section of the ith formation,the sum of the frequencies of the co-occurrence of the m lines in total,/->Characterizing m item support degrees;
building an m-term confidence coefficient calculation formula:
wherein (1)>Characterization ofThe sum of the frequency of co-occurrence of a certain group of m lines meeting the deviation threshold,in the n sets of data characterizing the degree of deviation of the section of the ith formation,/th>The sum of the frequencies of the co-occurrence of the m lines in total,/->Characterizing m item confidence;
traversing the exploration line record data and the stratum profile deviation degree record data according to the m item support degree calculation formulas and the m item confidence degree calculation formulas, and generating the multi-group exploration line mining results and the multi-exploration line confidence degrees.
2. The method of claim 1, wherein processing the plurality of sets of seismic survey data to generate a formation profile comprises:
acquiring a plurality of groups of first-order reflected wave propagation time length record data and a plurality of groups of first-order reflected wave propagation position record data according to the plurality of groups of seismic exploration data;
determining a first-level interface fluctuation profile according to the multiple sets of first-level reflected wave propagation duration record data and the multiple sets of first-level reflected wave propagation position record data;
Acquiring a plurality of groups of N-level reflected wave propagation time length record data and a plurality of groups of N-level reflected wave propagation position record data according to the plurality of groups of seismic exploration data;
determining an N-level interface relief profile according to the plurality of groups of N-level reflected wave propagation time length record data and the plurality of groups of N-level reflected wave propagation position record data;
and arranging the primary interface relief profile until the N-level interface relief profile from top to bottom to generate the stratum profile.
3. The method of claim 1, wherein said inputting the formation age characteristic, the formation lithology characteristic, and the formation thickness characteristic into an oil-bearing probability calibration table generates an oil-bearing probability assessment result comprising:
acquiring petroleum exploration record data when a preset updating period is met, wherein the petroleum exploration record data comprises a plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values;
any one group of the formation age record characteristic values, the formation lithology record characteristic values and the formation thickness record characteristic values is parallelly transmitted to a plurality of expert groups, and a plurality of initial calibration results of oil-containing probability are obtained;
Calculating an average value of the plurality of initial calibration results of the oil-containing probability to generate an expected calibration result of the oil-containing probability;
and constructing the oil-containing probability calibration table according to a plurality of expected oil-containing probability calibration results.
4. The method of claim 3, wherein said performing oil content assessment based on said formation boundary features to generate an oil content assessment and an oil-containing area assessment comprises:
the petroleum exploration record data also comprises a plurality of groups of oil deposit exploitation record data and a plurality of groups of stratum boundary record characteristic values;
acquiring a plurality of groups of oil output record data and a plurality of groups of oil output area record data according to the plurality of groups of oil reservoir exploitation record data;
performing supervised learning according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values, stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil yield record data to construct an oil content evaluation layer;
performing supervised learning according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values, stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil outlet area record data to construct an oil-containing area evaluation layer;
Combining the oil content evaluation layer and the oil content area evaluation layer as two parallel nodes to generate an oil content parameter evaluation model;
and outputting the oil content evaluation result and the oil content area evaluation result according to the oil content parameter evaluation model.
5. The method of claim 4, wherein said constructing an oil content evaluation layer based on said plurality of sets of formation age recorded eigenvalues, formation lithology recorded eigenvalues, and formation thickness recorded eigenvalues, said plurality of sets of formation boundary recorded eigenvalues, and said plurality of sets of oil yield recorded data comprises:
performing supervised learning based on a feedforward neural network according to the plurality of groups of stratum age record characteristic values, stratum lithology record characteristic values and stratum thickness record characteristic values, the plurality of groups of stratum boundary record characteristic values and the plurality of groups of oil yield record data to construct a first sub-model;
recording the multi-group stratum age record characteristic values, stratum lithology record characteristic values, stratum thickness record characteristic values and the oil yield record data of which the first sub-model does not meet the preset accuracy as a first loss data set;
Judging whether the data volume of the first loss data set is smaller than or equal to a data volume threshold value;
if the data is larger than the first loss data set, performing supervised learning based on a feedforward neural network, and constructing a second sub-model;
and when the data volume of the H-th loss data set is smaller than or equal to the data volume threshold, merging the first sub-model and the second sub-model until the H-th sub-model to generate the oil content assessment layer, wherein the oil content assessment layer is an output weighted average value of all the sub-models.
6. An artificial intelligence based oil exploration system, comprising:
the exploration survey line optimizing module is used for optimizing the seismic exploration survey lines according to the landform characteristics of the sedimentary basin to generate a plurality of seismic exploration survey lines;
the exploration data acquisition module is used for carrying out exploration according to the plurality of seismic exploration survey lines and acquiring a plurality of groups of seismic exploration data;
the stratum profile determining module is used for processing the plurality of groups of seismic exploration data to generate stratum profile diagrams;
the stratum feature extraction module is used for carrying out feature analysis according to the stratum profile to generate stratum age features, stratum lithology features, stratum thickness features and stratum boundary features;
The oil-containing probability calibration module is used for inputting the stratum age characteristic, the stratum lithology characteristic and the stratum thickness characteristic into an oil-containing probability calibration table to generate an oil-containing probability evaluation result;
the oil content parameter evaluation module is used for carrying out oil content evaluation according to the stratum boundary characteristics when the oil content probability evaluation result meets the preset oil content probability to generate an oil content evaluation result and an oil content area evaluation result;
the exploration data uploading module is used for adding the oil content evaluation result and the oil content area evaluation result into an oil exploration result;
the system further comprises;
the seismic exploration record data acquisition module is used for acquiring a plurality of groups of seismic exploration record data according to the geomorphic characteristics of the sedimentary basin, wherein the plurality of groups of seismic exploration record data comprise exploration survey line record data and stratum profile deviation record data;
the data mining module is used for carrying out strict data mining on the exploration line record data and the stratum profile deviation degree record data to generate a plurality of groups of exploration line mining results and a plurality of exploration line confidence degrees, wherein the plurality of groups of exploration line mining results and the plurality of exploration line confidence degrees are in one-to-one correspondence;
The seismic exploration line generation module is used for generating a plurality of seismic exploration lines according to exploration line mining results corresponding to the maximum value of the confidence coefficient of the plurality of exploration lines;
the support degree calculation formula construction module is used for constructing an m-term support degree calculation formula;
the confidence coefficient calculation formula construction module is used for constructing an m-term confidence coefficient calculation formula;
the recorded data traversing module is used for traversing the exploration line recorded data and the stratum profile deviation degree recorded data according to the m item support degree calculation formulas and the m item confidence degree calculation formulas to generate the multi-group exploration line mining results and the multi-exploration line confidence degrees.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211385134.0A CN116047598B (en) | 2022-11-07 | 2022-11-07 | Oil exploration method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211385134.0A CN116047598B (en) | 2022-11-07 | 2022-11-07 | Oil exploration method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116047598A CN116047598A (en) | 2023-05-02 |
| CN116047598B true CN116047598B (en) | 2023-09-19 |
Family
ID=86126260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211385134.0A Active CN116047598B (en) | 2022-11-07 | 2022-11-07 | Oil exploration method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116047598B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105572736A (en) * | 2016-01-07 | 2016-05-11 | 西南石油大学 | Quantitative prediction method for slope break belt by utilizing seismic data |
| CN105607129A (en) * | 2014-11-10 | 2016-05-25 | 中国石油化工股份有限公司 | Seismic identification method for complex fault block unconformity surfaces |
| CN106199707A (en) * | 2016-06-16 | 2016-12-07 | 中国石油天然气股份有限公司 | A kind of method and device predicting sandbody distribution |
| CN115061219A (en) * | 2022-08-17 | 2022-09-16 | 北京派特杰奥科技有限公司 | Fracture type reservoir prediction and identification method and system based on petroleum and natural gas detection |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7545704B2 (en) * | 2007-02-13 | 2009-06-09 | Landmark Graphics Corporation | Performing 3-D scatterer imaging from 2-D seismic data |
-
2022
- 2022-11-07 CN CN202211385134.0A patent/CN116047598B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105607129A (en) * | 2014-11-10 | 2016-05-25 | 中国石油化工股份有限公司 | Seismic identification method for complex fault block unconformity surfaces |
| CN105572736A (en) * | 2016-01-07 | 2016-05-11 | 西南石油大学 | Quantitative prediction method for slope break belt by utilizing seismic data |
| CN106199707A (en) * | 2016-06-16 | 2016-12-07 | 中国石油天然气股份有限公司 | A kind of method and device predicting sandbody distribution |
| CN115061219A (en) * | 2022-08-17 | 2022-09-16 | 北京派特杰奥科技有限公司 | Fracture type reservoir prediction and identification method and system based on petroleum and natural gas detection |
Non-Patent Citations (1)
| Title |
|---|
| 准噶尔盆地阜康凹陷白垩系清水河组低位体系域 充填模式及油气勘探意义;厚刚福，等;中国石油勘探;第26卷(第5期);74-82 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116047598A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109799533A (en) | A kind of method for predicting reservoir based on bidirectional circulating neural network | |
| CN112505778B (en) | Three-dimensional in-situ characterization method for heterogeneity of shale storage and generation performance | |
| CN109800954B (en) | Reservoir evaluation method based on logging data | |
| CN113553780B (en) | Stratum pore pressure prediction method based on machine learning | |
| CN113554849A (en) | Air-ground monitoring slope system and instability risk assessment method thereof | |
| CN111967079A (en) | Foundation pit deformation prediction method based on improved artificial bee colony algorithm and BP neural network | |
| CN114723095A (en) | Missing well logging curve prediction method and device | |
| CN113610945A (en) | Ground stress curve prediction method based on hybrid neural network | |
| CN111722283B (en) | Stratum velocity model building method | |
| CN112035941A (en) | Prediction method for surface subsidence of deep foundation pit excavation based on BAS-BP model | |
| Behzadi et al. | Introducing a novel digital elevation model using artificial neural network algorithm | |
| CN114943125A (en) | Intelligent inversion analysis method for tunnel surrounding rock parameters based on XGboost optimization algorithm | |
| CN116305850A (en) | Stratum thermal conductivity prediction method based on random forest model | |
| CN115327616A (en) | Automatic positioning method of mine micro-seismic source driven by mass data | |
| CN112100930B (en) | Formation pore pressure calculation method based on convolutional neural network and Eaton formula | |
| CN114488311A (en) | Transverse wave time difference prediction method based on SSA-ELM algorithm | |
| Nguyen et al. | Prediction of ground subsidence due to underground mining through time using multilayer feed-forward artificial neural networks and back-propagation algorithm–case study at Mong Duong underground coal mine (Vietnam) | |
| CN116047598B (en) | Oil exploration method and system based on artificial intelligence | |
| JP2000002769A (en) | Method and device for predicting the spatial distribution of geological structure to prepare geological map | |
| CN111751878A (en) | Method and device for predicting transverse wave velocity | |
| Fattahi et al. | Hybrid ANFIS with ant colony optimization algorithm for prediction of shear wave velocity from a carbonate reservoir in Iran | |
| Itani et al. | Three-dimensional modeling of spatial soil properties via artificial neural networks | |
| CN115759203A (en) | Offshore pile foundation erosion prediction method under multi-factor coupling condition | |
| Meng et al. | Quasi-site-specific prediction of shear wave velocity from CPTu | |
| CN115046516A (en) | Sliding surface position accurate determination method based on single-sliding-surface r-type deep hole inclination measuring curve |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |