CN116299664A - Method, device and equipment for determining fracture-controlled fracture-cavity type oil reservoir body - Google Patents
Method, device and equipment for determining fracture-controlled fracture-cavity type oil reservoir body Download PDFInfo
- Publication number
- CN116299664A CN116299664A CN202111551602.2A CN202111551602A CN116299664A CN 116299664 A CN116299664 A CN 116299664A CN 202111551602 A CN202111551602 A CN 202111551602A CN 116299664 A CN116299664 A CN 116299664A
- Authority
- CN
- China
- Prior art keywords
- fracture
- seismic
- reservoir
- development area
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 208000010392 Bone Fractures Diseases 0.000 claims abstract description 245
- 206010017076 Fracture Diseases 0.000 claims abstract description 245
- 238000011161 development Methods 0.000 claims abstract description 92
- 238000003062 neural network model Methods 0.000 claims abstract description 50
- 238000013508 migration Methods 0.000 claims abstract description 42
- 230000005012 migration Effects 0.000 claims abstract description 42
- 238000003384 imaging method Methods 0.000 claims abstract description 20
- 238000003860 storage Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 5
- 238000012512 characterization method Methods 0.000 abstract description 7
- 230000002159 abnormal effect Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 8
- 230000000875 corresponding effect Effects 0.000 description 7
- 238000005070 sampling Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 208000035126 Facies Diseases 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- BVKZGUZCCUSVTD-UHFFFAOYSA-L Carbonate Chemical compound [O-]C([O-])=O BVKZGUZCCUSVTD-UHFFFAOYSA-L 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 2
- 239000011324 bead Substances 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000002224 dissection Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000002364 input neuron Anatomy 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 239000011295 pitch Substances 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G01V1/282—Application of seismic models, synthetic seismograms
-
- 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
-
- 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
- G01V1/36—Effecting static or dynamic corrections on records, e.g. correcting spread; Correlating seismic signals; Eliminating effects of unwanted energy
- G01V1/362—Effecting static or dynamic corrections; Stacking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/50—Corrections or adjustments related to wave propagation
- G01V2210/51—Migration
- G01V2210/512—Pre-stack
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention discloses a fracture-control fracture-cavity type oil reservoir body determining method, a fracture-control fracture-cavity type oil reservoir body determining device and equipment, wherein the seismic reflection characteristics of a fracture development area are determined according to the seismic imaging section of the fracture development area, and the external contour of a fracture breaking zone is drawn according to the seismic reflection characteristics; extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone; inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model; the initial reservoir type of the fractured development zone is output. According to the method, different seismic attribute information representing the seismic phases of the fracture development area can be comprehensively characterized into an attribute data body for effectively representing the oil reservoir structure by utilizing the self-organizing neural network model, and quantitative characterization of different types of the oil reservoir bodies by utilizing the seismic phases is realized.
Description
Technical Field
The invention relates to the technical field of petroleum exploration, in particular to a fracture-control fracture-cavity type oil reservoir body determining method, device and equipment.
Background
The fracture control, storage and storage function is verified in the research of a plurality of large basins in China, and a great amount of research work is carried out on the seismic characterization method of fracture-control fracture-cavity type oil reservoir bodies at present by students at home and abroad. In the related technology, by combining with the interpretation result of the fine structure of the oil reservoir development area, the typical three-part structural characteristics exist on the section structure of the development area, and the development area can be divided into a bedrock section, a broken solution side part and a broken solution core part, and the development degree of the reservoir is different at different structural positions of the oil reservoir.
In the prior art, by adopting the thought of contour-inner curtain hierarchical representation, the contour and the inner structure of a broken zone of a broken solution oil reservoir are represented by utilizing tensor, energy, AFE (Advanced Fault Enhancement ) and other seismic attributes respectively, so that the inner structure of the broken solution is represented, the fine dissection of the dominant development area of the broken solution inner reservoir is realized, and the drilling track design is guided in production. However, the prior art does not relate to how to comprehensively characterize the seismic phases of fracture-controlled fracture-cavity type oil reservoirs by utilizing multiple seismic attributes and determine the reservoir types of the fracture-controlled fracture-cavity type oil reservoirs.
Disclosure of Invention
The invention aims to solve the technical problems that: how to comprehensively characterize the seismic phases of the fracture-controlled fracture-cavity type oil deposit by utilizing the multiple seismic attributes and determine the type of the reservoir body of the fracture-controlled fracture-cavity type oil deposit.
To solve the above technical problem, according to a first aspect of the present invention, a method for determining a fracture-cavity type reservoir body is provided, which includes:
determining the seismic reflection characteristics of a fracture development area according to the seismic imaging section of the fracture development area, and describing the external contour of a fracture breaking zone according to the seismic reflection characteristics;
extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone;
inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model;
outputting the initial reservoir type of the fracture development zone.
In some embodiments, extracting a plurality of sensitive seismic attributes from pre-stack depth migration data of the fractured zone includes:
processing the prestack depth migration data by using a structure tensor algorithm to obtain a structure tensor characteristic value; the method comprises the steps of,
and calculating the relative wave impedance difference based on the prestack depth migration data.
In some embodiments, calculating the relative wave impedance difference based on the pre-stack depth offset data comprises:
inverting the prestack depth migration data to obtain relative impedance;
carrying out low-pass filtering treatment on the relative impedance, wherein the cut-off frequency is 10-15 Hz;
and carrying out difference on the relative impedance and the relative impedance after the low-pass filtering treatment to obtain the relative wave impedance difference.
In some embodiments, the sensitive seismic attributes include at least two of variance for clutter reflection identification, edge detection, energy gradients, structure tensor eigenvalues, and relative wave impedance differences.
In some embodiments, the method further comprises:
acquiring logging data of the fracture development area;
logging interpretation is carried out on the logging data to obtain a standard reservoir body type of the fracture development area;
comparing the initial reservoir type with the standard reservoir;
and when the initial reservoir body type is inconsistent with the standard reservoir body in comparison, updating the classification parameters of the self-organizing neural network model.
In some embodiments, when the initial reservoir type is inconsistent with the comparison of the standard reservoir, after updating the classification parameters of the ad hoc neural network model, the method further comprises:
and obtaining the reservoir body type of the fracture development area by using the updated self-organizing neural network model.
In a second aspect of the present invention, there is provided a fracture-controlled cave reservoir determination apparatus comprising:
the determining module is used for determining the seismic reflection characteristics of the fracture development area according to the seismic imaging section of the fracture development area and describing the external contour of the fracture breaking zone according to the seismic reflection characteristics;
the extraction module is used for extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone;
the input module is used for inputting a plurality of sensitive seismic attributes into the trained self-organizing neural network model;
an output module for outputting an initial reservoir type for the fracture development zone.
In some embodiments, the fracture-controlled cave reservoir determination apparatus further comprises an update module to:
acquiring logging data of the fracture development area;
logging interpretation is carried out on the logging data to obtain a standard reservoir body type of the fracture development area;
comparing the initial reservoir type with the standard reservoir;
and when the initial reservoir body type is inconsistent with the standard reservoir body in comparison, updating the classification parameters of the self-organizing neural network model.
In a third aspect of the present invention, there is provided a storage medium having stored therein a computer program which, when executed by a processor, implements the fracture-controlled cave reservoir determination method as set forth in any one of the above.
In a fourth aspect of the present invention, there is provided an apparatus comprising a memory and a processor, the memory having stored therein a computer program which when executed by the processor implements a fracture-cave reservoir determination method as defined in any one of the preceding claims.
One or more embodiments of the above-described solution may have the following advantages or benefits compared to the prior art:
by applying the fracture-control fracture-cavity type oil reservoir body determining method provided by the invention, the seismic reflection characteristics of the fracture-development area are determined according to the seismic imaging section of the fracture-development area, and the external contour of the fracture zone is drawn according to the seismic reflection characteristics; extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone; inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model; the initial reservoir type of the fractured development zone is output. According to the method, different seismic attribute information representing the seismic phases of the fracture development area can be comprehensively characterized into an attribute data body for effectively representing the oil reservoir structure by utilizing the self-organizing neural network model, and quantitative characterization of different types of the oil reservoir bodies by utilizing the seismic phases is realized.
Drawings
The scope of the present disclosure may be better understood by reading the following detailed description of exemplary embodiments in conjunction with the accompanying drawings. The drawings included herein are:
FIG. 1 shows a schematic flow chart of a method for determining a fracture-controlled cave type reservoir body provided by an embodiment of the invention;
FIG. 2 is a schematic flow chart of another method for determining a fracture-controlled cave reservoir according to an embodiment of the present invention;
FIG. 3 shows a schematic cross-sectional view of pre-stack depth migration data for a fracture-controlled fracture-cave reservoir;
FIG. 4 shows a schematic cross-sectional view of the structure tensor eigenvalue of a fracture-controlled cave reservoir;
FIG. 5 shows a schematic cross-sectional view of the relative impedance differences of a fracture-controlled cave reservoir;
FIG. 6 shows a schematic diagram of the seismic phase partitioning results for a fracture-controlled fracture-cave reservoir;
FIG. 7 (1) shows a schematic diagram of a fracture interpretation of a fracture-controlled fracture-cave reservoir; FIG. 7 (2) shows the seismic facies division results for the same section as in FIG. 7 (1);
FIG. 8 shows a graph of interpreted fracture-zone nuclei versus seismic phase discrimination for a fracture-controlled fracture-cave reservoir;
FIG. 9 shows a schematic structural diagram of a fracture-controlled fracture-cave type reservoir body determining device according to an embodiment of the present invention;
fig. 10 shows a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following detailed description of the implementation method of the present invention will be given with reference to the accompanying drawings and examples, by which the technical means are applied to solve the technical problems, and the implementation process for achieving the technical effects can be fully understood and implemented accordingly.
The fracture control, storage and storage function is verified in the research of a plurality of large basins in China, and a great amount of research work is carried out on the seismic characterization method of fracture-control fracture-cavity type oil reservoir bodies at present by students at home and abroad. In the related technology, by combining with the interpretation result of the fine structure of the oil reservoir development area, the typical three-part structural characteristics exist on the section structure of the development area, and the development area can be divided into a bedrock section, a broken solution side part and a broken solution core part, and the development degree of the reservoir is different at different structural positions of the oil reservoir.
In the prior art, by adopting the thought of contour-inner curtain hierarchical representation, the contour and the inner structure of a broken zone of a broken solution oil reservoir are represented by utilizing tensor, energy, AFE (Advanced Fault Enhancement ) and other seismic attributes respectively, so that the inner structure of the broken solution is represented, the fine dissection of the dominant development area of the broken solution inner reservoir is realized, and the drilling track design is guided in production. However, the prior art does not relate to how to comprehensively characterize the seismic phases of the fracture-controlled fracture-cavity type oil reservoirs by utilizing multiple seismic attributes and determine the reservoir types of the fracture-controlled fracture-cavity type oil reservoirs.
In view of the above, the invention provides a fracture-controlled fracture-cave type reservoir body determining method, which is characterized in that the seismic reflection characteristics of a fracture development area are determined according to the seismic imaging section of the fracture development area, and the external contour of a fracture breaking zone is drawn according to the seismic reflection characteristics; extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone; inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model; the initial reservoir type of the fractured development zone is output. According to the method, different seismic attribute information representing the seismic phases of the fracture development area can be comprehensively characterized into an attribute data body for effectively representing the oil reservoir structure by utilizing the self-organizing neural network model, and quantitative characterization of different types of the oil reservoir bodies by utilizing the seismic phases is realized.
Example 1
Referring to fig. 1, fig. 1 shows a schematic flow chart of a method for determining a fracture-controlled cave type reservoir body according to an embodiment of the present invention, which may include:
step S101: determining the seismic reflection characteristics of the fracture development area according to the seismic imaging section of the fracture development area, and describing the external contour of the fracture breaking zone according to the seismic reflection characteristics;
step S102: extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone;
step S103: inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model;
step S104: the initial reservoir type of the fractured development zone is output.
The fracture development area is a dominant development area of fracture-cave reservoirs with different scales, and the development spread of the fracture-cave reservoirs is controlled by fracture, so that typical fracture development imaging and reservoir seismic reflection abnormality are well correlated when the fracture development area is reflected on a seismic section. The abnormal reflection characteristics such as 'bead string' reflection, disordered reflection, weak reflection and the like are mainly located on a fracture zone and the peripheral area of the fracture zone on the spatial distribution, the abnormal seismic reflection is obviously reduced when the fracture zone is far away, and the abnormal seismic reflection is more represented as medium-intensity continuous seismic reflection of a carbonate matrix.
Based on the particularity of fracture-controlled fracture-cave reservoirs, step S101 may specifically include determining, from a seismic imaging profile of a fracture development area, an abnormal seismic reflection characteristic that is relatively easy to identify, and characterizing an external profile of a fracture zone according to the seismic reflection characteristic. In some embodiments, the anomalous seismic reflection signature may include a "beaded" reflection, a clutter reflection, or a weak reflection around the in-phase axis discontinuity or disturbance, etc.
In embodiments of the present invention, sensitive seismic attributes may be used to characterize geologic elements of a fracture-controlled cave type reservoir, and in some embodiments, attributes that more effectively characterize the fracture-controlled cave type reservoir may be used as sensitive seismic attributes. In some embodiments, the sensitive seismic attributes may include at least two of variance for clutter reflection identification, edge detection, energy gradients, structural tensor feature pairs, and relative wave impedance differences.
In some embodiments, step S102 may be specifically:
processing the prestack depth migration data by using a structure tensor algorithm to obtain a structure tensor characteristic value; and calculating a relative wave impedance difference based on the pre-stack depth migration data.
In some embodiments, when the structure tensor algorithm is used to process the pre-stack depth migration data to extract the feature value of the structure tensor, extraction parameters can be set based on fracture zones marked on the seismic imaging profile, and the extraction parameters can include a plane main line, a cross-line and a range and a time window of longitudinal time sampling. As an example, the magnitude of the extraction parameter may be set according to the development range and intensity of the abnormal reflection feature. In the embodiment of the invention, aiming at the characteristics of larger development depth of the fracture-cavity type oil reservoir with fracture control and wider range of abnormal reflection characteristic spread, a relatively larger longitudinal time sampling range and window control can be set.
In some embodiments, the relative wave impedance difference may be calculated by:
inverting the prestack depth migration data to obtain relative impedance;
carrying out low-pass filtering treatment on the relative impedance, wherein the cut-off frequency is 10-15 Hz;
the relative impedance is different from the relative impedance after the low-pass filtering process, and a relative wave impedance difference is obtained.
In the embodiment of the invention, the relative impedance is calculated by the prestack depth migration data, and the prestack depth migration data is converted into stratum lithology information from reflection interface information by inverting the prestack depth migration data.
In the embodiment of the invention, in order to highlight the abnormal value characteristics in the relative impedance, the relative impedance can be subjected to low-pass filtering processing within a certain range and a time window, and a low-frequency signal smaller than the cut-off frequency is reserved, so that low-frequency trend information reflecting the relative wave impedance space transformation is obtained, and the representation of the seismic phase is more effectively performed.
In some embodiments, step S103 may specifically be to input the structural tensor eigenvalue and the relative wave group robust as input neurons into a trained self-organizing neural network model to perform a cluster analysis of the seismic phases. The self-organizing neural network model can be obtained through training by the following steps:
establishing learning sample sets of different reservoir types, each of which may include multiple sensitive seismic attribute groups;
setting the classification quantity of the reservoir bodies, respectively carrying out learning training on a learning sample set corresponding to each type of reservoir body, and determining a neural network weight corresponding to the reservoir body type and an initial self-organizing neural network model;
comparing the preliminary output result of the initial self-organizing neural network model with the reservoir type interpreted by logging, and adjusting classification parameters when the comparison is inconsistent, so as to optimize the initial self-organizing neural network model; and (3) until the comparison is consistent, establishing the association between the seismic phase and the reservoir type, and obtaining a trained self-organizing neural network model.
In the embodiment of the present invention, step S104 may be to classify the input sensitive seismic attribute according to the association of the seismic phase and the reservoir type by using the trained ad hoc neural network model.
In some embodiments, the reservoir development of the fracture-controlled fracture-cavity reservoir is generally characterized by the existence of a base rock segment, a fracture-solution edge and a "trisection structure" of the fracture-controlled fracture-cavity reservoir around the main control fracture surface, and the determination of the initial reservoir type of the fracture-controlled fracture-cavity reservoir can further provide a technical analysis means for the "trisection structure" and give corresponding geological meaning to the seismic facies classification results.
The method for determining the fracture-controlled fracture-cavity type oil reservoir body provided by the embodiment of the invention comprises the steps of determining the seismic reflection characteristics of a fracture development area according to the seismic imaging section of the fracture development area, and depicting the external contour of a fracture breaking zone according to the seismic reflection characteristics; extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone; inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model; the initial reservoir type of the fractured development zone is output. According to the method, different seismic attribute information representing the seismic phases of the fracture development area can be comprehensively characterized into an attribute data body for effectively representing the oil reservoir structure by utilizing the self-organizing neural network model, and quantitative characterization of different types of the oil reservoir bodies by utilizing the seismic phases is realized.
Example two
Referring to fig. 2, fig. 2 shows a schematic flow chart of another method for determining a fracture-controlled cave type reservoir according to an embodiment of the present invention, which may include:
step S201: determining the seismic reflection characteristics of the fracture development area according to the seismic imaging section of the fracture development area, and describing the external contour of the fracture breaking zone according to the seismic reflection characteristics;
step S202: extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone;
step S203: inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model;
step S204: outputting an initial reservoir type of the fracture development zone;
step S205: acquiring logging data of a fracture development area;
step S206: logging interpretation is carried out on logging data to obtain a standard reservoir body type of a fracture development area;
step S207: comparing the initial reservoir type with a standard reservoir;
step S208: updating classification parameters of the self-organizing neural network model when the initial reservoir type is inconsistent with the standard reservoir type in comparison;
step S209: and obtaining the reservoir body type of the fracture development area by using the updated self-organizing neural network model.
The fracture development area is a dominant development area of fracture-cave reservoirs with different scales, and the development spread of the fracture-cave reservoirs is controlled by fracture, so that typical fracture development imaging and reservoir seismic reflection abnormality are well correlated when the fracture development area is reflected on a seismic section. The abnormal reflection characteristics such as 'bead string' reflection, disordered reflection, weak reflection and the like are mainly located on a fracture zone and the peripheral area of the fracture zone on the spatial distribution, the abnormal seismic reflection is obviously reduced when the fracture zone is far away, and the abnormal seismic reflection is more represented as medium-intensity continuous seismic reflection of a carbonate matrix.
Based on the particularity of the fracture-cave type reservoir formation and storage, step S201 may specifically include determining, from the seismic imaging profile of the fracture development area, an abnormal seismic reflection characteristic that is relatively easy to identify, and characterizing an external profile of the fracture zone according to the seismic reflection characteristic. In some embodiments, the anomalous seismic reflection signature may include a "beaded" reflection, a clutter reflection, or a weak reflection around the in-phase axis discontinuity or disturbance, etc.
In embodiments of the present invention, sensitive seismic attributes may be used to characterize geologic elements of a fracture-controlled cave type reservoir, and in some embodiments, attributes that more effectively characterize the fracture-controlled cave type reservoir may be used as sensitive seismic attributes. In some embodiments, the sensitive seismic attributes may include at least two of variance for clutter reflection identification, edge detection, energy gradients, structural tensor feature pairs, and relative wave impedance differences.
In some embodiments, step S202 may be specifically:
processing the prestack depth migration data by using a structure tensor algorithm to obtain a structure tensor characteristic value; and calculating a relative wave impedance difference based on the pre-stack depth migration data.
In some embodiments, when the structure tensor algorithm is used to process the pre-stack depth migration data to extract the feature value of the structure tensor, extraction parameters can be set based on fracture zones marked on the seismic imaging profile, and the extraction parameters can include a plane main line, a cross-line and a range and a time window of longitudinal time sampling. As an example, the magnitude of the extraction parameter may be set according to the development range and intensity of the abnormal reflection feature. In the embodiment of the invention, aiming at the characteristics of larger development depth of the fracture-cavity type oil reservoir with fracture control and wider range of abnormal reflection characteristic spread, a relatively larger longitudinal time sampling range and window control can be set.
In some embodiments, the relative wave impedance difference may be calculated by:
inverting the prestack depth migration data to obtain relative impedance;
carrying out low-pass filtering treatment on the relative impedance, wherein the cut-off frequency is 10-15 Hz;
the relative impedance is different from the relative impedance after the low-pass filtering process, and a relative wave impedance difference is obtained.
In the embodiment of the invention, the relative impedance is calculated by the prestack depth migration data, and the prestack depth migration data is converted into stratum lithology information from reflection interface information by inverting the prestack depth migration data.
In the embodiment of the invention, in order to highlight the abnormal value characteristics in the relative impedance, the relative impedance can be subjected to low-pass filtering processing within a certain range and a time window, and a low-frequency signal smaller than the cut-off frequency is reserved, so that low-frequency trend information reflecting the relative wave impedance space transformation is obtained, and the representation of the seismic phase is more effectively performed.
In some embodiments, step S203 may specifically use the structural tensor eigenvalue and the relative wave group robust as input neurons to input a trained self-organizing neural network model to perform a cluster analysis of the seismic phases. The self-organizing neural network model can be obtained through training by the following steps:
establishing learning sample sets of different reservoir types, each of which may include multiple sensitive seismic attribute groups;
setting the classification quantity of the reservoir bodies, respectively carrying out learning training on a learning sample set corresponding to each type of reservoir body, and determining a neural network weight corresponding to the reservoir body type and an initial self-organizing neural network model;
comparing the preliminary output result of the initial self-organizing neural network model with the reservoir type interpreted by logging, and adjusting classification parameters when the comparison is inconsistent, so as to optimize the initial self-organizing neural network model; and (3) until the comparison is consistent, establishing the association between the seismic phase and the reservoir type, and obtaining a trained self-organizing neural network model.
In the embodiment of the present invention, step S204 may be to classify the input sensitive seismic attribute according to the association of the seismic phase and the reservoir type by using the trained ad hoc neural network model.
In some embodiments, reservoir development of fracture-controlled fracture-cave reservoirs typically exists around the main fracture face as a "trisection" of bedrock segments, fracture edges, and fracture nuclei. The method can further provide a technical analysis means for the three-part structure by determining the initial reservoir body type of the fracture-cavity type reservoir with fracture control, and endow corresponding geological meaning for the seismic facies division result.
In step S205, log data for the fracture development zone may be obtained using methods conventional in the art.
In some embodiments, step S208 may specifically update the classification parameters in the ad hoc neural network model when the initial reservoir type is inconsistent with the standard reservoir, until the comparison result is consistent, so as to update the ad hoc neural network model and improve the effectiveness of classifying the reservoir. In some embodiments, the classification parameters may include a number of classifications, a calculation error, which may be used to represent the error allowed in the training process, and a maximum calculation cycle number, which may be set to 0.1, as an example. The maximum calculation cycle number may be the number of times the attribute correlation is calculated for the ad hoc neural network model, and as an example, the maximum calculation cycle number may be set to 200.
In some embodiments, step S209 may specifically be to obtain the reservoir type of the fracture development region by using the updated ad hoc neural network model, so as to effectively improve the effectiveness of reservoir type identification.
The method for determining the fracture-controlled fracture-cavity type oil reservoir body provided by the second embodiment of the invention has the same beneficial effects as those of the first embodiment, and in addition, the classification parameters of the self-organizing neural network model are updated when the output initial reservoir body type is inconsistent with the standard reservoir body, and the updated self-organizing neural network model is utilized to determine the reservoir body type of the fracture development area, so that the accuracy of the self-organizing neural network model is improved, and the effectiveness of reservoir body type prediction is improved.
Detailed description of the preferred embodiments
The method for determining the fracture-controlled fracture-cavity oil reservoir body provided by the second embodiment of the invention is applied to a certain oil field, and is shown in fig. 3, and fig. 3 shows a schematic diagram of pre-stack depth migration data profile of the fracture-controlled fracture-cavity oil reservoir. The fracture imaging in fig. 3 is clear, the formation continuity and the reflection energy of the fracture periphery are changed, and the fracture imaging belongs to the typical seismic profile characteristics of fracture-controlled fracture-cave oil reservoirs.
Referring to fig. 4, fig. 4 shows a schematic cross-sectional view of the structure tensor eigenvalue of a fracture-controlled hole reservoir. In this example, a larger longitudinal time sampling range and time window is selected when computing the structural tensor feature values, where the longitudinal time sampling range and time window may be set to 7 times the interval of the seismic traces, 15 times the longitudinal time sampling rate. The characteristic value of the structure tensor calculated under the parameter value condition can be seen to clearly represent the fracture zone and the surrounding clutter reflection range thereof, and the characteristic value representation range can be used as the oil reservoir boundary.
Referring to FIG. 5, FIG. 5 shows a schematic cross-sectional view of the relative impedance differences of a fracture-controlled cave reservoir. The relative impedance difference is further obtained after targeted trending treatment based on the relative impedance, and the low abnormal value of the relative impedance difference represents the relative development of the reservoir. The abnormal body shown in fig. 5 has a better corresponding relation with the amplitude abnormality shown in fig. 3, and meanwhile, the wave impedance eliminates wavelet sidelobe effect in the longitudinal direction and has higher longitudinal resolution, so that the position focusing of the fracture-cavity aggregate is more accurate.
Referring to fig. 6, fig. 6 shows a schematic diagram of the seismic phase partitioning results for a fracture-controlled fracture-cave reservoir. The self-organizing neural network method is utilized to divide the seismic phases by the characteristic value attribute of the structure tensor shown in the figure 4 and the relative impedance difference attribute shown in the figure 5, and the self-organizing neural network method can be utilized to realize a better identification effect on the internal structure of the fracture-cavity type oil reservoir. Wherein the different seismic phase results represent differences in the degree of development of the reservoir.
Referring to fig. 7 (1) and 7 (2), fig. 7 (1) shows a fracture explanatory diagram of a fracture-controlled fracture-cavity reservoir, which shows an original prestack depth migration profile and the fracture explained by the fracture, and it can be seen that the middle and left fracture pitches are relatively clear, and the seismic reflection anomalies (generally considered as responses of fracture-cavity reservoirs) caused by the fracture are also clear. Fig. 7 (2) shows the seismic phase division result of the same section as that of fig. 7 (1), and it can be seen that the first type of fracture holes and the second type of fracture holes are mainly located in the clamping area of the middle fracture and the left main fracture surface, and the distribution of the first type of fracture holes between the middle fracture and the right fracture is less, and the three types of fracture holes are mainly. Such differences in reservoir spread characteristics are related to factors such as the number of fracture events and strength. The seismic phase division result can provide relevant basis for the three-division structure division of the oil reservoir of the type.
Referring to fig. 8, fig. 8 shows a graph of interpreted fracture-zone nuclei versus seismic phase discrimination results for a fracture-controlled fracture-cave reservoir. The left graph in fig. 8 is a schematic diagram of an explanation fracture zone core of a fracture-controlled fracture-cavity oil reservoir, the right graph in fig. 8 is a schematic diagram of a seismic phase division result of a section in the left graph, on which the seismic fracture breaking is more complex, but 2 larger fracture surfaces can be resolved, and seismic reflection anomalies (reservoir response) mainly occur under the influence of the fracture surfaces, so that the whole reservoir development zone is formed. The dotted line range in the right graph shows that the first type of fracture hole and the second type of fracture hole which are obtained by utilizing the seismic phase division result mainly develop in the clamping areas of 2 fracture surfaces, and the positions of the fracture surfaces are the core parts of fracture zones and are the most developed places of the reservoir bodies. The three types of fracture holes mainly develop around the nuclear band, the development range is large, the edge part of the fracture band is formed in space, the development probability of the reservoir body outside the edge is small, and the fracture hole is a bedrock section of a target layer. The three-division structure division is more visual than the original seismic section according to the seismic phase division result, and meanwhile, various seismic attributes are considered, so that the basis is more sufficient.
Example III
Referring to fig. 9, fig. 9 shows a schematic structural diagram of a fracture-controlled fracture-cavity type reservoir body determining device according to an embodiment of the present invention, which may include:
a determining module 91, configured to determine a seismic reflection characteristic of the fracture development area according to the seismic imaging profile of the fracture development area, and delineate an external contour of the fracture zone according to the seismic reflection characteristic;
an extraction module 92 for extracting a plurality of sensitive seismic attributes from pre-stack depth migration data of the fractured zone;
an input module 93 for inputting a plurality of sensitive seismic attributes into the trained ad hoc neural network model;
an output module 94 for outputting an initial reservoir type for the fractured development zone.
In some embodiments, the extraction module 92 is specifically configured to:
processing the prestack depth migration data by using a structure tensor algorithm to obtain a structure tensor characteristic value; and calculating a relative wave impedance difference based on the pre-stack depth migration data.
Wherein, the calculating the relative wave impedance difference based on the pre-stack depth migration data may include:
inverting the prestack depth migration data to obtain relative impedance;
carrying out low-pass filtering treatment on the relative impedance, wherein the cut-off frequency is 10-15 Hz;
the relative impedance is different from the relative impedance after the low-pass filtering process, and a relative wave impedance difference is obtained.
In other embodiments, the sensitive seismic attributes may include at least two of variance for clutter reflection identification, edge detection, energy gradients, structure tensor eigenvalues, and relative wave impedance differences.
In some embodiments, the fracture-controlled cave reservoir determination apparatus further comprises an update module 95 for:
acquiring logging data of a fracture development area;
logging interpretation is carried out on logging data to obtain a standard reservoir body type of a fracture development area;
comparing the initial reservoir type with a standard reservoir;
when the initial reservoir type is inconsistent with the standard reservoir, updating the classification parameters of the self-organizing neural network model.
In some embodiments, the update module 95 may also be used to derive reservoir types for the fractured development zones using the updated ad hoc neural network model.
The device for determining the fracture-controlled fracture-cavity type oil reservoir body provided by the embodiment of the invention comprises a determining module 91, a determining module and a determining module, wherein the determining module is used for determining the seismic reflection characteristics of the fracture-controlled fracture-cavity type oil reservoir body according to the seismic imaging section of a fracture development area and describing the external contour of a fracture zone according to the seismic reflection characteristics; an extraction module 92 for extracting a plurality of sensitive seismic attributes from pre-stack depth migration data of the fractured zone; an input module 93 for inputting a plurality of sensitive seismic attributes into the trained ad hoc neural network model; an output module 94 for outputting the initial reservoir type of the fracture development zone. The device can comprehensively characterize different seismic attribute information representing the seismic phases of the fracture development area into an attribute data body for effectively characterizing the oil reservoir structure by utilizing the self-organizing neural network model, and realizes quantitative characterization of different types of the oil reservoir body by utilizing the seismic phases.
Example IV
In another aspect of the present invention, a storage medium is provided, in which a computer program is stored, which when executed by a processor, implements the method for determining a fracture-cavity reservoir set according to the first or second embodiments.
The processes, functions, methods and/or software described above may be recorded, stored or fixed in one or more computer-readable storage media that include program instructions that are to be computer-implemented to cause a processor to execute the program instructions. The storage media may also include program instructions, data files, data structures, and the like, alone or in combination. The storage media or program instructions may be specially designed and construed by those skilled in the computer software arts, or may be of the kind well known and available to those having skill in the computer software arts. Examples of the computer readable medium include: magnetic media such as hard disks, floppy disks, and magnetic tape; optical media such as CDROM discs and DVDs; magneto-optical media, such as optical disks; and hardware devices, specifically configured to store and execute program instructions, such as read-only memory (ROM), random Access Memory (RAM), flash memory, and the like. Examples of program instructions include both machine code, such as produced by a compiler, and files containing higher level code that may be executed by the computer using an interpreter. The described hardware devices may be configured to act as one or more software modules to perform the operations and methods described above, and vice versa. In addition, the computer readable storage medium may be distributed among networked computer systems, and the computer readable code or program instructions may be stored and executed in a decentralized manner.
Example five
In another aspect of the present invention, an apparatus is provided, and referring to fig. 10, fig. 10 shows a schematic structural diagram of an apparatus provided in an embodiment of the present invention.
The apparatus may comprise a memory 101 and a processor 102, the memory 101 having stored therein a computer program which when executed by the processor 102 implements the fracture-controlled cave reservoir determination method as described in embodiment one or embodiment two above.
It is noted that the device may include one or more memories 101 and a processor 102, and that the memories 101 and the processor 102 may be connected by a bus or other means. The memory 101 is used as a non-volatile computer-readable storage medium for storing non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 102 executes various functional applications of the device and data processing, i.e., implements the fracture-controlled cave reservoir determination methods described above, by running non-volatile software programs, instructions, and modules stored in memory.
Although the embodiments of the present invention are disclosed above, the embodiments are only used for the convenience of understanding the present invention, and are not intended to limit the present invention. Any person skilled in the art can make any modification and variation in form and detail without departing from the spirit and scope of the present disclosure, but the scope of the present disclosure is still subject to the scope of the present disclosure as defined by the appended claims.
Claims (10)
1. A method for determining a fracture-controlled cave reservoir, comprising:
determining the seismic reflection characteristics of a fracture development area according to the seismic imaging section of the fracture development area, and describing the external contour of a fracture breaking zone according to the seismic reflection characteristics;
extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone;
inputting a plurality of sensitive seismic attributes into a trained self-organizing neural network model;
outputting the initial reservoir type of the fracture development zone.
2. The method of claim 1, wherein extracting a plurality of sensitive seismic attributes from pre-stack depth migration data of the fractured zone comprises:
processing the prestack depth migration data by using a structure tensor algorithm to obtain a structure tensor characteristic value; the method comprises the steps of,
and calculating the relative wave impedance difference based on the prestack depth migration data.
3. The method of claim 2, wherein calculating a relative wave impedance difference based on the pre-stack depth migration data comprises:
inverting the prestack depth migration data to obtain relative impedance;
carrying out low-pass filtering treatment on the relative impedance, wherein the cut-off frequency is 10-15 Hz;
and carrying out difference on the relative impedance and the relative impedance after the low-pass filtering treatment to obtain the relative wave impedance difference.
4. The method of claim 1, wherein the sensitive seismic attributes include at least two of variance for clutter identification, edge detection, energy gradients, structure tensor eigenvalues, and relative wave impedance differences.
5. The method according to claim 1, wherein the method further comprises:
acquiring logging data of the fracture development area;
logging interpretation is carried out on the logging data to obtain a standard reservoir body type of the fracture development area;
comparing the initial reservoir type with the standard reservoir;
and when the initial reservoir body type is inconsistent with the standard reservoir body in comparison, updating the classification parameters of the self-organizing neural network model.
6. The method of claim 5, wherein when the initial reservoir type is inconsistent with the comparison of the standard reservoir, after updating the classification parameters of the ad hoc neural network model, the method further comprises:
and obtaining the reservoir body type of the fracture development area by using the updated self-organizing neural network model.
7. A fracture-controlled cave reservoir body determination device, comprising:
the determining module is used for determining the seismic reflection characteristics of the fracture development area according to the seismic imaging section of the fracture development area and describing the external contour of the fracture breaking zone according to the seismic reflection characteristics;
the extraction module is used for extracting a plurality of sensitive seismic attributes according to pre-stack depth migration data of the fracture zone;
the input module is used for inputting a plurality of sensitive seismic attributes into the trained self-organizing neural network model;
an output module for outputting an initial reservoir type for the fracture development zone.
8. The apparatus of claim 7, further comprising an update module to:
acquiring logging data of the fracture development area;
logging interpretation is carried out on the logging data to obtain a standard reservoir body type of the fracture development area;
comparing the initial reservoir type with the standard reservoir;
and when the initial reservoir body type is inconsistent with the standard reservoir body in comparison, updating the classification parameters of the self-organizing neural network model.
9. A storage medium having stored therein a computer program which when executed by a processor implements the fracture-cave reservoir determination method of any one of claims 1 to 6.
10. An apparatus comprising a memory and a processor, wherein the memory stores a computer program that when executed by the processor implements the fracture-cave reservoir determination method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111551602.2A CN116299664A (en) | 2021-12-17 | 2021-12-17 | Method, device and equipment for determining fracture-controlled fracture-cavity type oil reservoir body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111551602.2A CN116299664A (en) | 2021-12-17 | 2021-12-17 | Method, device and equipment for determining fracture-controlled fracture-cavity type oil reservoir body |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116299664A true CN116299664A (en) | 2023-06-23 |
Family
ID=86798252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111551602.2A Pending CN116299664A (en) | 2021-12-17 | 2021-12-17 | Method, device and equipment for determining fracture-controlled fracture-cavity type oil reservoir body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116299664A (en) |
-
2021
- 2021-12-17 CN CN202111551602.2A patent/CN116299664A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2018340369A1 (en) | Method and device for determining thin interlayer | |
| CN105005080A (en) | Method for identifying stratigraphic trap pinch-out line by using amplitude ratio attribute | |
| Hernandez-Martinez et al. | Facies recognition using multifractal Hurst analysis: Applications to well-log data | |
| CN105116449A (en) | Method for identifying weak reflection reservoir | |
| Ali et al. | A novel machine learning approach for detecting outliers, rebuilding well logs, and enhancing reservoir characterization | |
| CN103869358A (en) | Histogram equalization-based fault identification method and equipment | |
| Yasin et al. | Seismic characterization of geologically complex geothermal reservoirs by combining structure-oriented filtering and attributes analysis | |
| CN111983671B (en) | Shallow water lake basin reservoir prediction method and device based on micro-ancient landform restoration | |
| CN111948709A (en) | Fracture zone structure identification method, device and system | |
| CN115877464A (en) | Lithology identification method and device, computer equipment and storage medium | |
| CN116299664A (en) | Method, device and equipment for determining fracture-controlled fracture-cavity type oil reservoir body | |
| Liu et al. | Seismic characterization of fault and fractures in deep buried carbonate reservoirs using CNN-LSTM based deep neural networks | |
| CN113640876B (en) | Method for carrying out fine recognition on collapse column by utilizing chaos attribute | |
| CN116027454A (en) | Method for imaging contour map of sandstone thickness and intelligent drawing device | |
| CN114996953A (en) | Electromagnetic imaging method, system, medium, device and terminal | |
| Rotimi et al. | Reservoir characterization and modeling of lateral heterogeneity using multivariate analysis | |
| CN109581489B (en) | Nested seismic facies extraction method and system | |
| Lin et al. | Time-frequency mixed domain multi-trace simultaneous inversion method | |
| CN110389381B (en) | Sand reservoir prediction method and device based on seismic attributes | |
| CN112987091A (en) | Reservoir detection method and device, electronic equipment and storage medium | |
| Zahraa et al. | Characterizing geological facies using seismic waveform classification in sarawak basin | |
| Carrasquilla et al. | Using facies, data mining and artificial intelligence concepts in the evaluation of a carbonate reservoir in Campos basin, Southeastern Brazil | |
| CN107831537B (en) | Method for describing high sand-to-land ratio nepheloid rock reservoir | |
| CN111239823A (en) | Method for identifying distribution of invaded rocks | |
| CN116774285B (en) | Thin interbed prediction method, device, equipment and medium based on characteristic curve reconstruction |
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 |