CN119471814A - Intelligent analysis and recognition method of 3D seismic point cloud data - Google Patents
Intelligent analysis and recognition method of 3D seismic point cloud data Download PDFInfo
- Publication number
- CN119471814A CN119471814A CN202510075893.4A CN202510075893A CN119471814A CN 119471814 A CN119471814 A CN 119471814A CN 202510075893 A CN202510075893 A CN 202510075893A CN 119471814 A CN119471814 A CN 119471814A
- Authority
- CN
- China
- Prior art keywords
- reflection
- positive
- data
- negative
- reflections
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004458 analytical method Methods 0.000 title claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 9
- 238000009826 distribution Methods 0.000 claims description 55
- 230000000877 morphologic effect Effects 0.000 claims description 10
- 238000009412 basement excavation Methods 0.000 claims description 3
- 230000000295 complement effect Effects 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims 1
- 230000004927 fusion Effects 0.000 abstract description 4
- 238000010191 image analysis Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000013506 data mapping Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
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. for interpretation or for event detection
- G01V1/30—Analysis
- G01V1/306—Analysis for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
本发明涉及地震波数据处理领域，为了实现自动化预报，提供了三维地震波点云数据智能分析识别方法，通过直接对地震波法生成的点云数据进行标准化处理，并通过工程经验中的对应关系，进行机器智能识别地质对象、自动生成预报结论。该方法绕开了原始数据到图像再到人工解译的过程，避免了人工图像分析中的诸多问题，同时将大量测试原始数据进行精简和结构化处理，节省了存储空间及后续工作的数据处理量，为不同预报方法下数据间的机器智能融合分析奠定了基础。
The present invention relates to the field of seismic wave data processing. In order to realize automatic prediction, a three-dimensional seismic wave point cloud data intelligent analysis and recognition method is provided. By directly standardizing the point cloud data generated by the seismic wave method, and through the corresponding relationship in engineering experience, the machine intelligently recognizes the geological objects and automatically generates the prediction conclusion. The method bypasses the process from raw data to image and then to manual interpretation, avoiding many problems in manual image analysis. At the same time, a large amount of test raw data is streamlined and structured, saving storage space and the amount of data processing for subsequent work, laying the foundation for machine intelligent fusion analysis between data under different prediction methods.
Description
Technical Field
The invention relates to the field of seismic wave data processing, in particular to an intelligent analysis and identification method for three-dimensional seismic wave point cloud data.
Background
At present, the technology similar to TRT, TSP and the like based on seismic wave reflection imaging is widely applied to the fields of tunnels and underground engineering, receives data through seismic wave reflection, generates images through software calculation, and accordingly analyzes and predicts geological conditions of non-excavated tunnel sections in front of the tunnels, and is an important means for advanced geological forecast of underground engineering. At present, most of equipment manufacturers at home and abroad research and development from the original data receiving to the data mapping are realized, and the process from the image to the prediction result is to further determine the spatial distribution rule of the prediction objects such as bad geologic bodies through manually identifying and analyzing the image.
The prior art has the following defects:
1. in the traditional forecasting mode, firstly, field test is carried out, test data are calculated through an algorithm built in the equipment to form a graph, and the image is the final result of machine operation. Then, the images are manually analyzed, and a forecast conclusion is obtained according to experience. The prediction in the prediction flow has strong subjectivity, more interfered factors in result analysis, lower accuracy and low analysis efficiency.
2. The images are difficult to quantitatively analyze, so that the images are difficult to be converted into a general data structure to enter an advanced forecast analysis system, and fusion analysis between data is difficult to be carried out with other dataized advanced forecast means results.
3. There is no standardized forecasting system and machine identification rules.
4. The original data volume is large, and the analysis is difficult to directly carry out.
Disclosure of Invention
In order to realize automatic forecasting, the application provides an intelligent analysis and identification method for three-dimensional seismic wave point cloud data.
The invention solves the problems by adopting the following technical scheme:
the intelligent analysis and identification method for the three-dimensional seismic wave point cloud data comprises the following steps:
step 1, collecting three-dimensional seismic wave point cloud data of a tunnel;
Step 2, classifying the seismic wave point cloud data according to the reflection form classification rule;
Step 3, obtaining the positions of various morphological reflecting interfaces, and obtaining the existence probability of the bad geologic body corresponding to each reflecting morphological classification according to the relation between the preset reflecting morphological classification and the existence probability of the bad geologic body;
and 4, accumulating the existence probabilities of the bad geologic bodies corresponding to the different reflection morphology classifications at the same position to obtain the existence probability of the bad geologic bodies at the position.
Further, the step 3 of obtaining the positions of the various morphological reflecting interfaces further comprises the steps of performing linear analysis on the various reflecting interfaces, and obtaining the existence probability of the bad geologic body corresponding to the linear relationship according to the relationship between the preset linear interface and the existence probability of the bad geologic body.
Further, the step 3 of obtaining the position of the reflection interface of various forms further comprises obtaining a wave speed variation trend at the position, and obtaining the existence probability of the bad geologic body corresponding to the wave speed variation trend according to the relation between the preset wave speed variation trend and the existence probability of the bad geologic body.
Further, the classification of the reflection morphology includes:
The method is divided into planar continuous reflection, planar discontinuous reflection, staggered reflection, dense point reflection and scattered point reflection according to the form;
According to the positive and negative reflection morphological characteristics, the method is divided into positive and negative interval distribution, negative reflection as a main component, positive reflection as a main component, only negative reflection and only positive reflection;
and combining the two classification results to obtain the final classification.
Further, the classification rule specifically includes:
Planar continuous reflection:
Detecting and extracting the minimum F% data in all seismic wave point cloud data, detecting the screened data, removing scattered data in discontinuous space distribution according to coordinate distribution corresponding to each data, and finally comparing the maximum value range of Y coordinates in the screened data with the space coordinate range of the tunnel diameter, wherein if the maximum value range of Y coordinates in the screened data is larger than or equal to the tunnel diameter, the data are continuously reflected in a plane shape and only negatively reflected;
Detecting and extracting the largest F% data in all seismic wave point cloud data, detecting the screened data, removing discontinuous distributed sporadic data in a space according to coordinate distribution corresponding to each data, and finally comparing the maximum value range of Y coordinates in the screened data with the space coordinate range of the tunnel diameter, wherein if the maximum value range of Y coordinates in the screened data is larger than or equal to the tunnel diameter, the data are continuously reflected in a planar shape and only are reflected in a regular shape;
searching in detected continuous reflections of each plane, firstly determining a distance A, and if the regular reflection and the negative reflection exist in the distance range at the same time, determining whether positive and negative interval distribution, negative reflection or regular reflection is dominant according to the quantity relation of the regular reflection and the negative reflection;
Planar discontinuous reflection:
Detecting and extracting the minimum F% data in all seismic wave point cloud data, detecting the screened data, removing data discontinuously distributed in space according to coordinate distribution, and finally comparing the maximum value range of Y coordinates in the screened data with the space coordinate range of the tunnel diameter, wherein if the maximum length is smaller than the tunnel diameter or a preset value B, the data are in planar discontinuous reflection and only in negative reflection;
Detecting and extracting the largest F% data in all seismic wave point cloud data, detecting the screened data, removing data discontinuously distributed in space according to coordinate distribution, and finally comparing the largest value range of Y coordinates in the screened data with the space coordinate range of tunnel diameter, wherein if the largest length is smaller than the tunnel diameter or a preset value B, the data are reflected discontinuously in a plane shape and are reflected only in a positive reflection manner;
Searching in the detected planar discontinuous reflection, firstly determining a distance C, and if the regular reflection and the negative reflection exist in the range at the same time, determining whether positive and negative interval distribution, negative reflection or regular reflection is dominant according to the quantity relation of the regular reflection and the negative reflection;
Dislocation reflection:
The detection of the offset and the distribution elevation of each regular reflection and negative reflection surface is carried out on the basis of all the regular reflection and the negative reflection surfaces, specifically, searching is carried out in the range of the regular reflection and the negative reflection, namely, if the regular reflection and the negative reflection exist in the range of the regular reflection and the negative reflection are detected, and the vertical distribution range is complementary with the detected object, the two regular reflection and the negative reflection are combined into the staggered reflection and the regular reflection is only;
determining a distance E, searching in each detected dislocation reflection, and determining whether positive and negative interval distribution, negative reflection or positive reflection is dominant according to the quantity relation of positive and negative reflection if positive and negative reflection exist in the distance E at the same time;
dense punctiform reflection and sporadic punctiform reflection:
after the detection is finished, the residual seismic wave point cloud data are screened, the maximum and minimum G% data are reserved, the seismic wave point cloud data are divided into dense point reflection and scattered point reflection according to the distribution density of scattered numerical point coordinates, and the seismic wave point cloud data are divided into positive and negative interval distribution, negative reflection is mainly, positive reflection is mainly, only positive reflection or only negative reflection according to the number of positive and negative numerical distribution;
A. B, C, D, E, F, G is a preset value.
Further, the step 2 further includes encoding the reflection forms of the different classifications.
Further, step 3 further includes encoding the positions after obtaining the positions of the reflection morphology classifications.
Further, the step 4 further includes structuring the data based on the encoding before calculating the probability of existence of the bad geological body.
And 5, adjusting the existence probability of the bad geologic body corresponding to the classification rule and the reflection morphology classification according to the actual condition of the excavated bad geologic body.
Compared with the prior art, the method has the advantages that the method directly performs standardized processing on the original point cloud data generated by a seismic wave method, and performs intelligent machine identification on geological objects and automatically generates forecast conclusion through corresponding relations in engineering experience. The method bypasses the process of transferring the original data to the image and then transferring the original data to the manual interpretation, avoids a plurality of problems in manual image analysis, simplifies and structuralizes a large amount of original point cloud data to be tested, saves storage space and data processing amount of subsequent work, and lays a foundation for intelligent fusion analysis of the machine among the data under different forecasting methods.
Drawings
FIG. 1 is a flow chart of a method for intelligent analysis and identification of three-dimensional seismic wave point cloud data.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, the intelligent analysis and identification method for three-dimensional seismic wave point cloud data comprises the following steps:
And step 1, collecting three-dimensional seismic wave point cloud data of the tunnel. The embodiment is described based on the TRT result, and the point cloud data detected at a time is a set of positive and negative values in normal distribution, wherein the median value is in a normal state, positive and negative values correspond to positive and negative reflection and reflection intensity, respectively, and each value corresponds to a set of space coordinates.
And step 2, classifying the seismic wave point cloud data according to the reflection form classification rule.
In order to improve the classification accuracy and reduce the data interference, seismic wave data are filtered before classification. The present embodiment is classified into four types of planar continuous reflection, planar discontinuous reflection, staggered reflection and punctiform reflection according to the form, wherein punctiform reflection can be further classified into dense punctiform reflection and sporadic punctiform reflection. According to the numerical values, the positive and negative can be divided into negative reflection and positive reflection, and the relationship between positive and negative reflection can be subdivided into five types of positive and negative interval distribution, negative reflection is mainly, positive reflection is mainly, only negative reflection and only positive reflection. And combining the two classifications to obtain the final classification result type.
The specific classification rules are as follows:
(1) Planar continuous reflection
Detecting and extracting the minimum F% data in all the seismic wave point cloud data, in the embodiment, F is taken as 20, detecting the screened data, rejecting non-adjacent data in space according to coordinate distribution, and finally comparing the maximum value range of Y coordinates in the screened data with the space coordinate range of the tunnel path, and if the maximum value range of Y coordinates in the screened data is greater than or equal to the tunnel path, determining the tunnel path as planar continuous reflection, and determining only negative reflection conclusion.
In order to facilitate subsequent data processing, reduce data processing amount, save data storage space, encode each type separately, encode and replace each reflection form classification in subsequent processing. The planar continuous reflection as described above and only the negative reflection is encoded as 14.
Detecting and extracting the largest 20% of data in all values, detecting the screened data, removing non-adjacent data in space according to coordinate distribution, comparing the largest value range of Y coordinates in the screened data with the space coordinate range of the tunnel diameter, if the value is larger than or equal to the tunnel diameter, obtaining a conclusion that the planar continuous reflection is only reflected in a regular way, and encoding the conclusion as 15;
further searching in the detected continuous reflections of each plane, firstly determining a distance A, if only a plurality of groups of regular reflection or a plurality of groups of negative reflection exist in the distance range, keeping the code unchanged, if positive and negative reflection exist in the distance range at the same time, determining positive and negative interval distribution, negative reflection is dominant or regular reflection is dominant according to the number relation of the positive and negative reflection, correspondingly encoding 11, 12 and 13, deleting the original code 14 or 15 in the distance, and if only regular reflection or negative reflection exists, keeping the original code.
(2) Planar discontinuous reflection
Detecting and extracting the minimum 20% of all values, detecting the screened data, removing non-adjacent data in space according to coordinate distribution, comparing the maximum value range of Y coordinates in the screened data with the space coordinate range of the tunnel path, and if the maximum length is smaller than the tunnel path or a preset value B, determining that the maximum length is planar discontinuous reflection and only negative reflection is judged, and encoding the maximum length as 24.
Detecting and extracting the largest 20% of data in all values, detecting the screened data, removing non-adjacent data in space according to coordinate distribution, comparing the largest value range of Y coordinates in the screened data with the space coordinate range of the tunnel diameter, if the largest length is smaller than the tunnel diameter or a preset value B, obtaining a conclusion that the surface is discontinuously reflected and only is regularly reflected, and encoding the conclusion as 25;
Searching in the detected surface discontinuous reflections, determining a distance C, if only a plurality of groups of regular reflections or a plurality of groups of negative reflections exist in the distance range, keeping the original code unchanged, if positive and negative reflections exist in the distance range at the same time, determining positive and negative interval distribution, negative reflections are dominant or regular reflections are dominant according to the number relation of the positive and negative reflections, correspondingly encoding 21, 22 and 23, deleting the original code 24 or 25 in the distance, and if only regular reflections or negative reflections exist, keeping the original code.
(3) Dislocation reflection
And detecting the offset and the distribution elevation of each reflecting surface on the basis of all the planar discontinuous reflection, wherein the positive and negative reflecting surfaces are required to be detected respectively. If the regular reflection is searched within the range of the planar discontinuous reflection +/-Dm, D is 10, if the other regular reflection exists and the vertical distribution range is complementary to the detected object, combining the previous two faces with the code of 25 into 35, and obtaining the code 34 by the same method;
after the detection is finished, the assigned staggered reflection is further detected, positive and negative interval distribution, negative reflection or regular reflection is determined to be dominant according to the number relation of the positive and negative reflection in the distance E, the corresponding codes are 31, 32 and 33, and the original codes (codes 34-35) in the distance are deleted.
(4) Dense punctiform reflection and sporadic punctiform reflection
After the detection is finished, the residual numerical points are screened, the maximum and minimum G% and G are reserved, 20 is taken, at the moment, the numerical points are divided into dense point-like reflection and scattered point-like reflection according to the distribution density of coordinates of the scattered numerical points (for example, the definition of 1m multiplied by 1m is carried out in the space of more than or equal to 50 hit points and the search is carried out in the axial direction of a tunnel according to the unit of 0.2 m), and further, the codes 41-55 are respectively defined and assigned according to the distribution proportion of positive and negative numerical values (for example, 55 points meet the requirement in a single search and the regular reflection point is larger than 70%, then 43 is assigned, the proportion of the regular reflection point is 50% -70%, 41 is assigned, and the proportion is larger than 90% and 45 is assigned).
A. c, D, E is a preset distance, and can be taken according to actual needs, if the range of 20 m-50 m is taken, the accuracy of the value is reduced too much, and if the value is too small, the value has no practical meaning. B. F, G may also be selected according to practical needs, and is not limited herein.
And step 3, acquiring the positions of various morphological reflecting interfaces, and acquiring the existence probability of the bad geologic body corresponding to each reflecting morphological classification according to the relation between the preset reflecting morphological classification and the existence probability of the bad geologic body.
The above steps complete classification and assignment of the point cloud to various reflection space forms, and in addition, the distribution space positions of the reflection forms corresponding to the codes are required to be described and coded. According to the preset, a single test starting surface (a section perpendicular to the axial direction of the tunnel) is defined as a starting point, and then the position of the detected object can be defined according to the X coordinate distribution range of each object. Depending on the nature of the test, the single test significance is typically in the range of 100m, and thus is encoded in four digits, e.g., 4055, representing a range 40 m-55 m forward from the test start section as the distribution range of the subject. When searching the distribution range, some data on two sides, such as 10% of coordinate data on two sides, are generally removed, so that the searched distribution range is prevented from being influenced by discrete points too much. In addition, the real pile number information of a single test is recorded in the system, and when a conclusion is output, the system directly increases the distribution range on the basis of the real pile number, so that the real space position of each object is obtained.
The existence probability of the bad geologic body corresponding to each reflection morphology classification can be obtained by a table look-up mode, and the probability table in the embodiment is as follows:
TABLE 1 probability table of bad geologic body existence corresponding to each reflection morphology classification
Further, after the above detection is completed, linear analysis between the reflection surfaces is performed on all the planar continuous reflection and the planar discontinuous reflection, firstly, under the top view condition (two of three coordinate values, such as XY values, i.e., plane distribution, are generally extracted at a time), each reflection surface is simplified into coordinates of two points (a starting point and an end point), and a straight line is used for replacing the coordinates, under the condition, the starting point and the end point of each adjacent reflection surface are respectively connected, if the connecting line is approximately a straight line (approximately judged according to the fitting degree), the linear image between the reflection surfaces is considered to exist, at this time, the linear structure formed between the regular reflection surfaces is divided according to the type of the original reflection surfaces forming the straight line, and the linear structure formed between the negative reflection surfaces or the linear structure formed between the positive reflection surfaces and the negative reflection surfaces are respectively assigned 61 to 63. The above procedure (i.e., XZ direction, where X is the tunnel axis direction) is repeated and assigned under side view conditions.
The existence probability of the bad geologic body corresponding to the special structural surface type is shown in the following table:
TABLE 2 probability table of existence of bad geologic body corresponding to special structural surface type
In addition to the above information, the raw data is generally collected with other related information, such as a wave velocity diagram, where the absolute value of the wave velocity diagram is greatly affected by the collection, but the waveform trend can be used as an auxiliary judgment factor, so that the variation trend of the wave velocity of each reflecting surface position can be counted and encoded by referring to the wave velocity of the excitation surface, as shown in table 3. The wave speed change trend can be preset and defined, if the average wave speed value of the position is larger than 30% compared with the average wave speed value of the position in the excitation direction of 20m, namely the rapid rise is realized, 10% -30% is slightly raised, less than 10% is basically consistent, and the like.
TABLE 3 probability table of existence of bad geologic body corresponding to wave velocity variation trend
And 4, accumulating the existence probabilities of the bad geologic bodies corresponding to the different reflection morphology classifications at the same position to obtain the existence probability of the bad geologic bodies at the position, wherein more than 100% is calculated according to 100%.
If the codes 11 and 24 exist in the 4055 range, the occurrence probability of the geological interface in the range is overlapped and output according to the occurrence probability of the geological interface (+30%, +55%) respectively, and the occurrence probability of the geological interface in the range is 85%.
In order to improve the forecasting accuracy, classification rules and output probabilities can be corrected according to the actual condition characteristics of the bad geologic bodies after excavation.
If 10 sections are counted, the surface detection is 11, the preset value of the corresponding probability is +30%, but the excavation proves that only 2 sections have geological interfaces, the actual probability is 20%, and therefore the preset value corresponding to 11 is modified to be +20%.
When forecasting and predicting bad geological bodies by adopting various geophysical prospecting methods, fusion analysis among data is involved. And similarly, structuring the data under the geophysical prospecting method with the same data structure according to the method, defining the prediction weight of each method at the moment, and finally obtaining the occurrence probability of each geological interface after comprehensive analysis.
After the single point cloud data scanning detection is completed, all the reflecting surfaces and the special structural surfaces are converted into corresponding codes according to rules. The structure of the encoded data is defined and standardized at this time, and the purpose is to perform normalization processing on various data streams under different detection methods. The later machine can perform mutual operation on the data obtained under different methods according to a preset algorithm, so as to achieve the purpose of comprehensive analysis. The recognized data are arranged in a matrix mode, each row is related information of a single reflecting surface, different meanings are expressed among columns according to different orders, and letters are used for replacing when no data or meaning exists in a certain order. Examples are as follows:
XX YY 4 0 5 5 1 2 2
XX 6 1 3 5 4 2 B B 1
If 11-bit codes are adopted in a certain project, 1-2 bits represent project parts, currently no information is input temporarily, letters X are used for replacing, 3-4 bits represent whether linear images among objects are displayed or not, a first row represents whether letters Y are used for replacing, second rows 61 are used for representing position distribution information, 9-10 bits are reflection surface characteristic information, and the characteristic information is displayed as linear images among objects of the second row, so that no data is input for the characteristic information bits, letters are used for replacing, and the last bit is other information such as wave speed change trend.
The arrangement of the reflection surfaces according to the rule can rapidly screen and identify the reflection surfaces under a certain characteristic, and also can rapidly calculate, for example, the distribution positions of the reflection surfaces in the first row are 40-55 m, the distribution positions of the reflection surfaces in the second row are 35-42 m, and the reflection surfaces in the range of 40-42 m are obtained after the intersection operation.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510075893.4A CN119471814B (en) | 2025-01-17 | 2025-01-17 | Intelligent analysis and recognition method of 3D seismic point cloud data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510075893.4A CN119471814B (en) | 2025-01-17 | 2025-01-17 | Intelligent analysis and recognition method of 3D seismic point cloud data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119471814A true CN119471814A (en) | 2025-02-18 |
| CN119471814B CN119471814B (en) | 2025-03-25 |
Family
ID=94570243
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510075893.4A Active CN119471814B (en) | 2025-01-17 | 2025-01-17 | Intelligent analysis and recognition method of 3D seismic point cloud data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119471814B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4298968A (en) * | 1965-12-27 | 1981-11-03 | Mobil Oil Corporation | Digital reflection searching and section plotting |
| CN107526098A (en) * | 2017-10-19 | 2017-12-29 | 云南省水利水电勘测设计研究院 | A kind of construction method for carrying out advance geologic prediction |
| CN113050157A (en) * | 2020-10-15 | 2021-06-29 | 中国石油天然气股份有限公司 | Carbonate rock seismic reservoir inversion method and system based on outcrop data |
| CN113075656A (en) * | 2021-03-31 | 2021-07-06 | 中国矿业大学(北京) | Method for comprehensively predicting coal mine working face fracture through ground penetrating radar and three-dimensional earthquake |
| CN114624763A (en) * | 2020-12-10 | 2022-06-14 | 中国石油天然气股份有限公司 | Seismic phase diagram generation method and device |
| US20220276383A1 (en) * | 2019-12-31 | 2022-09-01 | Shandong University | System and method for rock mass structure detection and dangerous rock detection |
| US20230251395A1 (en) * | 2022-02-09 | 2023-08-10 | Bp Corporation North America Inc. | Method and Apparatus for Seismic Data Inversion |
| CN117607958A (en) * | 2023-11-02 | 2024-02-27 | 成都理工大学 | Advanced prediction method, device, equipment and storage medium for bad geology |
| CN119126212A (en) * | 2024-11-12 | 2024-12-13 | 北京新兴环宇信息科技有限公司 | High-precision detection method, system, equipment and storage medium for urban underground space |
-
2025
- 2025-01-17 CN CN202510075893.4A patent/CN119471814B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4298968A (en) * | 1965-12-27 | 1981-11-03 | Mobil Oil Corporation | Digital reflection searching and section plotting |
| CN107526098A (en) * | 2017-10-19 | 2017-12-29 | 云南省水利水电勘测设计研究院 | A kind of construction method for carrying out advance geologic prediction |
| US20220276383A1 (en) * | 2019-12-31 | 2022-09-01 | Shandong University | System and method for rock mass structure detection and dangerous rock detection |
| CN113050157A (en) * | 2020-10-15 | 2021-06-29 | 中国石油天然气股份有限公司 | Carbonate rock seismic reservoir inversion method and system based on outcrop data |
| CN114624763A (en) * | 2020-12-10 | 2022-06-14 | 中国石油天然气股份有限公司 | Seismic phase diagram generation method and device |
| CN113075656A (en) * | 2021-03-31 | 2021-07-06 | 中国矿业大学(北京) | Method for comprehensively predicting coal mine working face fracture through ground penetrating radar and three-dimensional earthquake |
| US20230251395A1 (en) * | 2022-02-09 | 2023-08-10 | Bp Corporation North America Inc. | Method and Apparatus for Seismic Data Inversion |
| CN117607958A (en) * | 2023-11-02 | 2024-02-27 | 成都理工大学 | Advanced prediction method, device, equipment and storage medium for bad geology |
| CN119126212A (en) * | 2024-11-12 | 2024-12-13 | 北京新兴环宇信息科技有限公司 | High-precision detection method, system, equipment and storage medium for urban underground space |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119471814B (en) | 2025-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680542A (en) | Steel coil point cloud recognition and classification method based on multi-scale feature extraction and Pointnet neural network | |
| CN101718528B (en) | Digital image based rapid solving method of circle parameters | |
| CN112634447B (en) | Outcrop stratum layering method, device, equipment and storage medium | |
| CN108711148A (en) | A kind of wheel tyre defect intelligent detecting method based on deep learning | |
| CN111738945A (en) | A mine-based point cloud data preprocessing method | |
| CN116977999B (en) | Intelligent core identification method, system and storage medium based on machine vision | |
| CN119205694A (en) | An automatic detection and quantitative analysis method for bridge defects based on point cloud data processing | |
| CN119312170B (en) | Stratum type-based intelligent auxiliary method for shield tunneling | |
| CN118196783A (en) | Point cloud abnormal data processing method based on clustering algorithm and PointNet neural network | |
| CN117854061B (en) | Tunnel face trace crack extraction method and system based on three-dimensional point cloud | |
| CN117830377B (en) | Method, device, computer equipment and storage medium for determining rock quality | |
| CN119941697A (en) | A smart perception and automatic detection method and system | |
| CN102708367A (en) | Image identification method based on target contour features | |
| CN115019144A (en) | An intelligent identification method of shale gas reservoir lithology based on electrical imaging logging images | |
| CN115112032A (en) | A method for measuring the pitch of spherical grid components | |
| CN117538863A (en) | Method, device, equipment and medium for improving tunnel lining defect geological radar detection precision | |
| CN120182837B (en) | Historical cultural famous city data acquisition, analysis and evaluation method based on eagle eye inspection | |
| CN119471814B (en) | Intelligent analysis and recognition method of 3D seismic point cloud data | |
| CN119418066B (en) | A fracture contour extraction method for well logging images | |
| CN109785261A (en) | A kind of airborne LIDAR three-dimensional filtering method based on gray scale volume element model | |
| CN108205683B (en) | Infrared target identification system threshold value optimization method based on visible light satellite picture | |
| CN111723737B (en) | A target detection method based on multi-scale matching strategy deep feature learning | |
| CN120014305A (en) | A method, device, terminal and medium for detecting damage of assembled prefabricated components | |
| CN119399142A (en) | A video image defect detection, identification and processing method and system | |
| CN103853817B (en) | Spatial Singularity Mining Method Based on Massive Statistical Data in GIS |
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 |