CN113658245A - Method for acquiring rock mass structural plane occurrence information from drilling image - Google Patents
Method for acquiring rock mass structural plane occurrence information from drilling image Download PDFInfo
- Publication number
- CN113658245A CN113658245A CN202110749987.7A CN202110749987A CN113658245A CN 113658245 A CN113658245 A CN 113658245A CN 202110749987 A CN202110749987 A CN 202110749987A CN 113658245 A CN113658245 A CN 113658245A
- Authority
- CN
- China
- Prior art keywords
- image
- structural
- borehole
- structural surface
- structural plane
- 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 37
- 239000011435 rock Substances 0.000 title claims abstract description 33
- 238000005553 drilling Methods 0.000 title claims abstract description 27
- 238000013139 quantization Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 27
- 230000011218 segmentation Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 5
- 238000004445 quantitative analysis Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a method for acquiring rock mass structural plane occurrence information from a drilling image, which comprises the steps of extracting image characteristics of a training set by taking ResNet as a pre-training model, inputting the image characteristics into a Unet network for training to obtain a trained Unet model; segmenting the borehole photographic image by utilizing the Unet model to obtain a segmentation result of the structural surface; processing the segmentation result of the structural surface through an image thinning algorithm to obtain a structural surface image skeleton, and performing unit width processing on the structural surface image skeleton to form a structural surface quantization curve; carrying out sine function fitting on the structure surface quantization curve to obtain a quantization curve sine function expression; and calculating structural surface attitude information according to the segmentation result of the structural surface and the quantization curve sine function expression, wherein the structural surface attitude information comprises the inclination angle, the inclination and the thickness of the structural surface. And theory and method support is provided for quantitative analysis of the occurrence of the structural plane in the rock foundation of the hydraulic engineering.
Description
Technical Field
The invention belongs to the technical field of rock mass quality evaluation methods, and relates to a method for acquiring rock mass structural plane occurrence information from a drilling image.
Background
The hydraulic engineering is mostly built in high mountain canyon regions, and the geological conditions are very complicated. Poor geological conditions may cause instability or seepage damage of the hydraulic engineering foundation, and affect the stability of the dam body. Therefore, rock mass quality evaluation is very necessary in hydraulic engineering construction. A drill hole core photo and a drill hole shooting panoramic picture with position information are usually reserved in geological surveying engineering; recording rock RQD value and water pressure test data on site; and measuring and recording the drilling sound wave data, the seismic wave data and the like. And qualitatively analyzing the quality of the rock mass through data recorded and measured on the survey site, and making corresponding treatment measures.
The survey data can only be used for comprehensively analyzing the quality of the rock mass, and the integrity of the rock mass is integrally evaluated. And through analyzing the drilling photography panoramic picture, the occurrence information such as the position, the depth, the trend and the like of unfavorable geological structures such as fault layers, cracks and the like in the drilling can be obtained, the occurrence information of different drilling is combined, the detailed information of the structural plane of the fracture of the exploration rock mass can be analyzed, and a geological engineer can realize the prevention and control of the unfavorable geological problems of the hydraulic engineering according to the geological exploration information.
With the progress of computer computing power and the rapid development and application of deep learning, image analysis techniques have been widely applied. To acquire accurate structural surface information from a borehole image, firstly, precise identification and segmentation of a structural surface in the borehole image are realized, and a traditional image processing method based on a threshold or an edge is difficult to adapt to processing of a borehole photographic image under complex geology.
Disclosure of Invention
The invention aims to provide a method for acquiring the attitude information of a rock mass structural plane from a drilling image, which solves the problem that the attitude information of the rock mass structural plane cannot be automatically and accurately acquired in the prior art.
The invention adopts the technical scheme that the method for acquiring the attitude information of the rock mass structural plane from the borehole image comprises the following steps:
step 1, extracting image characteristics of a training set by taking ResNet as a pre-training model, inputting the image characteristics into a Unet network for training to obtain a trained Unet model;
step 2, segmenting the borehole photography image by utilizing the trained Unet model to obtain a segmentation result of the structural surface, processing the segmentation result of the structural surface by a Zhang-Suen image thinning algorithm to obtain a structural surface image skeleton, and performing unit width processing on the structural surface image skeleton to form a structural surface quantization curve;
and 4, calculating structural plane attitude information according to the segmentation result of the structural plane and the quantization curve sine function expression obtained in the step 2, wherein the structural plane attitude information comprises the inclination angle, the inclination and the thickness of the structural plane.
The invention is characterized in that:
the step 1 specifically comprises the following steps:
step 1.1, acquiring a drilling hole photographic image with a structural surface, labeling pixels of the structural surface part of the drilling hole photographic image, and dividing the drilling hole photographic image after labeling into a training set and a testing set;
and step 1.2, extracting image characteristics of a training set by taking ResNet as a pre-training model, and inputting the image characteristics into a Unet network for training to obtain a trained Unet model.
The step 1 further comprises the steps of,
and step 1.3, segmenting each borehole photographic image in the test set by using the Unet model, further calculating F1_ score value and IoU value, and judging the performance of the trained Unet model.
The F1_ score and IoU values are calculated as follows:
in the above formula, Precision is Precision, Recall is recalling, TP represents that the label is positive, and the prediction is positive; FP represents that the label is negative and the prediction is positive; TN represents that the label is negative and the prediction is negative; FN means tag is positive, predicted negative;
in the above formula, DT represents a prediction result range, and GT represents a real result range of the object; i represents the intersection and U represents the union.
The step 3 specifically comprises the following steps:
step 3.1, the relative coordinates of each point on the quantitative curve of the assumed structural plane are expressed as (x)i,yi) And fitting a structural surface quantization curve by adopting a least square method, wherein the sine function formula and the fitting single-point error are as follows:
in the formula y*Is the ordinate of the fitted point curve, A is the amplitude, omega is the angular velocity,
is the initial phase, b is the base line position of the sine curve, and delta is the fitting error;
in the above formula, T is the period of the sine function, L0Is the borehole photographic image width;
step 3.2, according to the deviation calculation formula in the formula (5), the overall deviation I is minimized, as shown in the formula (7), and A,
b：
The calculation modes of the inclination angle alpha, the inclination beta and the thickness H of the structural surface in the step 4 are as follows:
calculating dy/dx to be 0, two extreme points of the sine function are obtained, which are respectively marked as (x)min,ymin) And (x)max,ymax)；
The tendency beta is determined by the position of the lowest point of the fitted curve, and the calculation formula is as follows:
in the above formula, L0For borehole photographic image width, x0Is the initial pixel location of the borehole photographic image;
in the above formula, S is the area of the drilling structural surface, L is the length of the structural surface curve, and the calculation formula of L is:
in the above formula, n is the number of coordinate points of the structure surface quantization curve, xi、yiRespectively representing the relative abscissa and ordinate of the ith pixel in the quantization curve.
The invention has the beneficial effects that:
according to the method for acquiring the attitude information of the rock mass structural plane from the drilling image, the accurate identification of the drilling structural plane is realized by adopting a depth migration model algorithm, and the structural plane image segmentation result is evaluated by adopting multiple indexes, so that the influence of subjective factors is avoided, and the identification efficiency of the structural plane is improved; the method comprises the steps of segmenting a drilling photographic image in actual engineering by using a Unet model, extracting a structural surface framework by using a Zhang-Suen image thinning algorithm, carrying out unit width processing to obtain a structural surface quantization curve, fitting the quantization curve by using a least square method, realizing automatic quantization analysis of structural surface tendency, inclination angle and thickness from a segmentation result and the fitting curve, realizing an intelligent quantization process of structural surface information, and improving the efficiency of geological exploration; and theory and method support is provided for quantitative analysis of the occurrence of the structural plane in the rock foundation of the hydraulic engineering.
Drawings
FIG. 1 is a flow chart of a method for acquiring attitude information of a rock mass structural plane from a borehole image according to the invention;
FIG. 2 is a schematic structural diagram of a Unet model in a method for acquiring occurrence information of a rock mass structural plane from a borehole image according to the present invention;
FIG. 3 is a schematic diagram showing changes of different evaluation indexes in the training process of a Unet model in the method for acquiring occurrence information of a rock mass structural plane from a borehole image according to the present invention;
FIG. 4 is a photographic image of a borehole to be subjected to structural plane segmentation and quantification in a method of obtaining attitude information of a rock structural plane from a borehole image according to the present invention;
FIG. 5 is a schematic diagram of the training result of the Unet model in the method for acquiring the attitude information of the rock mass structural plane from the borehole image according to the present invention;
FIG. 6 is a schematic diagram of structural plane skeleton extracted by Zhang-Suen refining algorithm in the method for acquiring rock structural plane occurrence information from a borehole image according to the present invention;
fig. 7 is a diagram of a part of the quantified curve of the structural plane of the borehole photography image and the fitting curve thereof in the method for acquiring the occurrence information of the rock structural plane from the borehole image.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
A method for obtaining rock mass structural plane attitude information from a borehole image, as shown in fig. 1, comprises the following steps:
step 1, extracting image characteristics of a training set by taking ResNet as a pre-training model, inputting the image characteristics into a Unet network for training to obtain a trained Unet model;
step 1.1, acquiring a drilling photographic image with a structural surface, processing the length and width dimensions of the drilling photographic image to 160 multiplied by 1280, labeling pixels of the structural surface part of the drilling photographic image to be used as a segmentation foreground, and taking 80% of the labeled drilling photographic image as a training set and 20% as a test set;
step 1.2, using ResNet as a pre-training model to extract image characteristics of a training set, inputting the image characteristics into a Unet network for training to obtain a trained Unet model, as shown in FIG. 2,
step 1.3, segmenting each borehole photographic image in the test set by using a Unet model, further calculating F1_ score value and IoU value, and judging the performance of the trained Unet model, wherein different evaluation indexes change in the Unet model training process as shown in FIG. 3, in the embodiment, when the F1_ score value is more than 95% and the IoU value is more than 75%, the Unet is considered to be used for segmenting the borehole photographic image;
the F1_ score and IoU values are calculated as follows:
in the above formula, Precision is Precision, Recall is recalling, TP represents that the label is positive, and the prediction is positive; FP represents that the label is negative and the prediction is positive; TN represents that the label is negative and the prediction is negative; FN means tag is positive, predicted negative;
in the above formula, DT represents a prediction result range, and GT represents a real result range of the object; i represents the intersection and U represents the union.
Step 2, segmenting a drilling photographic image in actual engineering by using a Unet model to obtain a segmentation result of a structural surface, processing the segmentation result of the structural surface by using a Zhang-Suen image thinning algorithm to obtain a structural surface image skeleton, and performing unit width processing on the structural surface image skeleton to form a structural surface quantization curve;
step 2.1, selecting 10 drilling images in actual engineering as test cases, applying the trained Unet model to the test images to obtain segmentation results as shown in FIG. 4, and uniformly naming 17 structural surfaces in 10 test images as shown in FIG. 5 in a format Ii-jI represents the image number from left to right, and j represents the structural surface number from top to bottom in the image;
2.2, obtaining a structural plane image skeleton from the test image segmentation result of the figure 5 through a Zhang-Suen image thinning algorithm, as shown in figure 6;
and 2.3, firstly deriving a skeleton coordinate, and then carrying out unit width processing on the skeleton coordinate to form a structure surface quantization curve, wherein the unit width processing method adopts the mean value as a new longitudinal coordinate value under the condition that the same abscissa corresponds to a plurality of different longitudinal coordinates.
step 3.1, the relative coordinates of each point on the quantitative curve of the assumed structural plane are expressed as (x)i,yi) And fitting a structural surface quantization curve by adopting a least square method, wherein the sine function formula and the fitting single-point error are as follows:
in the formula y*Is a fitted point ordinate, A is amplitude, omega is angular velocity,
is an initial phase, b is the baseline position of the sine curve, delta is the fitting error, and the parameters to be determined are A,
And b;
in the above formula, T is the period of the sine function, L0Is the borehole photographic image width;
step 4.2, according to the deviation calculation formula in the formula (5), the overall deviation I is minimized, as shown in the formula (7), and A,
b：
In this example for4-1And I9-1、I9-2And I9-3The structural surface of (2) is subjected to function fitting, as shown in formula (8), the quantization and fitting curve of the structural surface is shown in fig. 7, and the error of the fitting result is small as can be seen from fig. 7;
and 4, calculating structural plane attitude information according to the segmentation result of the structural plane and the quantization curve sine function expression obtained in the step 2, wherein the structural plane attitude information comprises the inclination angle, the inclination and the thickness of the structural plane.
The calculation modes of the inclination angle alpha, the inclination beta and the thickness H of the structural surface in the step 4 are as follows:
calculating dy/dx to be 0, two extreme points of the sine function are obtained, which are respectively marked as (x)min,ymin) And (x)max,ymax)；
The tendency beta is determined by the position of the lowest point of the fitted curve, and the calculation formula is as follows:
in the above formula, L0For borehole photographic image width, x0Is the initial pixel location of the borehole photographic image;
in the above formula, S is the area of the drilling structural surface, L is the length of the structural surface curve, and the calculation formula of L is:
in the above formula, n is the number of coordinate points of the structure surface quantization curve, xi、yiRespectively representing the relative abscissa and ordinate of the ith pixel in the quantization curve.
Through the mode, the method for acquiring the attitude information of the rock mass structural plane from the borehole image comprises the steps of segmenting a borehole photographic image in actual engineering by using a Unet model, extracting a structural plane skeleton by using a Zhang-Suen image thinning algorithm and carrying out unit width processing to obtain a structural plane quantization curve, fitting the quantization curve by using a least square method, realizing automatic quantitative analysis of structural plane tendency, inclination angle and thickness from a segmentation result and the fitting curve, improving surveying efficiency, and providing theoretical and method support for the quantitative analysis of the structural plane attitude in a hydraulic engineering rock foundation.
Example (b):
the method is adopted to extract the occurrence information of the structural surface of the drilled photographic image, and the table 1 shows that the occurrence information of all the structural surfaces in the test image is extracted intelligently and compared with the manually extracted occurrence data, and the result proves the effectiveness of the extraction of the occurrence information of the structural surfaces.
TABLE 1 structural plane information manual extraction and automatic identification result comparison table
Note: relative error | (automatic identification-artificial extraction) |/artificial extraction
Claims (6)
1. A method for acquiring rock mass structural plane attitude information from a borehole image is characterized by comprising the following steps:
step 1, extracting image characteristics of a training set by taking ResNet as a pre-training model, inputting the image characteristics into a Unet network for training to obtain a trained Unet model;
step 2, segmenting the borehole photography image by utilizing the trained Unet model to obtain a segmentation result of the structural surface, processing the segmentation result of the structural surface by a Zhang-Suen image thinning algorithm to obtain a structural surface image skeleton, and performing unit width processing on the structural surface image skeleton to form a structural surface quantization curve;
step 3, performing sine function fitting on the structure surface quantization curve to obtain a quantization curve sine function expression;
and 4, calculating structural plane attitude information according to the segmentation result of the structural plane obtained in the step 2 and the quantized curve sine function expression, wherein the structural plane attitude information comprises a structural plane inclination angle, inclination and thickness.
2. The method for acquiring rock mass structural plane attitude information from the borehole image according to claim 1, wherein the step 1 specifically comprises the following steps:
step 1.1, acquiring a drilling photographic image with a structural surface, labeling pixels of the structural surface part of the drilling photographic image, and dividing the drilling photographic image after labeling into a training set and a testing set;
and step 1.2, extracting the characteristics of the borehole photographic images in the training set by taking ResNet as a pre-training model, and inputting the image characteristics into a Unet network for training to obtain a trained Unet model.
3. The method for acquiring rock mass structural plane attitude information from borehole images according to claim 1, wherein the step 1 further comprises,
and step 1.3, segmenting each borehole photographic image in the test set by using the Unet model, further calculating F1_ score value and IoU value, and judging the performance of the trained Unet model.
4. A method of obtaining rock mass structural plane attitude information from borehole images as claimed in claim 3 wherein the F1_ score and IoU values are calculated as follows:
in the above formula, Precision is Precision, Recall is recalling, TP represents that the label is positive, and the prediction is positive; FP represents that the label is negative and the prediction is positive; TN represents that the label is negative and the prediction is negative; FN means tag is positive, predicted negative;
in the above formula, DT represents a prediction result range, and GT represents a real result range of the object; i represents the intersection and U represents the union.
5. The method for acquiring rock mass structural plane attitude information from the borehole image according to claim 1, wherein the step 3 specifically comprises the following steps:
step 3.1, assuming that the relative coordinates of each point on the structure surface quantization curve are expressed as (x)i,yi) And fitting a structural surface quantization curve by adopting a least square method, wherein the sine function formula and the fitting single-point error are as follows:
in the formula y*Is a fitted point ordinate, A is amplitude, omega is angular velocity,
is the initial phase, b is the base line position of the sine curve, and delta is the fitting error;
in the above formula, T is the period of the sine function, L0Is the borehole photographic image width;
step 3.2, according to the deviation calculation formula in the formula (5), the overall deviation I is minimized, as shown in the formula (7), and A,
b：
6. The method for acquiring rock mass structural plane attitude information from the borehole image according to claim 1, wherein the inclination angle α, the inclination β and the thickness H of the structural plane in the step 4 are calculated as follows:
calculating dy/dx to be 0, two zeros of the sine function are obtained, which are respectively marked as (x)min,ymin) And (x)max,ymax)；
The tendency beta is determined by the position of the lowest point of the fitted curve, and the calculation formula is as follows:
in the above formula, L0For borehole photographic image width, x0Is the initial pixel location of the borehole photographic image;
in the above formula, S is the area of the drilling structural surface, L is the length of the structural surface curve, and the calculation formula of L is:
in the above formula, n is the number of coordinate points of the structure surface quantization curve, xi、yiRespectively representing the relative abscissa and ordinate of the ith pixel in the quantization curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110749987.7A CN113658245B (en) | 2021-07-01 | 2021-07-01 | Method for acquiring rock mass structural plane occurrence information from drilling image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110749987.7A CN113658245B (en) | 2021-07-01 | 2021-07-01 | Method for acquiring rock mass structural plane occurrence information from drilling image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113658245A true CN113658245A (en) | 2021-11-16 |
| CN113658245B CN113658245B (en) | 2024-04-30 |
Family
ID=78489860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110749987.7A Active CN113658245B (en) | 2021-07-01 | 2021-07-01 | Method for acquiring rock mass structural plane occurrence information from drilling image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113658245B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116258972A (en) * | 2023-05-16 | 2023-06-13 | 四川安信科创科技有限公司 | Deep learning-based rock high-steep slope structural surface extraction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140254884A1 (en) * | 2013-03-11 | 2014-09-11 | Peter Adrian Spencer Elkington | Methods of and Apparatuses for Identifying Geological Characteristics in Boreholes |
| CN104808248A (en) * | 2015-04-22 | 2015-07-29 | 长江大学 | Attitude of stratum detecting method based on electric imaging logging full hole image |
| CN107169504A (en) * | 2017-03-30 | 2017-09-15 | 湖北工业大学 | A kind of hand-written character recognition method based on extension Non-linear Kernel residual error network |
| GB201910300D0 (en) * | 2013-03-11 | 2019-09-04 | Reeves Wireline Tech Ltd | Method of and apparatuses for indentifying geological characteristics |
| CN110360963A (en) * | 2019-07-22 | 2019-10-22 | 中国科学院武汉岩土力学研究所 | A kind of rock mass discontinuity three-dimensional roughness of borehole camera technology describes method |
| CN112837269A (en) * | 2021-01-11 | 2021-05-25 | 西安理工大学 | Rock mass quality evaluation method based on deep learning model |
-
2021
- 2021-07-01 CN CN202110749987.7A patent/CN113658245B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140254884A1 (en) * | 2013-03-11 | 2014-09-11 | Peter Adrian Spencer Elkington | Methods of and Apparatuses for Identifying Geological Characteristics in Boreholes |
| GB201910300D0 (en) * | 2013-03-11 | 2019-09-04 | Reeves Wireline Tech Ltd | Method of and apparatuses for indentifying geological characteristics |
| CN104808248A (en) * | 2015-04-22 | 2015-07-29 | 长江大学 | Attitude of stratum detecting method based on electric imaging logging full hole image |
| CN107169504A (en) * | 2017-03-30 | 2017-09-15 | 湖北工业大学 | A kind of hand-written character recognition method based on extension Non-linear Kernel residual error network |
| CN110360963A (en) * | 2019-07-22 | 2019-10-22 | 中国科学院武汉岩土力学研究所 | A kind of rock mass discontinuity three-dimensional roughness of borehole camera technology describes method |
| CN112837269A (en) * | 2021-01-11 | 2021-05-25 | 西安理工大学 | Rock mass quality evaluation method based on deep learning model |
Non-Patent Citations (2)
| Title |
|---|
| ROMMEL ANATOLI QUINTANILLA CRUZ ET AL.: "Improving accuracy of automatic fracture detection in borehole images with deep learning and GPUs", 2017 30TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, 31 December 2017 (2017-12-31) * |
| 杨玉卿 等: "基于电成像测井图像识别求取地层产状的新方法", 石油物探, vol. 56, no. 2, 31 March 2017 (2017-03-31) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116258972A (en) * | 2023-05-16 | 2023-06-13 | 四川安信科创科技有限公司 | Deep learning-based rock high-steep slope structural surface extraction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113658245B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108960135B (en) | Dense ship target accurate detection method based on high-resolution remote sensing image | |
| WO2023185734A1 (en) | Mine digital model construction method based on three-dimensional point cloud database | |
| BR112015006701B1 (en) | METHOD FOR ANALYZING CHANGES IN ROCK PROPERTIES RESULTING FROM A TREATMENT. | |
| CN104948176B (en) | A kind of method based on infiltration Magnification identification carbonate reservoir crack | |
| CN107807387A (en) | Acquisition methods when seismic first break based on neutral net is walked | |
| CN112241711A (en) | Intelligent method for identifying RQD from borehole core photo | |
| CN114387328A (en) | RQD calculation method based on deep learning model and core image | |
| CN112837269B (en) | Rock mass quality evaluation method based on deep learning model | |
| CN113658245A (en) | Method for acquiring rock mass structural plane occurrence information from drilling image | |
| CN113674216A (en) | Subway tunnel disease detection method based on deep learning | |
| CN110211142A (en) | Water level online test method outside a kind of hole of the deep basal pit based on video image processing | |
| CN113515654B (en) | Pile foundation construction parameter visualization processing method and device based on building information modeling | |
| US11531138B2 (en) | Processes and systems for correlating well logging data | |
| Su et al. | A Framework for RQD Calculation Based on Deep Learning | |
| Gwynn et al. | Combined use of traditional core logging and televiewer imaging for practical geotechnical data collection | |
| CN115113281B (en) | Method, device, equipment and storage medium for determining marker well and marker layer thereof | |
| CN114612394B (en) | Concrete internal damage prediction method based on Yolo network and DIC technology | |
| CN116517520A (en) | Well control radius calculation method for oil and gas well | |
| CN116106139A (en) | Method for measuring shear strength of natural cracks under temperature difference condition | |
| CN116597193A (en) | Tunnel intelligent construction-oriented tunnel face unmanned geological logging method and system | |
| CN115577616A (en) | Carbonatite fracture-cave earthquake depicting method and device based on deep learning | |
| Zhang et al. | Segmentation and quantitative analysis of geological fracture: a deep transfer learning approach based on borehole televiewer image | |
| CN112282730A (en) | Real-time monitoring and evaluating method for deformation of underground casing induced by reservoir fracturing modification | |
| CN113848209A (en) | Dam crack detection method based on unmanned aerial vehicle and laser ranging | |
| CN111123373A (en) | Ground penetrating radar full waveform inversion method based on wave field expansion 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |